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

TL;DR

This paper introduces PDBL, a lightweight plug-and-play module that enhances histopathological tissue classification by mimicking multi-magnification analysis, improving accuracy especially for lightweight models with limited training data.

Contribution

The paper presents PDBL, a novel pyramidal deep-broad learning module that boosts classification performance of existing CNN backbones without retraining, inspired by pathologists' multi-magnification observation.

Findings

PDBL improves tissue classification accuracy across multiple CNN backbones.

The module is especially effective for lightweight models with small training datasets.

PDBL reduces computational time and annotation efforts.

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.