• Ruttik Trymbake
• Tayyaba Pinjari
• Sakshi Jagtap
• Aliasgar Pardawala

With over 5,000,000 new cases every year skin cancer is a concerning public health predicament. Generally, skin cancer is of two types: melanoma and non-melanoma. Melanoma also called Malignant Melanoma is the 19th most frequently occurring cancer in women and men. It is the deadliest form of skin cancer. Over 350,000 cases of melanoma skin cancer were detected in 2015 alone. The most prevalent non-melanoma tumors are squamous cell carcinoma and basal cell carcinoma. Non-melanoma skin cancer is the 5th most frequently occurring cancer, with over 1 million diagnoses worldwide in 2018 alone . As of 2019, more than 1.7 Million new cases are expected to be diagnosed . Even though the mortality is significantly high, when detected early, survival rate exceeds 95%. This encourages us to come up with a solution that could save millions of lives by detecting skin cancer at an early stage. Convolutional Neural Network (CNN) or ConvNet are a class of deep neural networks, basically generalized versions of multi-layer perceptrons. This project aims to develop a CNN model to help in early detection of skin cancer. To develop an optimized model, we analyzed research papers on the subject of skin cancer diagnosis published in well-known specialized journals. The proposed model will be developed and tested with different network architectures by training the network with varying types of layers.

Convolutional Neural Networks, Malignant Melanoma, Melanoma

"Survey Paper on Skin Cancer Detection Using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 12, page no.e6-e9, December-2021, Available :http://www.jetir.org/papers/JETIR2112402.pdf

"Survey Paper on Skin Cancer Detection Using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 12, page no. ppe6-e9, December-2021, Available at : http://www.jetir.org/papers/JETIR2112402.pdf