Elguindi Sharif, Zelefsky Michael J, Jiang Jue, Veeraraghavan Harini, Deasy Joseph O, Hunt Margie A, Tyagi Neelam
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United States.
Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United States.
Phys Imaging Radiat Oncol. 2019 Oct;12:80-86. doi: 10.1016/j.phro.2019.11.006. Epub 2019 Dec 12.
Magnetic resonance (MR) only radiation therapy for prostate treatment provides superior contrast for defining targets and organs-at-risk (OARs). This study aims to develop a deep learning model to leverage this advantage to automate the contouring process.
Six structures (bladder, rectum, urethra, penile bulb, rectal spacer, prostate and seminal vesicles) were contoured and reviewed by a radiation oncologist on axial T2-weighted MR image sets from 50 patients, which constituted expert delineations. The data was split into a 40/10 training and validation set to train a two-dimensional fully convolutional neural network, DeepLabV3+, using transfer learning. The T2-weighted image sets were pre-processed to 2D false color images to leverage pre-trained (from natural images) convolutional layers' weights. Independent testing was performed on an additional 50 patient's MR scans. Performance comparison was done against a U-Net deep learning method. Algorithms were evaluated using volumetric Dice similarity coefficient (VDSC) and surface Dice similarity coefficient (SDSC).
When comparing VDSC, DeepLabV3+ significantly outperformed U-Net for all structures except urethra ( < 0.001). Average VDSC was 0.93 ± 0.04 (bladder), 0.83 ± 0.06 (prostate and seminal vesicles [CTV]), 0.74 ± 0.13 (penile bulb), 0.82 ± 0.05 (rectum), 0.69 ± 0.10 (urethra), and 0.81 ± 0.1 (rectal spacer). Average SDSC was 0.92 ± 0.1 (bladder), 0.85 ± 0.11 (prostate and seminal vesicles [CTV]), 0.80 ± 0.22 (penile bulb), 0.87 ± 0.07 (rectum), 0.85 ± 0.25 (urethra), and 0.83 ± 0.26 (rectal spacer).
A deep learning-based model produced contours that show promise to streamline an MR-only planning workflow in treating prostate cancer.
仅使用磁共振（MR）进行前列腺治疗的放射治疗在定义靶区和危及器官（OARs）方面提供了更好的对比度。本研究旨在开发一种深度学习模型，以利用这一优势实现轮廓勾画过程的自动化。
由放射肿瘤学家在来自50例患者的轴向T2加权MR图像集上对六种结构（膀胱、直肠、尿道、阴茎球部、直肠间隔、前列腺和精囊）进行轮廓勾画并审核，这些构成了专家勾画结果。将数据划分为40/10的训练集和验证集，以使用迁移学习训练二维全卷积神经网络DeepLabV3+。将T2加权图像集预处理为二维伪彩色图像，以利用预训练（来自自然图像）卷积层的权重。对另外50例患者的MR扫描进行独立测试。与U-Net深度学习方法进行性能比较。使用体积骰子相似系数（VDSC）和表面骰子相似系数（SDSC）对算法进行评估。
比较VDSC时，除尿道外，DeepLabV3+在所有结构上均显著优于U-Net（<0.001）。平均VDSC分别为：膀胱0.93±0.04，前列腺和精囊（临床靶区[CTV]）0.83±0.06，阴茎球部0.74±0.13，直肠0.82±0.05，尿道0.69±0.10，直肠间隔0.81±0.1。平均SDSC分别为：膀胱0.92±0.1，前列腺和精囊（临床靶区[CTV]）0.85±0.11，阴茎球部0.80±0.22，直肠0.87±0.07，尿道0.85±0.25，直肠间隔0.83±0.26。
基于深度学习的模型生成的轮廓显示出有望简化仅使用MR的前列腺癌治疗计划工作流程。
