1
|
Insley BA, Bartkoski DA, Balter PA, Prajapati S, Tailor R, Jaffray D, Salehpour MR. Numerical optimization of longitudinal collimator geometry for novel x-ray field. Phys Med Biol 2024. [PMID: 38588671 DOI: 10.1088/1361-6560/ad3c0d] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/10/2024]
Abstract
OBJECTIVE A novel X-ray field produced by an ultrathin conical target is described in the literature. However, the optimal design for an associated collimator remains ambiguous. Current optimization methods using Monte Carlo calculations restrict the efficiency and robustness of the design process. A more generic optimization method that reduces parameter constraints while minimizing computational load is necessary. A numerical method for optimizing the longitudinal collimator hole geometry for a cylindrically-symmetrical X-ray tube is demonstrated and compared to Monte Carlo calculations.
Approach: The X-ray phase space was modelled as a four-dimensional histogram differential in photon initial position, final position, and photon energy. The collimator was modelled as a stack of thin washers with varying inner radii. Simulated annealing was employed to optimize this set of inner radii according to various objective functions calculated on the photon flux at a specified plane.
Main results: The analytical transport model used for optimization was validated against Monte Carlo calculations using Geant4 via its wrapper, TOPAS. Optimized collimators and the resulting photon flux profiles are presented for three focal spot sizes and five positions of the source. Optimizations were performed with multiple objective functions based on various weightings of precision, intensity, and field flatness metrics. Finally, a select set of these optimized collimators, plus a parallel-hole collimator for comparison, were modelled in TOPAS. The evolution of the radiation field profiles are presented for various positions of the source for each collimator.
Significance: This novel optimization strategy proved consistent and robust across the range of X-ray tube settings regardless of the optimization starting point. Common collimator geometries were re-derived using this algorithm while simultaneously optimizing geometry-specific parameters. The advantages of this strategy over iterative Monte Carlo-based techniques, including computational efficiency, radiation source-specificity, and solution flexibility, make it a desirable optimization method for complex irradiation geometries.
.
Collapse
Affiliation(s)
- Benjamin Abraham Insley
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, 1400 Pressler St, Houston, Texas, 77030, UNITED STATES
| | - Dirk Alan Bartkoski
- Empyrean Medical Systems Inc, 3010 N Military Trail, Boca Raton, Florida, 33431, UNITED STATES
| | - Peter A Balter
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Boulevard, Houston, Texas, 77030-4000, UNITED STATES
| | - Surendra Prajapati
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Boulevard, Houston, 77030-4000, UNITED STATES
| | - Ramesh Tailor
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, Texas, 77030-4000, UNITED STATES
| | - David Jaffray
- Division of Office of the Senior Vice President & Chief Technology and Digital Officer, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd., Houston, Texas, 77030-4000, UNITED STATES
| | - Mohammad R Salehpour
- Department of Radiation Physics , The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, Texas, 77030-4000, UNITED STATES
| |
Collapse
|
2
|
Salehjahromi M, Karpinets TV, Sujit SJ, Qayati M, Chen P, Aminu M, Saad MB, Bandyopadhyay R, Hong L, Sheshadri A, Lin J, Antonoff MB, Sepesi B, Ostrin EJ, Toumazis I, Huang P, Cheng C, Cascone T, Vokes NI, Behrens C, Siewerdsen JH, Hazle JD, Chang JY, Zhang J, Lu Y, Godoy MCB, Chung C, Jaffray D, Wistuba I, Lee JJ, Vaporciyan AA, Gibbons DL, Gladish G, Heymach JV, Wu CC, Zhang J, Wu J. Synthetic PET from CT improves diagnosis and prognosis for lung cancer: Proof of concept. Cell Rep Med 2024; 5:101463. [PMID: 38471502 PMCID: PMC10983039 DOI: 10.1016/j.xcrm.2024.101463] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2023] [Revised: 09/07/2023] [Accepted: 02/15/2024] [Indexed: 03/14/2024]
Abstract
[18F]Fluorodeoxyglucose positron emission tomography (FDG-PET) and computed tomography (CT) are indispensable components in modern medicine. Although PET can provide additional diagnostic value, it is costly and not universally accessible, particularly in low-income countries. To bridge this gap, we have developed a conditional generative adversarial network pipeline that can produce FDG-PET from diagnostic CT scans based on multi-center multi-modal lung cancer datasets (n = 1,478). Synthetic PET images are validated across imaging, biological, and clinical aspects. Radiologists confirm comparable imaging quality and tumor contrast between synthetic and actual PET scans. Radiogenomics analysis further proves that the dysregulated cancer hallmark pathways of synthetic PET are consistent with actual PET. We also demonstrate the clinical values of synthetic PET in improving lung cancer diagnosis, staging, risk prediction, and prognosis. Taken together, this proof-of-concept study testifies to the feasibility of applying deep learning to obtain high-fidelity PET translated from CT.
Collapse
Affiliation(s)
| | | | - Sheeba J Sujit
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
| | - Mohamed Qayati
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
| | - Pingjun Chen
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
| | - Muhammad Aminu
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
| | - Maliazurina B Saad
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
| | | | - Lingzhi Hong
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Ajay Sheshadri
- Department of Pulmonary Medicine, MD Anderson Cancer Center, Houston, TX USA
| | - Julie Lin
- Department of Pulmonary Medicine, MD Anderson Cancer Center, Houston, TX USA
| | - Mara B Antonoff
- Department of Thoracic and Cardiovascular Surgery, MD Anderson Cancer Center, Houston, TX, USA
| | - Boris Sepesi
- Department of Thoracic and Cardiovascular Surgery, MD Anderson Cancer Center, Houston, TX, USA
| | - Edwin J Ostrin
- Department of General Internal Medicine, MD Anderson Cancer Center, Houston, TX, USA
| | - Iakovos Toumazis
- Department of Health Services Research, MD Anderson Cancer Center, Houston, TX, USA
| | - Peng Huang
- Department of Oncology, The Sidney Kimmel Comprehensive Cancer Center at Johns Hopkins, Baltimore, MD, USA
| | - Chao Cheng
- Institute for Clinical and Translational Research, Baylor College of Medicine, Houston, TX, USA
| | - Tina Cascone
- Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Natalie I Vokes
- Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Carmen Behrens
- Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Jeffrey H Siewerdsen
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA; Institute for Data Science in Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - John D Hazle
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
| | - Joe Y Chang
- Department of Radiation Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Jianhua Zhang
- Department of Genomic Medicine, MD Anderson Cancer Center, Houston, TX, USA
| | - Yang Lu
- Department of Nuclear Medicine, MD Anderson Cancer Center, Houston, TX, USA
| | - Myrna C B Godoy
- Department of Thoracic Imaging, MD Anderson Cancer Center, Houston, TX, USA
| | - Caroline Chung
- Department of Radiation Oncology, MD Anderson Cancer Center, Houston, TX, USA; Institute for Data Science in Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - David Jaffray
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA; Institute for Data Science in Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Ignacio Wistuba
- Department of Translational Molecular Pathology, MD Anderson Cancer Center, Houston, TX, USA
| | - J Jack Lee
- Department of Biostatistics, MD Anderson Cancer Center, Houston, TX, USA
| | - Ara A Vaporciyan
- Department of Thoracic and Cardiovascular Surgery, MD Anderson Cancer Center, Houston, TX, USA
| | - Don L Gibbons
- Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Gregory Gladish
- Department of Thoracic Imaging, MD Anderson Cancer Center, Houston, TX, USA
| | - John V Heymach
- Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Carol C Wu
- Department of Thoracic Imaging, MD Anderson Cancer Center, Houston, TX, USA
| | - Jianjun Zhang
- Department of Genomic Medicine, MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA; Lung Cancer Genomics Program, MD Anderson Cancer Center, Houston, TX, USA; Lung Cancer Interception Program, MD Anderson Cancer Center, Houston, TX, USA
| | - Jia Wu
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA; Institute for Data Science in Oncology, MD Anderson Cancer Center, Houston, TX, USA.
| |
Collapse
|
3
|
Cavalli F, Mikkelsen B, Weiderpass E, Sullivan R, Jaffray D, Gospodarowicz M. World Oncology Forum amplifies its appeal in global fight against cancer. Lancet Oncol 2024; 25:170-174. [PMID: 38301688 DOI: 10.1016/s1470-2045(24)00010-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Revised: 01/04/2024] [Accepted: 01/05/2024] [Indexed: 02/03/2024]
Affiliation(s)
- Franco Cavalli
- European School of Oncology, Bellinzona, Switzerland; Institute for Oncology Research, 6500 Bellinzona, Switzerland.
| | - Bente Mikkelsen
- UHC/Communicable and Noncommunicable Diseases, World Health Organization Headquarters, Geneva, Switzerland
| | | | | | - David Jaffray
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Mary Gospodarowicz
- Princess Margaret Cancer Centre, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
4
|
Casar B, Mendez I, Gershkevitsh E, Wegener S, Jaffray D, Heaton R, Pesznyak C, Stelczer G, Bulski W, Chełminski K, Smirnov G, Antipina N, Beavis AW, Harding N, Jurković S, Hwang MS, Saiful Huq M. On dosimetric characteristics of detectors for relative dosimetry in small fields: a multicenter experimental study. Phys Med Biol 2024; 69:035009. [PMID: 38091616 DOI: 10.1088/1361-6560/ad154c] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2023] [Accepted: 12/13/2023] [Indexed: 01/25/2024]
Abstract
Objective. In this multicentric collaborative study, we aimed to verify whether the selected radiation detectors satisfy the requirements of TRS-483 Code of Practice for relative small field dosimetry in megavoltage photon beams used in radiotherapy, by investigating four dosimetric characteristics. Furthermore, we intended to analyze and complement the recommendations given in TRS-483.Approach. Short-term stability, dose linearity, dose-rate dependence, and leakage were determined for 17 models of detectors considered suitable for small field dosimetry. Altogether, 47 detectors were used in this study across ten institutions. Photon beams with 6 and 10 MV, with and without flattening filters, generated by Elekta Versa HDTMor Varian TrueBeamTMlinear accelerators, were used.Main results. The tolerance level of 0.1% for stability was fulfilled by 70% of the data points. For the determination of dose linearity, two methods were considered. Results from the use of a stricter method show that the guideline of 0.1% for dose linearity is not attainable for most of the detectors used in the study. Following the second approach (squared Pearson's correlation coefficientr2), it was found that 100% of the data fulfill the criteriar2> 0.999 (0.1% guideline for tolerance). Less than 50% of all data points satisfied the published tolerance of 0.1% for dose-rate dependence. Almost all data points (98.2%) satisfied the 0.1% criterion for leakage.Significance. For short-term stability (repeatability), it was found that the 0.1% guideline could not be met. Therefore, a less rigorous criterion of 0.25% is proposed. For dose linearity, our recommendation is to adopt a simple and clear methodology and to define an achievable tolerance based on the experimental data. For dose-rate dependence, a realistic criterion of 1% is proposed instead of the present 0.1%. Agreement was found with published guidelines for background signal (leakage).
Collapse
Affiliation(s)
- Božidar Casar
- Institute of Oncology Ljubljana, Ljubljana, Slovenia
- Faculty of Natural Sciences and Mathematics, University of Maribor, Slovenia
| | - Ignasi Mendez
- Institute of Oncology Ljubljana, Ljubljana, Slovenia
| | | | - Sonja Wegener
- University of Wuerzburg, Radiation Oncology, Wuerzburg, Germany
| | | | | | | | | | - Wojciech Bulski
- Maria Skłodowska-Curie National Research Institute of Oncology, Warsaw, Poland
| | | | | | | | - Andrew W Beavis
- Hull University Teaching Hospitals NHS Trust, Hull, United Kingdom
| | - Nicholas Harding
- Hull University Teaching Hospitals NHS Trust, Hull, United Kingdom
| | - Slaven Jurković
- Medical Physics Department, University Hospital Rijeka, Rijeka, Croatia
- Faculty of Medicine, University of Rijeka, Croatia
| | - Min-Sig Hwang
- University of Pittsburgh School of Medicine and UPMC Hillman Cancer Center, Pittsburgh, PA, United States of America
| | - M Saiful Huq
- Department of Radiation Oncology, Division of Medical Physics, University of Pittsburgh School of Medicine and UPMC Hillman Cancer Center, Pittsburgh, PA, United States of America
| |
Collapse
|
5
|
Insley B, Bartkoski D, Balter P, Prajapati S, Tailor R, Salehpour M, Jaffray D. Proof-of-concept for a thin conical X-ray target optimized for intensity and directionality for use in a carbon nanotube-based compact X-ray tube. Med Phys 2024; 51:447-463. [PMID: 37947472 DOI: 10.1002/mp.16835] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Revised: 10/20/2023] [Accepted: 10/29/2023] [Indexed: 11/12/2023] Open
Abstract
BACKGROUND Carbon nanotube-based cold cathode technology has revolutionized the miniaturization of X-ray tubes. However, current applications of these devices required optimization for large, uniform fields with low intensity. PURPOSE This work investigated the feasibility and radiological characteristics of a novel conical X-ray target optimized for high intensity and high directionality to be used in a compact X-ray tube. METHODS The proposed device uses an ultrathin, conical tungsten-diamond target that exhibits significant heat loading while maintaining a small focal spot size and promoting forward-directedness of the X-ray field through preferential attenuation of oblique-angled photons. The electrostatic and thermal properties of the theoretical tube were calculated and analyzed using COMSOL Multiphysics software. The production, transport, and calculation of radiological properties associated with the resultant X-ray field were performed using the Geant4 toolkit via its wrapper, TOPAS. RESULTS Heat transfer analysis of this X-ray tube demonstrated the feasibility of a 200-kV electron beam bombarding the proposed target at a maximum current of 100 mA using a 1-ms symmetric duty cycle. The cathode of the X-ray tube was designed to be segmented into nine switchable electrical segments for modulation of the focal spot size from 0.4- to 10.8-mm. After importing the COMSOL-derived electron beam into TOPAS for X-ray production simulations, radiological analysis of the resultant field demonstrated high levels of intrinsic beam collimation while maintaining high intensity. A maximum dose rate of 17,887 cGy/min was calculated for 1-mm depth in water at 7-cm distance. CONCLUSIONS The proposed X-ray tube design can create highly directional X-ray fields with superior fluence compared to that of current commercial X-ray tubes of comparable size.
Collapse
Affiliation(s)
- Ben Insley
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Dirk Bartkoski
- Empyrean Medical Systems, Inc., 950 Peninsula Corp Cir, Boca Raton, USA
| | - Peter Balter
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Surendra Prajapati
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Ramesh Tailor
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Mohammad Salehpour
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - David Jaffray
- Division of Office of the Sr. VP & Chief Technology and Digital Officer, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| |
Collapse
|
6
|
Bitterman DS, Gensheimer MF, Jaffray D, Pryma DA, Jiang SB, Morin O, Ginart JB, Upadhaya T, Vallis KA, Buatti JM, Deasy J, Hsiao HT, Chung C, Fuller CD, Greenspan E, Cloyd-Warwick K, Courdy S, Mao A, Barnholtz-Sloan J, Topaloglu U, Hands I, Maurer I, Terry M, Curran WJ, Le QT, Nadaf S, Kibbe W. Cancer Informatics for Cancer Centers: Sharing Ideas on How to Build an Artificial Intelligence-Ready Informatics Ecosystem for Radiation Oncology. JCO Clin Cancer Inform 2023; 7:e2300136. [PMID: 38055914 PMCID: PMC10703125 DOI: 10.1200/cci.23.00136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Revised: 08/15/2023] [Accepted: 10/16/2023] [Indexed: 12/08/2023] Open
Abstract
In August 2022, the Cancer Informatics for Cancer Centers brought together cancer informatics leaders for its biannual symposium, Precision Medicine Applications in Radiation Oncology, co-chaired by Quynh-Thu Le, MD (Stanford University), and Walter J. Curran, MD (GenesisCare). Over the course of 3 days, presenters discussed a range of topics relevant to radiation oncology and the cancer informatics community more broadly, including biomarker development, decision support algorithms, novel imaging tools, theranostics, and artificial intelligence (AI) for the radiotherapy workflow. Since the symposium, there has been an impressive shift in the promise and potential for integration of AI in clinical care, accelerated in large part by major advances in generative AI. AI is now poised more than ever to revolutionize cancer care. Radiation oncology is a field that uses and generates a large amount of digital data and is therefore likely to be one of the first fields to be transformed by AI. As experts in the collection, management, and analysis of these data, the informatics community will take a leading role in ensuring that radiation oncology is prepared to take full advantage of these technological advances. In this report, we provide highlights from the symposium, which took place in Santa Barbara, California, from August 29 to 31, 2022. We discuss lessons learned from the symposium for data acquisition, management, representation, and sharing, and put these themes into context to prepare radiation oncology for the successful and safe integration of AI and informatics technologies.
Collapse
Affiliation(s)
- Danielle S. Bitterman
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Brigham and Women's Hospital/Dana-Farber Cancer Institute, Boston, MA
| | - Michael F. Gensheimer
- Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA
| | - David Jaffray
- Department of Radiation Physics, M.D. Anderson Cancer Center, Houston, TX
| | - Daniel A. Pryma
- Abramson Cancer Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Steve B. Jiang
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX
| | - Olivier Morin
- Department of Radiation Oncology, MEDomics Laboratory, University of California San Francisco, San Francisco, CA
| | - Jorge Barrios Ginart
- Department of Radiation Oncology, MEDomics Laboratory, University of California San Francisco, San Francisco, CA
| | - Taman Upadhaya
- Department of Radiation Oncology, MEDomics Laboratory, University of California San Francisco, San Francisco, CA
| | - Katherine A. Vallis
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
| | - John M. Buatti
- Department of Oncology, University of Oxford, Oxford, United Kingdom
| | - Joseph Deasy
- Department of Radiation Oncology, University of Iowa Carver College of Medicine, Iowa City, IA
| | - H. Timothy Hsiao
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Caroline Chung
- Department of Scientific Affairs, American Society for Radiation Oncology, Arlington, VA
| | - Clifton D. Fuller
- Department of Scientific Affairs, American Society for Radiation Oncology, Arlington, VA
| | - Emily Greenspan
- Department of Radiation Oncology, M.D. Anderson Cancer Center, Houston, TX
| | - Kristy Cloyd-Warwick
- Center for Biomedical Informatics and Information Technology, National Cancer Institute, Rockville, MD
| | | | | | - Jill Barnholtz-Sloan
- Department of Radiation Oncology, M.D. Anderson Cancer Center, Houston, TX
- Center for Informatics, Digital Vertical, City of Hope National Comprehensive Cancer Center, Los Angeles, CA
| | - Umit Topaloglu
- Department of Radiation Oncology, M.D. Anderson Cancer Center, Houston, TX
| | - Isaac Hands
- Division of Cancer Epidemiology and Genetics, National Cancer Institute, Rockville, MD
- Cancer Research Informatics Shared Resource Facility, University of Kentucky Markey Cancer Center, Lexington, NY
| | | | | | | | - Quynh-Thu Le
- Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA
| | - Sorena Nadaf
- Department of Radiation Oncology, Emory University, Atlanta, GA
| | - Warren Kibbe
- Cancer Center Informatics Society, Los Angeles, CA
| |
Collapse
|
7
|
Al-Tashi Q, Saad MB, Sheshadri A, Wu CC, Chang JY, Al-Lazikani B, Gibbons C, Vokes NI, Zhang J, Lee JJ, Heymach JV, Jaffray D, Mirjalili S, Wu J. SwarmDeepSurv: swarm intelligence advances deep survival network for prognostic radiomics signatures in four solid cancers. Patterns (N Y) 2023; 4:100777. [PMID: 37602223 PMCID: PMC10435962 DOI: 10.1016/j.patter.2023.100777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Revised: 04/18/2023] [Accepted: 05/26/2023] [Indexed: 08/22/2023]
Abstract
Survival models exist to study relationships between biomarkers and treatment effects. Deep learning-powered survival models supersede the classical Cox proportional hazards (CoxPH) model, but substantial performance drops were observed on high-dimensional features because of irrelevant/redundant information. To fill this gap, we proposed SwarmDeepSurv by integrating swarm intelligence algorithms with the deep survival model. Furthermore, four objective functions were designed to optimize prognostic prediction while regularizing selected feature numbers. When testing on multicenter sets (n = 1,058) of four different cancer types, SwarmDeepSurv was less prone to overfitting and achieved optimal patient risk stratification compared with popular survival modeling algorithms. Strikingly, SwarmDeepSurv selected different features compared with classical feature selection algorithms, including the least absolute shrinkage and selection operator (LASSO), with nearly no feature overlapping across these models. Taken together, SwarmDeepSurv offers an alternative approach to model relationships between radiomics features and survival endpoints, which can further extend to study other input data types including genomics.
Collapse
Affiliation(s)
- Qasem Al-Tashi
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Maliazurina B. Saad
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Ajay Sheshadri
- Department of Pulmonary Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Carol C. Wu
- Department of Thoracic Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Joe Y. Chang
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Bissan Al-Lazikani
- Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Christopher Gibbons
- Section of Patient-Centered Analytics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Natalie I. Vokes
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Jianjun Zhang
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - J. Jack Lee
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - John V. Heymach
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - David Jaffray
- Office of the Chief Technology and Digital Officer, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Seyedali Mirjalili
- Centre for Artificial Intelligence Research and Optimization, Torrens University Australia, Fortitude Valley, Brisbane, QLD 4006, Australia
- Yonsei Frontier Lab, Yonsei University, Seoul 03722, Korea
- University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary
| | - Jia Wu
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| |
Collapse
|
8
|
Court L, Aggarwal A, Burger H, Cardenas C, Chung C, Douglas R, du Toit M, Jaffray D, Jhingran A, Mejia M, Mumme R, Muya S, Naidoo K, Ndumbalo J, Nealon K, Netherton T, Nguyen C, Olanrewaju N, Parkes J, Shaw W, Trauernicht C, Xu M, Yang J, Zhang L, Simonds H, Beadle BM. Addressing the Global Expertise Gap in Radiation Oncology: The Radiation Planning Assistant. JCO Glob Oncol 2023; 9:e2200431. [PMID: 37471671 PMCID: PMC10581646 DOI: 10.1200/go.22.00431] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2022] [Revised: 02/08/2023] [Accepted: 04/24/2023] [Indexed: 07/22/2023] Open
Abstract
PURPOSE Automation, including the use of artificial intelligence, has been identified as a possible opportunity to help reduce the gap in access and quality for radiotherapy and other aspects of cancer care. The Radiation Planning Assistant (RPA) project was conceived in 2015 (and funded in 2016) to use automated contouring and treatment planning algorithms to support the efforts of oncologists in low- and middle-income countries, allowing them to scale their efforts and treat more patients safely and efficiently (to increase access). DESIGN In this review, we discuss the development of the RPA, with a particular focus on clinical acceptability and safety/risk across jurisdictions as these are important indicators for the successful future deployment of the RPA to increase radiotherapy availability and ameliorate global disparities in access to radiation oncology. RESULTS RPA tools will be offered through a webpage, where users can upload computed tomography data sets and download automatically generated contours and treatment plans. All interfaces have been designed to maximize ease of use and minimize risk. The current version of the RPA includes automated contouring and planning for head and neck cancer, cervical cancer, breast cancer, and metastases to the brain. CONCLUSION The RPA has been designed to bring high-quality treatment planning to more patients across the world, and it may encourage greater investment in treatment devices and other aspects of cancer treatment.
Collapse
Affiliation(s)
- Laurence Court
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Ajay Aggarwal
- Guy's and St Thomas' Hospital, London, United Kingdom
| | - Hester Burger
- Groote Schuur Hospital, University of Cape Town, Cape Town, South Africa
| | | | - Christine Chung
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Raphael Douglas
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Monique du Toit
- Tygerberg Hospital, Stellenbosch University, Cape Town, South Africa
| | - David Jaffray
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Anuja Jhingran
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Michael Mejia
- Benavides Cancer Institute, University of Santo Tomas, Manila, Philippines
| | - Raymond Mumme
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | | | - Komeela Naidoo
- Tygerberg Hospital, Stellenbosch University, Cape Town, South Africa
| | | | - Kelly Nealon
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | | | | | - Niki Olanrewaju
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Jeannette Parkes
- Groote Schuur Hospital, University of Cape Town, Cape Town, South Africa
| | - Willie Shaw
- University of the Free State, Bloemfontein, South Africa
| | | | - Melody Xu
- University of California San Francisco, San Francisco, CA
| | - Jinzhong Yang
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Lifei Zhang
- The University of Texas MD Anderson Cancer Center, Houston, TX
| | | | | |
Collapse
|
9
|
Saad MB, Hong L, Aminu M, Vokes NI, Chen P, Salehjahromi M, Qin K, Sujit SJ, Lu X, Young E, Al-Tashi Q, Qureshi R, Wu CC, Carter BW, Lin SH, Lee PP, Gandhi S, Chang JY, Li R, Gensheimer MF, Wakelee HA, Neal JW, Lee HS, Cheng C, Velcheti V, Lou Y, Petranovic M, Rinsurongkawong W, Le X, Rinsurongkawong V, Spelman A, Elamin YY, Negrao MV, Skoulidis F, Gay CM, Cascone T, Antonoff MB, Sepesi B, Lewis J, Wistuba II, Hazle JD, Chung C, Jaffray D, Gibbons DL, Vaporciyan A, Lee JJ, Heymach JV, Zhang J, Wu J. Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study. Lancet Digit Health 2023; 5:e404-e420. [PMID: 37268451 PMCID: PMC10330920 DOI: 10.1016/s2589-7500(23)00082-1] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2022] [Revised: 01/28/2023] [Accepted: 04/04/2023] [Indexed: 06/04/2023]
Abstract
BACKGROUND Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. METHODS In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. FINDINGS Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features. INTERPRETATION This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer. FUNDING National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith.
Collapse
Affiliation(s)
- Maliazurina B Saad
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Lingzhi Hong
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Muhammad Aminu
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Natalie I Vokes
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Pingjun Chen
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Morteza Salehjahromi
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Kang Qin
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Sheeba J Sujit
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Xuetao Lu
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Elliana Young
- Department of Enterprise Data Engineering and Analytics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Qasem Al-Tashi
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Rizwan Qureshi
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Carol C Wu
- Department of Thoracic Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Brett W Carter
- Department of Thoracic Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Steven H Lin
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Percy P Lee
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Oncology, City of Hope National Medical Center, Los Angeles, CA, USA
| | - Saumil Gandhi
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Joe Y Chang
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Ruijiang Li
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Michael F Gensheimer
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Heather A Wakelee
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA; Stanford Cancer Institute, Stanford, CA, USA
| | - Joel W Neal
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA; Stanford Cancer Institute, Stanford, CA, USA
| | - Hyun-Sung Lee
- Systems Onco-Immunology Laboratory, David J Sugarbaker Division of Thoracic Surgery, Michael E DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX, USA
| | - Chao Cheng
- Institute for Clinical and Translational Research, Baylor College of Medicine, Houston, TX, USA
| | - Vamsidhar Velcheti
- Department of Hematology and Oncology, New York University Langone Health, New York, NY, USA
| | - Yanyan Lou
- Division of Hematology and Oncology, Mayo Clinic, Jacksonville, FL, USA
| | - Milena Petranovic
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Waree Rinsurongkawong
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Xiuning Le
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Vadeerat Rinsurongkawong
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Amy Spelman
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Yasir Y Elamin
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Marcelo V Negrao
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Ferdinandos Skoulidis
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Carl M Gay
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Tina Cascone
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Mara B Antonoff
- Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Boris Sepesi
- Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Jeff Lewis
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Ignacio I Wistuba
- Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - John D Hazle
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Caroline Chung
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Neuroradiology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - David Jaffray
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Don L Gibbons
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Ara Vaporciyan
- Department of Thoracic and Cardiovascular Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - J Jack Lee
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - John V Heymach
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
| | - Jianjun Zhang
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
| | - Jia Wu
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
| |
Collapse
|
10
|
Mehrens H, Molineu A, Hernandez N, Court L, Howell R, Jaffray D, Peterson CB, Pollard-Larkin J, Kry SF. Characterizing the interplay of treatment parameters and complexity and their impact on performance on an IROC IMRT phantom using machine learning. Radiother Oncol 2023; 182:109577. [PMID: 36841341 PMCID: PMC10121814 DOI: 10.1016/j.radonc.2023.109577] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Revised: 02/06/2023] [Accepted: 02/12/2023] [Indexed: 02/26/2023]
Abstract
AIM OF THE STUDY To elucidate the important factors and their interplay that drive performance on IMRT phantoms from the Imaging and Radiation Oncology Core (IROC). METHODS IROC's IMRT head and neck phantom contains two targets and an organ at risk. Point and 2D dose are measured by TLDs and film, respectively. 1,542 irradiations between 2012-2020 were retrospectively analyzed based on output parameters, complexity metrics, and treatment parameters. Univariate analysis compared parameters based on pass/fail, and random forest modeling was used to predict output parameters and determine the underlying importance of the variables. RESULTS The average phantom pass rate was 92% and has not significantly improved over time. The step-and-shoot irradiation technique had significantly lower pass rates that significantly affected other treatment parameters' pass rates. The complexity of plans has significantly increased with time, and all aperture-based complexity metrics (except MCS) were associated with the probability of failure. Random forest-based prediction of failure had an accuracy of 98% on held-out test data not used in model training. While complexity metrics were the most important contributors, the specific metric depended on the set of treatment parameters used during the irradiation. CONCLUSION With the prevalence of errors in radiotherapy, understanding which parameters affect treatment delivery is vital to improve patient treatment. Complexity metrics were strongly predictive of irradiation failure; however, they are dependent on the specific treatment parameters. In addition, the use of one complexity metric is insufficient to monitor all aspects of the treatment plan.
Collapse
Affiliation(s)
- Hunter Mehrens
- IROC Houston Quality Assurance Center, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, TX, USA
| | - Andrea Molineu
- IROC Houston Quality Assurance Center, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Nadia Hernandez
- IROC Houston Quality Assurance Center, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Laurence Court
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, TX, USA
| | - Rebecca Howell
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, TX, USA
| | - David Jaffray
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Christine B Peterson
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, TX, USA
| | - Julianne Pollard-Larkin
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, TX, USA
| | - Stephen F Kry
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, TX, USA.
| |
Collapse
|
11
|
Lu SC, Swisher CL, Chung C, Jaffray D, Sidey-Gibbons C. On the importance of interpretable machine learning predictions to inform clinical decision making in oncology. Front Oncol 2023; 13:1129380. [PMID: 36925929 PMCID: PMC10013157 DOI: 10.3389/fonc.2023.1129380] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Accepted: 02/14/2023] [Indexed: 03/04/2023] Open
Abstract
Machine learning-based tools are capable of guiding individualized clinical management and decision-making by providing predictions of a patient's future health state. Through their ability to model complex nonlinear relationships, ML algorithms can often outperform traditional statistical prediction approaches, but the use of nonlinear functions can mean that ML techniques may also be less interpretable than traditional statistical methodologies. While there are benefits of intrinsic interpretability, many model-agnostic approaches now exist and can provide insight into the way in which ML systems make decisions. In this paper, we describe how different algorithms can be interpreted and introduce some techniques for interpreting complex nonlinear algorithms.
Collapse
Affiliation(s)
- Sheng-Chieh Lu
- Section of Patient-Centered Analytics, Division of Internal Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Christine L Swisher
- The Ronin Project, San Mateo, CA, United States.,The Lawrence J. Ellison Institute for Transformative Medicine, Los Angeles, CA, United States
| | - Caroline Chung
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.,Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - David Jaffray
- Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.,Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.,Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Chris Sidey-Gibbons
- Section of Patient-Centered Analytics, Division of Internal Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| |
Collapse
|
12
|
Han K, Fyles A, Shek T, Croke J, Dhani N, D'Souza D, Lee TY, Chaudary N, Bruce J, Pintilie M, Cairns R, Vines D, Pakbaz S, Jaffray D, Metser U, Rouzbahman M, Milosevic M, Koritzinsky M. A Phase II Randomized Trial of Chemoradiation with or without Metformin in Locally Advanced Cervical Cancer. Clin Cancer Res 2022; 28:5263-5271. [PMID: 36037303 DOI: 10.1158/1078-0432.ccr-22-1665] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Revised: 07/13/2022] [Accepted: 08/25/2022] [Indexed: 01/24/2023]
Abstract
PURPOSE Tumor hypoxia is associated with poor response to radiation (RT). We previously discovered a novel mechanism of metformin: enhancing tumor RT response by decreasing tumor hypoxia. We hypothesized that metformin would decrease tumor hypoxia and improve cervical cancer response to RT. PATIENTS AND METHODS A window-of-opportunity, phase II randomized trial was performed in stage IB-IVA cervical cancer. Patients underwent screening positron emission tomography (PET) imaging with hypoxia tracer fluoroazomycin arabinoside (FAZA). Only patients with FAZA uptake (hypoxic tumor) were included and randomized 2:1 to receive metformin in combination with chemoRT or chemoRT alone. A second FAZA-PET/CT scan was performed after 1 week of metformin or no intervention (control). The primary endpoint was a change in fractional hypoxic volume (FHV) between FAZA-PET scans, compared using the Wilcoxon signed-rank test. The study was closed early due to FAZA availability and the COVID-19 pandemic. RESULTS Of the 20 consented patients, 6 were excluded due to no FAZA uptake and 1 withdrew. FHV of 10 patients in the metformin arm decreased by an average of 10.2% (44.4%-34.2%) ± SD 16.9% after 1 week of metformin, compared with an average increase of 4.7% (29.1%-33.8%) ± 11.5% for the 3 controls (P = 0.027). Those with FHV reduction after metformin had significantly lower MATE2 expression. With a median follow-up of 2.8 years, the 2-year disease-free survival was 67% for the metformin arm versus 33% for controls (P = 0.09). CONCLUSIONS Metformin decreased cervical tumor hypoxia in this trial that selected for patients with hypoxic tumor. See related commentary by Lyng et al., p. 5233.
Collapse
Affiliation(s)
- Kathy Han
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada.,Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada
| | - Anthony Fyles
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - Tina Shek
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Jennifer Croke
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - Neesha Dhani
- Department of Medical Oncology, Princess Margaret Cancer Centre, University Health Network, University of Toronto, Toronto, Ontario, Canada
| | - David D'Souza
- London Regional Cancer Program, London Health Sciences Centre, Department of Oncology, Western University, London, Ontario, Canada
| | - Ting-Yim Lee
- London Regional Cancer Program, London Health Sciences Centre, Department of Oncology, Western University, London, Ontario, Canada
| | - Naz Chaudary
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Jeffrey Bruce
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Melania Pintilie
- Department of Biostatistics, University Health Network, Toronto, Ontario, Canada
| | - Rob Cairns
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Douglass Vines
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - Sara Pakbaz
- Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Ontario, Canada
| | - David Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada
| | - Ur Metser
- Joint Department of Medical Imaging, University Health Network, University of Toronto, Toronto, Ontario, Canada
| | - Marjan Rouzbahman
- Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Ontario, Canada
| | - Michael Milosevic
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada.,Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada
| | - Marianne Koritzinsky
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|
13
|
Driscoll B, Shek T, Vines D, Sun A, Jaffray D, Yeung I. Phantom Validation of a Conservation of Activity-Based Partial Volume Correction Method for Arterial Input Function in Dynamic PET Imaging. Tomography 2022; 8:842-857. [PMID: 35314646 PMCID: PMC8938778 DOI: 10.3390/tomography8020069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2022] [Revised: 03/10/2022] [Accepted: 03/16/2022] [Indexed: 11/16/2022] Open
Abstract
Dynamic PET (dPET) imaging can be utilized to perform kinetic modelling of various physiologic processes, which are exploited by the constantly expanding range of targeted radiopharmaceuticals. To date, dPET remains primarily in the research realm due to a number of technical challenges, not least of which is addressing partial volume effects (PVE) in the input function. We propose a series of equations for the correction of PVE in the input function and present the results of a validation study, based on a purpose built phantom. 18F-dPET experiments were performed using the phantom on a set of flow tubes representing large arteries, such as the aorta (1" 2.54 cm ID), down to smaller vessels, such as the iliac arteries and veins (1/4" 0.635 cm ID). When applied to the dPET experimental images, the PVE correction equations were able to successfully correct the image-derived input functions by as much as 59 ± 35% in the presence of background, which resulted in image-derived area under the curve (AUC) values within 8 ± 9% of ground truth AUC. The peak heights were similarly well corrected to within 9 ± 10% of the scaled DCE-CT curves. The same equations were then successfully applied to correct patient input functions in the aorta and internal iliac artery/vein. These straightforward algorithms can be applied to dPET images from any PET-CT scanner to restore the input function back to a more clinically representative value, without the need for high-end Time of Flight systems or Point Spread Function correction algorithms.
Collapse
Affiliation(s)
- Brandon Driscoll
- Quantitative Imaging for Personalized Cancer Medicine (QIPCM)—Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada; (T.S.); (D.J.); (I.Y.)
- Correspondence:
| | - Tina Shek
- Quantitative Imaging for Personalized Cancer Medicine (QIPCM)—Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada; (T.S.); (D.J.); (I.Y.)
| | - Douglass Vines
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON M5G 2M9, Canada; (D.V.); (A.S.)
- Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada
| | - Alex Sun
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON M5G 2M9, Canada; (D.V.); (A.S.)
- Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada
| | - David Jaffray
- Quantitative Imaging for Personalized Cancer Medicine (QIPCM)—Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada; (T.S.); (D.J.); (I.Y.)
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON M5G 2M9, Canada; (D.V.); (A.S.)
- Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada
| | - Ivan Yeung
- Quantitative Imaging for Personalized Cancer Medicine (QIPCM)—Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada; (T.S.); (D.J.); (I.Y.)
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON M5G 2M9, Canada; (D.V.); (A.S.)
- Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada
| |
Collapse
|
14
|
Jimenez JE, Dai D, Xu G, Zhao R, Li T, Pan T, Wang L, Lin Y, Wang Z, Jaffray D, Hazle JD, Macapinlac HA, Wu J, Lu Y. Lesion-Based Radiomics Signature in Pretherapy 18F-FDG PET Predicts Treatment Response to Ibrutinib in Lymphoma. Clin Nucl Med 2022; 47:209-218. [PMID: 35020640 PMCID: PMC8851692 DOI: 10.1097/rlu.0000000000004060] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
PURPOSE The aim of this study was to develop a pretherapy PET/CT-based prediction model for treatment response to ibrutinib in lymphoma patients. PATIENTS AND METHODS One hundred sixty-nine lymphoma patients with 2441 lesions were studied retrospectively. All eligible lymphomas on pretherapy 18F-FDG PET images were contoured and segmented for radiomic analysis. Lesion- and patient-based responsiveness to ibrutinib was determined retrospectively using the Lugano classification. PET radiomic features were extracted. A radiomic model was built to predict ibrutinib response. The prognostic significance of the radiomic model was evaluated independently in a test cohort and compared with conventional PET metrics: SUVmax, metabolic tumor volume, and total lesion glycolysis. RESULTS The radiomic model had an area under the receiver operating characteristic curve (ROC AUC) of 0.860 (sensitivity, 92.9%, specificity, 81.4%; P < 0.001) for predicting response to ibrutinib, outperforming the SUVmax (ROC AUC, 0.519; P = 0.823), metabolic tumor volume (ROC AUC, 0.579; P = 0.412), total lesion glycolysis (ROC AUC, 0.576; P = 0.199), and a composite model built using all 3 (ROC AUC, 0.562; P = 0.046). The radiomic model increased the probability of accurately predicting ibrutinib-responsive lesions from 84.8% (pretest) to 96.5% (posttest). At the patient level, the model's performance (ROC AUC = 0.811; P = 0.007) was superior to that of conventional PET metrics. Furthermore, the radiomic model showed robustness when validated in treatment subgroups: first (ROC AUC, 0.916; P < 0.001) versus second or greater (ROC AUC, 0.842; P < 0.001) line of defense and single treatment (ROC AUC, 0.931; P < 0.001) versus multiple treatments (ROC AUC, 0.824; P < 0.001). CONCLUSIONS We developed and validated a pretherapy PET-based radiomic model to predict response to treatment with ibrutinib in a diverse cohort of lymphoma patients.
Collapse
Affiliation(s)
- Jorge E Jimenez
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Dong Dai
- Department of Nuclear Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Guofan Xu
- Department of Nuclear Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Ruiyang Zhao
- Department of Electrical and Computer Engineering, Rice University, Houston, TX
| | - Tengfei Li
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Tinsu Pan
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Linghua Wang
- Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Yingyan Lin
- Department of Electrical and Computer Engineering, Rice University, Houston, TX
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX
| | - David Jaffray
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - John D. Hazle
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Homer A. Macapinlac
- Department of Nuclear Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Jia Wu
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Yang Lu
- Department of Nuclear Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| |
Collapse
|
15
|
Noorbakhsh C, Liu Y, Lang F, DeGroot J, Akdemir K, Alfaro-Munoz K, Parker-Kerrigan B, Jaffray D, Huse J, Bhat K, Puduvalli V, Kannan K. EPCO-19. SYSTEMS BIOLOGY APPROACH ON MGMT-METHYLATED, IDH WILD-TYPE SHORT-TERM SURVIVORS REVEALS MUTATIONS IN THE BRCA1-MEDIATED DNA REPAIR SIGNALING PATHWAY. Neuro Oncol 2021. [DOI: 10.1093/neuonc/noab196.018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Abstract
Numerous multi-omic studies have revealed the vast molecular complexity of glioblastoma; however, these studies have failed to identify actionable drivers for definitive therapy. Unlike conventional relational data analysis methods used to examine such data, systems biology approaches using graph databases have emerged as powerful tools with flexibility and scalability needed to reveal specific vulnerabilities. Here we demonstrate the utility of a patient-centric graph database in identifying novel factors associated with poor outcome (survival < 8 months) in patients with MGMT promoter methylated glioblastoma. Using a cohort of 112 patients from the TCGA database, we integrated high-impact mutations with MGMT methylation status. Network analysis revealed three subnetworks, consisting of (a) methylated patients, the M-network, (b) methylated and unmethylated patients, the MU-network, and (c) unmethylated patients, the U-network. In addition, querying the genes in the M-network revealed three key molecules in the DNA repair pathway, namely, FANC-A, FANC-E, and MYUTH, mutated in five patients (q-value < 2.3E-02). Moreover, we observed that BRCA1 mediates other critical signaling molecules in the MU-network. Interestingly, in intermediate (8-24 months) or long-term ( >24 months) survivors networks, this pathway is not implicated. In light of recent studies implicating BRCA1 modulating temozolomide resistance in GBM sphere-forming cells and BRCA1’s protein expression predicting survival in patients, this result suggests that mutations in BRCA1-mediated DNA repair pathways hinder response to chemotherapy despite methylated MGMT, reducing the survival in patients. Besides this novel result explaining low survival in MGMT methylated patients through a synthesis of epigenetic and genetic data, our framework provides a novel and compelling paradigm for data integration at various scales from molecular events in a single patient’s tumor to integrating the molecular profile (or genotype) with phenotypic characteristics at the population level. We will present additional insights derived from this analysis at the SNO annual meeting.
Collapse
Affiliation(s)
| | - Yang Liu
- Rice University, Houston, TX, USA
| | - Frederick Lang
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - John DeGroot
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Kadir Akdemir
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | | | | | - David Jaffray
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Jason Huse
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Krishna Bhat
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Vinay Puduvalli
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Kasthuri Kannan
- University of Texas MD Anderson Cancer Center, Houston, TX, USA
| |
Collapse
|
16
|
El Hussein S, Chen P, Medeiros LJ, Wistuba II, Jaffray D, Wu J, Khoury JD. Artificial intelligence strategy integrating morphologic and architectural biomarkers provides robust diagnostic accuracy for disease progression in chronic lymphocytic leukemia. J Pathol 2021; 256:4-14. [PMID: 34505705 DOI: 10.1002/path.5795] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2021] [Revised: 08/04/2021] [Accepted: 09/03/2021] [Indexed: 12/17/2022]
Abstract
Artificial intelligence-based tools designed to assist in the diagnosis of lymphoid neoplasms remain limited. The development of such tools can add value as a diagnostic aid in the evaluation of tissue samples involved by lymphoma. A common diagnostic question is the determination of chronic lymphocytic leukemia (CLL) progression to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) in patients who develop progressive disease. The morphologic assessment of CLL, aCLL, and RT can be diagnostically challenging. Using established diagnostic criteria of CLL progression/transformation, we designed four artificial intelligence-constructed biomarkers based on cytologic (nuclear size and nuclear intensity) and architectural (cellular density and cell to nearest-neighbor distance) features. We analyzed the predictive value of implementing these biomarkers individually and then in an iterative sequential manner to distinguish tissue samples with CLL, aCLL, and RT. Our model, based on these four morphologic biomarker attributes, achieved a robust analytic accuracy. This study suggests that biomarkers identified using artificial intelligence-based tools can be used to assist in the diagnostic evaluation of tissue samples from patients with CLL who develop aggressive disease features. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Collapse
Affiliation(s)
- Siba El Hussein
- Department of Pathology, The University of Rochester Medical Center, Rochester, NY, USA.,Department of Hematopathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Pingjun Chen
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - L Jeffrey Medeiros
- Department of Hematopathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Ignacio I Wistuba
- Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - David Jaffray
- Department of Technology and Digital Office, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Jia Wu
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Joseph D Khoury
- Department of Hematopathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| |
Collapse
|
17
|
Wu J, Li C, Gensheimer M, Padda S, Kato F, Shirato H, Wei Y, Schönlieb CB, Price SJ, Jaffray D, Heymach J, Neal JW, Loo BW, Wakelee H, Diehn M, Li R. Radiological tumor classification across imaging modality and histology. NAT MACH INTELL 2021; 3:787-798. [PMID: 34841195 PMCID: PMC8612063 DOI: 10.1038/s42256-021-00377-0] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Accepted: 06/24/2021] [Indexed: 02/07/2023]
Abstract
Radiomics refers to the high-throughput extraction of quantitative features from radiological scans and is widely used to search for imaging biomarkers for prediction of clinical outcomes. Current radiomic signatures suffer from limited reproducibility and generalizability, because most features are dependent on imaging modality and tumor histology, making them sensitive to variations in scan protocol. Here, we propose novel radiological features that are specially designed to ensure compatibility across diverse tissues and imaging contrast. These features provide systematic characterization of tumor morphology and spatial heterogeneity. In an international multi-institution study of 1,682 patients, we discover and validate four unifying imaging subtypes across three malignancies and two major imaging modalities. These tumor subtypes demonstrate distinct molecular characteristics and prognoses after conventional therapies. In advanced lung cancer treated with immunotherapy, one subtype is associated with improved survival and increased tumor-infiltrating lymphocytes compared with the others. Deep learning enables automatic tumor segmentation and reproducible subtype identification, which can facilitate practical implementation. The unifying radiological tumor classification may inform prognosis and treatment response for precision medicine.
Collapse
Affiliation(s)
- Jia Wu
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
- Department of Thoracic and Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Chao Li
- The Centre for Mathematical Imaging in Healthcare, Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK
- Cambridge Brain Tumor Imaging Laboratory, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK
| | - Michael Gensheimer
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Sukhmani Padda
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA
| | - Fumi Kato
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, Sapporo, Hokkaido, Japan
| | - Hiroki Shirato
- Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo, Hokkaido, Japan
| | - Yiran Wei
- Cambridge Brain Tumor Imaging Laboratory, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK
| | | | - Stephen John Price
- Cambridge Brain Tumor Imaging Laboratory, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK
| | - David Jaffray
- Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
- Office of the Chief Technology and Digital Officer, MD Anderson Cancer Center, Houston, TX, USA
| | - John Heymach
- Department of Thoracic and Head and Neck Medical Oncology, MD Anderson Cancer Center, Houston, TX, USA
| | - Joel W Neal
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA
| | - Billy W Loo
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Heather Wakelee
- Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, USA
| | - Maximilian Diehn
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Ruijiang Li
- Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA
| |
Collapse
|
18
|
Driscoll B, Vines D, Shek T, Publicover J, Yeung I, Breen S, Jaffray D. 4D-CT Attenuation Correction in Respiratory-Gated PET for Hypoxia Imaging: Is It Really Beneficial? ACTA ACUST UNITED AC 2021; 6:241-249. [PMID: 32548302 PMCID: PMC7289254 DOI: 10.18383/j.tom.2019.00027] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Previous literature has shown that 4D respiratory-gated positron emission tomography (PET) is beneficial for quantitative analysis and defining targets for boosting therapy. However the case for addition of a phase-matched 4D-computed tomography (CT) for attenuation correction (AC) is less clear. We seek to validate the use of 4D-CT for AC and investigate the impact of motion correction for low signal-to-background PET imaging of hypoxia using radiotracers such as FAZA and FMISO. A new insert for the Modus Medicals' QUASAR™ Programmable Respiratory Motion Phantom was developed in which a 3D-printed sphere was placed within the "lung" compartment while an additional compartment is added to simulate muscle/blood compartment required for hypoxia quantification. Experiments are performed at 4:1 or 2:1 signal-to-background ratio consistent with clinical FAZA and FMISO imaging. Motion blur was significant in terms of SUVmax, mean, and peak for motion ≥1 cm and could be significantly reduced (from 20% to 8% at 2-cm motion) for all 4D-PET-gated reconstructions. The effect of attenuation method on precision was significant (σ2 hCT-AC = 5.5%/4.7%/2.7% vs σ2 4D-CT-AC = 0.5%/0.6%/0.7% [max%/peak%/mean% variance]). The simulated hypoxic fraction also significantly decreased under conditions of 2-cm amplitude motion from 55% to 20% and was almost fully recovered (HF = 0.52 for phase-matched 4D-CT) using gated PET. 4D-gated PET is valuable under conditions of low radiotracer uptake found in hypoxia imaging. This work demonstrates the importance of using 4D-CT for AC when performing gated PET based on its significantly improved precision over helical CT.
Collapse
Affiliation(s)
- Brandon Driscoll
- Quantitative Imaging for Personalized Cancer Medicine Program-Techna Institute, University Health Network, Toronto, ON, Canada
| | - Douglass Vines
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON, Canada; and.,Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| | - Tina Shek
- Quantitative Imaging for Personalized Cancer Medicine Program-Techna Institute, University Health Network, Toronto, ON, Canada
| | - Julia Publicover
- Quantitative Imaging for Personalized Cancer Medicine Program-Techna Institute, University Health Network, Toronto, ON, Canada
| | - Ivan Yeung
- Quantitative Imaging for Personalized Cancer Medicine Program-Techna Institute, University Health Network, Toronto, ON, Canada.,Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON, Canada; and.,Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| | - Stephen Breen
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON, Canada; and.,Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| | - David Jaffray
- Quantitative Imaging for Personalized Cancer Medicine Program-Techna Institute, University Health Network, Toronto, ON, Canada.,Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, ON, Canada; and.,Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
19
|
Mahadevaiah G, Rv P, Bermejo I, Jaffray D, Dekker A, Wee L. Artificial intelligence-based clinical decision support in modern medical physics: Selection, acceptance, commissioning, and quality assurance. Med Phys 2021; 47:e228-e235. [PMID: 32418341 PMCID: PMC7318221 DOI: 10.1002/mp.13562] [Citation(s) in RCA: 35] [Impact Index Per Article: 11.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2019] [Revised: 04/27/2019] [Accepted: 04/27/2019] [Indexed: 01/16/2023] Open
Abstract
Background Recent advances in machine and deep learning based on an increased availability of clinical data have fueled renewed interest in computerized clinical decision support systems (CDSSs). CDSSs have shown great potential to improve healthcare, increase patient safety and reduce costs. However, the use of CDSSs is not without pitfalls, as an inadequate or faulty CDSS can potentially deteriorate the quality of healthcare and put patients at risk. In addition, the adoption of a CDSS might fail because its intended users ignore the output of the CDSS due to lack of trust, relevancy or actionability. Aim In this article, we provide guidance based on literature for the different aspects involved in the adoption of a CDSS with a special focus on machine and deep learning based systems: selection, acceptance testing, commissioning, implementation and quality assurance. Results A rigorous selection process will help identify the CDSS that best fits the preferences and requirements of the local site. Acceptance testing will make sure that the selected CDSS fulfills the defined specifications and satisfies the safety requirements. The commissioning process will prepare the CDSS for safe clinical use at the local site. An effective implementation phase should result in an orderly roll out of the CDSS to the well‐trained end‐users whose expectations have been managed. And finally, quality assurance will make sure that the performance of the CDSS is maintained and that any issues are promptly identified and solved. Conclusion We conclude that a systematic approach to the adoption of a CDSS will help avoid pitfalls, improve patient safety and increase the chances of success.
Collapse
Affiliation(s)
| | - Prasad Rv
- Philips Research India, Bangalore, 560045, India
| | - Inigo Bermejo
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, 6229 ET, Netherlands
| | - David Jaffray
- Princess Margaret Cancer Centre, University Health Network, Toronto, ON, M5G 2M9, Canada
| | - Andre Dekker
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, 6229 ET, Netherlands
| | - Leonard Wee
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, 6229 ET, Netherlands
| |
Collapse
|
20
|
Traverso A, Hosni Abdalaty A, Hasan M, Tadic T, Patel T, Giuliani M, Kim J, Ringash J, Cho J, Bratman S, Bayley A, Waldron J, O'Sullivan B, Irish J, Chepeha D, De Almeida J, Goldstein D, Jaffray D, Wee L, Dekker A, Hope A. PO-1549: Non-invasive prediction of lymph node risk in oral cavity cancer patients. Radiother Oncol 2020. [DOI: 10.1016/s0167-8140(21)01567-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
21
|
Glicksman R, Metser U, Vines D, Chan R, Valliant J, Chung P, Gospodarowicz M, Bayley A, Catton C, Warde P, Helou J, Raman S, Green D, Perlis N, Fleshner N, Hamilton RJ, Zlotta A, Finelli A, Jaffray D, Berlin A. 4: Caro Acura 2016 Primary Analysis of a Phase II Study of Metastasis-Directed Ablative Therapy to Psma (18F-DCFPYL) Pet-Mr/ Ct Defined Oligorecurrent Prostate Cancer. Radiother Oncol 2020. [DOI: 10.1016/s0167-8140(20)30896-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
22
|
Glicksman R, Metser U, Vines D, Chan R, Valliant J, Chung PWM, Gospodarowicz MK, Bayley A, Catton CN, Warde PR, Helou J, Raman S, Green D, Perlis N, Fleshner N, Hamilton RJ, Zlotta A, Finelli A, Jaffray D, Berlin A. Primary analysis of a phase II study of metastasis-directed ablative therapy to PSMA ( 18F-DCFPyL) PET-MR/CT defined oligorecurrent prostate cancer. J Clin Oncol 2020. [DOI: 10.1200/jco.2020.38.15_suppl.5553] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
5553 Background: Despite maximal local therapies (MLT) (radical prostatectomy followed by radiotherapy [RT]), 20-30% of men will progress to incurable prostate cancer (PCa). Most recurrences in this scenario are characterized by rise in PSA with negative bone scan (BS) and computed tomography (CT). We conducted a phase II trial for men with rising PSA after MLT using 18F-DCFPyL (PSMA) PET-MR/CT followed by metastasis-directed therapy (MDT) to PET positive foci. We report the results of our primary analysis. Methods: Patients with rising PSA (0.4-3.0 ng/mL) after MLT, negative BS/CT and no prior salvage ADT were eligible. All patients underwent PSMA PET-MR and PET-CT. Those with limited disease burden amenable to MDT underwent either stereotactic ablative RT (SABR) or surgery (lymph node dissection). No ADT was used. The primary endpoint was biochemical response rate (complete [undetectable PSA] or partial [PSA decline ≥50% from baseline]) following MDT. A Simon’s two-stage study design was employed. Estimated time of delay in salvage ADT was calculated using the Kaplan-Meier method. Toxicity was prospectively recorded (CTCAE v4.0). Results: After a median of 63 months (range 3-180) post MLT, 72 patients underwent PSMA PET-MR/CT with median PSA 0.98 ng/mL (range 0.4-3.1). Sixteen patients had negative and 56 had positive PET-MR/CT scans, of which 37 (51%) were amenable to MDT. The median number of treated lesions was 2 (range 1-5). Of the treated patients, 30 (81%) had miT0N1M0 disease, 2 (5.5%) had miT0N1M1a, 2 (5.5%) had miT0N0M1a and 3 (8%) had miT0N0M1b. Twenty-seven patients underwent SABR (median 30 Gy in 3 fractions) and 10 had surgery. At a median of 11 months (range 1-29) post MDT, 8 patients (22%) had complete (CR) and 14 (38%) had partial (PR) responses. Among the 8 CRs, 5 had surgery and 3 had SABR; of the 14 PRs, 2 had surgery and 12 had SABR. The estimated median delay in salvage ADT for the entire cohort, PR and CR subgroups was 13 months (IQR 8-20), 16 months (IQR 13-20) and 30 months (IQR not reached), respectively. Two grade 2+ toxicities were observed, both in surgical patients: deep venous thrombosis and ureteric injury requiring stent placement. Conclusions: 18F-DCFPyL PET-MR/CT has high detection rates (78%) in men with rising PSA after MLT. We observed a favorable therapeutic index with MDT (60% response rate) for patients with metachronous PSMA-unveiled oligometastatic PCa following MLT. Phase III studies using validated intermediate clinical endpoints are needed before integration into routine practice. Clinical trial information: NCT03160794 .
Collapse
Affiliation(s)
- Rachel Glicksman
- Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| | - Ur Metser
- Joint Department of Medical Imaging, University Health Network, Toronto, ON, Canada
| | - Doug Vines
- Department of Radiation Oncology, University of Toronto; Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Rosanna Chan
- Joint Department of Medical Imaging, University Health Network, Toronto, ON, Canada
| | - John Valliant
- Centre for Probe Development and Commercialization, Chemistry and Chemical Biology, McMaster University, Hamilton, ON, Canada
| | - Peter W. M. Chung
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Mary K. Gospodarowicz
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Andrew Bayley
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Charles N. Catton
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Padraig Richard Warde
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Joelle Helou
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | | | - David Green
- Princess Margaret Cancer Centre, Toronto, ON, Canada
| | - Nathan Perlis
- Department of Surgery, Division of Urology, University Health Network, Princess Margaret Cancer Centre, Toronto, ON, Canada
| | - Neil Fleshner
- Division of Urology, Princess Margaret Cancer Centre, University Health Network, University of Toronto, Toronto, ON, Canada
| | - Robert James Hamilton
- Division of Urologic Oncology, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | - Alexandre Zlotta
- Division of Urologic Oncology, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| | | | | | - Alejandro Berlin
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada
| |
Collapse
|
23
|
Traverso A, Kazmierski M, Zhovannik I, Welch M, Wee L, Jaffray D, Dekker A, Hope A. Machine learning helps identifying volume-confounding effects in radiomics. Phys Med 2020; 71:24-30. [PMID: 32088562 DOI: 10.1016/j.ejmp.2020.02.010] [Citation(s) in RCA: 28] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/30/2019] [Revised: 02/12/2020] [Accepted: 02/13/2020] [Indexed: 01/06/2023] Open
Abstract
PURPOSE Highlighting the risk of biases in radiomics-based models will help improve their quality and increase usage as decision support systems in the clinic. In this study we use machine learning-based methods to identify the presence of volume-confounding effects in radiomics features. Methods 841 radiomics features were extracted from two retrospective publicly available datasets of lung and head neck cancers using open source software. Unsupervised hierarchical clustering and principal component analysis (PCA) identified relations between radiomics and clinical outcomes (overall survival). Bootstrapping techniques with logistic regression verified features' prognostic power and robustness. Results Over 80% of the features had large pairwise correlations. Nearly 30% of the features presented strong correlations with tumor volume. Using volume-independent features for clustering and PCA did not allow risk stratification of patients. Clinical predictors outperformed radiomics features in bootstrapping and logistic regression. Conclusions The adoption of safeguards in radiomics is imperative to improve the quality of radiomics studies. We proposed machine learning (ML) - based methods for robust radiomics signatures development.
Collapse
Affiliation(s)
- Alberto Traverso
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands; Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada.
| | - Michal Kazmierski
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - Ivan Zhovannik
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands; Department of Radiation Oncology, Radboudumc, Nijmegen, The Netherlands
| | - Mattea Welch
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands; Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada
| | - Leonard Wee
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - David Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada
| | - Andre Dekker
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - Andrew Hope
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada
| |
Collapse
|
24
|
Cho Y, Farrokhkish M, Norrlinger B, Heaton R, Jaffray D, Islam M. An artificial neural network to model response of a radiotherapy beam monitoring system. Med Phys 2020; 47:1983-1994. [DOI: 10.1002/mp.14033] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2019] [Revised: 12/26/2019] [Accepted: 01/07/2020] [Indexed: 11/09/2022] Open
Affiliation(s)
- Young‐Bin Cho
- Radiation Medicine Program Princess Margaret Cancer Center University Health Network Toronto Canada M5G 2C1
- Department of Radiation Oncology University of Toronto Toronto Canada M5T 1P5
- Techna Institute University Health Network Toronto Ontario Canada M5G 1L5
| | - Makan Farrokhkish
- Radiation Medicine Program Princess Margaret Cancer Center University Health Network Toronto Canada M5G 2C1
| | - Bern Norrlinger
- Radiation Medicine Program Princess Margaret Cancer Center University Health Network Toronto Canada M5G 2C1
| | - Robert Heaton
- Radiation Medicine Program Princess Margaret Cancer Center University Health Network Toronto Canada M5G 2C1
- Department of Radiation Oncology University of Toronto Toronto Canada M5T 1P5
| | - David Jaffray
- Radiation Medicine Program Princess Margaret Cancer Center University Health Network Toronto Canada M5G 2C1
- Department of Radiation Oncology University of Toronto Toronto Canada M5T 1P5
- Techna Institute University Health Network Toronto Ontario Canada M5G 1L5
- Institute of Biomaterials and Biomedical Engineering University of Toronto Toronto Canada M5S 3G9
- Department of Medical Biophysics University of Toronto Toronto Canada M5G 1L7
| | - Mohammad Islam
- Radiation Medicine Program Princess Margaret Cancer Center University Health Network Toronto Canada M5G 2C1
- Department of Radiation Oncology University of Toronto Toronto Canada M5T 1P5
- Techna Institute University Health Network Toronto Ontario Canada M5G 1L5
- Institute of Biomaterials and Biomedical Engineering University of Toronto Toronto Canada M5S 3G9
| |
Collapse
|
25
|
Wong RK, Myrehaug S, Brierley J, Laidley D, Juergens R, Yeung I, Breen S, Shessel A, Driscoll B, Farncombe T, Zukotynski K, Stodilka R, Caldwell C, Liu AZ, Valliant J, McCann J, Metser U, Mohan R, Beauregard JM, Jaffray D. 70 Quantifying Tumour Dose Using Individualized Dosimetry Methodology in 177LU Dotatate Therapy. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)33360-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
26
|
Welch M, McIntosh C, Wee L, McNiven A, Huang SH, Zhang BB, Traverso A, O’Sullivan B, Hoebers F, Dekker A, Jaffray D. 163 Application of Novel Radiotherapy and Imaging Features for Head and Neck Patient Locoregional Failure Predictions. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)33219-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
27
|
Traverso A, Kazmierski M, Shi Z, Kalendralis P, Welch M, Nissen HD, Jaffray D, Dekker A, Wee L. Stability of radiomic features of apparent diffusion coefficient (ADC) maps for locally advanced rectal cancer in response to image pre-processing. Phys Med 2019; 61:44-51. [PMID: 31151578 DOI: 10.1016/j.ejmp.2019.04.009] [Citation(s) in RCA: 36] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/03/2018] [Revised: 04/11/2019] [Accepted: 04/12/2019] [Indexed: 12/14/2022] Open
Abstract
Quantitative imaging features (radiomics) extracted from apparent diffusion coefficient (ADC) maps of rectal cancer patients can provide additional information to support treatment decision. Most available radiomic computational packages allow extraction of hundreds to thousands of features. However, two major factors can influence the reproducibility of radiomic features: interobserver variability, and imaging filtering applied prior to features extraction. In this exploratory study we seek to determine to what extent various commonly-used features are reproducible with regards to the mentioned factors using ADC maps from two different clinics (56 patients). Features derived from intensity distribution histograms are less sensitive to manual tumour delineation differences, noise in ADC images, pixel size resampling and intensity discretization. Shape features appear to be strongly affected by delineation quality. On the whole, textural features appear to be poorly or moderately reproducible with respect to the image pre-processing perturbations we reproduced.
Collapse
Affiliation(s)
- Alberto Traverso
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, The Netherlands; Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada.
| | - Michal Kazmierski
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, The Netherlands
| | - Zhenwei Shi
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, The Netherlands
| | - Petros Kalendralis
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, The Netherlands
| | - Mattea Welch
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada
| | | | - David Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada
| | - Andre Dekker
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, The Netherlands
| | - Leonard Wee
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, The Netherlands
| |
Collapse
|
28
|
Traverso A, Kazmierski M, Shi Z, Weiss J, Fiset S, Wee L, Dekker A, Jaffray D, Han K. PO-0959 Robust features selection in Apparent Diffusion Coefficient (ADC) maps of cervix cancer patients. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)31379-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
29
|
Traverso A, Kazmierski M, Wee L, Dekker A, Welch M, Hosni A, Jaffray D, Hope A. PV-0314 Machine learning helps identifying relations and confounding factors in radiomics-based models. Radiother Oncol 2019. [DOI: 10.1016/s0167-8140(19)30734-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
30
|
Cho YB, Alasti H, Kong V, Catton C, Berlin A, Chung P, Bayley A, Jaffray D. Impact of high dose volumetric CT on PTV margin reduction in VMAT prostate radiotherapy. ACTA ACUST UNITED AC 2019; 64:065017. [DOI: 10.1088/1361-6560/ab050f] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
31
|
Han K, Shek T, Vines D, Driscoll B, Fyles A, Jaffray D, Keller H, Metser U, Pintilie M, Xie J, Yeung I, Milosevic M. Measurement of Tumor Hypoxia in Patients With Locally Advanced Cervical Cancer Using Positron Emission Tomography with 18F-Fluoroazomyin Arabinoside. Int J Radiat Oncol Biol Phys 2018; 102:1202-1209. [PMID: 29680257 DOI: 10.1016/j.ijrobp.2018.02.030] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2018] [Revised: 02/11/2018] [Accepted: 02/20/2018] [Indexed: 01/25/2023]
Abstract
PURPOSE To assess cervical tumor hypoxia using the hypoxia tracer 18F-fluoroazomycin arabinoside (18F-FAZA) and compare different reference tissues and thresholds for quantifying tumor hypoxia. METHODS AND MATERIALS Twenty-seven patients with cervical cancer were studied prospectively by positron emission tomography (PET) imaging with 18F-FAZA before starting standard chemoradiation. The hypoxic volume was defined as all voxels within a tumor (T) with standardized uptake values (SUVs) greater than 3 standard deviations from the mean gluteus maximus muscle SUV value (M) or SUVs greater than 1 to 1.4 times the mean SUV value of the left ventricle, a blood (B) surrogate. The hypoxic fraction was defined as the ratio of the number of hypoxic voxels to the total number of tumor voxels. RESULTS A 18F-FAZA-PET hypoxic volume could be identified in the majority of cervical tumors (89% when using T/M or T/B > 1.2 as threshold) on the 2-hour static scan. The hypoxic fraction ranged from 0% to 99% (median 31%) when defined using the T/M threshold and from 0% to 78% (median 32%) with the T/B > 1.2 threshold. Hypoxic volumes derived from the different thresholds were highly correlated (Spearman's correlation coefficient ρ between T/M and T/B > 1-1.4 were 0.82-0.91), as were hypoxic fractions (0.75-0.85). Compartmental analysis of the dynamic scans showed k3, the FAZA accumulation constant, to be strongly correlated with hypoxic fraction defined using the T/M (Spearman's ρ=0.72) and T/B > 1.2 thresholds (0.76). CONCLUSIONS Hypoxia was detected in the majority of cervical tumors on 18F-FAZA-PET imaging. The extent of hypoxia varied markedly between tumors but not significantly with different reference tissues/thresholds.
Collapse
Affiliation(s)
- Kathy Han
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada.
| | - Tina Shek
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Douglass Vines
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada; Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Brandon Driscoll
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Anthony Fyles
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - David Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada; Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Harald Keller
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada; Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Ur Metser
- Joint Department of Medical Imaging, University Health Network, Toronto, Ontario, Canada; Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada
| | - Melania Pintilie
- Department of Biostatistics, University Health Network, Toronto, Ontario, Canada
| | - Jason Xie
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Ivan Yeung
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada; Quantitative Imaging for Personalized Cancer Medicine, Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Michael Milosevic
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|
32
|
Pistenmaa DA, Dosanjh M, Amaldi U, Jaffray D, Zubizarreta E, Holt K, Lievens Y, Pipman Y, Coleman CN. Changing the global radiation therapy paradigm. Radiother Oncol 2018; 128:393-399. [DOI: 10.1016/j.radonc.2018.05.025] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2018] [Revised: 05/23/2018] [Accepted: 05/23/2018] [Indexed: 02/08/2023]
|
33
|
Stanescu T, Jaffray D. Technical Note: Harmonic analysis applied to MR image distortion fields specific to arbitrarily shaped volumes. Med Phys 2018; 45:3705-3712. [PMID: 29799634 DOI: 10.1002/mp.13000] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2017] [Revised: 04/26/2018] [Accepted: 05/15/2018] [Indexed: 11/10/2022] Open
Abstract
PURPOSE Magnetic resonance imaging is expected to play a more important role in radiation therapy given the recent developments in MR-guided technologies. MR images need to consistently show high spatial accuracy to facilitate RT-specific tasks such as treatment planning and in-room guidance. The present study investigates a new harmonic analysis method for the characterization of complex three-dimensional (3D) fields derived from MR images affected by system-related distortions. METHODS An interior Dirichlet problem based on solving the Laplace equation with boundary conditions (BCs) was formulated for the case of a 3D distortion field. The second-order boundary value problem (BVP) was solved using a finite elements method (FEM) for several quadratic geometries - that is, sphere, cylinder, cuboid, D-shaped, and ellipsoid. To stress-test the method and generalize it, the BVP was also solved for more complex surfaces such as a Reuleaux 9-gon and the MR imaging volume of a scanner featuring a high degree of surface irregularities. The BCs were formatted from reference experimental data collected with a linearity phantom featuring a volumetric grid structure. The method was validated by comparing the harmonic analysis results with the corresponding experimental reference fields. RESULTS The harmonic fields were found to be in good agreement with the baseline experimental data for all geometries investigated. In the case of quadratic domains, the percentage of sampling points with residual values larger than 1 mm was 0.5% and 0.2% for the axial components and vector magnitude, respectively. For the general case of a domain defined by the available MR imaging field of view, the reference data showed a peak distortion of about 1 mm and 79% of the sampling points carried a distortion magnitude larger than 1 mm (tolerance intrinsic to the experimental data). The upper limits of the residual values after comparison with the harmonic fields showed max and mean of 1.4 and 0.25 mm, respectively, with only 1.5% of sampling points exceeding 1 mm. CONCLUSIONS A novel harmonic analysis approach relying on finite element methods was introduced and validated for multiple volumes with surface shape functions ranging from simple to highly complex. Since a boundary value problem is solved the method requires input data from only the surface of the desired domain of interest. It is believed that the harmonic method will facilitate (a) the design of new phantoms dedicated for the quantitation of MR image distortions in large volumes and (b) an integrative approach of combining multiple imaging tests specific to radiotherapy into a single test object for routine imaging quality control.
Collapse
Affiliation(s)
- T Stanescu
- Princess Margaret Cancer Centre & The Techna Institute, University Health Network, Toronto, ON, M5G 2M9, Canada
- Department of Radiation Oncology, University of Toronto, 610 University Avenue, Toronto, ON, M5G 2M9, Canada
| | - D Jaffray
- Princess Margaret Cancer Centre & The Techna Institute, University Health Network, Toronto, ON, M5G 2M9, Canada
- Department of Radiation Oncology, University of Toronto, 610 University Avenue, Toronto, ON, M5G 2M9, Canada
| |
Collapse
|
34
|
Sternheim A, Kashigar A, Daly M, Chan H, Qiu J, Weersink R, Jaffray D, Irish JC, Ferguson PC, Wunder JS. Cone-Beam Computed Tomography-Guided Navigation in Complex Osteotomies Improves Accuracy at All Competence Levels: A Study Assessing Accuracy and Reproducibility of Joint-Sparing Bone Cuts. J Bone Joint Surg Am 2018; 100:e67. [PMID: 29762285 DOI: 10.2106/jbjs.16.01304] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
BACKGROUND The objective of this study was to assess the accuracy and reproducibility of a novel cone-beam computed tomography (CBCT)-guided navigation system designed for osteotomies with joint-sparing bone cuts. METHODS Eighteen surgeons participated in this study. First, 3 expert tumor surgeons resected bone tumors in 3 Sawbones tumor models identical to actual patient scenarios. They first performed these osteotomies without navigation and then performed them using a navigation system and 3-dimensional (3D) planning tools based on CBCT imaging. The 2 sets of measurements were compared using image-based measurements from post-resection CBCT. Next, 15 residents, fellows, and orthopaedic staff surgeons were instructed on the use of the system, and their navigated resections were compared with navigated resections performed by the 3 expert tumor surgeons. RESULTS One hundred and twenty-six navigated cuts done by the orthopaedic oncologists were compared with 126 non-navigated cuts by the same surgeons. The cuts violated the tumor in 22% (6) of the 27 non-navigated resections compared with none of the 27 navigated resections. The navigated cuts were significantly more accurate in terms of entry point, pitch, and roll (p < 0.001). The variation among the 3 surgeons when they used navigation was <0.6 mm for the entry cut and, on average, 1.5° for pitch and roll. All 18 surgeons then completed a total of 144 navigated cuts. The level of experience did not result in a significant difference among groups with regard to cut accuracy. Two cuts went into the tumor. The mean distance from the planned bone cuts to the actual entry points into bone was 1.5 mm (standard deviation [SD] = 1.4 mm) for all users. The mean difference in pitch and roll between the planned and actual cuts was 3.5° (SD = 2.8°) and 3.7° (SD = 3.2°) for all users. CONCLUSIONS Even in expert hands, navigated cuts were significantly more accurate than non-navigated cuts. When the osteotomies were aided by navigation, their accuracy did not differ according to the level of professional experience. CBCT-based metrics enable intraoperative assessments of cut accuracy and reconstruction planning. CLINICAL RELEVANCE CBCT-guided navigated osteotomies can improve accuracy regardless of surgeon experience and decrease the variability among different surgeons.
Collapse
Affiliation(s)
- Amir Sternheim
- National Unit of Orthopaedic Oncology, Tel Aviv Medical Center, and Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Aidin Kashigar
- Division of Orthopaedic Surgery, Queen's University, Kingston, Ontario, Canada
| | - Michael Daly
- Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Harley Chan
- Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Jimmy Qiu
- Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Robert Weersink
- Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - David Jaffray
- Techna Institute, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Physics, Princess Margaret Cancer Centre, Toronto, Ontario, Canada.,Ontario Cancer Institute, Princess Margaret Cancer Centre, Toronto, Ontario, Canada
| | - Jonathan C Irish
- Techna Institute, University Health Network, Toronto, Ontario, Canada.,Department of Surgical Oncology, University Health Network, Toronto, Ontario, Canada.,Department of Otolaryngology-Head and Neck Surgery, University of Toronto, Toronto, Ontario, Canada
| | - Peter C Ferguson
- Department of Surgical Oncology, University Health Network, Toronto, Ontario, Canada.,Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Ontario, Canada.,University Musculoskeletal Oncology Unit, Mount Sinai Hospital, Toronto, Ontario, Canada
| | - Jay S Wunder
- Department of Surgical Oncology, University Health Network, Toronto, Ontario, Canada.,Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Ontario, Canada.,University Musculoskeletal Oncology Unit, Mount Sinai Hospital, Toronto, Ontario, Canada
| |
Collapse
|
35
|
Gillan C, Harnett N, Milne E, Purdie T, Wiljer D, Jaffray D, Hodges B. Professional Implications of Introducing Artificial Intelligence in Healthcare: An Evaluation using Radiation Medicine as a Testing Ground. J Med Imaging Radiat Sci 2018. [DOI: 10.1016/j.jmir.2018.02.006] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
36
|
Hamilton JL, Foxcroft S, Moyo E, Cooke-Lauder J, Spence T, Zahedi P, Bezjak A, Jaffray D, Lam C, Létourneau D, Milosevic M, Tsang R, Wong R, Liu FF. Strategic planning in an academic radiation medicine program. Curr Oncol 2017; 24:e518-e523. [PMID: 29270061 DOI: 10.3747/co.24.3725] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Background In this paper, we report on the process of strategic planning in the Radiation Medicine Program (rmp) at the Princess Margaret Cancer Centre. The rmp conducted a strategic planning exercise to ensure that program priorities reflect the current health care environment, enable nimble responses to the increasing burden of cancer, and guide program operations until 2020. Methods Data collection was guided by a project charter that outlined the project goal and the roles and responsibilities of all participants. The process was managed by a multidisciplinary steering committee under the guidance of an external consultant and consisted of reviewing strategic planning documents from close collaborators and institutional partners, conducting interviews with key stakeholders, deploying a program-wide survey, facilitating an anonymous and confidential e-mail feedback box, and collecting information from group deliberations. Results The process of strategic planning took place from December 2014 to December 2015. Mission and vision statements were developed, and core values were defined. A final document, Strategic Roadmap to 2020, was established to guide programmatic pursuits during the ensuing 5 years, and an implementation plan was developed to guide the first year of operations. Conclusions The strategic planning process provided an opportunity to mobilize staff talents and identify environmental opportunities, and helped to enable more effective use of resources in a rapidly changing health care environment. The process was valuable in allowing staff to consider and discuss the future, and in identifying strategic issues of the greatest importance to the program. Academic programs with similar mandates might find our report useful in guiding similar processes in their own organizations.
Collapse
Affiliation(s)
- J L Hamilton
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network
| | - S Foxcroft
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network
| | - E Moyo
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network
| | - J Cooke-Lauder
- Health Industry Management Practice, Schulich School of Business, York University, and
| | - T Spence
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network
| | - P Zahedi
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network
| | - A Bezjak
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network
| | - D Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| | - C Lam
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| | - D Létourneau
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| | - M Milosevic
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| | - R Tsang
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| | - R Wong
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| | - F F Liu
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network.,Department of Radiation Oncology, University of Toronto, Toronto, ON
| |
Collapse
|
37
|
Lievens Y, Gospodarowicz M, Grover S, Jaffray D, Rodin D, Torode J, Yap ML, Zubizarreta E. Global impact of radiotherapy in oncology: Saving one million lives by 2035. Radiother Oncol 2017; 125:175-177. [DOI: 10.1016/j.radonc.2017.10.027] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2017] [Accepted: 10/20/2017] [Indexed: 10/18/2022]
|
38
|
Alasti H, Cho YB, Catton C, Berlin A, Chung P, Bayley A, Vandermeer A, Kong V, Jaffray D. Evaluation of high dose volumetric CT to reduce inter-observer delineation variability and PTV margins for prostate cancer radiotherapy. Radiother Oncol 2017; 125:118-123. [DOI: 10.1016/j.radonc.2017.08.012] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2017] [Revised: 07/20/2017] [Accepted: 08/07/2017] [Indexed: 01/28/2023]
|
39
|
Van Soest J, Purdie T, Giuliani M, Lindsay P, Hope A, Jaffray D, Dekker A. PV-0239: Validation of lung cancer survival models in a clinical routine SBRT population. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)30682-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
40
|
Islam M, Farrokhkish M, Wang Y, Norrlinger B, Heaton R, Jaffray D. EP-1758: Towards Clinical Implementation of an Online Beam Monitoring System. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)32121-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
41
|
Stanescu T, Berlin A, Dawson L, Abed J, Simeonov A, Craig T, Letourneau D, Jaffray D. EP-1761: Workflow development for the clinical implementation of an MR-guided linear accelerator. Radiother Oncol 2017. [DOI: 10.1016/s0167-8140(17)32124-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
42
|
Coleman CN, Pistenmaa D, Jaffray D, Gospodarowicz M, Vikram B, Myers S, Vretenar M, Amaldi U, Dosanjh M. Effective Global Cancer Care Requires Radiation Therapy: Defining a Path From No Radiotherapy to Radiotherapy of High Quality Globally. J Glob Oncol 2017. [DOI: 10.1200/jgo.2017.009241] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
Abstract 46 Background: The increasing global burden of cancer in health disparity regions is now well recognized. To appropriately address the need, the full spectrum of cancer care is required, including cancer control plans, cancer registries, prevention, diagnosis, treatment, multidisciplinary care, and follow-up. Radiation therapy is required for curative treatment, particularly for solid tumors, and for palliation. The Global Task Force for Radiation for Cancer Control, created by the Union for International Cancer Control, demonstrated that radiotherapy is economically beneficial and affordable (Lancet Oncol. 2015 16:1153-86). Recognizing that many low- and middle-income countries have inadequate or no radiation therapy and that there is a need globally for at least 5,000 radiation therapy machines, a well-designed implementation plan is necessary. This includes attention to the potential danger from misuse or mishandling of cobalt-60 and the potential for remote networking to ensure high-quality treatment. Methods: Experts with a broad range of interests and representatives from public and private sectors met at an International Cancer Expert Corps–sponsored workshop on the CERN campus on November 7 and 8, 2016, to consider future options, including innovative technology, a software and systems approach to dealing with the complexity of radiation therapy, and the need for ongoing education and training. Discussions included replacement of cobalt-60 units over time for security and safety reasons. Results: The International Cancer Expert Corps–CERN workshop produced criteria for what could be a newly designed linear accelerator. Three task groups were established to address technology/software solutions, education and training, and economic issues. Conclusion: The workshop report is forthcoming and the task groups will work to define short- and long-term solutions to this major global shortfall. This workshop represents a potential watershed moment for augmenting global cancer care by bringing together expertise and potential investment at the scope needed to address the gap in radiation treatment capacity. AUTHORS' DISCLOSURES OF POTENTIAL CONFLICTS OF INTEREST C. Norman Coleman No relationship to disclose David Pistenmaa No relationship to disclose David Jaffray Consulting or Advisory Role: IBA Mary Gospodarowicz No relationship to disclose Bhadrasain Vikram No relationship to disclose Steve Myers No relationship to disclose Maurizio Vrentenar No relationship to disclose Ugo Amaldi No relationship to disclose Manjit Dosanjh No relationship to disclose
Collapse
Affiliation(s)
- C. Norman Coleman
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - David Pistenmaa
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - David Jaffray
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - Mary Gospodarowicz
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - Bhadrasain Vikram
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - Steve Myers
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - Maurizio Vretenar
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - Ugo Amaldi
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| | - Manjit Dosanjh
- C. Norman Coleman and David Pistenmaa, International Cancer Expert Corps, Washington, DC; Bhadrasain Vikram, National Cancer Institute, Bethesda, MD; David Jaffray and Mary Gospodarowicz, Princess Margaret Cancer Center, Toronto, Ontario, Canada; Steve Myers, ADAM; Maurizio Vretenar and Manjit Dosanjh, CERN; and Ugo Amaldi, TERA Foundation, Geneva, Switzerland
| |
Collapse
|
43
|
Stapleton S, Jaffray D, Milosevic M. Radiation effects on the tumor microenvironment: Implications for nanomedicine delivery. Adv Drug Deliv Rev 2017; 109:119-130. [PMID: 27262923 DOI: 10.1016/j.addr.2016.05.021] [Citation(s) in RCA: 109] [Impact Index Per Article: 15.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2015] [Revised: 04/22/2016] [Accepted: 05/24/2016] [Indexed: 01/24/2023]
Abstract
The tumor microenvironment has an important influence on cancer biological and clinical behavior and radiation treatment (RT) response. However, RT also influences the tumor microenvironment in a complex and dynamic manner that can either reinforce or inhibit this response and the likelihood of long-term disease control in patients. It is increasingly evident that the interplay between RT and the tumor microenvironment can be exploited to enhance the accumulation and intra-tumoral distribution of nanoparticles, mediated by changes to the vasculature and stroma with secondary effects on hypoxia, interstitial fluid pressure (IFP), solid tissue pressure (STP), and the recruitment and activation of bone marrow-derived myeloid cells (BMDCs). The use of RT to modulate nanoparticle drug delivery offers an exciting opportunity to improve antitumor efficacy. This review explores the interplay between RT and the tumor microenvironment, and the integrated effects on nanoparticle drug delivery and efficacy.
Collapse
Affiliation(s)
- Shawn Stapleton
- Radiation Medicine Program, Princess Margaret Cancer Centre and University Health Network, Toronto, ON, Canada
| | - David Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre and University Health Network, Toronto, ON, Canada; Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| | - Michael Milosevic
- Radiation Medicine Program, Princess Margaret Cancer Centre and University Health Network, Toronto, ON, Canada; Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada.
| |
Collapse
|
44
|
Klinz S, Zheng J, Souza RD, Ventura M, Paz N, Hedley D, Jaffray D, Fitzgerald J. Abstract B47: Nanoliposomal irinotecan (nal-IRI) is an active treatment and reduces hypoxia as measured through longitudinal imaging using [18F]FAZA-PET in an orthotopic patient-derived model of pancreatic cancer. Cancer Res 2016. [DOI: 10.1158/1538-7445.panca16-b47] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Abstract
Introduction: Tumor hypoxia has been strongly linked to aggressive disease progression and resistance to therapy, especially in pancreatic cancer where the desmoplastic reaction is thought to also interfere with deposition of both small molecule drugs and nanotherapeutics. [18F]fluoroazomycin arabinoside (FAZA) is a radioactive tracer that allows for non-invasive quantification of tumor hypoxia during treatment by positron emission tomography (PET). We have previously shown that in the HT-29 cell-line derived xenograft model of colorectal cancer, nanoliposomal irinotecan (nal-IRI) achieves improved tumor growth control and is able to maintain a significantly lower level of tumor hypoxia as compared to non-liposomal irinotecan. Here, we evaluate the effects of nal-IRI on the kinetics and magnitude of hypoxia changes in an orthotopic patient-derived tumorgraft model of a pancreatic cancer (OCIP51) that is highly hypoxic.
Experimental Procedures: Tumor growth of orthotopically implanted OCIP51 tumors was monitored using magnetic resonance imaging. Longitudinal FAZA-PET imaging of tumor hypoxia changes was performed over a 21-day period following weekly administration of nal-IRI at 20 mg/kg (n = 10) and compared to untreated controls (n = 5). Mean tumor FAZA uptake (%ID/g) and hypoxic fractions were calculated. In addition [18F]-fluorothymidine (FLT-) PET was conducted before treatment initiation and after the 3rd dosing cycle to assess tumor cell proliferation. Tumor levels of irinotecan and its active metabolite SN-38 were evaluated using an HPLC method in samples harvested 24 h after the last administration of nal-IRI and in a separate pharmacodynamic study component (n = 10) at 24 h and 72 h after administration of a single dose of nal-IRI at 10 mg/kg. Nal-IRI induced DNA damage was assessed using γH2AX immunohistochemistry.
Results: nal-IRI treatment resulted in tumor growth inhibition of 71.6% compared to controls at study end. Tumor growth control was observable at Day 5 post treatment initiation. FAZA uptake in treated tumors decreased by 36% within the first treatment cycle, while average FAZA levels in control tumors remained unchanged during this period. Nal-IRI treatment resulted in statistically significant decreases in the FLTmax and FLTmean values compared to pre-treatment values. 100% of nal-IRI treated mice survived to study end compared to only 40% of controls. Tumor weights at study end were almost 4 times smaller in nal-IRI-treated mice compared to the controls. Tumors from treated mice were fluid-filled and showed extensive blood pooling, while tumors from untreated mice appeared to be much less vascularized.
Irinotecan levels detected in the OCIP51 tumors were 8 times lower at 72 h after nal-IRI administration, while SN-38 levels were ~28 times lower when compared to previous findings in HT-29 tumors. Treatment with nal-IRI in the OCIP51 tumors significantly increased the frequency and intensity of γH2AX staining across tumor cell areas compared to that observed in the untreated tumors, which were characterized by only a scattered and sporadic γH2AX staining. Importantly, the stromal areas did not show γH2AX staining in either the treated or the control group.
Conclusions: This study demonstrated the feasibility of performing longitudinal tumor hypoxia and proliferation assessments using FAZA- and FLT-PET imaging in a highly hypoxic orthotopic model of pancreatic cancer. Although this model showed reduced levels of liposomal drug deposition compared to cell-line derived xenograft models, treatment with nal-IRI led to effective tumor growth control, as well as significant changes in the tumor microenvironment as measured by reduced hypoxia levels compared to baseline and control tumors. Results from this study support the utility of FAZA-PET for evaluation of tumor hypoxia after anti-cancer therapy with nal-IRI as a means to provide early assessment of treatment activity.
Citation Format: Stephan Klinz, Jinzi Zheng, Raquel De Souza, Manuela Ventura, Nancy Paz, David Hedley, David Jaffray, Jonathan Fitzgerald.{Authors}. Nanoliposomal irinotecan (nal-IRI) is an active treatment and reduces hypoxia as measured through longitudinal imaging using [18F]FAZA-PET in an orthotopic patient-derived model of pancreatic cancer. [abstract]. In: Proceedings of the AACR Special Conference on Pancreatic Cancer: Advances in Science and Clinical Care; 2016 May 12-15; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2016;76(24 Suppl):Abstract nr B47.
Collapse
Affiliation(s)
| | - Jinzi Zheng
- 2Techna Institute for the Advancement of Technology for Health, University Health Network, Toronto, ON, Canada,
| | - Raquel De Souza
- 3STTARR Innovation Centre, Radiation Medicine Program, UHN Princess Margaret Cancer Centre, Toronto, ON, Canada,
| | - Manuela Ventura
- 3STTARR Innovation Centre, Radiation Medicine Program, UHN Princess Margaret Cancer Centre, Toronto, ON, Canada,
| | - Nancy Paz
- 1Merrimack Pharmaceuticals, Inc., Cambridge, MA,
| | - David Hedley
- 4Division of Medical Oncology and Hematology, UHN Princess Margaret Cancer Centre/Ontario Cancer Inst, Toronto, ON, Canada
| | - David Jaffray
- 2Techna Institute for the Advancement of Technology for Health, University Health Network, Toronto, ON, Canada,
| | | |
Collapse
|
45
|
Stanescu T, Jaffray D. Investigation of the 4D composite MR image distortion field associated with tumor motion for MR-guided radiotherapy. Med Phys 2016; 43:1550-62. [PMID: 26936738 DOI: 10.1118/1.4941958] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022] Open
Abstract
PURPOSE Magnetic resonance (MR) images are affected by geometric distortions due to the specifics of the MR scanner and patient anatomy. Quantifying the distortions associated with mobile tumors is particularly challenging due to real anatomical changes in the tumor's volume, shape, and relative location within the MR imaging volume. In this study, the authors investigate the 4D composite distortion field, which combines the effects of the susceptibility-induced and system-related distortion fields, experienced by mobile lung tumors. METHODS The susceptibility (χ) effects were numerically simulated for two specific scenarios: (a) a full motion cycle of a lung tumor due to breathing as depicted on ten phases of a 4D CBCT data set and (b) varying the tumor size and location in lung tissue via a synthetically generated sphere with variable diameter (4-80 mm). The χ simulation procedure relied on the segmentation and generation of 3D susceptibility (χ) masks and computation of the magnetic field by means of finite difference methods. A system-related distortion field, determined with a phantom and image processing algorithm, was used as a reference. The 4D composite distortion field was generated as the vector summation of the χ-induced and system-related fields. The analysis was performed for two orientations of the main magnetic field (B0), which correspond to several MRIgRT system configurations. Specifically, B0 was set along the z-axis as in the case of a cylindrical-bore scanner and in the (x,y)-plane as for a biplanar MR. Computations were also performed for a full revolution at 15° increments in the case of a rotating biplanar magnet. Histograms and metrics such as maximum, mean, and range were used to evaluate the characteristics of the 4D distortion field. RESULTS The χ-induced field depends on the change in volume and shape of the moving tumor as well as the local surrounding anatomy. In the case of system-related distortions, the tumor experiences increased field perturbations as it moves further away from the MR isocenter. For a mobile lung tumor, the 4D composite field, corresponding to a 1.5 T field and a readout gradient of 5 mT/m, amounts to 3.0 and 2.8 mm for the MRIgRT system designs featuring B0 oriented along the z-axis (cylindrical-bore scanner) and in the (x,y)-plane (biplanar scanner), respectively. For a rotating biplanar scanner, the composite distortion field varied nonlinearly with the rotation angle. Overall, the dominant contribution to the composite field was from the system-related distortion field. The tumor centroid experienced a systematic shift of 2 mm and showed a negligible perturbation for different B0 values. The dependency on the tumor size was also investigated, namely the max values varied from 1.2 to 2.5 mm for spherical volumes with a diameter between 4 and 80 mm. CONCLUSIONS The composite distortion field requires adequate quantification for lung radiation therapy applications such as treatment planning, pretreatment patient setup verification, and real-time treatment delivery guidance. For certain scenarios such as small tumor volumes, the spatial distortions may be corrected by applying systematic shifts derived from a single tumor motion phase. In the case of high readout gradients common to fast imaging applications, the χ distortions were found to be less than 1 mm irrespective of scanner configuration.
Collapse
Affiliation(s)
- T Stanescu
- Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario M5G 2M9, Canada and Department of Radiation Oncology, University of Toronto, 610 University Avenue, Toronto, Ontario M5G 2M9, Canada
| | - D Jaffray
- Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario M5G 2M9, Canada and Department of Radiation Oncology, University of Toronto, 610 University Avenue, Toronto, Ontario M5G 2M9, Canada
| |
Collapse
|
46
|
Sandström H, Chung C, Jokura H, Torrens M, Jaffray D, Toma-Dasu I. Assessment of organs-at-risk contouring practices in radiosurgery institutions around the world – The first initiative of the OAR Standardization Working Group. Radiother Oncol 2016; 121:180-186. [DOI: 10.1016/j.radonc.2016.10.014] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2015] [Revised: 10/10/2016] [Accepted: 10/17/2016] [Indexed: 11/17/2022]
|
47
|
Rodin D, Hanna TP, Burger E, Zubizarreta E, Yap ML, Barton M, Atun R, Knaul F, Van Dyk J, Lievens Y, Gospodarowicz M, Jaffray D, Milosevic M. 11: Global Access to Radiotherapy for Cervical Cancer: The Cost of Inaction. Radiother Oncol 2016. [DOI: 10.1016/s0167-8140(16)33410-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
48
|
Carlone M, Tadic T, Keller H, Rezaee M, Jaffray D. Technical Note: Enhancing the surface dose using a weak longitudinal magnetic field. Med Phys 2016; 43:2927-2932. [PMID: 27277041 DOI: 10.1118/1.4949001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE The surface dose in radiotherapy is subject to the physical properties of the radiation beam and collimator. The purpose of this work is to investigate the manipulation of surface dose using magnetic fields produced with a resistive magnet. Better understanding of the feasibility and mechanisms of altered surface dose could have important clinical applications where the surface dose must be increased for therapeutic goals, or reduced to enhance the therapeutic benefit. METHODS A resistive magnet capable of generating a peak magnetic field up to 0.24 T was integrated with a cobalt treatment unit. The magnetic fringe field of the magnet was small due to the self-shielding built within the magnet. The magnetic field at the beam collimation jaws of the cobalt irradiator was less than 10 G. The surface dose and depth dose were measured for varying magnetic field strengths. RESULTS The resistive magnet was able to alter the dose in the buildup region of the (60)Co depth dose significantly, and the magnitude of dose enhancement was directly related to the strength of the longitudinal magnetic field. Peak magnetic fields as low as 0.08 T were able to affect the surface dose. At a peak field of 0.24 T, the authors measured a surface dose enhancement of 2.8-fold. CONCLUSIONS Surface dose enhancement using resistive magnets is feasible. Further experimental study is needed to understand the origin of the scattered electrons that contribute to the increase in surface dose.
Collapse
Affiliation(s)
- Marco Carlone
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Ontario M5G 2M9, Canada and Department of Radiation Oncology, University of Toronto, Toronto, Ontario M5S 1A1, Canada
| | - Tony Tadic
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Ontario M5G 2M9, Canada
| | - Harald Keller
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Ontario M5G 2M9, Canada and Department of Radiation Oncology, University of Toronto, Toronto, Ontario M5S 1A1, Canada
| | - Mohammad Rezaee
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Ontario M5G 2M9, Canada and Department of Radiation Oncology, University of Toronto, Toronto, Ontario M5S 1A1, Canada
| | - David Jaffray
- Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Ontario M5G 2M9, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Ontario M5S 1A1, Canada; and Department of Medical Biophysics, University of Toronto, Toronto, Ontario M5S 1A1, Canada
| |
Collapse
|
49
|
|
50
|
Malkov V, Rogers D, Jaffray D. TH-AB-BRA-05: Lung Cannot Be Treated as Homogeneous in Radiation Transport Simulations in Magnetic Fields. Med Phys 2016. [DOI: 10.1118/1.4958056] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
|