MEDLINE/PubMed Journal Browser Search

Pubmed for Handhelds

PUBMED FOR HANDHELDS

Search MEDLINE/PubMed

Title: [Automatic segmentation of head and neck organs at risk based on three-dimensional U-NET deep convolutional neural network].
Author: Dai X, Wang X, Du L, Ma N, Xu S, Cai B, Wang S, Wang Z, Qu B.
Journal: Sheng Wu Yi Xue Gong Cheng Xue Za Zhi; 2020 Feb 25; 37(1):136-141. PubMed ID: 32096387.
Abstract:
The segmentation of organs at risk is an important part of radiotherapy. The current method of manual segmentation depends on the knowledge and experience of physicians, which is very time-consuming and difficult to ensure the accuracy, consistency and repeatability. Therefore, a deep convolutional neural network (DCNN) is proposed for the automatic and accurate segmentation of head and neck organs at risk. The data of 496 patients with nasopharyngeal carcinoma were reviewed. Among them, 376 cases were randomly selected for training set, 60 cases for validation set and 60 cases for test set. Using the three-dimensional (3D) U-NET DCNN, combined with two loss functions of Dice Loss and Generalized Dice Loss, the automatic segmentation neural network model for the head and neck organs at risk was trained. The evaluation parameters are Dice similarity coefficient and Jaccard distance. The average Dice Similarity coefficient of the 19 organs at risk was 0.91, and the Jaccard distance was 0.15. The results demonstrate that 3D U-NET DCNN combined with Dice Loss function can be better applied to automatic segmentation of head and neck organs at risk. 勾画危及器官是放射治疗中的重要环节。目前人工勾画的方式依赖于医生的知识和经验，非常耗时且难以保证勾画准确性、一致性和重复性。为此，本研究提出一种深度卷积神经网络，用于头颈部危及器官的自动和精确勾画。研究回顾了 496 例鼻咽癌患者数据，随机选择 376 例用于训练集，60 例用于验证集，60 例作为测试集。使用三维（3D）U-NET 深度卷积神经网络结构，结合 Dice Loss 和 Generalized Dice Loss 两种损失函数训练头颈部危及器官自动勾画深度卷积神经网络模型，评估参数为 Dice 相似性系数和 Jaccard 距离。19 种危及器官 Dice 相似性指数平均达到 0.91，Jaccard 距离平均值为 0.15。研究结果显示基于 3D U-NET 深度卷积神经网络结合 Dice 损失函数可以较好地应用于头颈部危及器官的自动勾画。.

[Abstract] [Full Text] [Related] [New Search]