Bio-Inspired Leafy Seadragon Optimization for Automated Segmentation of Skin Cancer in Dermoscopy

Accurate segmentation of skin lesions in dermoscopic images is essential for early melanoma detection and reliable computer-aided diagnosis. This paper proposes a novel bio-inspired segmentation algorithm, the Leafy Seadragon Optimization (LSDO) method, which models the drifting locomotion and appendage-based micro-refinement behavior of the leafy seadragon to achieve robust boundary localization. LSDO incorporates a dual-phase search strategy combining global drifting with fine local adjustments, guided by a boundary-aware fitness function that enhances lesion–background separation. The algorithm was evaluated on the ISIC 2018 and HAM10000 datasets and demonstrated superior performance compared with six strong baselines: HFOA, GJO, FA, Pyramid U-Net, Attention-based CNN, and YOLOSAMIC. On ISIC 2018, LSDO achieved a Dice score of 0.94, IoU of 0.88, Sensitivity of 0.95, Specificity of 0.98, Accuracy of 0.96, and BF-score of 0.92. On the more challenging HAM10000 dataset, the method maintained high performance with a Dice of 0.90, IoU of 0.82, Sensitivity of 0.93, and Accuracy of 0.94. Qualitative comparisons further revealed that LSDO produces cleaner, more complete lesion masks and superior boundary adherence. These results confirm that the proposed LSDO algorithm is a powerful, stable, and generalizable segmentation tool for dermoscopic image analysis.