Deep Learning based Novel Cascaded Approach for Skin Lesion Analysis

TL;DR

This paper presents a novel cascaded deep learning framework combining segmentation and classification for skin lesion analysis, significantly improving diagnostic accuracy in dermoscopic images.

Contribution

It introduces the first end-to-end cascaded deep learning approach that enhances lesion classification accuracy through prior segmentation.

Findings

Improved accuracy, mean IoU, and Dice scores for lesion segmentation.

Significant enhancement in classification accuracy due to segmentation.

First end-to-end cascaded deep learning method for skin lesion analysis.

Abstract

Automatic lesion analysis is critical in skin cancer diagnosis and ensures effective treatment. The computer aided diagnosis of such skin cancer in dermoscopic images can significantly reduce the clinicians workload and help improve diagnostic accuracy. Although researchers are working extensively to address this problem, early detection and accurate identification of skin lesions remain challenging. This research focuses on a two step framework for skin lesion segmentation followed by classification for lesion analysis. We explored the effectiveness of deep convolutional neural network based architectures by designing an encoder-decoder architecture for skin lesion segmentation and CNN based classification network. The proposed approaches are evaluated quantitatively in terms of the Accuracy, mean Intersection over Union and Dice Similarity Coefficient. Our cascaded end to end deep learning based approach is the first of its kind, where the classification accuracy of the lesion is significantly improved because of prior segmentation.