Skin Lesions Classification Using Convolutional Neural Networks in Clinical Images

TL;DR

This paper presents a deep learning approach using ResNet-152 to classify 12 skin lesion types, achieving high accuracy on a large, augmented dataset, aiding early skin cancer detection.

Contribution

The study introduces a ResNet-152 based model trained on a large, augmented dataset for classifying multiple skin lesion types, including melanoma and carcinoma.

Findings

Achieved AUC of 0.96 for Melanoma

Achieved AUC of 0.91 for Basal Cell Carcinoma

Utilized extensive data augmentation to improve model performance

Abstract

Skin lesions are conditions that appear on a patient due to many different reasons. One of these can be because of an abnormal growth in skin tissue, defined as cancer. This disease plagues more than 14.1 million patients and had been the cause of more than 8.2 million deaths, worldwide. Therefore, the construction of a classification model for 12 lesions, including Malignant Melanoma and Basal Cell Carcinoma, is proposed. Furthermore, in this work, it is used a ResNet-152 architecture, which was trained over 3,797 images, later augmented by a factor of 29 times, using positional, scale, and lighting transformations. Finally, the network was tested with 956 images and achieve an area under the curve (AUC) of 0.96 for Melanoma and 0.91 for Basal Cell Carcinoma.