Development and evaluation of deep learning models for estimating the organ at-risk dose constraint from two-dimensional cine magnetic resonance imaging scans during irradiation.

[PURPOSE] Two-dimensional (2D) cine magnetic resonance imaging (MRI), available with a MR-linear accelerator (MR-Linac), allows real-time visualization of anatomical information during irradiation. The present study aimed to develop and evaluate a deep learning model that can estimate the organ-at-risk (OAR) dose constraints (mainly bladder V37Gy) from 2D cine MRI.

[METHODS] The present study enrolled 91 prostate cancer patients treated with MR-Linac. From 381 treatment fractions, sagittal images at the start and end of the 2D cine MRI were extracted. Additionally, 3D MRI data acquired pre- and post-irradiation were collected, from which bladder V37Gy was calculated. We designed the deep learning model to predict the end-of-irradiation bladder V37Gy value based on the bladder image on the end-of-irradiation 2D cine MRI. The model inputs included the start and end 2D cine MR images, a difference image between them, and the pre-irradiation bladder V37Gy. The model output was the post-irradiation bladder V37Gy. We utilized a five-fold cross-validation for model training and evaluated the performance using a test dataset. For reference, we also evaluated the predictions made using only the pre-irradiation bladder V37Gy.

[RESULTS] In the test dataset, the model-predicted and true bladder V37Gy values showed a strong correlation (r = 0.89), with a mean absolute error (MAE) of 1.40 cm. Using only the pre-irradiation bladder V37Gy value yielded an r of 0.79 and an MAE of 2.02 cm. Our model also achieved an area under the curve, sensitivity, and specificity values of 0.98, 0.91, and 0.95, respectively, in detecting dose constraint violations (bladder V37Gy of > 10 cm).

[CONCLUSIONS] Our results demonstrated that deep learning can effectively predict the OAR dose constraints during irradiation. However, it is noteworthy that these results show only a limited improvement and are constrained by several limitations.