GatedSegDiff: a gated fusion diffusion model for skin lesion segmentation.

Abstract

Skin lesion segmentation is a vital process in skin disease diagnosis, crucial for maintaining diagnostic precision. Despite progress in existing image segmentation methods, challenges remain in handling the fuzzy boundaries of skin lesion areas. To address this, we developed GatedSegDiff-a dedicated end-to-end framework for melanoma skin lesion image segmentation. Innovatively integrating the semantic representation capabilities of denoising networks with a novel gated attention fusion module, this model effectively merges feature maps across various scales, enhancing segmentation precision. We evaluate our model on the ISIC 2017, ISIC 2018, and PH2 image datasets. For the IoU score, our model achieved an average increase of 4.3% across three datasets, while the HD95 score decreased by 1.5%. GatedSegDiff outperforms existing advanced methods across multiple performance metrics, showing significant progress in skin lesion segmentation tasks and validating its effectiveness within this specific domain. Impact statement-The GatedSegDiff model's innovative application in medical image segmentation, particularly in skin lesion segmentation, significantly enhances diagnostic precision and efficiency. By concentrating on information in lesion boundary areas, it substantially improves segmentation accuracy for lesions with fuzzy boundaries, which is crucial for the early diagnosis of serious skin diseases like melanoma. Additionally, it provides a solution to the shortcomings of general medical image segmentation methods in handling specific skin lesions, its applicability to other types of medical images requires further investigation. The model's outstanding performance on multiple skin lesion datasets highlights its potential for application in digital dermatological diagnosis, offering faster and more reliable services to patients, with significant implications for clinical use in the field of skin disease diagnosis. Melanin segmentation can be applied to medical integrated classification techniques to help experts select the most suitable treatment options for patients.