Automatic segmentation of high-risk clinical target volume for tandem-and-ovoids brachytherapy patients using an asymmetric dual-path convolutional neural network.
Automatic segmentation of high-risk clinical target volume for tandem-and-ovoids brachytherapy patients using an asymmetric dual-path convolutional neural network.
复制标题
作者：
植入前诊断磁共振成像是图像引导串联卵圆（T&O）近距离宫颈癌治疗的金标准。然而，高剂量率近距离治疗计划通常是在植入后基于CT的高风险临床靶体积（HR-CTVCT）上进行的，因为植入前磁共振（MR）基于HR-CTV （HR-CTVMR）转移到植入后计划CT上是困难的，这是由于应用器插入、阴道填塞以及膀胱和直肠填充状态引起的解剖变化。本研究旨在训练一个双路径卷积神经网络（CNN），在植入前诊断MR的指导下，对植入后计划CT上的HR-CTVCT进行自动分割。该研究回顾性地从我们的机构数据库中检索了65例患者（48例用于训练，8例用于验证，9例用于测试）植入前t2加权MR和植入后CT图像。使用刚性配准将MR对准相应的CT。HR-CTVCT和HR-CTVMR是由经验丰富的放射肿瘤学家在CT和MR上手工绘制的。然后将所有图像重新采样到0.5 × 0.5 × 1.25 mm的空间分辨率。构建了具有两条编码路径的双路径三维非对称CNN结构，用于提取CT和MR图像特征。MR被HR-CTVMR轮廓线掩盖，而整个CT体积被包括在内。基于体素的骰子相似系数（DSCV）、灵敏度、精度和95% Hausdorff距离（95-HD）用于评估模型的性能。进行交叉验证以评估模型的稳定性。根据HR-CTVCT将研究队列分为小肿瘤组（< 20cc）、中等肿瘤组（20 - 40cc）和大肿瘤组（> 40cc）进行模型评价。单路径CNN模型使用与双路径模型相同的参数进行训练。对于该患者队列，双路径CNN模型改善了我们的每个客观结果，包括DSCV、灵敏度和精度，平均分别提高了8%、7%和12%。与仅输入CT图像的单路径模型相比，95-HD模型平均提高了1.65 mm。此外，不同网络的曲线下面积分别为0.86 （CT和MR双路径）和0.80 （CT单路径）。采用非对称加权的双路径CNN模型在小、中、大分组的DSCV分别为0.65±0.03（0.61-0.70）、0.79±0.02（0.74-0.85）和0.75±0.04(0.68-0.79)，取得了较好的效果。95-HD分别为7.34 (5.35 ~ 10.45)mm、5.48 (3.21 ~ 8.43)mm和6.21 (5.34 ~ 9.32)mm。针对T&O近距离放疗患者的HR-CTVCT自动分割，成功建立了一种具有植入前MR（被HR-CTVMR掩盖）和植入后CT图像两条编码路径的非对称CNN模型。
Preimplant diagnostic magnetic resonance imaging is the gold standard for image-guided tandem-and-ovoids (T&O) brachytherapy for cervical cancer. However, high dose rate brachytherapy planning is typically done on postimplant CT-based high-risk clinical target volume (HR-CTVCT) because the transfer of preimplant Magnetic resonance (MR)-based HR-CTV (HR-CTVMR) to the postimplant 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 postimplant planning CT with guidance from preimplant diagnostic MR. Preimplant T2-weighted MR and postimplant CT images for 65 (48 for training, eight for validation, and nine 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. 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 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. An asymmetric CNN model with two encoding paths from preimplant MR (masked by HR-CTVMR) and postimplant CT images was successfully developed for automatic segmentation of HR-CTVCT for T&O brachytherapy patients.