Research on Cancer Detection Reported by Researchers at City University of New York (CUNY) (MUCM-Net: a Mamba powered UCM-Net for skin lesion segmentation).

Researchers at City University of New York (CUNY) have developed a model called MUCM-Net for skin lesion segmentation to aid in early skin cancer detection. The model combines Convolutional Neural Networks (CNNs), multi-layer perceptions (MLPs), and Mamba elements to achieve high accuracy and efficiency. MUCM-Net outperformed existing models with an average Dice Similarity Coefficient (DSC) of 0.91 on the ISIC2017 dataset and 0.89 on the ISIC2018 dataset, making it a promising tool for mobile health diagnostics in resource-limited settings. The open-source availability of MUCM-Net encourages further research and collaboration in the fight against skin cancer. [Extracted from the article]