Reversed Active Learning based Atrous DenseNet for Pathological Image Classification

TL;DR

This paper introduces a novel framework combining reversed active learning and an atrous DenseNet for improved pathological image classification, effectively handling high-resolution images and limited annotations.

Contribution

It proposes a new training strategy (RAL) to remove mislabels and a novel network (ADN) for multi-scale feature extraction in pathology images.

Findings

Achieved over 94% patch-level accuracy on BACH dataset.

Demonstrated effectiveness of RAL in refining training data.

Validated framework on two pathological datasets.

Abstract

Witnessed the development of deep learning in recent years, increasing number of researches try to adopt deep learning model for medical image analysis. However, the usage of deep learning networks for the pathological image analysis encounters several challenges, e.g. high resolution (gigapixel) of pathological images and lack of annotations of cancer areas. To address the challenges, we proposed a complete framework for the pathological image classification, which consists of a novel training strategy, namely reversed active learning (RAL), and an advanced network, namely atrous DenseNet (ADN). The proposed RAL can remove the mislabel patches in the training set. The refined training set can then be used to train widely used deep learning networks, e.g. VGG-16, ResNets, etc. A novel deep learning network, i.e. atrous DenseNet (ADN), is also proposed for the classification of pathological images. The proposed ADN achieves multi-scale feature extraction by integrating the atrous convolutions to the Dense Block. The proposed RAL and ADN have been evaluated on two pathological datasets, i.e. BACH and CCG. The experimental results demonstrate the excellent performance of the proposed ADN + RAL framework, i.e. the average patch-level ACAs of 94.10% and 92.05% on BACH and CCG validation sets were achieved.