Machine learning approach in melanoma cancer stage detection

Melanoma is a dangerous skin cancer and spreads very fast. Hence, it is the deadliest skin cancer and causes most deaths. Classification of cancer stages is a very tedious task and very important when a patient is diagnosed. Diagnosis of cancer at the surgical treatment time mainly depends on the stage of cancer or tumor thickness. In this paper, two methods are designed to classify melanoma cancer stages. The first system classifies melanoma as stage 1 and stage 2. Second system classifies melanoma as stage 1, stage 2 or stage 3 melanoma. The proposed system uses convolutional neural network (CNN) algorithm with Similarity Measure for Text Processing (SMTP) as loss function. The experimental results with different loss functions are demonstrated and compared with proposed SMTP loss function. The proposed algorithm is more efficient than several other loss functions that are specifically designed for the classification problem.