PURPOSES
Pre-implant diagnostic MRI is the gold standard for image-guided tandem-and-ovoids brachytherapy for cervical cancer. However, high dose rate (HDR) brachytherapy planning is typically done on post-implant CT-based high-risk clinical target volume (HR-CTVCT ) because the transfer of pre-implant MR-based HR-CTV (HR-CTVMR ) to the post-implant planning CT is difficult due to anatomical changes caused by applicator insertion, vaginal packing and the filling status of the bladder and rectum. This study aims to train a dual-path convolutional neural network (CNN) for automatic segmentation of HR-CTVCT on post-implant planning CT with guidance from pre-implant diagnostic MR.
METHODS
Pre-implant T2-weighted MR and post-implant CT images for 65 (48 for training, 8 for validation, and 9 for testing) patients were retrospectively solicited from our institutional database. MR was aligned to the corresponding CT using rigid registration. HR-CTVCT and HR-CTVMR were manually contoured on CT and MR by an experienced radiation oncologist. All images were then resampled to a spatial resolution of 0.5 × 0.5 × 1.25 mm. A dual-path 3D asymmetric CNN architecture with two encoding paths was built to extract CT and MR image features. The MR was masked by HR-CTVMR contour while the entire CT volume was included. The network put an asymmetric weighting of 18:6 for CT: MR. Voxel-based dice similarity coefficient (DSCV ), sensitivity, precision, and 95% Hausdorff distance (95-HD) were used to evaluate model performance. Cross-validation was performed to assess model stability. The study cohort was divided into a small tumor group (< 20 cc), medium tumor group (20-40 cc), and large tumor group (> 40 cc) based on the HR-CTVCT for model evaluation. Single-path CNN models were trained with the same parameters as those in dual-path models.
RESULTS
For this patient cohort, the dual-path CNN model improved each of our objective findings, including DSCV , sensitivity, and precision, with an average improvement of 8%, 7%, and 12%, respectively. The 95-HD was improved by an average of 1.65 mm compared to the single-path model with only CT images as input. In addition, the area under the curve (AUC) for different networks was 0.86 (dual-path with CT and MR) and 0.80 (single-path with CT), respectively. The dual-path CNN model with asymmetric weighting achieved the best performance with DSCV of 0.65 ± 0.03 (0.61-0.70), 0.79 ± 0.02 (0.74-0.85) and 0.75 ± 0.04 (0.68-0.79) for small, medium, and large group. 95-HD were 7.34 (5.35-10.45) mm, 5.48 (3.21-8.43) mm, and 6.21 (5.34-9.32) mm for the three size groups, respectively.
CONCLUSIONS
An asymmetric CNN model with two encoding paths from pre-implant MR (masked by HR-CTVMR ) and post-implant CT images was successfully developed for automatic segmentation of HR-CTVCT for tandem-and-ovoids brachytherapy patients. This article is protected by copyright. All rights reserved.