DenseNet approach to segmentation and classification of dermatoscopic skin lesions images

TL;DR

This paper combines U-Net and DenseNet121 architectures to improve segmentation and classification of dermatoscopic skin lesion images, aiding early skin cancer detection with promising accuracy.

Contribution

It introduces a novel combination of U-Net and DenseNet121 for skin lesion analysis, achieving competitive results in segmentation and classification tasks.

Findings

Segmentation tested on ISIC-2018 dataset shows high accuracy.

Classification of cancerous vs non-cancerous samples achieved 79.49% and 93.11% accuracy.

The combined approach outperforms previous methods in dermatoscopic image analysis.

Abstract

At present, cancer is one of the most important health issues in the world. Because early detection and appropriate treatment in cancer are very effective in the recovery and survival of patients, image processing as a diagnostic tool can help doctors to diagnose in the first recognition of cancer. One of the most important steps in diagnosing a skin lesion is to automatically detect the border of the skin image because the accuracy of the next steps depends on it. If these subtleties are identified, they can have a great impact on the diagnosis of the disease. Therefore, there is a good opportunity to develop more accurate algorithms to analyze such images. This paper proposes an improved method for segmentation and classification for skin lesions using two architectures, the U-Net for image segmentation and the DenseNet121 for image classification which have excellent accuracy. We tested the segmentation architecture of our model on the ISIC-2018 dataset and the classification on the HAM10000 dataset. Our results show that the combination of U-Net and DenseNet121 architectures provides acceptable results in dermatoscopic image analysis compared to previous research. Another classification examined in this study is cancerous and non-cancerous samples. In this classification, cancerous and non-cancerous samples were detected in DenseNet121 network with 79.49% and 93.11% accuracy respectively.