Boundary-aware Transformers for Skin Lesion Segmentation

TL;DR

This paper introduces a boundary-aware transformer model for skin lesion segmentation, combining global dependency modeling with local boundary detail extraction to improve accuracy in challenging melanoma images.

Contribution

The paper proposes a novel boundary-aware transformer with a boundary-wise attention gate that enhances local detail capture while modeling global dependencies for skin lesion segmentation.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively captures both global context and local boundary details.

Demonstrates robustness across different skin lesion datasets.

Abstract

Skin lesion segmentation from dermoscopy images is of great importance for improving the quantitative analysis of skin cancer. However, the automatic segmentation of melanoma is a very challenging task owing to the large variation of melanoma and ambiguous boundaries of lesion areas. While convolutional neutral networks (CNNs) have achieved remarkable progress in this task, most of existing solutions are still incapable of effectively capturing global dependencies to counteract the inductive bias caused by limited receptive fields. Recently, transformers have been proposed as a promising tool for global context modeling by employing a powerful global attention mechanism, but one of their main shortcomings when applied to segmentation tasks is that they cannot effectively extract sufficient local details to tackle ambiguous boundaries. We propose a novel boundary-aware transformer (BAT) to comprehensively address the challenges of automatic skin lesion segmentation. Specifically, we integrate a new boundary-wise attention gate (BAG) into transformers to enable the whole network to not only effectively model global long-range dependencies via transformers but also, simultaneously, capture more local details by making full use of boundary-wise prior knowledge. Particularly, the auxiliary supervision of BAG is capable of assisting transformers to learn position embedding as it provides much spatial information. We conducted extensive experiments to evaluate the proposed BAT and experiments corroborate its effectiveness, consistently outperforming state-of-the-art methods in two famous datasets.