Enhancing Prostate Cancer Segmentation for Multi-Domain Generalization using a novel Parallel-Route Coherent Mixup Regularization Training

MRI guided adaptive radiotherapy (MRgART) for prostate cancer (PCa) targets tumors while sparing organs from unnecessary radiation. Daily treatment adaptation requires accurate segmentation of tumors and organs. Manual delineation can be time and cost prohibitive. Deep learning segmentation methods have limited success applied to datasets distinct from training, hampering generalizability and adoption of MRgART. We develop a novel parallel route coherent mixup (PaRC-mix) training approach for single source to multi-domain generalization. PaRC-mix creates feature augmentations at multiple network layers through linear combination of features from different training samples in a batch. PaRC-mix training was implemented on two deep and residually connected networks, a multiple resolution residual network (MRRN) and UNet++ to segment PCa dominant intraprostatic lesions from apparent diffusion coefficient images. Models were trained on 2,029 samples from 3.0T GE MRI and tested on 1,547 PCa samples from 5 datasets acquired using 3T Siemens, 3T Philips, and 1.5T Elekta Unity MR-Linac scanners. PaRC-mix training led to significantly more accurate tumor detection and segmentation for both networks compared to training without mixup as well as input-mix training. PaRC-mix also achieved better recall to precision tradeoff than mixup applied only on the network backbone or input-mixup. Using a normalized composite DSC, HD95, and MSD score the accuracy gap between aggressive and non-aggressive lesions decreased from 21.1 and 19.5 for MRRN and UNet++ models trained without mixup to 5.2 and 7.9 with same models trained with PaRC-mix. This paper presents an easy to implement network agnostic approach to feature augmentation in multi-stream networks that enhances generalizability for the difficult problem of prostate cancer lesion segmentation.

Segmentation Regularized Training for Multi-Domain Deep Learning Registration applied to MR-Guided Prostate Cancer Radiotherapy

Background: Accurate deformable image registration (DIR) is required for contour propagation and dose accumulation in MR-guided adaptive radiotherapy (MRgART). This study trained and evaluated a deep learning DIR method for domain invariant MR-MR registration. Methods: A progressively refined registration and segmentation (ProRSeg) method was trained with 262 pairs of 3T MR simulation scans from prostate cancer patients using weighted segmentation consistency loss. ProRSeg was tested on same- (58 pairs), cross- (72 1.5T MR Linac pairs), and mixed-domain (42 MRSim-MRL pairs) datasets for contour propagation accuracy of clinical target volume (CTV), bladder, and rectum. Dose accumulation was performed for 42 patients undergoing 5-fraction MRgART. Results: ProRSeg demonstrated generalization for bladder with similar Dice Similarity Coefficients across domains (0.88, 0.87, 0.86). For rectum and CTV, performance was domain-dependent with higher accuracy on cross-domain MRL dataset (DSCs 0.89) versus same-domain data. The model's strong cross-domain performance prompted us to study the feasibility of using it for dose accumulation. Dose accumulation showed 83.3% of patients met CTV coverage (D95 >= 40.0 Gy) and bladder sparing (D50 <= 20.0 Gy) constraints. All patients achieved minimum mean target dose (>40.4 Gy), but only 9.5% remained under upper limit (<42.0 Gy). Conclusions: ProRSeg showed reasonable multi-domain MR-MR registration performance for prostate cancer patients with preliminary feasibility for evaluating treatment compliance to clinical constraints.

Deep Learning Based Dominant Index Lesion Segmentation for MR-guided Radiation Therapy of Prostate Cancer

Dose escalation radiotherapy allows increased control of prostate cancer (PCa) but requires segmentation of dominant index lesions (DIL), motivating the development of automated methods for fast, accurate, and consistent segmentation of PCa DIL. We evaluated five deep-learning networks on apparent diffusion coefficient (ADC) MRI from 500 lesions in 365 patients arising from internal training Dataset 1 (1.5Tesla GE MR with endorectal coil), external ProstateX Dataset 2 (3Tesla Siemens MR), and internal inter-rater Dataset 3 (3Tesla Philips MR). The networks include: multiple resolution residually connected network (MRRN) and MRRN regularized in training with deep supervision (MRRN-DS), Unet, Unet++, ResUnet, and fast panoptic segmentation (FPSnet) as well as fast panoptic segmentation with smoothed labels (FPSnet-SL). Models were evaluated by volumetric DIL segmentation accuracy using Dice similarity coefficient (DSC) and detection accuracy, as a function of lesion aggressiveness, size, and location (Dataset 1 and 2), and accuracy with respect to two-raters (on Dataset 3). In general MRRN-DS more accurately segmented tumors than other methods on the testing datasets. MRRN-DS significantly outperformed ResUnet in Dataset2 (DSC of 0.54 vs. 0.44, p<0.001) and the Unet++ in Dataset3 (DSC of 0.45 vs. p=0.04). FPSnet-SL was similarly accurate as MRRN-DS in Dataset2 (p = 0.30), but MRRN-DS significantly outperformed FPSnet and FPSnet-SL in both Dataset1 (0.60 vs 0.51 [p=0.01] and 0.54 [p=0.049] respectively) and Dataset3 (0.45 vs 0.06 [p=0.002] and 0.24 [p=0.004] respectively). Finally, MRRN-DS produced slightly higher agreement with experienced radiologist than two radiologists in Dataset 3 (DSC of 0.45 vs. 0.41).