1
|
Yousefirizi F, Klyuzhin IS, O JH, Harsini S, Tie X, Shiri I, Shin M, Lee C, Cho SY, Bradshaw TJ, Zaidi H, Bénard F, Sehn LH, Savage KJ, Steidl C, Uribe CF, Rahmim A. TMTV-Net: fully automated total metabolic tumor volume segmentation in lymphoma PET/CT images - a multi-center generalizability analysis. Eur J Nucl Med Mol Imaging 2024; 51:1937-1954. [PMID: 38326655 DOI: 10.1007/s00259-024-06616-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Accepted: 01/15/2024] [Indexed: 02/09/2024]
Abstract
PURPOSE Total metabolic tumor volume (TMTV) segmentation has significant value enabling quantitative imaging biomarkers for lymphoma management. In this work, we tackle the challenging task of automated tumor delineation in lymphoma from PET/CT scans using a cascaded approach. METHODS Our study included 1418 2-[18F]FDG PET/CT scans from four different centers. The dataset was divided into 900 scans for development/validation/testing phases and 518 for multi-center external testing. The former consisted of 450 lymphoma, lung cancer, and melanoma scans, along with 450 negative scans, while the latter consisted of lymphoma patients from different centers with diffuse large B cell, primary mediastinal large B cell, and classic Hodgkin lymphoma cases. Our approach involves resampling PET/CT images into different voxel sizes in the first step, followed by training multi-resolution 3D U-Nets on each resampled dataset using a fivefold cross-validation scheme. The models trained on different data splits were ensemble. After applying soft voting to the predicted masks, in the second step, we input the probability-averaged predictions, along with the input imaging data, into another 3D U-Net. Models were trained with semi-supervised loss. We additionally considered the effectiveness of using test time augmentation (TTA) to improve the segmentation performance after training. In addition to quantitative analysis including Dice score (DSC) and TMTV comparisons, the qualitative evaluation was also conducted by nuclear medicine physicians. RESULTS Our cascaded soft-voting guided approach resulted in performance with an average DSC of 0.68 ± 0.12 for the internal test data from developmental dataset, and an average DSC of 0.66 ± 0.18 on the multi-site external data (n = 518), significantly outperforming (p < 0.001) state-of-the-art (SOTA) approaches including nnU-Net and SWIN UNETR. While TTA yielded enhanced performance gains for some of the comparator methods, its impact on our cascaded approach was found to be negligible (DSC: 0.66 ± 0.16). Our approach reliably quantified TMTV, with a correlation of 0.89 with the ground truth (p < 0.001). Furthermore, in terms of visual assessment, concordance between quantitative evaluations and clinician feedback was observed in the majority of cases. The average relative error (ARE) and the absolute error (AE) in TMTV prediction on external multi-centric dataset were ARE = 0.43 ± 0.54 and AE = 157.32 ± 378.12 (mL) for all the external test data (n = 518), and ARE = 0.30 ± 0.22 and AE = 82.05 ± 99.78 (mL) when the 10% outliers (n = 53) were excluded. CONCLUSION TMTV-Net demonstrates strong performance and generalizability in TMTV segmentation across multi-site external datasets, encompassing various lymphoma subtypes. A negligible reduction of 2% in overall performance during testing on external data highlights robust model generalizability across different centers and cancer types, likely attributable to its training with resampled inputs. Our model is publicly available, allowing easy multi-site evaluation and generalizability analysis on datasets from different institutions.
Collapse
Affiliation(s)
- Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10Th Avenue, Vancouver, BC, V5Z 1L3, Canada.
| | - Ivan S Klyuzhin
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10Th Avenue, Vancouver, BC, V5Z 1L3, Canada
| | - Joo Hyun O
- College of Medicine, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, Republic of Korea
| | | | - Xin Tie
- Department of Radiology, University of WI-Madison, Madison, WI, USA
| | - Isaac Shiri
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland
| | - Muheon Shin
- Department of Radiology, University of WI-Madison, Madison, WI, USA
| | - Changhee Lee
- Department of Radiology, University of WI-Madison, Madison, WI, USA
| | - Steve Y Cho
- Department of Radiology, University of WI-Madison, Madison, WI, USA
| | - Tyler J Bradshaw
- Department of Radiology, University of WI-Madison, Madison, WI, USA
| | - Habib Zaidi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland
- University Medical Center Groningen, University of Groningen, Groningen, Netherlands
- Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark
- University Research and Innovation Center, Óbuda University, Budapest, Hungary
| | - François Bénard
- BC Cancer, Vancouver, BC, Canada
- Department of Radiology, University of British Columbia, Vancouver, BC, Canada
| | - Laurie H Sehn
- BC Cancer, Vancouver, BC, Canada
- Centre for Lymphoid Cancer, BC Cancer, Vancouver, Canada
| | - Kerry J Savage
- BC Cancer, Vancouver, BC, Canada
- Centre for Lymphoid Cancer, BC Cancer, Vancouver, Canada
| | - Christian Steidl
- BC Cancer, Vancouver, BC, Canada
- Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, Canada
| | - Carlos F Uribe
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10Th Avenue, Vancouver, BC, V5Z 1L3, Canada
- BC Cancer, Vancouver, BC, Canada
- Department of Radiology, University of British Columbia, Vancouver, BC, Canada
| | - Arman Rahmim
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10Th Avenue, Vancouver, BC, V5Z 1L3, Canada
- Department of Radiology, University of British Columbia, Vancouver, BC, Canada
- Departments of Physics and Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada
- Department of Biomedical Engineering, University of British Columbia, Vancouver, Canada
| |
Collapse
|
2
|
Sadik M, Barrington SF, Trägårdh E, Saboury B, Nielsen AL, Jakobsen AL, Gongora JLL, Urdaneta JL, Kumar R, Edenbrandt L. Metabolic tumour volume in Hodgkin lymphoma-A comparison between manual and AI-based analysis. Clin Physiol Funct Imaging 2024; 44:220-227. [PMID: 38011940 DOI: 10.1111/cpf.12868] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2023] [Revised: 11/10/2023] [Accepted: 11/24/2023] [Indexed: 11/29/2023]
Abstract
AIM To compare total metabolic tumour volume (tMTV), calculated using two artificial intelligence (AI)-based tools, with manual segmentation by specialists as the reference. METHODS Forty-eight consecutive Hodgkin lymphoma (HL) patients staged with [18F] fluorodeoxyglucose positron emission tomography/computed tomography were included. The median age was 35 years (range: 7-75), 46% female. The tMTV was automatically measured using the AI-based tools positron emission tomography assisted reporting system (PARS) (from Siemens) and RECOMIA (recomia.org) without any manual adjustments. A group of eight nuclear medicine specialists manually segmented lesions for tMTV calculations; each patient was independently segmented by two specialists. RESULTS The median of the manual tMTV was 146 cm3 (interquartile range [IQR]: 79-568 cm3) and the median difference between two tMTV values segmented by different specialists for the same patient was 26 cm3 (IQR: 10-86 cm3). In 22 of the 48 patients, the manual tMTV value was closer to the RECOMIA tMTV value than to the manual tMTV value segmented by the second specialist. In 11 of the remaining 26 patients, the difference between the RECOMIA tMTV and the manual tMTV was small (<26 cm3, which was the median difference between two manual tMTV values from the same patient). The corresponding numbers for PARS were 18 and 10 patients, respectively. CONCLUSION The results of this study indicate that RECOMIA and Siemens PARS AI tools could be used without any major manual adjustments in 69% (33/48) and 58% (28/48) of HL patients, respectively. This demonstrates the feasibility of using AI tools to support physicians measuring tMTV for assessment of prognosis in clinical practice.
Collapse
Affiliation(s)
- May Sadik
- Department of Molecular and Clinical Medicine, Clinical Physiology, Sahlgrenska University Hospital, Sahlgrenska Academy at the University of Gothenburg, Gothenburg, Sweden
| | - Sally F Barrington
- School of Biomedical Engineering and Imaging Sciences Kings College, King's College London and Guy's and St Thomas' PET Centre, London, UK
| | - Elin Trägårdh
- Departmet of Clinical Physiology and Nuclear Medicine, Skåne University Hospital, Lund University, Malmö, Sweden
| | - Babak Saboury
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, USA
| | - Anne L Nielsen
- Department of Nuclear Medicine, Odense University Hospital, Odense, Denmark
| | - Annika L Jakobsen
- Department of Clinical Physiology, Nuclear Medicine and PET, Centre of Diagnostic Investigations, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Jose L L Gongora
- Department of Diagnostic Imaging, Akershus University Hospital, Oslo, Norway
| | - Jesus L Urdaneta
- Department of Molecular and Clinical Medicine, Clinical Physiology, Sahlgrenska University Hospital, Sahlgrenska Academy at the University of Gothenburg, Gothenburg, Sweden
| | - Rajender Kumar
- Department of Nuclear Medicine, Post Graduate Institute of Medical Education and Research, Chandigarh, India
| | - Lars Edenbrandt
- Department of Molecular and Clinical Medicine, Clinical Physiology, Sahlgrenska University Hospital, Sahlgrenska Academy at the University of Gothenburg, Gothenburg, Sweden
| |
Collapse
|
3
|
Alderuccio JP, Kuker RA, Yang F, Moskowitz CH. Quantitative PET-based biomarkers in lymphoma: getting ready for primetime. Nat Rev Clin Oncol 2023; 20:640-657. [PMID: 37460635 DOI: 10.1038/s41571-023-00799-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/21/2023] [Indexed: 08/20/2023]
Abstract
The use of functional quantitative biomarkers extracted from routine PET-CT scans to characterize clinical responses in patients with lymphoma is gaining increased attention, and these biomarkers can outperform established clinical risk factors. Total metabolic tumour volume enables individualized estimation of survival outcomes in patients with lymphoma and has shown the potential to predict response to therapy suitable for risk-adapted treatment approaches in clinical trials. The deployment of machine learning tools in molecular imaging research can assist in recognizing complex patterns and, with image classification, in tumour identification and segmentation of data from PET-CT scans. Initial studies using fully automated approaches to calculate metabolic tumour volume and other PET-based biomarkers have demonstrated appropriate correlation with calculations from experts, warranting further testing in large-scale studies. The extraction of computer-based quantitative tumour characterization through radiomics can provide a comprehensive view of phenotypic heterogeneity that better captures the molecular and functional features of the disease. Additionally, radiomics can be integrated with genomic data to provide more accurate prognostic information. Further improvements in PET-based biomarkers are imminent, although their incorporation into clinical decision-making currently has methodological shortcomings that need to be addressed with confirmatory prospective validation in selected patient populations. In this Review, we discuss the current knowledge, challenges and opportunities in the integration of quantitative PET-based biomarkers in clinical trials and the routine management of patients with lymphoma.
Collapse
Affiliation(s)
- Juan Pablo Alderuccio
- Department of Medicine, Division of Hematology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA.
| | - Russ A Kuker
- Department of Radiology, Division of Nuclear Medicine, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Fei Yang
- Department of Radiation Oncology, Division of Medical Physics, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Craig H Moskowitz
- Department of Medicine, Division of Hematology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| |
Collapse
|
4
|
Constantino CS, Leocádio S, Oliveira FPM, Silva M, Oliveira C, Castanheira JC, Silva Â, Vaz S, Teixeira R, Neves M, Lúcio P, João C, Costa DC. Evaluation of Semiautomatic and Deep Learning-Based Fully Automatic Segmentation Methods on [ 18F]FDG PET/CT Images from Patients with Lymphoma: Influence on Tumor Characterization. J Digit Imaging 2023; 36:1864-1876. [PMID: 37059891 PMCID: PMC10407010 DOI: 10.1007/s10278-023-00823-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Revised: 03/14/2023] [Accepted: 03/27/2023] [Indexed: 04/16/2023] Open
Abstract
The objective is to assess the performance of seven semiautomatic and two fully automatic segmentation methods on [18F]FDG PET/CT lymphoma images and evaluate their influence on tumor quantification. All lymphoma lesions identified in 65 whole-body [18F]FDG PET/CT staging images were segmented by two experienced observers using manual and semiautomatic methods. Semiautomatic segmentation using absolute and relative thresholds, k-means and Bayesian clustering, and a self-adaptive configuration (SAC) of k-means and Bayesian was applied. Three state-of-the-art deep learning-based segmentations methods using a 3D U-Net architecture were also applied. One was semiautomatic and two were fully automatic, of which one is publicly available. Dice coefficient (DC) measured segmentation overlap, considering manual segmentation the ground truth. Lymphoma lesions were characterized by 31 features. Intraclass correlation coefficient (ICC) assessed features agreement between different segmentation methods. Nine hundred twenty [18F]FDG-avid lesions were identified. The SAC Bayesian method achieved the highest median intra-observer DC (0.87). Inter-observers' DC was higher for SAC Bayesian than manual segmentation (0.94 vs 0.84, p < 0.001). Semiautomatic deep learning-based median DC was promising (0.83 (Obs1), 0.79 (Obs2)). Threshold-based methods and publicly available 3D U-Net gave poorer results (0.56 ≤ DC ≤ 0.68). Maximum, mean, and peak standardized uptake values, metabolic tumor volume, and total lesion glycolysis showed excellent agreement (ICC ≥ 0.92) between manual and SAC Bayesian segmentation methods. The SAC Bayesian classifier is more reproducible and produces similar lesion features compared to manual segmentation, giving the best concordant results of all other methods. Deep learning-based segmentation can achieve overall good segmentation results but failed in few patients impacting patients' clinical evaluation.
Collapse
Affiliation(s)
- Cláudia S Constantino
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal.
| | - Sónia Leocádio
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Francisco P M Oliveira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Mariana Silva
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Carla Oliveira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Joana C Castanheira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Ângelo Silva
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Sofia Vaz
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Ricardo Teixeira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Manuel Neves
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Paulo Lúcio
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Cristina João
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Durval C Costa
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| |
Collapse
|
5
|
Keijzer K, Niezink AG, de Boer JW, van Doesum JA, Noordzij W, van Meerten T, van Dijk LV. Semi-automated 18F-FDG PET segmentation methods for tumor volume determination in Non-Hodgkin lymphoma patients: a literature review, implementation and multi-threshold evaluation. Comput Struct Biotechnol J 2023; 21:1102-1114. [PMID: 36789266 PMCID: PMC9900370 DOI: 10.1016/j.csbj.2023.01.023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Revised: 01/18/2023] [Accepted: 01/18/2023] [Indexed: 01/21/2023] Open
Abstract
In the treatment of Non-Hodgkin lymphoma (NHL), multiple therapeutic options are available. Improving outcome predictions are essential to optimize treatment. The metabolic active tumor volume (MATV) has shown to be a prognostic factor in NHL. It is usually retrieved using semi-automated thresholding methods based on standardized uptake values (SUV), calculated from 18F-Fluorodeoxyglucose Positron Emission Tomography (18F-FDG PET) images. However, there is currently no consensus method for NHL. The aim of this study was to review literature on different segmentation methods used, and to evaluate selected methods by using an in house created software tool. A software tool, MUltiple SUV Threshold (MUST)-segmenter was developed where tumor locations are identified by placing seed-points on the PET images, followed by subsequent region growing. Based on a literature review, 9 SUV thresholding methods were selected and MATVs were extracted. The MUST-segmenter was utilized in a cohort of 68 patients with NHL. Differences in MATVs were assessed with paired t-tests, and correlations and distributions figures. High variability and significant differences between the MATVs based on different segmentation methods (p < 0.05) were observed in the NHL patients. Median MATVs ranged from 35 to 211 cc. No consensus for determining MATV is available based on the literature. Using the MUST-segmenter with 9 selected SUV thresholding methods, we demonstrated a large and significant variation in MATVs. Identifying the most optimal segmentation method for patients with NHL is essential to further improve predictions of toxicity, response, and treatment outcomes, which can be facilitated by the MUST-segmenter.
Collapse
Key Words
- 18F-FDG PET
- AT, adaptive thresholding methods
- CAR, chimeric antigen receptor
- CT, computed tomography
- DICOM, Digital Imaging and Communications in Medicine
- DLBCL, Diffuse large B-cell lymphoma
- EANM, European Association of Nuclear Medicine
- EARL, EANM Research Ltd.
- FDG, fluorodeoxyglucose
- HL, Hodgkin lymphoma
- IMG, robustness across image reconstruction methods
- IQR, interquartile range
- LBCL, Large B-cell lymphoma
- LDH, lactate dehydrogenase
- MAN, clinician based evaluation using manual segmentations
- MATV, Metabolic active tumor volume
- MIP, Maximum Intensity Projection
- MUST, Multiple SUV Thresholding
- Metabolic tumor volume
- NHL, Non-Hodgkin lymphoma
- Non-Hodgkin lymphoma
- OBS, robustness across observers
- OS, overall survival
- PD-L1, programmed cell death ligand-1
- PET segmentation
- PET, positron emission tomography
- PFS, progression free survival
- PROG, progression vs non-progression
- PTCL, Peripheral T-cell lymphoma
- PTLD, Post-transplant lymphoproliferative disorder
- QS, quality scores
- SOFT, robustness across software
- SUV thresholding
- SUV, standardized uptake value
- Segmentation software
- TCL, T-cell lymphoma
- UMCG, University Medical Center Groningen
- VOI, volume of interest
- cc, cubic centimeter
Collapse
Affiliation(s)
- Kylie Keijzer
- Department of Hematology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands,Department of Radiation Oncology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands
| | - Anne G.H. Niezink
- Department of Radiation Oncology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands
| | - Janneke W. de Boer
- Department of Hematology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands
| | - Jaap A. van Doesum
- Department of Hematology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands
| | - Walter Noordzij
- Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands
| | - Tom van Meerten
- Department of Hematology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands
| | - Lisanne V. van Dijk
- Department of Radiation Oncology, University Medical Center Groningen, Hanzeplein 1, 9713GZ Groningen, the Netherlands,Corresponding author.
| |
Collapse
|
6
|
Kotsyfakis S, Iliaki-Giannakoudaki E, Anagnostopoulos A, Papadokostaki E, Giannakoudakis K, Goumenakis M, Kotsyfakis M. The application of machine learning to imaging in hematological oncology: A scoping review. Front Oncol 2022; 12:1080988. [PMID: 36605438 PMCID: PMC9808781 DOI: 10.3389/fonc.2022.1080988] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2022] [Accepted: 12/05/2022] [Indexed: 12/24/2022] Open
Abstract
Background Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is being applied to hematological cancer radiology; and (iii) identify addressable research gaps. Methods The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews guidelines. The inclusion criteria were (i) pediatric and adult patients with suspected or confirmed hematological malignancy undergoing imaging (population); (ii) any study using ML techniques to derive models using radiological images to apply to the clinical management of these patients (concept); and (iii) original research articles conducted in any setting globally (context). Quality Assessment of Diagnostic Accuracy Studies 2 criteria were used to assess diagnostic and segmentation studies, while the Newcastle-Ottawa scale was used to assess the quality of observational studies. Results Of 53 eligible studies, 33 applied diverse ML techniques to diagnose hematological malignancies or to differentiate them from other diseases, especially discriminating gliomas from primary central nervous system lymphomas (n=18); 11 applied ML to segmentation tasks, while 9 applied ML to prognostication or predicting therapeutic responses, especially for diffuse large B-cell lymphoma. All studies reported discrimination statistics, but no study calculated calibration statistics. Every diagnostic/segmentation study had a high risk of bias due to their case-control design; many studies failed to provide adequate details of the reference standard; and only a few studies used independent validation. Conclusion To deliver validated ML-based models to radiologists managing hematological malignancies, future studies should (i) adhere to standardized, high-quality reporting guidelines such as the Checklist for Artificial Intelligence in Medical Imaging; (ii) validate models in independent cohorts; (ii) standardize volume segmentation methods for segmentation tasks; (iv) establish comprehensive prospective studies that include different tumor grades, comparisons with radiologists, optimal imaging modalities, sequences, and planes; (v) include side-by-side comparisons of different methods; and (vi) include low- and middle-income countries in multicentric studies to enhance generalizability and reduce inequity.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Michail Kotsyfakis
- Biology Center of the Czech Academy of Sciences, Budweis (Ceske Budejovice), Czechia,*Correspondence: Michail Kotsyfakis,
| |
Collapse
|
7
|
Bradshaw TJ, Boellaard R, Dutta J, Jha AK, Jacobs P, Li Q, Liu C, Sitek A, Saboury B, Scott PJH, Slomka PJ, Sunderland JJ, Wahl RL, Yousefirizi F, Zuehlsdorff S, Rahmim A, Buvat I. Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development. J Nucl Med 2022; 63:500-510. [PMID: 34740952 PMCID: PMC10949110 DOI: 10.2967/jnumed.121.262567] [Citation(s) in RCA: 32] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Revised: 11/01/2021] [Indexed: 11/16/2022] Open
Abstract
The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.
Collapse
Affiliation(s)
- Tyler J Bradshaw
- Department of Radiology, University of Wisconsin-Madison, Madison, Wisconsin;
| | - Ronald Boellaard
- Department of Radiology and Nuclear Medicine, Cancer Centre Amsterdam, Amsterdam University Medical Centres, Amsterdam, The Netherlands
| | - Joyita Dutta
- Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, Massachusetts
| | - Abhinav K Jha
- Department of Biomedical Engineering and Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, Missouri
| | | | - Quanzheng Li
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Chi Liu
- Department of Radiology and Biomedical Imaging, Yale University, New Haven, Connecticut
| | | | - Babak Saboury
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, Maryland
| | - Peter J H Scott
- Department of Radiology, University of Michigan Medical School, Ann Arbor, Michigan
| | - Piotr J Slomka
- Department of Imaging, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, California
| | - John J Sunderland
- Departments of Radiology and Physics, University of Iowa, Iowa City, Iowa
| | - Richard L Wahl
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, Missouri
| | - Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, British Columbia, Canada
| | | | - Arman Rahmim
- Departments of Radiology and Physics, University of British Columbia, Vancouver, British Columbia, Canada; and
| | - Irène Buvat
- Institut Curie, Université PSL, INSERM, Université Paris-Saclay, Orsay, France
| |
Collapse
|
8
|
Hasani N, Paravastu SS, Farhadi F, Yousefirizi F, Morris MA, Rahmim A, Roschewski M, Summers RM, Saboury B. Artificial Intelligence in Lymphoma PET Imaging:: A Scoping Review (Current Trends and Future Directions). PET Clin 2022; 17:145-174. [PMID: 34809864 PMCID: PMC8735853 DOI: 10.1016/j.cpet.2021.09.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Malignant lymphomas are a family of heterogenous disorders caused by clonal proliferation of lymphocytes. 18F-FDG-PET has proven to provide essential information for accurate quantification of disease burden, treatment response evaluation, and prognostication. However, manual delineation of hypermetabolic lesions is often a time-consuming and impractical task. Applications of artificial intelligence (AI) may provide solutions to overcome this challenge. Beyond segmentation and detection of lesions, AI could enhance tumor characterization and heterogeneity quantification, as well as treatment response prediction and recurrence risk stratification. In this scoping review, we have systematically mapped and discussed the current applications of AI (such as detection, classification, segmentation as well as the prediction and prognostication) in lymphoma PET.
Collapse
Affiliation(s)
- Navid Hasani
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA; University of Queensland Faculty of Medicine, Ochsner Clinical School, New Orleans, LA 70121, USA
| | - Sriram S Paravastu
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA
| | - Faraz Farhadi
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA
| | - Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada
| | - Michael A Morris
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA; Department of Computer Science and Electrical Engineering, University of Maryland-Baltimore Country, Baltimore, MD, USA
| | - Arman Rahmim
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada; Department of Radiology, BC Cancer Research Institute, University of British Columbia, 675 West 10th Avenue, Vancouver, British Columbia, V5Z 1L3, Canada
| | - Mark Roschewski
- Lymphoid Malignancies Branch, Center for Cancer Research, National Institutes of Health, Bethesda, MD, USA
| | - Ronald M Summers
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA.
| | - Babak Saboury
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA; Department of Computer Science and Electrical Engineering, University of Maryland-Baltimore Country, Baltimore, MD, USA; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
| |
Collapse
|
9
|
Abstract
Trust in artificial intelligence (AI) by society and the development of trustworthy AI systems and ecosystems are critical for the progress and implementation of AI technology in medicine. With the growing use of AI in a variety of medical and imaging applications, it is more vital than ever to make these systems dependable and trustworthy. Fourteen core principles are considered in this article aiming to move the needle more closely to systems that are accurate, resilient, fair, explainable, safe, and transparent: toward trustworthy AI.
Collapse
|
10
|
Modiri A, Vogelius I, Rechner LA, Nygård L, Bentzen SM, Specht L. Outcome-based multiobjective optimization of lymphoma radiation therapy plans. Br J Radiol 2021; 94:20210303. [PMID: 34541859 PMCID: PMC8553178 DOI: 10.1259/bjr.20210303] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2021] [Revised: 09/02/2021] [Accepted: 09/06/2021] [Indexed: 02/04/2023] Open
Abstract
At its core, radiation therapy (RT) requires balancing therapeutic effects against risk of adverse events in cancer survivors. The radiation oncologist weighs numerous disease and patient-level factors when considering the expected risk-benefit ratio of combined treatment modalities. As part of this, RT plan optimization software is used to find a clinically acceptable RT plan delivering a prescribed dose to the target volume while respecting pre-defined radiation dose-volume constraints for selected organs at risk. The obvious limitation to the current approach is that it is virtually impossible to ensure the selected treatment plan could not be bettered by an alternative plan providing improved disease control and/or reduced risk of adverse events in this individual. Outcome-based optimization refers to a strategy where all planning objectives are defined by modeled estimates of a specific outcome's probability. Noting that various adverse events and disease control are generally incommensurable, leads to the concept of a Pareto-optimal plan: a plan where no single objective can be improved without degrading one or more of the remaining objectives. Further benefits of outcome-based multiobjective optimization are that quantitative estimates of risks and benefit are obtained as are the effects of choosing a different trade-off between competing objectives. Furthermore, patient-level risk factors and combined treatment modalities may be integrated directly into plan optimization. Here, we present this approach in the clinical setting of multimodality therapy for malignant lymphoma, a malignancy with marked heterogeneity in biology, target localization, and patient characteristics. We discuss future research priorities including the potential of artificial intelligence.
Collapse
Affiliation(s)
- Arezoo Modiri
- Department of Radiation Oncology, University of Maryland, School of Medicine, Baltimore, MD, USA
| | - Ivan Vogelius
- Department of Oncology, Section of Radiotherapy, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Laura Ann Rechner
- Department of Oncology, Section of Radiotherapy, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Lotte Nygård
- Department of Oncology, Section of Radiotherapy, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Søren M Bentzen
- Department of Epidemiology and Public Health, University of Maryland, School of Medicine, Baltimore, MD, USA
| | - Lena Specht
- Department of Oncology, Section of Radiotherapy, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
11
|
Yousefirizi F, Jha AK, Brosch-Lenz J, Saboury B, Rahmim A. Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging. PET Clin 2021; 16:577-596. [PMID: 34537131 DOI: 10.1016/j.cpet.2021.06.001] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Artificial intelligence (AI) techniques for image-based segmentation have garnered much attention in recent years. Convolutional neural networks have shown impressive results and potential toward fully automated segmentation in medical imaging, and particularly PET imaging. To cope with the limited access to annotated data needed in supervised AI methods, given tedious and prone-to-error manual delineations, semi-supervised and unsupervised AI techniques have also been explored for segmentation of tumors or normal organs in single- and bimodality scans. This work reviews existing AI techniques for segmentation tasks and the evaluation criteria for translational AI-based segmentation efforts toward routine adoption in clinical workflows.
Collapse
Affiliation(s)
- Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10th Avenue, Vancouver, British Columbia V5Z 1L3, Canada.
| | - Abhinav K Jha
- Department of Biomedical Engineering, Washington University in St. Louis, St Louis, MO 63130, USA; Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, MO 63110, USA
| | - Julia Brosch-Lenz
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10th Avenue, Vancouver, British Columbia V5Z 1L3, Canada
| | - Babak Saboury
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Bethesda, MD 20892, USA; Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD, USA; Department of Radiology, Hospital of the University of Pennsylvania, 3400 Spruce Street, Philadelphia, PA 19104, USA
| | - Arman Rahmim
- Department of Radiology, University of British Columbia, BC Cancer, BC Cancer Research Institute, 675 West 10th Avenue, Office 6-112, Vancouver, British Columbia V5Z 1L3, Canada; Department of Physics, University of British Columbia, Senior Scientist & Provincial Medical Imaging Physicist, BC Cancer, BC Cancer Research Institute, 675 West 10th Avenue, Office 6-112, Vancouver, British Columbia V5Z 1L3, Canada
| |
Collapse
|
12
|
Capobianco N, Sibille L, Chantadisai M, Gafita A, Langbein T, Platsch G, Solari EL, Shah V, Spottiswoode B, Eiber M, Weber WA, Navab N, Nekolla SG. Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning. Eur J Nucl Med Mol Imaging 2021; 49:517-526. [PMID: 34232350 PMCID: PMC8803695 DOI: 10.1007/s00259-021-05473-2] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2021] [Accepted: 06/17/2021] [Indexed: 01/16/2023]
Abstract
Purpose In PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers. Methods In 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework. Results In the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1–87.8] for identification of suspicious uptake sites, 77% (CI: 70.0–83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage. Conclusion The evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden. Supplementary Information The online version contains supplementary material available at 10.1007/s00259-021-05473-2.
Collapse
Affiliation(s)
- Nicolò Capobianco
- Technische Universität München, Munich, Germany. .,Siemens Healthcare GmbH, Erlangen, Germany.
| | | | - Maythinee Chantadisai
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany.,Faculty of Medicine, King Chulalongkorn Memorial Hospital, The Thai Red Cross Society, Chulalongkorn University, Bangkok, Thailand
| | - Andrei Gafita
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany
| | - Thomas Langbein
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany
| | | | - Esteban Lucas Solari
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany
| | - Vijay Shah
- Siemens Medical Solutions USA, Inc., Knoxville, TN, USA
| | | | - Matthias Eiber
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany
| | - Wolfgang A Weber
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany
| | - Nassir Navab
- Computer Aided Medical Procedures (CAMP), Technische Universität München, Munich, Germany
| | - Stephan G Nekolla
- School of Medicine, Department of Nuclear Medicine, Technische Universität München, Munich, Germany
| |
Collapse
|
13
|
Zwezerijnen GJ, Eertink JJ, Burggraaff CN, Wiegers SE, Shaban EA, Pieplenbosch S, Oprea-Lager DE, Lugtenburg PJ, Hoekstra OS, de Vet HC, Zijlstra JM, Boellaard R. Interobserver agreement in automated metabolic tumor volume measurements of Deauville score 4 and 5 lesions at interim 18F-FDG PET in DLBCL. J Nucl Med 2021; 62:1531-1536. [PMID: 33674403 DOI: 10.2967/jnumed.120.258673] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2020] [Accepted: 02/16/2021] [Indexed: 11/16/2022] Open
Abstract
Introduction: Metabolic tumor volume (MTV) on interim-PET (I-PET) is a potential prognostic biomarker for diffuse large B-cell lymphoma (DLBCL). Implementation of MTV on I-PET requires consensus which semi-automated segmentation method delineates lesions most successfully with least user interaction. Methods used for baseline PET are not necessarily optimal for I-PET due to lower lesional standardized uptake values (SUV) at I-PET. Therefore, we aimed to evaluate which method provides the best delineation quality of Deauville-score (DS) 4-5 DLBCL lesions on I-PET at best interobserver agreement on delineation quality and, secondly, to assess the effect of lesional SUVmax on delineation quality and performance agreements. Methods: DS4-5 lesions from 45 I-PET scans were delineated using six semi-automated methods i) SUV 2.5, ii) SUV 4.0, iii) adaptive threshold [A50%peak], iv) 41% of maximum SUV [41%max], v) majority vote including voxels detected by ≥2 methods [MV2] and vi) detected by ≥3 methods [MV3]. Delineation quality per MTV was rated by three independent observers as acceptable or non-acceptable. For each method, observer scores on delineation quality, specific agreements and MTV were assessed for all lesions, and per category of lesional SUVmax (<5, 5-10, >10). Results: In 60 DS4-5 lesions on I-PET, MV3 performed best, with acceptable delineation in 90% of lesions, with a positive agreement (PA) of 93%. Delineation quality scores and agreements per method strongly depended on lesional SUV: the best delineation quality scores were obtained using MV3 in lesions with SUVmax<10 and SUV4.0 in more FDG-avid lesions. Consequently, overall delineation quality and PA improved by applying the most preferred method per SUV category instead of using MV3 as single best method. MV3- and SUV4.0-derived MTVs of lesions with SUVmax>10, were comparable after excluding visually failed MV3 contouring. For lesions with SUVmax<10, MTVs using different methods correlated poorly. Conclusion: On I-PET, MV3 performed best and provided the highest interobserver agreement regarding acceptable delineations of DS4-5 DLBCL lesions. However, delineation method preference strongly depended on lesional SUV. Therefore, we suggest to explore an approach that identifies the optimal delineation method per lesion as function of tumor FDG uptake characteristics, i.e. SUVmax.
Collapse
Affiliation(s)
- Gerben Jc Zwezerijnen
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Netherlands
| | - Jakoba J Eertink
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Hematology, Cancer Center Amsterdam, Netherlands
| | - Coreline N Burggraaff
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Hematology, Cancer Center Amsterdam, Netherlands
| | - Sanne E Wiegers
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Hematology, Cancer Center Amsterdam, Netherlands
| | - Ekhlas A Shaban
- Radiodiagnosis and medical imaging department, Faculty of Medicine, Tanta University, Egypt
| | - Simone Pieplenbosch
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Netherlands
| | - Daniela E Oprea-Lager
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Netherlands
| | | | - Otto S Hoekstra
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Netherlands
| | - Henrica Cw de Vet
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Epidemiology and Data Science, Amsterdam Public Health research institute, Netherlands
| | - Josee M Zijlstra
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Hematology, Cancer Center Amsterdam, Netherlands
| | - Ronald Boellaard
- Amsterdam UMC, Vrije Universiteit Amsterdam, department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Netherlands
| |
Collapse
|