Deep Pneumonia: Attention-Based Contrastive Learning for Class-Imbalanced Pneumonia Lesion Recognition in Chest X-rays

TL;DR

This paper introduces Deep Pneumonia, a deep learning framework that uses attention-based contrastive learning and class-balanced loss to improve pneumonia lesion recognition in chest X-rays, especially under class imbalance and limited data.

Contribution

It proposes a novel attention-guided contrastive learning approach with class-balanced loss for improved pneumonia detection in X-rays, addressing data scarcity and class imbalance challenges.

Findings

Enhanced recognition accuracy demonstrated in experiments

Effective focus on lesion areas via attention strategies

Improved performance over traditional methods

Abstract

Computer-aided X-ray pneumonia lesion recognition is important for accurate diagnosis of pneumonia. With the emergence of deep learning, the identification accuracy of pneumonia has been greatly improved, but there are still some challenges due to the fuzzy appearance of chest X-rays. In this paper, we propose a deep learning framework named Attention-Based Contrastive Learning for Class-Imbalanced X-Ray Pneumonia Lesion Recognition (denoted as Deep Pneumonia). We adopt self-supervised contrastive learning strategy to pre-train the model without using extra pneumonia data for fully mining the limited available dataset. In order to leverage the location information of the lesion area that the doctor has painstakingly marked, we propose mask-guided hard attention strategy and feature learning with contrastive regulation strategy which are applied on the attention map and the extracted features respectively to guide the model to focus more attention on the lesion area where contains more discriminative features for improving the recognition performance. In addition, we adopt Class-Balanced Loss instead of traditional Cross-Entropy as the loss function of classification to tackle the problem of serious class imbalance between different classes of pneumonia in the dataset. The experimental results show that our proposed framework can be used as a reliable computer-aided pneumonia diagnosis system to assist doctors to better diagnose pneumonia cases accurately.