Abstract
Segmenting melanoma lesions accurately is harder than it might appear. Even in high-quality dermoscopic images, lesion edges can be gradual rather than sharp, colordifferences between lesion and healthy skin are sometimes minimal, and no two lesionslook quite alike. These are not just technical inconveniences; they directly affect howreliably a computer-aided system can support a clinician's decision. In this work, weexplored whether combining deep learning with swarm intelligence could address someof these difficulties. Specifically, we paired three CNN architectures U-Net, SegNet, andDeepLabv3+ with ResNet-50, with the Grasshopper Optimization Algorithm (GOA),using it not as a preprocessing step but as a refinement stage applied after the networkproduces its initial prediction. The idea was that GOA's color-based clustering couldtighten boundaries in regions where the CNN's confidence was low. We tested this hybridmodel on the ISBI 2016 and ISIC 2018 dermoscopic datasets. Not all architecturesresponded equally U-Net struggled noticeably, while SegNet performed reasonably well.In previous approaches, deep learning and swarm intelligence were treated as separatestages, whereas our proposed framework, the GOA, is integrated directly into the post-prediction step of DeepLabv3+-ResNet-50, which enables boundary refinement thatcomplements rather than replaces CNN predictions. The results from DeepLabv3+ withResNet-50 were the best, achieving Dice coefficients of 91.7% and 88.2% and Jaccardindices of 84.9% and 79.7% on the ISBI 2016 and ISIC 2018 datasets, respectively,demonstrating the effectiveness of the proposed hybrid approach for lesion segmentation. (PDF) A Hybrid Framework Combining DeepLabv3+ with ResNet-50 Backbone and GOA for Automated Melanoma Lesion Segmentationإطار عمل هجين يجمع بين DeepLabv3+ مع ResNet-50 Backbone وخوارزمية تحسين الجراد لتجزئة ورم الميلانوما آليا. Available from: https://www.researchgate.net/publication/409245042_A_Hybrid_Framework_Combining_DeepLabv3_with_ResNet-50_Backbone_and_GOA_for_Automated_Melanoma_Lesion_Segmentationatar_ml_hjyn_yjm_byn_DeepLabv3_m_ResNet-50_Backbone_wkhwarzmyt_thsyn_aljrad_ltjzyt_wrm_ [accessed Jul 17 2026].