RADIANT: A fully configurable radiotherapy dose prediction framework.
Authors
Affiliations (4)
Affiliations (4)
- Radiation Physics, The University of Texas MD Anderson Cancer Center, 1155 Pressler Street, Houston, Texas, 77030-4000, United States.
- Department of Computational Applied Mathematics and Operations Research, Rice University, 6100 Main St, Houston, Texas, 77005-1892, United States.
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, 6767 Bertner Ave, Houston, Texas, 77030, United States.
- Imaging Physics, The University of Texas MD Anderson Cancer Center, 1155 Pressler Street, Houston, Texas, 77030-4000, United States.
Abstract
Treatment planning is a multi-disciplinary effort that requires medical decision-making, specialized training, and access to specialized software. Recently, deep learning has arisen as a powerful method for predicting patient-specific dose distributions. This work presents the Radiotherapy Dose Inference and Analysis Toolkit (RADIANT), an open-source, fully configurable framework for 3D radiotherapy dose prediction. Built upon the Medical Imaging Segmentation Toolkit, RADIANT supports diverse network architectures, loss functions, and training strategies.
Approach: We demonstrate its capabilities on cervical and prostate treatment plans generated with the Radiation Planning Assistant, and on head and neck cancer plans from the AAPM OpenKBP challenge data. For cervical cancer, we trained and compared nnU-Net, FMG-Net, W-Net, ddU-Net, and Swin UNETR using clinical metrics such as dose score, homogeneity index, and percent errors in D_95, D_98, and D_99. Benchmarking was also performed on the OpenKBP dataset using dose score and dose-volume histogram (DVH) score for comparison with top challenge submissions. 
Results: Our results indicate that RADIANT provides a scalable platform for the rapid development and benchmarking of dose prediction models for selected cancer sites (cervix, prostate, head and neck). For cervical cancer, the best configuration (nnU-Net architecture, MAE loss, cosine learning rate scheduler) achieved a dose score of 1.31 and sub-1% errors in D_95 and D_98 on the training set, and a dose score of 1.20 on the test set. The same configuration performed best on prostate data with a dose score of 1.96 on a test set. On the head and neck OpenKBP data, RADIANT achieved a dose score of 2.702 and a DVH score of 1.495, competitive with top challenge results.
Significance: This work provides an open-source, fully configurable framework for deep learning-based dose prediction. RADIANT facilitates reproducible experimentation across data preprocessing, model configuration, training, and evaluation for multiple cancer sites and anatomical structures.