Using Deep Learning Method for Classification: A Proposed Algorithm for the ISIC 2017 Skin Lesion Classification Challenge

TL;DR

This paper proposes a deep learning-based algorithm utilizing CNNs within the Caffe framework to classify skin lesions in the ISIC 2017 challenge, aiming to enhance diagnostic accuracy in dermatology.

Contribution

It introduces a novel three-step CNN-based algorithm specifically designed for skin lesion classification in the ISIC 2017 challenge, focusing on improving accuracy and reliability.

Findings

The algorithm achieved competitive classification scores.

Preprocessing and dual-model prediction improved accuracy.

The method demonstrates potential for automated skin cancer diagnosis.

Abstract

Skin cancer, the most common human malignancy, is primarily diagnosed visually by physicians [1]. Classification with an automated method like CNN [2, 3] shows potential for challenging tasks [1]. By now, the deep convolutional neural networks are on par with human dermatologist [1]. This abstract is dedicated on developing a Deep Learning method for ISIC [5] 2017 Skin Lesion Detection Competition hosted at [6] to classify the dermatology pictures, which is aimed at improving the diagnostic accuracy rate and general level of the human health. The challenge falls into three sub-challenges, including Lesion Segmentation, Lesion Dermoscopic Feature Extraction and Lesion Classification. This project only participates in the Lesion Classification part. This algorithm is comprised of three steps: (1) original images preprocessing, (2) modelling the processed images using CNN [2, 3] in Caffe [4] framework, (3) predicting the test images and calculating the scores that represent the likelihood of corresponding classification. The models are built on the source images are using the Caffe [4] framework. The scores in prediction step are obtained by two different models from the source images.