低倍率病理全切片图像伪影检测  

Artifact detection of low-magnification pathology whole-slide images

作　　者：丁维龙[1] 廖婉茵 朱伟[1] 汪春年 祝行琴 朱红波 Ding Weilong;Liao Wanyin;Zhu Wei;Wang Chunnian;Zhu Xingqin;Zhu Hongbo(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China;Ningbo Diagnostic Pathology Center,Ningbo 315021,China;Department of Pathology,Shanghai Pudong Hospital,Fudan University Affiliated Pudong Medical Center,Shanghai 201399,China)

机构地区：[1]浙江工业大学计算机科学技术学院,杭州310023 [2]宁波市临床病理诊断中心,宁波315021 [3]上海市浦东医院暨复旦大学附属浦东医院病理科,上海201399

出　　处：《中国图象图形学报》2024年第10期3157-3170,共14页Journal of Image and Graphics

基　　金：国家自然科学基金项目(32271983);浙江省基础公益研究计划项目(TGY24F020014,LTGY23F020005)。

摘　　要：目的高质量的病理切片对人工诊断和计算机辅助诊断至关重要。当前基于图像块的伪影检测方法存在着计算资源消耗巨大以及伪影检测过程的完整性缺失问题。为此,本文提出了一种适用于低倍率病理全切片图像的伪影检测算法WRC_Net(window-row-col_net)。方法首先,将低倍率的全切片图像输入到ResNet50(residual neural network)网络中,以提取图像的低级特征。随后,这些低级特征被传入特征融合模块,用于聚合来自不同深度和方向的特征。此外,在特征提取模块中,引入了WRC模块,包括WRC注意力和多尺度扩张模块,其能够同时捕捉全局和局部信息,提取多尺度特征,从而增强了特征的表达能力。最后,将融合后的特征传入单一检测头,以获取最终的检测结果。结果在SPDPSD(Shanghai Pudong department of pathology slide dataset)和NCPDCSD(Ningbo clinical pathology diagnosis center slide dataset)两个数据集上,所提方法的平均精度(mean average precision,mAP)分别达到了63.1%和55.0%,与目前主流的目标检测算法相比具有一定竞争力。结论本文提出的病理切片伪影检测算法能够准确识别数字病理切片中的不同种类伪影,为病理图像质量评估提供了一种有效的技术解决方案。Objective High-quality pathological slides are crucial for manual diagnosis and computer-aided diagnosis.However,pathology slides may contain artifacts that can affect their quality and consequently influence expert diagnostic judgment.Currently,the assessment of pathology slide quality often depends on manual sampling,which is time consuming and cannot encompass all slides.Additionally,despite relatively standardized detection criteria across different institutions,different quality control personnel may have varying interpretations,leading to subjective differences.These limitations restrict the traditional quality control process.Current methods typically involve analyzing image patches cropped at high magnifications,resulting in considerable consumption of computational resources.Moreover,certain artifacts,such as hole and tremor,often have larger dimensions and are better suited for learning on low-resolution images.However,cropping image blocks at high magnifications may exclude artifacts that coexist in tissue and background regions,such as ink and bubble,which compromise the integrity of artifact detection and analysis.To tackle these challenges,the process of assessing the quality of pathology slides must be digitized to enhance efficiency and accuracy.Therefore,this study introduces a novel algorithm,Window-Row-Col_Net(WRC_Net),designed for the detection of artifacts in digital pathology slides,specifically tailored for low-magnification pathological whole slide images.Method This study primarily consists of four components:pathological slide preprocessing,feature extraction module,feature fusion module,and single detection head.First,we tackle the problem of artifacts in pathological slides by performing preprocessing,which involves transforming the tissue pathological slides into lower-pixel-resolution versions of whole-slide images(thumbnails).This step helps reduce computational resource consumption and is well-suited for addressing larger-sized artifacts,such as holes and wrinkles.Afterward,these t

关 键 词：数字病理学 数字病理切片 伪影检测 多尺度 特征融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]