Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, USA.
Med Phys. 2021 Jun;48(6):3055-3064. doi: 10.1002/mp.14895. Epub 2021 May 14.
Current prostate brachytherapy uses transrectal ultrasound images for implant guidance, where contours of the prostate and organs-at-risk are necessary for treatment planning and dose evaluation. This work aims to develop a deep learning-based method for male pelvic multi-organ segmentation on transrectal ultrasound images.
We developed an anchor-free mask convolutional neural network (CNN) that consists of three subnetworks, that is, a backbone, a fully convolutional one-state object detector (FCOS), and a mask head. The backbone extracts multi-level and multi-scale features from an ultrasound (US) image. The FOCS utilizes these features to detect and label (classify) the volume-of-interests (VOIs) of organs. In contrast to the design of a previously investigated mask regional CNN (Mask R-CNN), the FCOS is anchor-free, which can capture the spatial correlation of multiple organs. The mask head performs segmentation on each detected VOI, where a spatial attention strategy is integrated into the mask head to focus on informative feature elements and suppress noise. For evaluation, we retrospectively investigated 83 prostate cancer patients by fivefold cross-validation and a hold-out test. The prostate, bladder, rectum, and urethra were segmented and compared with manual contours using the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD ), mean surface distance (MSD), center of mass distance (CMD), and volume difference (VD).
The proposed method visually outperforms two competing methods, showing better agreement with manual contours and fewer misidentified speckles. In the cross-validation study, the respective DSC and HD results were as follows for each organ: bladder 0.75 ± 0.12, 2.58 ± 0.7 mm; prostate 0.93 ± 0.03, 2.28 ± 0.64 mm; rectum 0.90 ± 0.07, 1.65 ± 0.52 mm; and urethra 0.86 ± 0.07, 1.85 ± 1.71 mm. For the hold-out tests, the DSC and HD results were as follows: bladder 0.76 ± 0.13, 2.93 ± 1.29 mm; prostate 0.94 ± 0.03, 2.27 ± 0.79 mm; rectum 0.92 ± 0.03, 1.90 ± 0.28 mm; and urethra 0.85 ± 0.06, 1.81 ± 0.72 mm. Segmentation was performed in under 5 seconds.
The proposed method demonstrated fast and accurate multi-organ segmentation performance. It can expedite the contouring step of prostate brachytherapy and potentially enable auto-planning and auto-evaluation.
目前的前列腺近距离放射治疗使用经直肠超声图像进行植入物引导，其中前列腺和危险器官的轮廓对于治疗计划和剂量评估是必要的。本研究旨在开发一种基于深度学习的经直肠超声图像上男性盆腔多器官分割方法。
我们开发了一种无锚点掩模卷积神经网络（CNN），它由三个子网组成，即骨干网、全卷积一状态目标检测器（FCOS）和掩模头。骨干网从超声（US）图像中提取多层次和多尺度特征。FOCS 利用这些特征来检测和标记（分类）器官的感兴趣区域（VOIs）。与之前研究的掩模区域 CNN（Mask R-CNN）的设计不同，FCOS 是无锚点的，它可以捕捉多个器官的空间相关性。掩模头对每个检测到的 VOI 进行分割，其中集成了空间注意力策略，以关注信息丰富的特征元素并抑制噪声。为了评估，我们通过五重交叉验证和保留测试对 83 名前列腺癌患者进行了回顾性研究。使用 Dice 相似系数（DSC）、95%Hausdorff 距离（HD）、平均表面距离（MSD）、质心距离（CMD）和体积差（VD）将前列腺、膀胱、直肠和尿道与手动轮廓进行了分割和比较。
所提出的方法在视觉上优于两种竞争方法，与手动轮廓的一致性更好，误识别的斑点更少。在交叉验证研究中，每个器官的相应 DSC 和 HD 结果如下：膀胱为 0.75±0.12，2.58±0.7mm；前列腺为 0.93±0.03，2.28±0.64mm；直肠为 0.90±0.07，1.65±0.52mm；尿道为 0.86±0.07，1.85±1.71mm。对于保留测试，DSC 和 HD 结果如下：膀胱为 0.76±0.13，2.93±1.29mm；前列腺为 0.94±0.03，2.27±0.79mm；直肠为 0.92±0.03，1.90±0.28mm；尿道为 0.85±0.06，1.81±0.72mm。分割在 5 秒内完成。
所提出的方法表现出快速准确的多器官分割性能。它可以加快前列腺近距离放射治疗的轮廓步骤，并有可能实现自动规划和自动评估。
