Title: Enhancing Skin Cancer Detection in Dermoscopic Images via Neuro-Fuzzy and Colonial Competition Algorithms

Abstract: With skin cancer rates climbing alongside a deficit in clinical specialists and low public awareness, there is a critical demand for sophisticated diagnostic support. Artificial Intelligence (AI) has risen as a compelling solution, especially for differentiating between malignant and benign skin growths. While researchers are utilizing open-source skin lesion datasets to build AI-driven diagnostic tools, the actual deployment of these computer systems within clinical environments remains in its early stages. To address this disconnect, this research integrates image processing methods with machine learning models, focusing on neuro-fuzzy and colonial competition techniques. By applying this methodology to 560 dermoscopic images sourced from the ISIC database, the study attained a significant accuracy rate of 94%. These findings highlight the capability of the proposed method to assist healthcare providers in the timely identification of melanoma, offering a substantial advancement in skin cancer diagnosis.

Source: arXiv Generated at: 2026-06-03 00:00:00 UTC