Artificial Intelligence for Image Registration in Radiation Oncology

Teuwen, Jonas; Gouw, Zeno A.R.; Sonke, J.J.

doi:10.1016/j.semradonc.2022.06.003

Cited by 14 publications

(5 citation statements)

References 128 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classical algorithms, such as intensity-based matching or biomechanical models remain popular, but recently research in deep-learning (DL) methods is increasing. For a comprehensive overview of DIR algorithms, we refer the reader to review articles (Maintz and Viergever 1998 , Holden 2008 , Haskins et al 2020 , Chen et al 2021 , Teuwen et al 2022 , Zou et al 2022 ).…”

Section: Dir Algorithmsmentioning

confidence: 99%

“…In the past decade, machine learning algorithms in radiotherapy have increased dramatically, and DL has likewise made advances in the field of medical DIR (Teuwen et al 2022 , Zou et al 2022 ). Topical reviews of the literature present extensive summaries of the current state of DL algorithms within DIR (Boveiri et al 2020 , Xiao et al 2021 , Zou et al 2022 ).…”

Section: Dir Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Review and recommendations on deformable image registration uncertainties for radiotherapy applications

Nenoff,

Amstutz,

Murr

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Deformable image registration (DIR) is a versatile tool used in many applications in radiotherapy (RT). DIR algorithms have been implemented in many commercial treatment planning systems providing accessible and easy-to-use solutions. However, the geometric uncertainty of DIR can be large and difficult to quantify, resulting in barriers to clinical practice. Currently, there is no agreement in the RT community on how to quantify these uncertainties and determine thresholds that distinguish a good DIR result from a poor one. This review summarises the current literature on sources of DIR uncertainties and their impact on RT applications. Recommendations are provided on how to handle these uncertainties for patient-specific use, commissioning, and research. Recommendations are also provided for developers and vendors to help users to understand DIR uncertainties and make the application of DIR in RT safer and more reliable.

show abstract

Section: Dir Algorithmsmentioning

confidence: 99%

Section: Dir Algorithmsmentioning

confidence: 99%

Review and recommendations on deformable image registration uncertainties for radiotherapy applications

Nenoff,

Amstutz,

Murr

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…This is a crucial advantage to traditional registration algorithms since (near) real-time registration is often required in clinical practice, e.g., in radiotherapy and image-guided surgery. 5,6 For successful registration, regularization is essential as it can drive the registration process towards anatomically feasible solutions. The majority of the popular learning-based registration methods employ a regularizer to control the global smoothness of the deformation.…”

Section: Introductionmentioning

confidence: 99%

Learning physics-inspired regularization for medical image registration with hypernetworks

Reithmeir,

Schnabel,

Zimmer

2024

Medical Imaging 2024: Image Processing

View full text Add to dashboard Cite

Medical image registration aims to identify the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy. To date, the majority of the deep learning-based registration methods employ regularizers that enforce global spatial smoothness, e.g., the diffusion regularizer. However, such regularizers are not tailored to the data and might not be capable of reflecting the complex underlying deformation. In contrast, physics-inspired regularizers promote physically plausible deformations. One such regularizer is the linear elastic regularizer, which models the deformation of elastic material. These regularizers are driven by parameters that define the material's physical properties. For biological tissue, a wide range of estimations of such parameters can be found in the literature, and it remains an open challenge to identify suitable parameter values for successful registration.To overcome this problem and to incorporate physical properties into learning-based registration, we propose to use a hypernetwork that learns the effect of the physical parameters of a physics-inspired regularizer on the resulting spatial deformation field. In particular, we adapt the HyperMorph framework to learn the effect of the two elasticity parameters of the linear elastic regularizer. Our approach enables the efficient discovery of suitable, data-specific physical parameters at test time. To the best of our knowledge, we are the first to use a hypernetwork to learn physics-inspired regularization for medical image registration. We evaluate our approach on 3D intrapatient lung CT images. The results show that the linear elastic regularizer can yield comparable results to the diffusion regularizer in unsupervised learning-based registration while predicting deformations with fewer foldings. With our method, the adaptation of the physical parameters to the data can successfully be performed at test time. Our code is available at https://github.com/annareithmeir/elastic-regularization-hypermorph.

show abstract

“…Due to the highly quantitative and structured nature of the RT clinical workflow, AI-based methodologies -namely, machine learning (ML) and deep learning (DL)have been increasingly investigated to automate and improve a variety of tasks [8]. Advances in DL algorithms trained on increasingly larger, diverse datasets have allowed for impressive performance in a variety of RT-related applications such as image synthesis [9], registration [10], contouring [11], dose prediction [12], and outcome prediction [13][14][15]. However, despite the impressive performance of these models in research studies, to date there are relatively few standard AI-based tools that are routinely used in RT workflows.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review

Wahid,

Kaffey,

Farris

et al. 2024

Preprint

View full text Add to dashboard Cite

Background/purpose: The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. Methods: We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. Results: We identified 56 articles published from 2015-2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50%), followed by image-synthesis (13%), and multiple applications simultaneously (11%). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32%). Imaging data was used in 91% of studies, while only 13% incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60%), with Monte Carlo dropout being the most commonly implemented UQ method (32%) followed by ensembling (16%). 55% of studies did not share code or datasets. Conclusion: Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, there was a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

show abstract

Artificial Intelligence for Image Registration in Radiation Oncology

Cited by 14 publications

References 128 publications

Review and recommendations on deformable image registration uncertainties for radiotherapy applications

Review and recommendations on deformable image registration uncertainties for radiotherapy applications

Learning physics-inspired regularization for medical image registration with hypernetworks

Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review

Contact Info

Product

Resources

About