DeepLabv3+-Based Segmentation and Best Features Selection Using Slime Mould Algorithm for Multi-Class Skin Lesion Classification

The development of abnormal cell growth is caused by different pathological alterations and some genetic disorders. This alteration in skin cells very dangerous life-threatening, its timely identification essential for better treatment safe cure. Therefore, the present article, an approach proposed lesions’ segmentation classification. So, framework, pre-trained Mobilenetv2 utilised act back pillar DeepLabv3+ model trained on optimum parameters that provide significant improvement infected segmentation. multi-classification lesions carried out through feature extraction from DesneNet201 with N × 1000 dimension, which informative features are picked Slim Mould Algorithm (SMA) input to SVM KNN classifiers. method provided a mean ROC 0.95 ± 0.03 MED-Node, 0.97 0.04 PH2, 0.98 0.02 HAM-10000, 0.00 ISIC-2019 datasets.