Deep Learning for Skin Lesion Classification

TL;DR

This paper presents an automated system using deep learning and pretrained CNN features to classify skin lesions as benign or malignant, and further categorize cancer causes, achieving 65.8% accuracy on validation data.

Contribution

It introduces a novel application of Google's Inception-v3 model combined with neural networks for skin lesion classification in the ISIC 2017 challenge.

Findings

Achieved 65.8% accuracy on validation set

Successfully classified lesions as benign or malignant

Categorized cancer causes with neural networks

Abstract

Melanoma, a malignant form of skin cancer is very threatening to life. Diagnosis of melanoma at an earlier stage is highly needed as it has a very high cure rate. Benign and malignant forms of skin cancer can be detected by analyzing the lesions present on the surface of the skin using dermoscopic images. In this work, an automated skin lesion detection system has been developed which learns the representation of the image using Google's pretrained CNN model known as Inception-v3 \cite{cnn}. After obtaining the representation vector for our input dermoscopic images we have trained two layer feed forward neural network to classify the images as malignant or benign. The system also classifies the images based on the cause of the cancer either due to melanocytic or non-melanocytic cells using a different neural network. These classification tasks are part of the challenge organized by International Skin Imaging Collaboration (ISIC) 2017. Our system learns to classify the images based on the model built using the training images given in the challenge and the experimental results were evaluated using validation and test sets. Our system has achieved an overall accuracy of 65.8\% for the validation set.