CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysis

TL;DR

This paper introduces CUAB, a novel convolutional uncertainty attention block that leverages uncertainty information to enhance CNN performance in medical image segmentation, outperforming existing attention methods.

Contribution

The paper proposes CUAB, a flexible attention module that utilizes uncertainty information to improve CNNs, demonstrated on ResNet and ResNeXt for medical image segmentation.

Findings

CUAB outperforms baseline models in pneumonia and pneumothorax segmentation.

CUAB effectively utilizes uncertainty to improve feature extraction.

The approach is adaptable to various CNN architectures.

Abstract

In recent years, convolutional neural networks (CNNs) have been successfully implemented to various image recognition applications, such as medical image analysis, object detection, and image segmentation. Many studies and applications have been working on improving the performance of CNN algorithms and models. The strategies that aim to improve the performance of CNNs can be grouped into three major approaches: (1) deeper and wider network architecture, (2) automatic architecture search, and (3) convolutional attention block. Unlike approaches (1) and (2), the convolutional attention block approach is more flexible with lower cost. It enhances the CNN performance by extracting more efficient features. However, the existing attention blocks focus on enhancing the significant features, which lose some potential features in the uncertainty information. Inspired by the test time augmentation and test-time dropout approaches, we developed a novel convolutional uncertainty attention block (CUAB) that can leverage the uncertainty information to improve CNN-based models. The proposed module discovers potential information from the uncertain regions on feature maps in computer vision tasks. It is a flexible functional attention block that can be applied to any position in the convolutional block in CNN models. We evaluated the CUAB with notable backbone models, ResNet and ResNeXt, on a medical image segmentation task. The CUAB achieved a dice score of 73% and 84% in pneumonia and pneumothorax segmentation, respectively, thereby outperforming the original model and other notable attention approaches. The results demonstrated that the CUAB can efficiently utilize the uncertainty information to improve the model performance.