PAANet: Progressive Alternating Attention for Automatic Medical Image Segmentation

TL;DR

PAANet introduces a novel progressive alternating attention mechanism with dense blocks and guiding attention maps to improve the accuracy of medical image segmentation, especially in boundary and edge detection.

Contribution

The paper proposes PAANet, a new network architecture with PAAD blocks and alternating attention maps for enhanced feature focus in medical image segmentation.

Findings

PAANet outperforms existing methods on three biomedical datasets.

The use of guiding attention maps improves boundary and edge detection.

PAANet achieves state-of-the-art segmentation accuracy.

Abstract

Medical image segmentation can provide detailed information for clinical analysis which can be useful for scenarios where the detailed location of a finding is important. Knowing the location of disease can play a vital role in treatment and decision-making. Convolutional neural network (CNN) based encoder-decoder techniques have advanced the performance of automated medical image segmentation systems. Several such CNN-based methodologies utilize techniques such as spatial- and channel-wise attention to enhance performance. Another technique that has drawn attention in recent years is residual dense blocks (RDBs). The successive convolutional layers in densely connected blocks are capable of extracting diverse features with varied receptive fields and thus, enhancing performance. However, consecutive stacked convolutional operators may not necessarily generate features that facilitate the identification of the target structures. In this paper, we propose a progressive alternating attention network (PAANet). We develop progressive alternating attention dense (PAAD) blocks, which construct a guiding attention map (GAM) after every convolutional layer in the dense blocks using features from all scales. The GAM allows the following layers in the dense blocks to focus on the spatial locations relevant to the target region. Every alternate PAAD block inverts the GAM to generate a reverse attention map which guides ensuing layers to extract boundary and edge-related information, refining the segmentation process. Our experiments on three different biomedical image segmentation datasets exhibit that our PAANet achieves favourable performance when compared to other state-of-the-art methods.