基于深度学习的结直肠腺体自动分割算法研究  

AUTOMATIC COLORECTAL GLAND SEGMENTATION ALGORITHM BASED ON DEEP LEARNING

作　　者：杨佐鹏 丁秋阳 丁偕[1] 王瑜 Yang Zuopeng;Ding Qiuyang;Ding Xie;Wang Yu(Wonders Information Co.,Ltd.,Shanghai 200000,China;School of Software Engineering,University of Science and Technology of China,Hefei 230000,Anhui,China)

机构地区：[1]万达信息股份有限公司,上海200000 [2]中国科学技术大学软件学院,安徽合肥230000

出　　处：《计算机应用与软件》2024年第9期201-206,264,共7页Computer Applications and Software

基　　金：长三角全数字智能病理远程诊断平台项目(沪经信智[2019]1014号)。

摘　　要：为实现腺体自动化分割,减轻病理学医生的工作量,帮助医生做出更加准确的临床决策,提出一种基于注意力机制和可变形卷积的适合腺体分割的深度神经网络模型(Adaptive-Gland-Segmentation-Net,AGS-Net)。该模型使用分组卷积和注意力机制使模型具有更强的表征能力,增加可变形卷积层以适应不同分化程度的腺体形状。在GlaS数据集上,加入染色标准化预处理的AGS-Net在检测结果、分割性能和形状相似性等三方面与竞争方法相比,具有很大的优势。In order to realize automatic gland segmentation,reduce the workload of pathologists and help doctors make more accurate clinical decisions,an adaptive-gland-segmentation-net(AGS-net)based on attention mechanism and deformable convolution is proposed.In this model,grouping convolution and attention mechanism were used to make the model more representative.A deformable convolution layer was added to adapt to the glands with different levels of differentiation.In GlaS dataset,the performance of AGS-Net with stain normalization ranked in the top three of the existing algorithms in terms of detection results,segmentation performance and shape similarity,and it had great advantages.

关 键 词：结直肠癌腺体 语义分割 染色标准化 注意力机制 可变形卷积 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]