1
|
Kovacs DG, Ladefoged CN, Andersen KF, Brittain JM, Christensen CB, Dejanovic D, Hansen NL, Loft A, Petersen JH, Reichkendler M, Andersen FL, Fischer BM. Clinical Evaluation of Deep Learning for Tumor Delineation on 18F-FDG PET/CT of Head and Neck Cancer. J Nucl Med 2024; 65:jnumed.123.266574. [PMID: 38388516 PMCID: PMC10995525 DOI: 10.2967/jnumed.123.266574] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 01/29/2024] [Accepted: 01/29/2024] [Indexed: 02/24/2024] Open
Abstract
Artificial intelligence (AI) may decrease 18F-FDG PET/CT-based gross tumor volume (GTV) delineation variability and automate tumor-volume-derived image biomarker extraction. Hence, we aimed to identify and evaluate promising state-of-the-art deep learning methods for head and neck cancer (HNC) PET GTV delineation. Methods: We trained and evaluated deep learning methods using retrospectively included scans of HNC patients referred for radiotherapy between January 2014 and December 2019 (ISRCTN16907234). We used 3 test datasets: an internal set to compare methods, another internal set to compare AI-to-expert variability and expert interobserver variability (IOV), and an external set to compare internal and external AI-to-expert variability. Expert PET GTVs were used as the reference standard. Our benchmark IOV was measured using the PET GTV of 6 experts. The primary outcome was the Dice similarity coefficient (DSC). ANOVA was used to compare methods, a paired t test was used to compare AI-to-expert variability and expert IOV, an unpaired t test was used to compare internal and external AI-to-expert variability, and post hoc Bland-Altman analysis was used to evaluate biomarker agreement. Results: In total, 1,220 18F-FDG PET/CT scans of 1,190 patients (mean age ± SD, 63 ± 10 y; 858 men) were included, and 5 deep learning methods were trained using 5-fold cross-validation (n = 805). The nnU-Net method achieved the highest similarity (DSC, 0.80 [95% CI, 0.77-0.86]; n = 196). We found no evidence of a difference between expert IOV and AI-to-expert variability (DSC, 0.78 for AI vs. 0.82 for experts; mean difference of 0.04 [95% CI, -0.01 to 0.09]; P = 0.12; n = 64). We found no evidence of a difference between the internal and external AI-to-expert variability (DSC, 0.80 internally vs. 0.81 externally; mean difference of 0.004 [95% CI, -0.05 to 0.04]; P = 0.87; n = 125). PET GTV-derived biomarkers of AI were in good agreement with experts. Conclusion: Deep learning can be used to automate 18F-FDG PET/CT tumor-volume-derived imaging biomarkers, and the deep-learning-based volumes have the potential to assist clinical tumor volume delineation in radiation oncology.
Collapse
Affiliation(s)
- David G Kovacs
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark;
- Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Claes N Ladefoged
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
- Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark
| | - Kim F Andersen
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Jane M Brittain
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Charlotte B Christensen
- Department of Clinical Physiology and Nuclear Medicine, Herlev Hospital, University of Copenhagen, Copenhagen, Denmark
| | - Danijela Dejanovic
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Naja L Hansen
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Annika Loft
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Jørgen H Petersen
- Section of Biostatistics, Institute of Public Health, Faculty of Health Sciences, University of Copenhagen, Denmark; and
| | - Michala Reichkendler
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Flemming L Andersen
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
- Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Barbara M Fischer
- Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
- Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
- PET Centre, School of Biomedical Engineering and Imaging Science, King's College London, London, United Kingdom
| |
Collapse
|
2
|
Thorwarth D. Clinical use of positron emission tomography for radiotherapy planning - Medical physics considerations. Z Med Phys 2023; 33:13-21. [PMID: 36272949 PMCID: PMC10068574 DOI: 10.1016/j.zemedi.2022.09.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2022] [Revised: 08/17/2022] [Accepted: 09/21/2022] [Indexed: 11/06/2022]
Abstract
PET/CT imaging plays an increasing role in radiotherapy treatment planning. The aim of this article was to identify the major use cases and technical as well as medical physics challenges during integration of these data into treatment planning. Dedicated aspects, such as (i) PET/CT-based radiotherapy simulation, (ii) PET-based target volume delineation, (iii) functional avoidance to optimized organ-at-risk sparing and (iv) functionally adapted individualized radiotherapy are discussed in this article. Furthermore, medical physics aspects to be taken into account are summarized and presented in form of check-lists.
Collapse
Affiliation(s)
- Daniela Thorwarth
- Section for Biomedical Physics, Department of Radiation Oncology, University of Tübingen, Tübingen, Germany; German Cancer Consortium (DKTK), partner site Tübingen; and German Cancer Research Center (DKFZ), Heidelberg, Germany.
| |
Collapse
|
4
|
Li Q, Hou W, Li L, Su M, Ren Y, Wang W, Zou K, Tian R, Sun X. The use of systematic review evidence to support the development of guidelines for positron emission tomography: a cross-sectional survey. Eur Radiol 2021; 31:6992-7002. [PMID: 33683391 DOI: 10.1007/s00330-021-07756-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2020] [Revised: 01/06/2021] [Accepted: 02/04/2021] [Indexed: 02/05/2023]
Abstract
OBJECTIVES To examine to what degree guidelines for PET and PET/CT used systematic review evidence. METHODS The latest version of guidelines for PET, PET/CT or PET/MRI published in English in PubMed until December 2019 was analysed in two categories: (1) for indications, if mainly discussing the appropriate use of PET in diverse conditions; (2) for procedures, if providing step-by-step instructions for imaging. We surveyed the general characteristics and the use of systematic review evidence for developing recommendations across all guidelines, and surveyed the citation of evidence for five recommendation topics in guidelines for procedures. RESULTS Forty-seven guidelines, published between 2004 and 2020, were included. Guidelines for indications were developed mainly on systematic reviews (13 of 19, 68.4%). Among those, 12 (63.2%) reported the level of evidence, 4 (21.1%) reported the strength of recommendations, 3 (15.8%) described external review and 7 (36.8%) involved methodologists. Guidelines for procedures were seldom developed on systematic reviews (1 of 27, 3.7%). Among those, 1 (3.7%) reported the level of evidence, 1 (3.7%) reported the strength of recommendations, 3 (11.1%) described external review and 1 (3.7%) involved methodologists. Systematic review evidence was cited by 2 (7.4%) procedure guidelines per recommendation topic in median. CONCLUSION The use of systematic review evidence for developing recommendations among PET or PET/CT guidelines was suboptimal. While our survey is an icebreaking attempt to explore a key element (i.e. use of systematic review evidence) for developing nuclear medicine guidelines, assessments of other domains of guideline quality may help capture the entire picture. KEY POINTS • The use of systematic review evidence for developing recommendations among guidelines for PET or PET/CT was suboptimal. • Only 13 (68.4%) guidelines for indications and 1 (3.7%) guideline for procedures systematically reviewed the literature during guideline development. • For each recommendation topic we examined, only a median of 2 (7.4%) procedure guidelines cited systematic review evidence.
Collapse
Affiliation(s)
- Qianrui Li
- Department of Nuclear Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China.,Chinese Evidence-based Medicine Centre, Cochrane China Centre and MAGIC China Centre, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Wenxiu Hou
- Department of Nuclear Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Ling Li
- Chinese Evidence-based Medicine Centre, Cochrane China Centre and MAGIC China Centre, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Minggang Su
- Department of Nuclear Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Yan Ren
- Chinese Evidence-based Medicine Centre, Cochrane China Centre and MAGIC China Centre, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Wen Wang
- Chinese Evidence-based Medicine Centre, Cochrane China Centre and MAGIC China Centre, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Kang Zou
- Chinese Evidence-based Medicine Centre, Cochrane China Centre and MAGIC China Centre, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Rong Tian
- Department of Nuclear Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
| | - Xin Sun
- Chinese Evidence-based Medicine Centre, Cochrane China Centre and MAGIC China Centre, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
| |
Collapse
|