RTA-Former: Reverse Transformer Attention for Polyp Segmentation
This work addresses polyp segmentation for clinical diagnostics, offering an incremental improvement in edge accuracy for transformer-based methods.
The paper tackles the problem of accurate edge segmentation in polyp segmentation for colorectal cancer prevention by introducing RTA-Former, a novel network that uses a transformer encoder and adapts reverse attention with a transformer decoder, achieving state-of-the-art performance on five datasets.
Polyp segmentation is a key aspect of colorectal cancer prevention, enabling early detection and guiding subsequent treatments. Intelligent diagnostic tools, including deep learning solutions, are widely explored to streamline and potentially automate this process. However, even with many powerful network architectures, there still comes the problem of producing accurate edge segmentation. In this paper, we introduce a novel network, namely RTA-Former, that employs a transformer model as the encoder backbone and innovatively adapts Reverse Attention (RA) with a transformer stage in the decoder for enhanced edge segmentation. The results of the experiments illustrate that RTA-Former achieves state-of-the-art (SOTA) performance in five polyp segmentation datasets. The strong capability of RTA-Former holds promise in improving the accuracy of Transformer-based polyp segmentation, potentially leading to better clinical decisions and patient outcomes. Our code is publicly available on GitHub.