Managing Tumor changes during Radiotherapy using a Deep Learning Model.

Purpose We propose a treatment planning framework that accounts for weekly lung tumor shrinkage using cone beam computed tomography (CBCT) images with a deep learning-based model. Methods Sixteen patients with non-small cell lung cancer (NSCLC) were selected with one planning CT and six weekly CBCTs each. A deep learning-based model was applied to predict the weekly deformation of the primary tumor based on the spatial and temporal features extracted from previous weekly CBCTs. Starting from Week 3, the tumor contour at Week N was predicted by the model based on the input from all the previous weeks (1,2…N-1), and was evaluated against the manually contoured tumor using Dice coefficient, precision, average surface distance and Hausdorff distance. Information about the predicted tumor was then entered into the treatment planning system and the plan was re-optimized every week. The objectives were to maximize the dose coverage in the target region while minimizing the toxicity to the surrounding healthy tissue. Dosimetric evaluation of the target and organs at risk (heart, lung, esophagus, spinal cord) was performed on four cases, comparing between a conventional plan (ignoring tumor shrinkage) and the shrinkage-based plan. Results The primary tumor volumes decreased on average by 38% ± 26% during six weeks of treatment. Dice coefficients (DSC) and average surface distance (ASD) between the predicted tumor and the actual tumor for Week 3, 4, 5, 6 were (0.81, 0.82, 0.79, 0.78) and (1.49, 1.59, 1.92, 2.12) mm, respectively, which were significantly superior to the score of (0.70, 0.68, 0.66, and 0.63) and (2.81, 3.22, 3.69, and 3.63) mm between the rigidly transferred tumors ignoring shrinkage and the actual tumor. While target coverage metrics were maintained for the re-optimized plans, lung mean dose dropped by 2.85, 0.46, 2.39, and 1.48 Gy for four sample cases when compared to the original plan. Doses in other organs such as esophagus were also reduced for some cases. Conclusion We developed a deep learning-based model for tumor shrinkage prediction. This model used CBCTs and contours from previous weeks as input and produced reasonable tumor contours with a high prediction accuracy (DSC, precision, HD, ASD). The proposed framework maintained target coverage while reducing dose in the lungs and esophagus.