Skin cancer is one of the most common diseases that can be initially detected by visual observation and further with the help of dermoscopic analysis and other tests. As at an initial stage, visual observation gives the opportunity of utilizing artificial intelligence to intercept the different skin images, so several skin lesion classification methods using deep learning based on convolution neural network (CNN) and annotated skin photos exhibit improved results. In this respect, the paper presents a reliable approach for diagnosing skin cancer utilizing dermoscopy images in order to improve health care professionals’ visual perception and diagnostic abilities to discriminate benign from malignant lesions. The swarm intelligence (SI) algorithms were used for skin lesion region of interest (RoI) segmentation from dermoscopy images, and the speeded-up robust features (SURF) was used for feature extraction of the RoI marked as the best segmentation result obtained using the Grasshopper Optimization Algorithm (GOA). The skin lesions are classified into two groups using CNN against three data sets, namely, ISIC-2017, ISIC-2018, and PH-2 data sets. The proposed segmentation and classification techniques’ results are assessed in terms of classification accuracy, sensitivity, specificity, F-measure, precision, MCC, dice coefficient, and Jaccard index, with an average classification accuracy of 98.42 percent, precision of 97.73 percent, and MCC of 0.9704 percent. In every performance measure, our suggested strategy exceeds previous work.

JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.

Skin cancer is a severe and rapidly advancing condition that can be impacted by multiple factors, including alcohol and tobacco use, allergies, infections, physical activity, exposure to UV light, viral infections, and the effects of climate change. While the steep death tolls continue rising at an alarming rate, lack of symptoms recognition and its preventive measures further worsen the case. In this article, we employ the ISBI-2017 dataset to present an improved FrCN-based hybrid image segmentation method with U-Net to improve detection performance. This paper proposes a hybrid approach using the FrCN-(U-Net) image segmentation technique to enhance results compared to an advanced method for detecting skin cancer types, such as Benign or Melanoma. The classification phase is then handled using the R-CNN algorithm. Our model shows better performance in both training and testing accuracy than any other existing approaches. The results show that the combined method is effective in enhancing early disease diagnosis, which in turn improves treatment outcomes and prognosis. This paper presents an alternative technique for skin cancer detection, which can serve as a guide for clinical practices and public health strategies on how to lower skin-cancer-related deaths.