Library of deep-learning image segmentation and outcomes model-implementations. (May 2020)

• Record Type: Journal Article
• Authors: Apte, Aditya P.; Iyer, Aditi; Thor, Maria; Pandya, Rutu; Haq, Rabia; Jiang, Jue; LoCastro, Eve; Shukla-Dave, Amita; Sasankan, Nishanth; Xiao, Ying; Hu, Yu-Chi; Elguindi, Sharif; Veeraraghavan, Harini; Oh, Jung Hun; Jackson, Andrew; Deasy, Joseph O.
• Is Part Of: Physica medica. Volume 73(2020)
• Page Start: 190
• Page End: 196
• Publication Date: 2020-05
• Subjects: Image segmentation -- Deep-learning -- Radiomics -- Radiotherapy outcomes -- Normal tissue complication -- Tumor control -- Model implementations -- Library; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2020.04.011
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: This work allows reproducible/consistent application of models, facilitating validation of models on external datasets. Centralizing model implementations would allow creation of ensembles for improving performance. This work would serve as a reference while translating validated models in the clinical workflow. This work enhances CERR's capabilities for deep-learning-based image segmentation and outcomes modeling. Abstract: An open-source library of implementations for deep-learning-based image segmentation and outcomes models based on radiotherapy and radiomics is presented. As oncology treatment planning becomes increasingly driven by automation, such a library of model implementations is crucial to (i) validate existing models on datasets collected at different institutions, (ii) automate segmentation, (iii) create ensembles for improving performance and (iv) incorporate validated models in the clinical workflow. Inclusion of deep-learning-based image segmentation and outcomes models in the same library provides a fully automated and reproduceable pipeline to estimate prognosis. The library was developed with the Computational Environment for Radiological Research (CERR) software platform. Centralizing model implementations in CERR builds upon its rich set of radiotherapy and radiomics tools and caters to the world-wide user base. CERR provides well-validated feature extraction pipelines for radiotherapy dosimetry and radiomics with fine control over the calculation settings, allowing users to select appropriate parameters used in model derivation. Models for automatic image segmentation are distributed via containers, allowing them to be deployed with a variety of scientific computing architectures. The library includes implementations of popular DVH-based models outlined in the Quantitative Analysis of Normal Tissue Effects in the Clinic effort and recently published literature. Radiomics models include features from the Image Biomarker Standardization Initiative and application-specific features found to be relevant across multiple sites and image modalities. The library is distributed as a module within CERR at https://www.github.com/cerr/CERR under the GNU-GPL copyleft with additional restrictions on clinical and commercial use and provision to dual license in future.