Добавил:
Sekretar
kiopkiopkiop18@yandex.ru
t.me/Prokururor I Вовсе не секретарь, но почту проверяю
Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз:
Предмет:
Файл:Ординатура / Хирургия / Библиотека им академика М.И. Перельмана / Книга_5525_Библиотеки_им_академика_М_И_Перельмана.pdf
X
- •Foreword
- •Acknowledgments
- •Editor biographies
- •Yi Wang
- •X. Sharon Qi
- •List of contributors
- •1.2.3 Feature engineering and representation
- •1.2.4 Linear separability
- •1.2.5 Classical models
- •1.1 A brief introduction to AI
- •1.2 Machine learning basics
- •1.2.1 Learning paradigms
- •1.3 Artificial neural networks
- •1.3.1 Feed-forward neural networks
- •1.3.2 Recurrent neural networks
- •1.3.3 Convolutional neural networks
- •1.3.4 Attention
- •1.3.5 Training neural networks
- •1.3.6 Applications and use cases of deep learning
- •1.4 Model training and evaluation
- •1.4.1 Hyperparameters
- •1.4.2 Data split
- •1.4.3 Evaluation metrics
- •1.5 Generative models
- •1.5.1 Generative adversarial networks
- •1.5.2 Diffusion models
- •1.5.3 Applications and use cases
- •1.6 Ethical consideration and bias
- •1.6.1 Transparency and explainability
- •1.6.2 Bias and fairness
- •1.6.3 Data privacy violation
- •1.6.4 Risk and misuse
- •1.7 Summary
- •References
- •2.1 Introduction
- •2.1.2 Staff roles in radiation therapy
- •2.2 Overview of AI in radiation therapy
- •2.2.1 Patient evaluation and dose prescription
- •2.2.2 Treatment simulation
- •2.2.3 Contouring
- •2.2.4 Treatment planning
- •2.2.5 Quality assurance
- •2.2.6 Treatment delivery
- •2.2.7 Response assessment and toxicity management
- •2.3 Summary
- •3.1 Introduction
- •3.1.1 Introduction of clinical decision making and AI
- •3.1.2 The role of AI in clinical decision making
- •3.2 AI algorithms for clinical decision making
- •3.2.2 Radiomics
- •3.2.3 Data integration by AI
- •3.2.4 Interpretability of AI models
- •3.3 Application of AI in clinical decision making
- •3.3.1 Diagnosis and disease phenotyping
- •3.3.2 Personalized treatment
- •3.3.3 Treatment outcome and prognosis prediction
- •3.4 Challenges and future directions of AI in clinical decision making
- •3.4.1 Challenges and concerns
- •3.4.2 Future directions
- •3.5 Summary
- •References
- •4.1 Introduction
- •4.2 Imaging for treatment planning
- •4.2.1 CT simulation
- •4.2.2 4D-CT
- •4.2.3 PET/CT
- •4.2.4 MRI
- •4.3 Imaging for treatment guidance
- •4.3.1 Portal imaging
- •4.3.2 CBCT
- •4.3.3 CT-on-rail and CT-linac
- •4.3.4 MR-linac
- •4.3.5 PET-linac
- •4.4 Imaging for motion management
- •4.4.1 ExacTrac
- •4.4.2 Varian triggered imaging
- •4.4.3 4D-CBCT
- •4.4.4 Cine MRI
- •4.4.5 4D-MRI
- •4.4.6 Surface imaging
- •4.5 Imaging for treatment assessment
- •4.5.1 Contrasted CT
- •4.5.2 PET/CT
- •4.5.3 Functional MRI
- •4.6 Summary
- •5.1 Introduction to big data in radiation oncology
- •5.1.1 Overview of big data
- •5.1.2 Sources of big data in radiation oncology
- •5.1.3 Big data and AI in radiation oncology
- •5.2 Big data lifecycle in radiation oncology
- •5.2.1 Data aggregation and storage
- •5.2.2 Data sharing and security
- •5.4 The application of big data in radiation oncology
- •5.4.1 Medical image segmentation
- •5.4.2 Automatic treatment planning
- •5.4.3 Treatment response prediction
- •5.4.4 Quality assurance and patient safety
- •5.4.5 Clinical decision support
- •5.2.3 Data visualization
- •5.2.4 Knowledge creation and implementation
- •5.2.5 Data archiving and deletion
- •5.3 Big data analytics with AI
- •5.3.1 Data processing and integration
- •5.3.2 AI modeling
- •5.5 Challenges and future perspectives
- •5.6 Summary
- •Reference
- •6.1 The road to ART
- •6.1.1 3D conformal radiotherapy (3DCRT)
- •6.1.2 Intensity modulated radiotherapy (IMRT)
- •6.1.3 Image-guided radiotherapy (IGRT)
- •6.1.4 Adaptive radiotherapy (ART)
- •6.2 ART workflow and implementation
- •6.2.2 Current practice
- •6.2.3 Clinical impact
- •6.3 Considerations for implementing online ART
- •6.3.1 Time as a limiting factor
- •6.3.2 Implications for fast and reliable re-planning
- •6.3.4 Clinical considerations
- •6.4 Summary
- •7.1 Components of ART workflow
- •7.1.1 Simulation
- •7.1.2 Pre-planning
- •7.1.3 Online imaging and daily re-planning
- •7.1.4 Quality assurance
- •7.2 AI-driven ART
- •7.2.1 Simulation
- •7.2.2 Pre-planning
- •7.2.3 AI for delivery
- •7.3 Outlook and future directions
- •7.3.1 Real-time ART with AI
- •7.3.2 Dose escalation and functional adaption with AI
- •7.4 Summary
- •References
- •8.1 Introduction
- •8.2 Synthetic CT: deep learning methods
- •8.2.1 Conventional methods
- •8.2.2 U-Net
- •8.2.3 Generative adversarial networks
- •8.2.4 Denoising diffusion probabilistic model
- •8.3 Synthetic CT from CBCT
- •8.3.1 Noise and artifact reduction
- •8.3.2 Online dose calculation
- •8.3.3 Online image segmentation
- •8.4 Synthetic CT from MRI
- •8.4.1 Synthetic image accuracy
- •8.4.2 Dose calculation in MR-only radiation therapy
- •8.4.3 PET attenuation correction
- •8.4.4 Image registration
- •8.5 Discussion and outlook
- •8.6 Summary
- •References
- •9.1 AI-based image registration and segmentation for ART
- •9.1.1 Adaptive radiation therapy
- •9.2 Artificial intelligence
- •9.2.1 What is machine learning?
- •9.2.2 What is deep learning?
- •9.3 Deep learning: the basic components
- •9.3.1 Convolutional neural networks: looking at the picture
- •9.3.2 Pooling layers: keeping what matters most
- •9.3.3 Fully connected (dense) layers: bringing it all together
- •9.3.4 Activations
- •9.3.5 Loss: driving the model
- •9.3.6 Auto-encoders: remove the noise
- •9.3.7 Supervised versus unsupervised learning
- •9.3.8 Pre-trained convolutional neural networks
- •9.4 Image registration: bringing two images together
- •9.4.1 Registration similarity metrics
- •9.4.2 Types of registrations
- •9.5 AI-based image registration
- •9.5.1 Supervised learning
- •9.5.2 Unsupervised learning
- •9.5.3 Registration in ART
- •9.5.4 Commonalities in architectures
- •9.6 Image segmentation
- •9.6.1 Introduction: coloring by the numbers
- •9.6.2 Segmentation networks
- •9.6.3 Best practices
- •9.7 Summary
- •10.1 Introduction
- •10.1.1 Overview of chapter content
- •10.2 The landscape of AI-assisted dose prediction
- •10.2.1 Traditional machine learning for dose prediction
- •10.2.2 Deep learning-based dose prediction
- •10.2.3 Challenges in AI-assisted dose prediction
- •10.3 Re-planning workflows powered by AI
- •10.3.1 Deep learning for re-planning pipelines
- •10.4 Future directions of AI-assisted dose prediction and re-planning
- •10.5 Summary
- •11.1 Introduction
- •11.2.1 Imaging-based motion monitoring
- •11.2.2 Delivery system actions
- •11.2.3 Challenges for real-time ART implementation
- •11.3 AI in real-time ART workflows
- •11.3.1 Improving intrafraction motion monitoring through AI
- •11.3.2 Mitigating system latency through AI
- •11.4 AI for ART delivery: future directions
- •11.4.1 Management of non-respiratory motion
- •11.4.2 Training AI models with small or unpaired datasets
- •11.4.4 Biology-guided ART delivery
- •11.5 Summary
- •References
- •12.1 Introduction
- •12.2 Patient QA
- •12.2.1 Pre-planning QA
- •12.2.2 Pre-treatment plan QA
- •12.2.3 On-treatment QA
- •12.3 Treatment delivery systems and instruments
- •12.3.1 Machine commissioning
- •12.3.2 Machine QA
- •12.3.3 Dosimetry tool QA
- •12.4 Summary
- •References
- •13.1 Data resources for response modeling in radiotherapy
- •13.1.1 Clinical data
- •13.1.2 Imaging (radiomics)
- •13.1.3 Treatment planning (dosiomics)
- •13.1.4 Multiomics
- •13.2 Radiotherapy treatment outcome modeling
- •13.2.1 TCP/NTCP in radiotherapy
- •13.2.2 Clinical outcomes versus PROs
- •13.2.3 Machine learning response prediction
- •13.2.4 Explainability of ML response models
- •13.2.5 Sample use cases
- •13.3 AI response-based adaptive radiotherapy
- •13.3.1 Requirements and challenges
- •13.3.2 Prediction versus treatment optimization
- •13.3.3 Sample use cases
- •13.4 Challenges and recommendations
- •13.5 Summary
- •Acknowledgments
- •References
- •14.1 Overview of challenges in AI-driven ART
- •14.2 Data challenges
- •14.2.1 Data availability
- •14.2.2 Data quality
- •14.2.3 Data privacy
- •14.3 Technical challenges
- •14.3.2 Model robustness and generalizability
- •14.3.3 Model explainability and interpretability
- •14.4 Challenges associated with online and real-time workflows
- •14.4.1 Image quality
- •14.4.2 Dose calculation
- •14.4.3 Real-time ART
- •14.5 Operational challenges
- •14.5.1 Clinical validation
- •14.5.3 Staff training
- •14.5.4 User experiences
- •14.5.5 Quality management program
- •14.5.6 Financial challenges
- •14.6 Ethical, regulatory, and legal challenges
- •14.6.1 Ethical issues
- •14.6.2 Regulatory and legal issues
- •14.7 Summary
- •References
- •15.1 Clinical considerations for CT-based offline ART
- •15.1.1 Patient and site selection
- •15.1.2 Re-simulation
- •15.1.3 Re-planning
- •15.1.4 Plan summation and evaluation
- •15.1.6 Limitations and future directions
- •15.2 Clinical considerations for CBCT/CT-based online ART
- •15.2.2 Patient and site selection
- •15.2.3 Simulation
- •15.2.4 Pre-planning review
- •15.2.5 Reference planning
- •15.2.9 Limitations and future directions
- •15.3 Summary
- •References
- •16.1 Introduction
- •16.2 Overview of MRI-guided ART systems
- •16.3 MRI-guided ART workflow
- •16.4 AI applications for MRI-guided ART
- •16.4.1 Synthetic CT generation
- •References
- •16.4.2 Auto-segmentation
- •16.4.3 Image registration
- •16.4.4 Others
- •16.4.5 Future AI development and implementation
- •16.5 Summary
- •17.1 Functional PET-guided ART
- •17.1.1 PET-based functional imaging overview
- •17.1.2 From anatomy to function: the power of PET in radiation therapy
- •17.1.5 Conclusions and future prospects
- •17.2 Functional MRI-guided ART
- •17.2.1 From anatomy to function: the power of functional MRI in radiation therapy
- •17.2.4 Conclusion and future prospects
- •17.3 Summary
- •References
- •18.1 Proton ART
- •18.1.1 Clinical context and necessity
- •18.1.2 Patient populations
- •18.1.4 Rationale for AI in proton ART
- •18.2 AI in proton ART
- •18.2.1 Imaging
- •18.2.2 Deformable and rigid registration
- •18.2.3 Contour propagation
- •18.2.4 Dose calculations
- •18.2.5 Plan optimization
- •18.2.6 Other developments
- •18.3 Implementation of adaptive proton therapy
- •18.4 Summary
- •References
- •19.1 Designing clinical trials with AI
- •19.1.1 The essential role of clinical trials
- •19.1.2 Trial protocols and methodologies
- •19.1.3 AI-driven clinical trial design and execution
- •19.1.4 Incorporation of digital twins (DTs) in clinical trials
- •19.2 Implementation of AI in ongoing clinical trials
- •19.2.1 Integration with existing clinical trial frameworks
- •19.2.2 Quality assurance, compliance, and standardization
- •19.3 Case studies of AI in adaptive radiotherapy trials
- •19.3.1 Overview of guidance for advanced radiotherapy in clinical trials
- •19.3.2 AI in the radiotherapy clinical trial quality assurance processes
- •19.4 Ethical and regulatory considerations
- •19.4.1 Patient consent and data privacy
- •19.4.2 Bias, fairness, and transparency
- •19.4.3 Regulatory guidelines and compliance
- •19.5 Future directions and challenges
- •19.5.1 Emerging technologies and techniques
- •19.5.2 Alternative strategies
- •19.6 Conclusion
- •19.7 Summary
- •References
- •20.1 Risk management
- •20.1.1 Prospective risk assessments
- •20.1.2 Root cause analysis

Artificial Intelligence in Adaptive Radiation Therapy
[38] Murr M et al 2023 Applicability and usage of dose mapping/accumulation in radiotherapy
Radiother. Oncol.
[39] Byrne M et al 2022 Varian Ethos online adaptive radiotherapy for prostate cancer: early
results of contouring accuracy, treatment plan quality, and treatment time J. Appl. Clin.
Med. Phys.
[40] Wall P D H, Hirata E, Morin O, Valdes G and Witztum A 2022 Prospective clinical
validation of virtual patient-specific quality assurance of volumetric modulated arc therapy
radiation therapy plans Int. J. Radiat. Oncol.
[41] Zeng L et al 2023 TransQA: deep hybrid transformer network for measurement-guided
volumetric dose prediction of pre-treatment patient-specific quality assurance Phys. Med.
Biol.
68 205010
[42] Kimura Y, Kadoya N, Tomori S, Oku Y and Jingu K 2020 Error detection using a
convolutional neural network with dose difference maps in patient-speci fic quality assurance for volumetric modulated arc therapy Phys. Med.
[43] Vandewinckele L et al 2020 Overview of artificial intelligence-based applications in
radiotherapy: recommendations for implementation and quality assurance Radiother.
Oncol.
153 55–66
[44] Schreier J, Genghi A, Laaksonen H, Morgas T and Haas B 2020 Clinical evaluation of a
full-image deep segmentation algorithm for the male pelvis on cone-beam CT and CT
Radiother. Oncol.
[45] de la Zerda A, Armbruster B and Xing L 2007 Formulating adaptive radiation therapy
(ART) treatment planni ng into a c losed-lo op control framework Phys.Med.Biol.
4137
[46] Kim M M et al 2019 Dosimetric characterization of the dual layer MLC system for an
O-ring linear accelerator Technol. Cancer Res. Treat.
[47] Byrne M, Archibald-Heeren B, Hu Y, Greer P, Luo S and Aland T 2022 Assessment of
semi-automated stereotactic treatment planning for online adaptive radiotherapy in ethos
Med. Dosim.
[48] Yu L, Zhao J, Zhang Z, Wang J and Hu W 2021 Commissioning of and preliminary
experience with a new fully integrated computed tomography linac J. Appl. Clin. Med.
Phys.
22 208–23
[49] Sun W et al 2024 The performance of a new type accelerator uRT-linac 506c evaluated by a
quality assurance automation system J. Appl. Clin. Med. Phys.
[50] Kisling K, Keiper T D, Branco D, Kim G G-Y, Moore K L and Ray X 2022 Clinical
commissioning of an adaptive radiotherapy platform: results and recommendations J. Appl.
Clin. Med. Phys.
[51] Nelissen K J, Versteijne E, Senan S, Hoffmans D, Slotman B J and Verbakel W F A R 2023
Evaluation of a workflow for cone-beam CT-guided online adaptive palliative radiotherapy
planned using diagnostic CT scans J. Appl. Clin. Med. Phys.
[52] Wegener S, Schindhelm R, Tamihardja J, Sauer O A and Razinskas G 2023 Evaluation of
the Ethos synthetic computed tomography for bolus-covered surfaces Phys. Med.
102662
[53] Lemus O M D et al 2023 Influence of air mapping errors on the dosimetric accuracy of
prostate CBCT-guided online adaptive radiation therapy J. Appl. Clin. Med. Phys.
e14057
182 109527
23 e13479
113 1091–102
73 57–64
145 1–6
52
18 1533033819883641
47 342–7
25 e14226
23 e13801
24 e13841
113
24
15-22

Artificial Intelligence in Adaptive Radiation Therapy
[54] Schiff J P et al 2022 Simulated computed tomography-guided stereotactic adaptive
radiotherapy (CT-STAR) for the treatment of locally advanced pancreatic cancer
Radiother. Oncol.
[55] Shen C et al 2023 Clinical experience on patient-specific quality assurance for CBCT-based
online adaptive treatment plan J. Appl. Clin. Med. Phys.
[56] Zhao X, Stanley D N, Cardenas C E, Harms J and Popple R A 2023 Do we need patient-
specific QA for adaptively generated plans? Retrospective evaluation of delivered online
adaptive treatment plans on Varian Ethos J. Appl. Clin. Med. Phys.
[57] Bertholet J et al 2020 Patterns of practice for adaptive and real-time radiation therapy
(POP-ART RT) part II: offline and online plan adaption for interfractional changes
Radiother. Oncol.
[58] Viscariello N N et al 2024 Quantitative assessment of full-time equivalent effort for
kilovoltage-cone beam computed tomography guided online adaptive radiation therapy for
medical physicists Pract. Radiat. Oncol.
[59] Branco D, Mayadev J, Moore K and Ray X 2023 Dosimetric and feasibility evaluation of a
CBCT-based daily adaptive radiotherapy protocol for locally advanced cervical cancer
J. Appl. Clin. Med. Phys.
[60] Shepherd M et al 2021 Pathway for radiation therapists online advanced adapter training
and credentialing Tech. Innov. Patient Support Radiat. Oncol.
[61] Stanley D N et al 2023 A roadmap for implementation of kV-CBCT online adaptive
radiation therapy and initial first year experiences J. Appl. Clin. Med. Phys.
[62] Yock A D, Ahmed M, Ayala-Peacock D, Chakravarthy A B and Price M 2021 Initial
analysis of the dosimetric benefit and clinical resource cost of CBCT-based online adaptive
radiotherapy for patients with cancers of the cervix or rectum J. Appl. Clin. Med. Phys.
210–21
[63] Rahman M et al 2024 Mitigating risks in cone beam computed tomography guided online
adaptive radiation therapy: a preventative reference planning review approach Adv. Radiat.
Oncol.
9 101614
[64] Morgan H E et al 2023 Preliminary evaluation of PTV margins for online adaptive
radiation therapy of the prostatic fossa Pract. Radiat. Oncol.
[65] Zwart L G M et al 2022 Cone-beam computed tomography-guided online adaptive
radiotherapy is feasible for prostate cancer patients Phys. Imaging Radiat. Oncol.
[66] Moazzezi M, Rose B, Kisling K, Moore K L and Ray X 2021 Prospects for daily online
adaptive radiotherapy via ethos for prostate cancer patients without nodal involvement
using unedited CBCT auto-segmentation J. Appl. Clin. Med. Phys.
[67] Shelley C E et al 2023 Implementing cone-beam computed tomography-guided online
adaptive radiotherapy in cervical cancer Clin. Transl. Radiat. Oncol.
[68] Peng H, Zhang J, Xu N, Zhou Y, Tan H and Ren T 2023 Fan beam CT-guided online
adaptive external radiotherapy of uterine cervical cancer: a dosimetric evaluation BMC
Cancer
23 588
[69] Sibolt P et al 2021 Clinical implementation of artificial intelligence-driven cone-beam
computed tomography-guided online adaptive radiotherapy in the pelvic region Phys.
Imaging Radiat. Oncol.
[70] de Jong R, Visser J, van Wieringen N, Wiersma J, Geijsen D and Bel A 2021 Feasibility of
conebeam CT-based online adaptive radiotherapy for neoadjuvant treatment of rectal
cancer Radiat. Oncol.
175 144–51
24 e13918
24 e13876
153 88–96
15 e72–e81
24 e13783
20 54–60
24 e13961
22
13 e345–53
22 98–103
22 82–93
40 100596
17 1–7
16 136
15-23

Artificial Intelligence in Adaptive Radiation Therapy
[71] Åström L M, Behrens C P, Storm K S, Sibolt P and Serup-Hansen E 2022 Online adaptive
radiotherapy of anal cancer: normal tissue sparing, target propagation methods, and first
clinical experience Radiother. Oncol.
[72] Xia X et al 2021 An artificial intelligence-based full-process solution for radiotherapy: a
proof of concept study on rectal cancer Front. Oncol.
[73] Yu L et al 2023 Technical note: first implementation of a one-stop solution of
radiotherapy with full-workflow automation based on CT-linac combination Med.
Phys.
50 3117–26
[74] Åström L M et al 2022 Online adaptive radiotherapy of urinary bladder cancer with full
re-optimization to the anatomy of the day: initial experience and dosimetric benefits
Radiother. Oncol.
[75] Khouya A et al 2023 Adaptation time as a determinant of the dosimetric effectiveness of
online adaptive radiotherapy for bladder cancer Cancers
[76] Hotsinpiller W S, Stanley D N, Harms J, Pogue J A, Cardenas C and McDonald A M 2023
Early experience with CBCT-guided online adaptive radiotherapy for muscle invasive
bladder cancer Int. J. Radiat. Oncol. Biol. Phys.
[77] Azzarouali S et al 2023 Online adaptive radiotherapy for bladder cancer using a
simultaneous integrated boost and fiducial markers Radiat. Oncol.
[78] Pöttgen C et al 2023 Fractionation versus adaptation for compensation of target volume
changes during online adaptive radiotherapy for bladder cancer: answers from a prospective
registry Cancers
[79] Håkansson K, Giannoulis E, Lindegaard A, Friborg J and Vogelius I 2023 CBCT-based
online adaptive radiotherapy for head and neck cancer—dosimetric evaluation of first
clinical experience Acta. Oncol.
[80] All S et al 2023 In silico analysis of adjuvant head and neck online adaptive radiation
therapy Adv. Radiat. Oncol.
[81] Guberina M et al 2024 Prospects for online adaptive radiation therapy (ART) for head and
neck cancer Radiat. Oncol.
[82] Yoon S W et al 2020 Initial evaluation of a novel cone-beam CT-based semi-automated
online adaptive radiotherapy system for head and neck cancer treatment—a timing and
automation quality study Cureus
[83] Mao W et al 2022 Evaluation of auto-contouring and dose distributions for online adaptive
radiation therapy of patients with locally advanced lung cancers Pract. Radiat. Oncol.
e329–38
[84] Li R et al 2024 Adapt-on-demand: a novel strategy for personalized adaptive radiotherapy
for locally advance lung cancer Pract. Radiat. Oncol.
[85] Duan J et al 2024 Enhancing precision in radiation therapy for locally advanced lung
cancer: a case study of cone-beam computed tomography (CBCT)-based online adaptive
techniques and the promise of HyperSight™ iterative CBCT Cureus
[86] Duan J et al 2025 Assessing dosimetric benefits of cone beam computed tomography-guided
online adaptive radiation treatment frequencies for lung cancer Adv. Radiat. Oncol.
101740
[87] Brown M B, Yusuf M B, Harms J M, Pogue J A, Stanley D N and McDonald A 2024 The
use of adaptive radiation in a retroperitoneal seminoma patient with poor candidacy for
chemotherapy: a teaching case Appl. Radiat. Oncol.
171 37–42
15 20
9 101319
19 4
176 92–8
10
15 23
117 e393–4
18 165
62 1369–74
12 e9660
12
14 e395–e406
16 e66943
10
13 49–54
15-24

Artificial Intelligence in Adaptive Radiation Therapy
[88] Montalvo S K et al 2023 On the feasibility of improved target coverage without
compromising organs at risk using online adaptive stereotactic partial breast irradiation
(A-SPBI) J. Appl. Clin. Med. Phys.
[89] Pogue J A et al 2023 Improved dosimetry and plan quality for accelerated partial breast
irradiation using online adaptive radiotherapy: a single institutional study Adv. Radiat.
Oncol.
9 101414
[90] Schiff J P et al 2022 In silic o trial of computed tomography-guided stereotactic
adaptive radiation therapy (CT-STAR) for the treatment of abdominal oligometastases
Int. J. Radiat. Oncol.
[91] Kim M et al 2022 The first reported case of a patient with pancreatic cancer treated with
cone beam computed tomography-guided stereotactic adaptive radiotherapy (CT-STAR)
Radiat. Oncol.
[92] Yock A D et al 2023 Triggering daily online adaptive radiotherapy in the pelvis: dosimetric
effects and procedural implications of trigger parameer-value selection J. Appl. Clin. Med.
Phys.
24 e14060
[93] Ghimire R, Moore K L, Branco D, Rash D L, Mayadev J and Ray X 2023 Forecasting
patient-specific dosimetric benefit from daily online adaptive radiotherapy for cervical
cancer Biomed. Phys. Eng. Express
[94] Pogue J A et al 2024 Utilizing unsupervised machine learning to identify an optimal
planning target volume size threshold for online adaptive stereotactic partial breast
irradiation Cureus 16 a1191
[95] Pogue J A et al 2024 Unlocking the adaptive advantage: correlation and machine learning
classification to identify optimal online adaptive stereotactic partial breast candidates Phys.
Med. Biol.
[96] Oldenburger E, De Roover R, Poels K, Depuydt T, Isebaert S and Haustermans K 2023
‘Scan-(pre)plan-treat’ workflow for bone metastases using the ethos therapy system: a
single-center, in silico experience Adv. Radiat. Oncol.
[97] Price A T et al 2023 In silico trial of simulation-free hippocampal-avoidance whole brain
adaptive radiotherapy Phys. Imaging Radiat. Oncol.
[98] Nelissen K J et al 2023 Same-day adaptive palliative radiotherapy without prior CT
simulation: early outcomes in the FAST-METS study Radiother. Oncol.
[99] Wegener S, Weick S, Schindhelm R, Tamihardja J, Sauer O A and Razinskas G 2024
Feasibility of Ethos adaptive treatments of lung tumors and associated quality assurance
J. Appl. Clin. Med. Phys.
[100] Lin M, Kavanaugh J A, Kim M, Cardenas C E and Rong Y 2023 Physicists should perform
reference planning for CBCT guided online adaptive radiotherapy J. Appl. Clin. Med. Phys.
24 e14163
[101] Wegener S et al 2022 Prospective risk analysis of the online-adaptive artificial intelligence-
driven workflow using the Ethos treatment system Z. Für Med. Phys.
[102] Iqbal Z et al 2025 Establishing a safety net in x-ray-based online adaptive radiation therapy:
early detection of planning deficiencies through upstream physics plan review Int. J. Radiat.
Oncol.
122 865–72
[103] Archambault Y et al 2020 Making on-line adaptive radiotherapy possible using artificial
intelligence and machine learning for efficient daily re-planning Med. Phys. Int. J. 8 77–86
17 157
69 115050
114 1022–31
25 e14311
24 e13813
9 045030
8 101258
28 100491
182 109538
34 384–96
15-25

Artificial Intelligence in Adaptive Radiation Therapy
[104] Pokharel S, Pacheco A and Tanner S 2022 Assessment of efficacy in automated plan
generation for Varian Ethos intelligent optimization engine J. Appl. Clin. Med. Phys.
e13539
[105] Calmels L et al 2022 Evaluation of an automated template-based treatment planning
system for radiotherapy of anal, rectal and prostate cancer Tech. Innov. Patient Support
Radiat. Oncol.
[106] El-qmache A and McLellan J 2023 Investigating the feasibility of using Ethos generated
treatment plans for head and neck cancer patients Tech. Innov. Patient. Support. Radiat.
Oncol.
27 100216
[107] Pogue J A et al 2023 Benchmarking automated machine learning-enhanced planning with
Ethos against manual and knowledge-based planning for locally advanced lung cancer Adv.
Radiat. Oncol.
[108] Roberfroid B, Barragán-Montero A M, Dechambre D, Sterpin E, Lee J A and Geets X
2023 Comparison of Ethos template-based planning and AI-based dose prediction: general
performance, patient optimality, and limitations Phys. Med.
[109] Visak J et al 2023 Evaluating machine learning enhanced intelligent-optimization-engine
(IOE) performance for ethos head-and-neck (HN) plan generation J. Appl. Clin. Med. Phys.
24 e13950
[110] Pogue J A et al 2023 Leveraging intelligent optimization for automated, cardiac-sparing
accelerated partial breast treatment planning Front. Oncol.
[111] Stanley D N et al 2024 Suitability of the Ethos treatment planning system for automated
SRT planning for large body habitus patients AAPM 65th Annual Meeting and Exhibition
(Houston, TX, July 2023)
[112] Ram U et al 2025 Evaluation of high-fidelity mode for semi-automated multi-met, single-
isocenter stereotactic radiosurgery planning using the ethos 2.0 planning system Cureus 17
a1420
[113] Pogue J A et al 2025 Leveraging high-fidelity planning for improved online adaptive
stereotactic partial breast treatment efficacy Cureus 17 a1447
[114] Zhong Y et al 2021 Clinical implementation of automated treatment planning for rectum
intensity-modulated radiotherapy using voxel-based dose prediction and post-optimization
strategies Front. Oncol.
[115] Sun Z et al 2022 A hybrid optimization strategy for deliverable intensity-modulated
radiotherapy plan generation using deep learning-based dose prediction Med. Phys.
1344–56
[116] Lin J et al 2024 ART2Dose: a comprehensive dose verification platform for online adaptive
radiotherapy Med. Phys.
[117] Mori S, Endo M, Komatsu S, Kandatsu S, Yashiro T and Baba M 2006 A combination-
weighted Feldkamp-based reconstruction algorithm for cone-beam CT Phys. Med. Biol.
3953
[118] Lim R, Penoncello G P, Hobbis D, Harrington D P and Rong Y 2022 Technical note:
characterization of novel iterative reconstructed cone beam CT images for dose tracking
and adaptive radiotherapy on L-shape linacs Med. Phys.
[119] Wang Y- F et al 2023 Enhancing safety in AI-driven cone-beam CT-based online
adaptive radiotherapy: development and implementation of an interdisciplinary
workflow Adv. Radiat. Onc ol.
22 30–6
8 101292
116 103178
13 1130119
11 697995
51 18–30
49 7715–32
9 101399
23
49
51
15-26

Artificial Intelligence in Adaptive Radiation Therapy
[120] Peterlik I et al 2021 Reducing residual-motion artifacts in iterative 3D CBCT reconstruc-
tion in image-guided radiation therapy Med. Phys.
[121] Ni X et al 2023 Metal artifacts reduction in kV-CT images with polymetallic dentures and
complex metals based on MV-CBCT images in radiotherapy Sci. Rep.
[122] Rueckert D, Aljabar P, Heckemann R A, Hajnal J V and Hammers A 2006
Diffeomorphic registration using B-splines Medical Image Computing and Computer-
Assisted Intervention—MICCAI 2006
Springer) pp 702–9
[123] Stanley D N, Covington E, Harms J, Pogue J, Cardenas C E and Popple R A 2023
Evaluation and correlation of patient movement during online adaptive radiotherapy with
CBCT and a surface imaging system J. Appl. Clin. Med. Phys.
[124] Kim T et al 2024 Feasibility of surface-guidance combined with CBCT for intra-fractional
breath-hold motion management during Ethos RT J. Appl. Clin. Med. Phys.
[125] Chen L et al 2022 A clinically relevant online patient QA solution with daily CT scans and
EPID-based in vivo dosimetry: a feasibility study on rectal cancer Phys. Med. Biol.
225003
[126] Sun W et al 2024 Machine learning-based ensemble prediction model for the gamma
passing rate of VMAT-SBRT plan Phys. Med.
[127] Jiang D et al 2023 Total marrow lymphoid irradiation IMRT treatment using a novel
CT-linac Eur. J. Med. Res.
28 463
ed R Larsen, M Nielsen and J Sporring (Berlin:
48 6497–507
13 8970
24 e14133
25 e14242
67
117 103204
15-27

IOP Publishing
Artificial Intelligence in Adaptive Radiation Therapy
Yi Wang and X. Sharon Qi
Chapter 16
Artificial intelligence in MRI-guided adaptive
radiation therapy
Lauren Smith, Yao Zhao, Jinzhong Yang and X. Sharon Qi
Adaptive radiation therapy (ART) is a process where a personalized treatment plan
may be created for each fraction based on daily imaging information. ART is
growing in popularity and has been shown to improve the therapeutic ratio for
certain RT sites. In particular, the introduction of MR-linac systems in radiation
therapy has allowed for high-quality, real-time MR images to be used to facilitate
adaptive treatment. Artificial intelligence (AI) has recently been introduced as a tool
in modern radiation therapy and may provide a solution to some challenges that
currently burden the efficiency of MR-guided ART. This chapter provides an
overview of clinically available MR-guided ART systems and techniques. Further,
clinical challenges associated with MR-guided ART, such as synthetic CT generation, auto-segmentation, and image registration, will be introduced and the
integration of AI solutions into the MR-guided ART domain will be explored.
16.1 Introduction
Radiation therapy (RT) is currently one of the mainstays of cancer treatment, with
approximately 50% or higher of all cancer patients receiving RT during their
treatment [1]. Image-guided radiation therapy (IGRT) has become the standard RT
practice to enable accurate and precise delivery, leading to the widening of the
therapeutic ratio [2, 3]. Various imaging technologies, such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography
(PET), are used to guide RT to precisely deliver the dose to targets while avoiding
unnecessary dose to nearby critical structures [3]. CT-guided RT, a type of radiation
therapy using CT-based technology, is used to guide the delivery of radiation beams
to the tumor, ensuring accurate targeting [3]. The latest development of combining
PET-CT and radiotherapy delivery involves using biological markers or characteristics of tumors to guide the delivery of radiation treatment, allowing radiation
therapy to be tailored more specifically to the individual characteristics of the tumor
doi:10.1088/978-0-7503-6119-4ch16 16-1 ª IOP Publishing Ltd 2025. All rights,
including for text and data mining (TDM), artificial intelligence (AI) training, and similar technologies, are reserved.

Artificial Intelligence in Adaptive Radiation Therapy
and patient to potentially improve treatment outcomes and minimize side effects [4].
Recent development of magnetic resonance-guided radiation therapy (MRgRT)
integrates advanced MRI technology with a radiation therapy delivery system,
providing a paradigm change in aspects of treatment planning, monitoring, and
adaptation. Compared to CT-guided RT, MRgRT provides advantages such as
superior soft-tissue contrast, organ motion visualization, and the ability to monitor
tumor and tissue physiologic changes [5].
Adaptive radiation therapy (ART) is a closed-loop radiation treatment process
where the initial treatment plan may be modified, via frequent imaging acquisition
such as daily imaging, using systematic feedback of measurements [6]. ART is
expected to maximize the therapeutic ratio by further increasing tumor dose while
maintaining or reducing normal tissue complication.
16.2 Overview of MRI-guided ART systems
MRI-guided adaptive therapy is an advanced approach that utilizes real-time MRI
during treatment sessions to guide and adapt the delivery of radiation based on
changes in the tumor and surrounding anatomy. Real-time MRI provides detailed
information about the tumor and surrounding tissues, allowing for adjustments to
be made to the radiation treatment plan as needed.
The MRgRT technique allows for precise targeting of tumors while minimizing
radiation exposure to healthy tissues, leading to an improved therapeutic ratio. In
addition, MRgRT provides superior soft-tissue contrast compared to CT guidance
and is capable of providing different contrast based on the sequences used. Unlike
CBCT on the linac, MRgRT has the advantage of being able to acquire images
while the treatment beam is on, enabling real-time monitoring of organ motion
without the need for implanted fiducials or surrogate motion management systems.
16.2.1 High field MRI system
Elekta Unity (Elekta AB, Stockholm, Sweden) is the world’s first high-field MRlinac that integrates a 7 MV flattening filter-free (FFF) linear accelerator system
with a 1.5 tesla Philips (Philips Healthcare, Best, the Netherlands) MRI system [7].
The system received the CE mark in June 2018 and FDA approval in December
2018 [8]. The Unity system is designed as a bore-type machine with a linac system
that rotates around the MRI system and has an inner bore diameter of 70 cm
(figure 16.1)[9]. Due to this design, the system has a source axis distance (SAD) of
143.5 cm and a maximum field size of 57.4 cm × 22.0 cm. The radiation beam is
perpendicular to the magnetic field orientation. The diaphragms define the crossplane field size while the multi-leaf collimator (MLC) leaves move in the in-plane
direction to shape the field, parallel to the magnet bore. The MLC has 160 leaves
with a nominal leaf width of 0.7175 cm. The treatment couch moves in the
longitudinal direction only; however, during treatment the couch is not designed
to move to adjust treatment iso-center location. Instead, online adaptive planning
can be utilized to account for iso-center shifts. The system offers an integrated online
adaptive planning workflow implemented with online Moncaco, a Monte Carlo
16-2

Artificial Intelligence in Adaptive Radiation Therapy
Figure 16.1. (a) Elekta Unity components, IEC61217 coordinate system, and B-field direction. (b) Cross-
section of the beam delivery system and the magnet. The main B0 field has its vector directed out of the bore
(negative IECY axis). (Reproduced from [
9]. CC BY 3.0.)
based treatment planning system (TPS) that optimizes and calculates the dose
distribution in the presence of a magnetic field [10]. The system is also capable of
real-time tumor tracking, allowing simultaneous MR imagining and treatment
delivery. In its first version, the Unity system offered only tumor motion monitoring
[11]. In late 2023, Elekta released the comprehensive motion management (CMM)
system, allowing for different levels of motion management, including beam gating,
16-3

Artificial Intelligence in Adaptive Radiation Therapy
for better control of respiratory motion and other motion uncertainty during
treatment delivery [12]. It is also worth noting that due to the high strength of the
magnetic field, the beam profile is inherently off-central and asymmetric. In
addition, the electron return effect (ERE) resulting from the magnetic field causes
electrons to change trajectory to ‘return’ to a higher density material at the interface
of exiting a higher density material into a lower density material [13].
16.2.2 Low-field MRI system
The ViewRay MRIdian (Oakwood, Cleveland, OH), shown in figure 16.2, is one of
the two currently commercially available MRgRT platforms. In contrast to Elekta’s
Unity, the ViewRay system makes use of a 0.35 tesla low-field MRI scanner for
MRI-guided treatment. This system paved the way for clinical MRgRT, being the
first MR-linac device to gain FDA approval in 2012 [14]. The initial system was
designed with cobalt-60 sources for irradiation and was later integrated with a linear
accelerator, which was cleared by the FDA in 2017 [14]. The MRIdian design
consists of a split-bore superconducting magnet with a 70 cm bore diameter
perpendicular to a linear accelerator capable of producing 6 MV FFF photon
treatment beams [15]. The MRIdian is capable of producing coplanar static IMRT
fields and can deliver dose at 650 MU/min with a 0.5 rpm gantry rotation [5].
Currently, the MRIdian uses a balanced steady state free precession pulse sequence
for MRI that may be used for treatment planning, set-up verification, and imaging
during delivery [5]. Compared to the high-field MR-linac, the 0.35 T MRIdian has
the disadvantage of lower image signal–noise ratio (SNR), but the advantages of
diminished magnetic susceptibility artifacts, smaller geometric distortion in MR
images, and a more minimal electron return effect—resulting in less perturbations to
the dose distribution [14]. A significant benefit of the MRIdian system is its ability
for real-time imaging during treatment while the radiation beam is on, enabling
high-quality monitoring of intrafraction motion during treatment. This feature
allows for real-time tracking and automatic gating based on user defined boundaries
where the 2D motion is evaluated from a sagittal cine image [5]. Additionally, unlike
conventional linacs, the MRIdian has functionality for online adaptive therapy
Figure 16.2. (a) Schematic of the Viewray MRIdian system and (b) gantry with linac components.
(Reproduced with permission from [
16]. Copyright 2019 Elsevier.)
16-4
Соседние файлы в папке Библиотека им академика М.И. Перельмана
