天津工业大学学报2023，Vol.42Issue(6)：84-90,7.DOI:10.3969/j.issn.1671-024x.2023.06.012
基于深层多尺度聚合3D U-Net的肾脏与肾肿瘤分割方法
Segmentation method of kidney and kidney tumors based on deep multi-scale aggregation 3D U-Net
摘要
Abstract
Aiming at the problems of complex and changeable kidney tumors morphology,small tumor targets,and complex tumor edges in CT images,a DMSA 3D U-Net network segmentation model of deep multi-scale aggregation(DMSA)is proposed.Based on U-Net++,the model introduces three new down-sampling operations.Using the densely nested 3D U-Net and decoder end jump connections,as well as the jump connections between 3D U-Net sub-networks at each level,the model promotes the fusion of feature information at each level and at each scale,enhances the ability to extract detailed features.The above steps improve the segmentation accuracy of small-scale kidney tumors and tumor edges.The experimental results show that the proposed model can accu-rately segment kidney tumors with small scale and complex margins.When evaluated on the KiTS19 public dataset,the proposed model achieved an accuracy of 0.968 2 for kidney segmentation,0.790 8 for tumor seg-mentation,indicating its segmentation performance is good.关键词
肾肿瘤/自动分割/CT图像/3D U-Net/深层多尺度聚合Key words
kidney tumors/automatic segmentation/CT images/3D U-Net/deep multi-scale aggregation分类
信息技术与安全科学引用本文复制引用
张芳,郝思敏,耿磊..基于深层多尺度聚合3D U-Net的肾脏与肾肿瘤分割方法[J].天津工业大学学报,2023,42(6):84-90,7.基金项目
京津冀基础研究合作专项(H2021202008) （H2021202008）
天津市自然科学基金青年项目(18JCQNJC70600) （18JCQNJC70600）
