一种融合个性化细胞关系和背景信息的宫颈细胞分类方法  

A Fusion-based Approach for Cervical Cell Classification Incorporating Personalized Relationships and Background Information

作　　者：丁博[1] 李超炜 秦健 何勇军[2] 洪振龙 DING Bo;LI Chaowei;QIN Jian;HE Yongjun;HONG Zhenlong(School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080,China;School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150006,China)

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080 [2]哈尔滨工业大学计算学部,哈尔滨150006

出　　处：《电子与信息学报》2024年第8期3390-3399,共10页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61673142);黑龙江省自然科学基金(LH2022F029,JQ2019F002)。

摘　　要：宫颈细胞分类在宫颈癌辅助诊断中发挥着重要的作用。然而,现有的宫颈细胞分类方法未充分考虑细胞关系和背景信息,也没有模拟病理医生的诊断方式,导致分类性能较低。因此,该文提出了一种融合细胞关系和背景信息的宫颈细胞分类方法,由基于细胞关系的图注意力分支(GAB-CCR)和背景信息注意力分支(BAB-WSI)组成。GAB-CCR采用细胞特征间的余弦相似度,首先构建相似和差异细胞关系图,并利用GATv2增强模型对细胞关系建模。BAB-WSI使用多头注意力模块捕捉涂片背景上的关键信息并反映不同区域的重要性。最后,将增强后的细胞特征和背景特征融合,提升了网络的分类性能。实验表明,相比于基线模型Swin Transformer-L,所提方法在准确率、敏感度、特异性和F1-Score分别提高了15.9%,30.32%,8.11%和31.62%。Cervical cell classification plays a crucial role in assisting the diagnosis of cervical cancer.However,existing methods for cervical cell classification do not enough consider relationships among cells and background information,and fail to effectively simulate the diagnostic approach of pathology doctors.As a result,their classification performance is limited.In this study,a novel approach that integrates cell relationships and background information for cervical cell classification is proposed.The proposed method consists of a Graph Attention Branching for Cell-Cell Relationships(GAB-CCR)and a Background Attention Branching for Whole Slide Images(BAB-WSI).GAB-CCR utilizes cosine similarity of cell features to construct preliminary graphs representing similar and distinct cell relationships.Additionally,GAB-CCR enhances the ability of models in modeling cell relationships through GATv2.BAB-WSI employs multi-head attention to effectively capture crucial information on the slide background and reflect the importance of different regions.Finally,the enhanced cell and background features are fused to improve the classification performance of the network.Experimental results demonstrate that the proposed method achieves significant improvements over the baseline model,Swin Transformer-L,with improvement in accuracy,sensitivity,specificity,and F1-Score by 15.9%,30.32%,8.11%,and 31.62%respectively.

关 键 词：图像处理 宫颈细胞分类 细胞关系 背景信息 注意力机制 

分 类 号：TN911.73[电子电信—通信与信息系统]