文献速递泌尿生殖与妇科肿瘤放疗放疗物理与技术

基于全残差深度卷积神经网络的男性盆腔CT分割软件开发

Development of in-house fully residual deep convolutional neural network-based segmentation software for the male pelvic CT.
PubMed 文献 · Radiat Oncol · 2021-07-22

本研究开发了基于FusionNet的全残差深度卷积神经网络分割软件,用于男性盆腔CT图像分割。共纳入470例接受IMRT或VMAT的前列腺癌患者,其中450例随机分为训练、验证和测试组(270、90、90例),另20例用于最终评估。实验1显示训练集从90例增至180例时各器官中位DSC显著提高,但180例至270例无进一步改善;实验2中训练标签数量对DSC影响较小;实验3中前列腺、精囊腺、直肠和膀胱的中位DSC分别为0.82、0.71、0.89和0.95。

要点

  • 训练集从90例增至180例时各器官中位DSC显著提高,但180例至270例无进一步改善。
  • 训练标签数量变化对DSC影响较小。
  • 最终模型中位DSC:前列腺0.82、精囊腺0.71、直肠0.89、膀胱0.95。

核心结论

  • 基于CNN的分割软件对男性盆腔区域是有效的。
  • 270例训练集和4个器官构建的模型为最优模型。

研究设计与样本

  • 共纳入470例接受IMRT或VMAT的前列腺癌患者。
  • 450例随机分为训练、验证和测试组(270、90、90例),另20例用于实验3评估。
  • 模型基于FusionNet全残差深度CNN开发。

主要发现

  • 实验1中前列腺中位DSC:90例数据集为0.61,180例为0.86,270例为0.86。
  • 实验1中训练集从90例增至180例时所有器官中位DSC显著提高,180例至270例无进一步改善。
  • 实验2中训练标签数量对DSC影响较小。
  • 实验3中位DSC和95%HD:前列腺0.82和3.23 mm,精囊腺0.71和3.82 mm,直肠0.89和2.65 mm,膀胱0.95和4.18 mm。

关键数值与推荐

  • 最优模型由270例患者和4个器官构建。
  • 分割精度以容积Dice相似系数(DSC)和第95百分位Hausdorff距离(95%HD)评估。

临床怎么用

  • 该软件可用于男性盆腔CT图像分割,辅助前列腺癌放疗流程。
  • 训练集达到180例后增加病例数未进一步改善DSC,可供数据量规划参考。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: This study aimed to (1) develop a fully residual deep convolutional neural network (CNN)-based segmentation software for computed tomography image segmentation of the male pelvic region and (2) demonstrate its efficiency in the male pelvic region. METHODS: A total of 470 prostate cancer patients who had undergone intensity-modulated radiotherapy or volumetric-modulated arc therapy were enrolled. Our model was based on FusionNet, a fully residual deep CNN developed to semantically segment biological images. To develop the CNN-based segmentation software, 450 patients were randomly selected and separated into the training, validation and testing groups (270, 90, and 90 patients, respectively). In Experiment 1, to determine the optimal model, we first assessed the segmentation accuracy according to the size of the training dataset (90, 180, and 270 patients). In Experiment 2, the effect of varying the number of training labels on segmentation accuracy was evaluated. After determining the optimal model, in Experiment 3, the developed software was used on the remaining 20 datasets to assess the segmentation accuracy. The volumetric dice similarity coefficient (DSC) and the 95th-percentile Hausdorff distance (95%HD) were calculated to evaluate the segmentation accuracy for each organ in Experiment 3. RESULTS: In Experiment 1, the median DSC for the prostate were 0.61 for dataset 1 (90 patients), 0.86 for dataset 2 (180 patients), and 0.86 for dataset 3 (270 patients), respectively. The median DSCs for all the organs increased significantly when the number of training cases increased from 90 to 180 but did not improve upon further increase from 180 to 270. The number of labels applied during training had a little effect on the DSCs in Experiment 2. The optimal model was built by 270 patients and four organs. In Experiment 3, the median of the DSC and the 95%HD values were 0.82 and 3.23 mm for prostate; 0.71 and 3.82 mm for seminal vesicles; 0.89 and 2.65 mm for the rectum; 0.95 and 4.18 mm for the bladder, respectively. CONCLUSIONS: We have developed a CNN-based segmentation software for the male pelvic region and demonstrated that the CNN-based segmentation software is efficient for the male pelvic region.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Hirashima H, Nakamura M, Baillehache P, et al. Development of in-house fully residual deep convolutional neural network-based segmentation software for the male pelvic CT. Radiat Oncol. 2021. PMID: 34294090. doi:10.1186/s13014-021-01867-6

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。