贺宝春,贾富仓.基于组合 U-Net 网络的 CT 图像头颈放疗危及器官 自动分割[J].集成技术,2020,(2):17-24
基于组合 U-Net 网络的 CT 图像头颈放疗危及器官 自动分割
Head and Neck CT Segmentation Based on a Combined U-Net Model
  
DOI:10.12146/j.issn.2095-3135.20191216001
中文关键词:  头颈;危及器官;图像分割;nnU-Net;组合模型
英文关键词:head and neck; organ at risk; image segmentation; nnU-Net; model combination
基金项目:国家自然科学基金项目(U1613221)
作者单位
贺宝春 中国科学院深圳先进技术研究院 深圳 518055;中国科学院大学深圳先进技术学院 深圳 518055 
贾富仓 中国科学院深圳先进技术研究院 深圳 518055;中国科学院大学深圳先进技术学院 深圳 518055 
摘要点击次数: 472
全文下载次数: 528
中文摘要:
      CT 图像头颈分割面临着以下难点:CT 图像的低对比度导致边界不清,图像扫描间距过大导 致冠状面和矢状面图像分辨率低,头颈中待分割的 22 个器官对于神经网络构建建模的需求不同,且由于存在极小器官造成了类间不平衡。为解决上述问题,该文提出一种 U-Net 组合模型——由 3 种 U-Net 模型组成,分别是 2D U-Net 模型、3D U-Net 模型及 3D-small U-Net 模型。其中,2D U-Net 模型用于厚层图像的分割,3D U-Net 模型利用三维空间信息,3D-small U-Net 模型用于分割最小的两个器官以解决类不平衡问题。该方法在 MICCAI 2019 StructSeg 头颈放疗危及器官分割任务中取得了第 2 名的成绩,平均 DSC 系数为 80.66%,95% 豪斯道夫距离为 2.96 mm。
英文摘要:
      Head and neck (HaN) segmentation in CT image is difficult due to low contrast and large slice thickness that resulted in useless information in coronal and sagittal plane for some organs. In addition, complex and small organs have different requirements on neural network modeling. To achieve an accurate segmentation of 22 HaN organs, we combined three U-Net models. The first model was a 2D model that is advantage for dealing with thick slice images. The second model was a 3D model using a cropped input to cover most organs with original resolution in the transverse plane. The third model was a 3D-small U-Net model that focuses on the segmentation of two small organs together and uses a small region of interest (ROI) computed from the bounding box of 2D model segmentation. All the three models were trained using nnUNet method. The final trained model was submitted through docker image to the StructSeg challenge. The leaderboard showed that the proposed method achieved the second place among all methods on ten unseen testing cases with an average Dice value of 80.66% and 95% Hausdorff distance of 2.96 mm.
查看全文  查看/发表评论  下载PDF阅读器
关闭
微信关注二维码 用微信扫一扫 用微信扫一扫 用微信扫一扫

美女

美女图片

美女

美女图片