边界信息保持的全染色肾脏切片多粒度分割  

Boundary-preserving multi-scale glomerulus segmentation for full-stained kidney slice

作　　者：花勇 李珍珍 潘建宏 杨烜[1] Hua Yong;Li Zhenzhen;Pan Jianhong;Yang Xuan(College of Computer Science and Software Engineering,Shenzhen University,Shenzhen 518060,China)

机构地区：[1]深圳大学计算机与软件学院,深圳518060

出　　处：《中国图象图形学报》2023年第11期3575-3589,共15页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61871269);深圳市科技计划基础研究项目(JCYJ20220531102407018)。

摘　　要：目的肾小球图像的准确分割对肾脏病理学的疾病诊断和定量分析起到关键作用,然而全染色肾脏切片图像存在由肾小球个体差异大导致的空间尺度和上下文形状变化大,以及图像分辨率过高的问题,给高精度、高性能分割任务带来挑战。为此,提出一种边界信息保持的全染色肾脏切片多粒度分割方法。方法使用一种多粒度上下文的空间注意力机制生成多粒度和多形状变化的空间注意力图,以限制上下文特征,减弱背景对目标的影响,强化网络对目标的感知能力,使网络更多地关注小目标特征;将原图像切分为若干小图来解决全染色图像分辨率高的问题,使用增广路径边界补零策略处理卷积核存在的贡献偏移效应,解决了肾小球目标处于图像边界所导致的分割困难问题,保证图像块的信息无损失地向高层传递,提高处于图像块边界的肾小球目标的分割精度;进一步地,针对图像块拼接带来的边缘肾小球容易漏检、计算开销大的问题,采用特征复用的概率累积滑窗策略,同时提高了分割精度和效率。结果在小鼠肾脏细胞切片和HuBMAP(human biomolecular atlas program)人体肾脏数据上,本文方法提高了分割精度,并使预测速度提高50%左右。结论对于全染色肾脏切片的肾小球分割问题,多粒度上下文特征和增广路径边界补零策略解决了边界区域肾小球目标分割困难、分割精度低的问题,并通过概率累积滑窗策略提高分割速度,相较传统的分割方法有更优秀的性能。Objective Medical image segmentation is a key issue in determining whether medical images can provide reli⁃able information in treatment and clinical diagnosis.The accurate segmentation of glomeruli plays a key role in diagnosing and quantitatively analyzing diseases in renal pathology.Traditional methods used in glomerular image segmentation include traditional pattern recognition and machine learning-based recognition.However,these methods required handcrafted features.Segmentation methods based on convolutional neural networks(CNNs)have shown strong generalization performance with features learned by networks.Early diagnosis is conducive to treating kidney disease.However,a fullstained kidney slice suffers from significant variations in the scale,shape,and texture of objects.Moreover,the high image resolution brings challenges to prediction efficiency.Therefore,CNN-based glomerulus segmentation plays an important role in clinical applications.Method This paper proposes a method for glomerular segmentation in full-stained kidney slices.A multi-granularity spatial attention mechanism is designed to deal with the diverse appearances of the glomerulus.This mechanism generates multiple scales and shape-changing feature maps for each pixel to focus on its context area instead of a fixed rectangular area as in traditional networks.For glomerulus with different sizes,the features of these fea⁃ture maps should be fused at different scales,and the spatial information of features should be extracted by networks.Multigranularities context feature maps are generated to pay attention to small objects using the context-based spatial attention mechanism,which can control the receptive field to obtain multi-granularities information and reduce background interfer⁃ence.The problem of high image resolution is addressed by cutting the original image into image patches.To detect the glomerulus located on the edge of two image patches,a padding strategy is formulated based on an augmented path.The disadvantages of the zero-pa

关 键 词：卷积神经网络(CNN) 医学图像分割 全染色图像 多粒度上下文特征 补零 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]