English

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

Image and Video Processing 2021-11-08 v1 Computer Vision and Pattern Recognition Quantitative Methods

Abstract

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.

Keywords

Cite

@article{arxiv.2111.03063,
  title  = {PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning},
  author = {Jiatai Lin and Guoqiang Han and Xipeng Pan and Hao Chen and Danyi Li and Xiping Jia and Zhenwei Shi and Zhizhen Wang and Yanfen Cui and Haiming Li and Changhong Liang and Li Liang and Zaiyi Liu and Chu Han},
  journal= {arXiv preprint arXiv:2111.03063},
  year   = {2021}
}

Comments

10 pages, 5 figures

R2 v1 2026-06-24T07:26:40.740Z