• Abhishek Rana
• Dhruv Kumar Singh
• Subodh Kumar Panda

Skin cancer is a major concern for global health as there is an increase in the number of cases day by day with 123,000 incidences of melanoma and 30,000 cases of non-melanoma cases worldwide per year. High UV radiation exposure has been identified as a major risk factor for skin cancer in recent research. Early detection of skin lesions is the most effective strategy to lower the death rate from skin cancer because melanoma patients have a 99 percent five-year survival probability when discovered and screened at the early stage. The inability of dermatologists to diagnose skin cancer accurately has necessitated the development of an automated, efficient method. The purpose of this paper is to offer a means by which anyone can profit by uploading an image of a lesion to our web API to determine whether or not it is a melanoma or a skin cancerous lesion. This work investigates an efficient automated system for classifying skin cancer with better evaluation criteria compared to past studies or skilled physicians. Without computer aid, a qualified dermatologist's physical melanoma detection accuracy ranges from 50-70 %. The ResNext model, which was adjusted on roughly more than 1 million images from the ImageNet Challenge, was utilized. It was transfer-learned using 10015 dermoscopy images from the HAM10000 dataset. For the seven classes in the dataset, the model used in this paper had an accuracy of 89.1 percent. Anyone can obtain a rudimentary diagnosis of their skin lesions and determine whether or not they are among one of the seven classes of skin cancer, using the created web API.

Tensor Flow, HAM10000 Dataset, Melanoma, Skin Cancer, ResNext architecture, Deep Learning, Node.js, Web Development

"SKIN CANCER DETECTION WITH DEEP LEARNING USING WEB API", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 7, page no.g40-g44, July-2022, Available :http://www.jetir.org/papers/JETIR2207607.pdf

"SKIN CANCER DETECTION WITH DEEP LEARNING USING WEB API", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 7, page no. ppg40-g44, July-2022, Available at : http://www.jetir.org/papers/JETIR2207607.pdf