1
|
Xu C, Song Y, Zhang D, Bittencourt LK, Tirumani SH, Li S. Spatiotemporal knowledge teacher-student reinforcement learning to detect liver tumors without contrast agents. Med Image Anal 2023; 90:102980. [PMID: 37820417 DOI: 10.1016/j.media.2023.102980] [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: 04/04/2023] [Revised: 09/18/2023] [Accepted: 09/22/2023] [Indexed: 10/13/2023]
Abstract
Detecting Liver tumors without contrast agents (CAs) has shown great potential to advance liver cancer screening. It enables the provision of a reliable liver tumor-detecting result from non-enhanced MR images comparable to the radiologists' results from CA-enhanced MR images, thus eliminating the high risk of CAs, preventing an experience gap between radiologists and simplifying clinical workflows. In this paper, we proposed a novel spatiotemporal knowledge teacher-student reinforcement learning (SKT-RL) as a safe, speedy, and inexpensive contrast-free technology for liver tumor detection. Our SKT-RL builds a teacher-student framework to realize the exploring of explicit liver tumor knowledge from a teacher network on clear contrast-enhanced images to guide a student network to detect tumors from non-enhanced images directly. Importantly, our STK-RL enables three novelties in aspects of construction, transferring, and optimization to tumor knowledge to improve the guide effect. (1) A new spatiotemporal ternary knowledge set enables the construction of accurate knowledge that allows understanding of DRL's behavior (what to do) and reason (why to do it) behind reliable detection within each state and between their related historical states. (2) A novel pixel momentum transferring strategy enables detailed and controlled knowledge transfer ability. It transfers knowledge at a pixel level to enlarge the explorable space of transferring and control how much knowledge is transferred to prevent over-rely of the student to the teacher. (3) A phase-trend reward function designs different evaluations according to different detection phases to optimal for each phase in high-precision but also allows reward trend to constraint the evaluation to improve stability. Comprehensive experiments on a generalized liver tumor dataset with 375 patients (including hemangiomas, hepatocellular carcinoma, and normal controls) show that our novel SKT-RL attains a new state-of-the-art performance (improved precision by at least 4% when comparing the six recent advanced methods) in the task of liver tumor detection without CAs. The results proved that our SKT-DRL has greatly promoted the development and deployment of contrast-free liver tumor technology.
Collapse
Affiliation(s)
- Chenchu Xu
- School of Computer Science and Technology, Anhui University, Hefei, China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China
| | - Yuhong Song
- School of Computer Science and Technology, Anhui University, Hefei, China
| | - Dong Zhang
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada.
| | | | | | - Shuo Li
- School of Engineering, Case Western Reserve University, Cleveland, United States.
| |
Collapse
|
2
|
Guzene L, Beddok A, Nioche C, Modzelewski R, Loiseau C, Salleron J, Thariat J. Assessing Interobserver Variability in the Delineation of Structures in Radiation Oncology: A Systematic Review. Int J Radiat Oncol Biol Phys 2023; 115:1047-1060. [PMID: 36423741 DOI: 10.1016/j.ijrobp.2022.11.021] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Revised: 11/04/2022] [Accepted: 11/09/2022] [Indexed: 11/23/2022]
Abstract
PURPOSE The delineation of target volumes and organs at risk is the main source of uncertainty in radiation therapy. Numerous interobserver variability (IOV) studies have been conducted, often with unclear methodology and nonstandardized reporting. We aimed to identify the parameters chosen in conducting delineation IOV studies and assess their performances and limits. METHODS AND MATERIALS We conducted a systematic literature review to highlight major points of heterogeneity and missing data in IOV studies published between 2018 and 2021. For the main used metrics, we did in silico analyses to assess their limits in specific clinical situations. RESULTS All disease sites were represented in the 66 studies examined. Organs at risk were studied independently of tumor site in 29% of reviewed IOV studies. In 65% of studies, statistical analyses were performed. No gold standard (GS; ie, reference) was defined in 36% of studies. A single expert was considered as the GS in 21% of studies, without testing intraobserver variability. All studies reported both absolute and relative indices, including the Dice similarity coefficient (DSC) in 68% and the Hausdorff distance (HD) in 42%. Limitations were shown in silico for small structures when using the DSC and dependence on irregular shapes when using the HD. Variations in DSC values were large between studies, and their thresholds were inconsistent. Most studies (51%) included 1 to 10 cases. The median number of observers or experts was 7 (range, 2-35). The intraclass correlation coefficient was reported in only 9% of cases. Investigating the feasibility of studying IOV in delineation, a minimum of 8 observers with 3 cases, or 11 observers with 2 cases, was required to demonstrate moderate reproducibility. CONCLUSIONS Implementation of future IOV studies would benefit from a more standardized methodology: clear definitions of the gold standard and metrics and a justification of the tradeoffs made in the choice of the number of observers and number of delineated cases should be provided.
Collapse
Affiliation(s)
- Leslie Guzene
- Department of Radiation Oncology, University Hospital of Amiens, Amiens, France
| | - Arnaud Beddok
- Department of Radiation Oncology, Institut Curie, Paris/Saint-Cloud/Orsay, France; Laboratory of Translational Imaging in Oncology (LITO), InsermUMR, Institut Curie, Orsay, France
| | - Christophe Nioche
- Laboratory of Translational Imaging in Oncology (LITO), InsermUMR, Institut Curie, Orsay, France
| | - Romain Modzelewski
- LITIS - EA4108-Quantif, Normastic, University of Rouen, and Nuclear Medicine Department, Henri Becquerel Center, Rouen, France
| | - Cedric Loiseau
- Department of Radiation Oncology, Centre François Baclesse; ARCHADE Research Community Caen, France; Département de Biostatistiques, Institut de Cancérologie de Lorraine, Vandœuvre-lès-Nancy, France
| | - Julia Salleron
- Département de Biostatistiques, Institut de Cancérologie de Lorraine, Vandœuvre-lès-Nancy, France
| | - Juliette Thariat
- Department of Radiation Oncology, Centre François Baclesse; ARCHADE Research Community Caen, France; Laboratoire de Physique Corpusculaire, Caen, France; Unicaen-Université de Normandie, Caen, France.
| |
Collapse
|
3
|
Groot Koerkamp ML, Vasmel JE, Russell NS, Shaitelman SF, Anandadas CN, Currey A, Vesprini D, Keller BM, De-Colle C, Han K, Braunstein LZ, Mahmood F, Lorenzen EL, Philippens MEP, Verkooijen HM, Lagendijk JJW, Houweling AC, van den Bongard HJGD, Kirby AM. Optimizing MR-Guided Radiotherapy for Breast Cancer Patients. Front Oncol 2020; 10:1107. [PMID: 32850318 PMCID: PMC7399349 DOI: 10.3389/fonc.2020.01107] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2020] [Accepted: 06/03/2020] [Indexed: 01/01/2023] Open
Abstract
Current research in radiotherapy (RT) for breast cancer is evaluating neoadjuvant as opposed to adjuvant partial breast irradiation (PBI) with the aim of reducing the volume of breast tissue irradiated and therefore the risk of late treatment-related toxicity. The development of magnetic resonance (MR)-guided RT, including dedicated MR-guided RT systems [hybrid machines combining an MR scanner with a linear accelerator (MR-linac) or 60Co sources], could potentially reduce the irradiated volume even further by improving tumour visibility before and during each RT treatment. In this position paper, we discuss MR guidance in relation to each step of the breast RT planning and treatment pathway, focusing on the application of MR-guided RT to neoadjuvant PBI.
Collapse
Affiliation(s)
| | - Jeanine E. Vasmel
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, Netherlands
| | - Nicola S. Russell
- Department of Radiotherapy, The Netherlands Cancer Institute–Antoni van Leeuwenhoek Hospital, Amsterdam, Netherlands
| | - Simona F. Shaitelman
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Carmel N. Anandadas
- Department of Clinical Oncology, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Adam Currey
- Department of Radiation Oncology, Medical College of Wisconsin, Milwaukee, WI, United States
| | - Danny Vesprini
- Department of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON, Canada
| | - Brian M. Keller
- Department of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON, Canada
| | - Chiara De-Colle
- Department of Radiation Oncology, University Hospital and Medical Faculty, Eberhard Karls University Tübingen, Tübingen, Germany
| | - Kathy Han
- Department of Radiation Oncology, Princess Margaret Cancer Centre, University Health Network, University of Toronto, Toronto, ON, Canada
| | - Lior Z. Braunstein
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Faisal Mahmood
- Department of Oncology, Odense University Hospital, Odense, Denmark
- Research Unit for Oncology, Department of Clinical Research, University of Southern Denmark, Odense, Denmark
| | - Ebbe L. Lorenzen
- Department of Oncology, Odense University Hospital, Odense, Denmark
| | | | | | - Jan J. W. Lagendijk
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, Netherlands
| | - Antonetta C. Houweling
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, Netherlands
| | | | - Anna M. Kirby
- Department of Radiotherapy, Royal Marsden NHS Foundation Trust and Institute of Cancer Research, Sutton, United Kingdom
| |
Collapse
|
4
|
Abstract
The Publisher regrets that this article is an accidental duplication of an article that has already been published in [Seminars in Ultrasound, CT, and MRI, 41/2 (2020) 170–182], https://dx.doi.org/10.1053/j.sult.2019.12.005. The duplicate article has therefore been withdrawn.
The full Elsevier Policy on Article Withdrawal can be found at https://www.elsevier.com/about/our-business/policies/article-withdrawal
Collapse
Affiliation(s)
- Colleen M Costelloe
- Division of Diagnostic Imaging, University of Texas MD Anderson Cancer Center, Houston, TX.
| | - Behrang Amini
- Division of Diagnostic Imaging, University of Texas MD Anderson Cancer Center, Houston, TX
| | - John E Madewell
- Division of Diagnostic Imaging, University of Texas MD Anderson Cancer Center, Houston, TX
| |
Collapse
|
6
|
Mouawad M, Biernaski H, Brackstone M, Lock M, Yaremko B, Shmuilovich O, Kornecki A, Ben Nachum I, Muscedere G, Lynn K, Prato FS, Thompson RT, Gaede S, Gelman N. DCE-MRI assessment of response to neoadjuvant SABR in early stage breast cancer: Comparisons of single versus three fraction schemes and two different imaging time delays post-SABR. Clin Transl Radiat Oncol 2020; 21:25-31. [PMID: 32021911 PMCID: PMC6993055 DOI: 10.1016/j.ctro.2019.12.004] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [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] [Received: 12/18/2019] [Accepted: 12/22/2019] [Indexed: 12/25/2022] Open
Abstract
PURPOSE To determine the effect of dose fractionation and time delay post-neoadjuvant stereotactic ablative radiotherapy (SABR) on dynamic contrast-enhanced (DCE)-MRI parameters in early stage breast cancer patients. MATERIALS AND METHODS DCE-MRI was acquired in 17 patients pre- and post-SABR. Five patients were imaged 6-7 days post-21 Gy/1fraction (group 1), six 16-19 days post-21 Gy/1fraction (group 2), and six 16-18 days post-30 Gy/3 fractions every other day (group 3). DCE-MRI scans were performed using half the clinical dose of contrast agent. Changes in the surrounding tissue were quantified using a signal-enhancement threshold metric that characterizes changes in signal-enhancement volume (SEV). Tumour response was quantified using Ktrans and ve (Tofts model) pre- and post-SABR. Significance was assessed using a Wilcoxin signed-rank test. RESULTS All group 1 and 4/6 group 2 patients' SEV increased post-SABR. All group 3 patients' SEV decreased. The mean Ktrans increased for group 1 by 76% (p = 0.043) while group 2 and 3 decreased 15% (p = 0.028) and 34% (p = 0.028), respectively. For ve, there was no significant change in Group 1 (p = 0.35). Groups 2 showed an increase of 24% (p = 0.043), and Group 3 trended toward an increase (23%, p = 0.08). CONCLUSION Kinetic parameters measured 2.5 weeks post-SABR in both single fraction and three fraction groups were indicative of response but only the single fraction protocol led to enhancement in the surrounding tissue. Our results also suggest that DCE-MRI one-week post-SABR may be too early for response assessment, at least for single fraction SABR, whereas 2.5 weeks appears sufficiently long to minimize confounding acute effects.
Collapse
Affiliation(s)
- Matthew Mouawad
- Medical Biophysics, Western University, London, Ontario, Canada
| | | | - Muriel Brackstone
- Medical Biophysics, Western University, London, Ontario, Canada
- Lawson Health Research Institute, London, Ontario, Canada
- London Health Sciences Centre, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
| | - Michael Lock
- London Health Sciences Centre, London, Ontario, Canada
- Department of Oncology, Western University, London, Ontario, Canada
| | - Brian Yaremko
- London Health Sciences Centre, London, Ontario, Canada
- Department of Oncology, Western University, London, Ontario, Canada
| | - Olga Shmuilovich
- Lawson Health Research Institute, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
- Department of Medical Imaging, Western University, London, Ontario, Canada
| | - Anat Kornecki
- Lawson Health Research Institute, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
- Department of Medical Imaging, Western University, London, Ontario, Canada
| | - Ilanit Ben Nachum
- Lawson Health Research Institute, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
- Department of Medical Imaging, Western University, London, Ontario, Canada
| | - Giulio Muscedere
- Lawson Health Research Institute, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
- Department of Medical Imaging, Western University, London, Ontario, Canada
| | - Kalan Lynn
- Lawson Health Research Institute, London, Ontario, Canada
- London Health Sciences Centre, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
| | - Frank S. Prato
- Medical Biophysics, Western University, London, Ontario, Canada
- Lawson Health Research Institute, London, Ontario, Canada
- St. Joseph’s Health Care, London, Ontario, Canada
- Department of Medical Imaging, Western University, London, Ontario, Canada
| | - R. Terry Thompson
- Medical Biophysics, Western University, London, Ontario, Canada
- Lawson Health Research Institute, London, Ontario, Canada
| | - Stewart Gaede
- Medical Biophysics, Western University, London, Ontario, Canada
- Lawson Health Research Institute, London, Ontario, Canada
- London Health Sciences Centre, London, Ontario, Canada
- Department of Oncology, Western University, London, Ontario, Canada
| | - Neil Gelman
- Medical Biophysics, Western University, London, Ontario, Canada
- Lawson Health Research Institute, London, Ontario, Canada
- Department of Medical Imaging, Western University, London, Ontario, Canada
| |
Collapse
|