arXiv 2111.030632021-11-04eess.IVcs.CVq-bio.QM

PDBL：通过即插即用金字塔式深度-广度学习改进组织学组织分类

PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning

South China University of Technology（华南理工大学）；Guangdong Provincial People’s Hospital（广东省人民医院）；Guangdong Academy of Medical Sciences（广东省医学科学院）；The Hong Kong University of Science and Technology（香港科技大学）；Guangdong Polytechnic Normal University（广东技术师范大学）

Jiatai Lin, Guoqiang Han, Xipeng Pan, Hao Chen, Danyi Li, Xiping Jia, Zhenwei Shi, Zhizhen Wang, Yanfen Cui, Haiming Li, Changhong Liang, Li Liang, Zaiyi Liu, Chu Han

备注：: 10 pages, 5 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

组织病理学分类是肿瘤病理组学研究的基础。精确区分不同的组织类型有利于下游研究，如癌症诊断，预后等。现有的工作大多利用计算机视觉中流行的分类骨干来实现组织病理学组织分类。在本文中，我们提出了一个超级轻量级的即插即用模块，名为Pyramidal Deep-Broad Learning（PDBL），用于任何训练有素的分类骨干，以进一步提高分类性能，而无需重新训练负担。我们模仿病理学家如何观察病理切片在不同的放大倍率，并构建一个图像金字塔的输入图像，以获得金字塔的上下文信息。对于金字塔中的每一层，我们通过我们提出的深宽块（DB块）提取多尺度深宽特征。我们在三个流行的分类主干ShuffLeNetV 2，EfficientNetb 0和ResNet 50中配备了PDBL，以评估我们在两个数据集（Kather Multiclass Dataset和LC 25000 Dataset）上提出的模块的有效性和效率。实验结果表明，PDBL算法可以稳定地提高任何CNN骨干的组织级分类性能，特别是在训练样本较少（小于10%）的轻量级模型中，大大节省了计算时间和标注工作量.

英文摘要：

Histopathological tissue classification is a fundamental task in pathomics cancer research. Precisely differentiating different tissue types is a benefit for the downstream researches, like cancer diagnosis, prognosis and etc. Existing works mostly leverage the popular classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we proposed a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to further improve the classification performance without a re-training burden. We mimic how pathologists observe pathology slides in different magnifications and construct an image pyramid for the input image in order to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equipped PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%), which greatly saves the computational time and annotation efforts.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。