基于多尺度多实例学习的非小细胞肺癌亚型分类方法  

Non-small Cell Lung Cancer Subtype Classification Method Based on Multi-scale Multi-instance Learning

作　　者：罗超繁 刘震宇[2] Luo Chaofan;Liu Zhenyu(School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China;School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学计算机学院,广东广州510006 [2]广东工业大学信息工程学院,广东广州510006

出　　处：《广东工业大学学报》2025年第1期33-41,共9页Journal of Guangdong University of Technology

基　　金：2021年广东省企业科技特派员专项项目(GDKTP2021011000)。

摘　　要：非小细胞肺癌的准确诊断与亚型鉴别对指导患者的个体化精准治疗意义重大。但由于非小细胞肺癌固有的肿瘤异质性,导致其同一亚型的病理形态差异较大,而不同亚型之间也可能存在一定的形态学重叠,给临床诊断带来很大困难。为解决这一问题,本文设计了一种基于多实例学习的多尺度特征提取与融合的计算机辅助诊断框架。首先,该框架在细胞级、组织级等不同层次对病理图像进行多尺度采样和特征提取。然后,利用Transformer网络实现端到端的多尺度信息融合,建模不同粒度实例之间的依赖关系。最后,本文设计了一种基于注意力的实例损失,通过区分最具区分性实例的特征,提供了额外的监督信号,以进一步提高模型的分类性能。在包含1674张病理切片的公开数据集上的实验结果显示,本文方法可以更充分地利用病理图像的多粒度信息,显著提高非小细胞肺癌亚型的分类准确率。并且所提方法的注意力热图具有良好的可解释性,可以直观判断单个样本的分类质量,为后续模型优化提供了定量分析方法。Accurate diagnosis and subtyping of non-small cell lung cancer(NSCLC)are crucial for providing patient-specific precision treatment.However,the inherent tumor heterogeneity of NSCLC leads to significant morphological variations within the same subtype and similarities across different subtypes,presenting substantial challenges for pathologists.To address this issue,this study proposes a novel computer-aided diagnostic framework that integrates multi-scale feature extraction and fusion through multi-instance deep learning.The proposed method aims to effectively leverage the heterogeneous information presented in pathological whole-slide images(WSIs)to improve the accuracy of NSCLC subtype classification.Initially,the framework performs multi-scale sampling and feature extraction from WSIs at various levels,such as cellular and tissue levels,to capture both local and global contextual information.Subsequently,a vision transformer network is employed to model the complex dependencies among instances of varying granularity,facilitating end-to-end fusion of the extracted features for accurate classification.Furthermore,we introduce an attention-based instance loss function that adaptively weighs the contribution of each instance based on its discriminative power,providing additional supervision to enhance the classification performance of the model.We evaluat our method on a large public dataset containing 1674 H&Estained pathological slide images of NSCLC.The experimental results demonstrate that our multi-scale fusion method effectively leverages the rich information in multi-grained pathological data,significantly outperforming single-scale approaches in NSCLC subtype classification accuracy.Moreover,the method's attention heatmaps offer interpretability and allow for intuitive assessment of individual sample classification quality,serving as a quantitative analytical tool for further model refinement and validation.In conclusion,the proposed multi-scale multi-instance learning framework provides a powerful and int

关 键 词：非小细胞肺癌 组织病理图像 多实例学习 TRANSFORMER 多尺度特征融合 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.4[自动化与计算机技术—控制科学与工程]