A Multi-task Framework for Skin Lesion Detection and Segmentation

TL;DR

This paper presents a multi-task CNN framework combining lesion detection and segmentation to improve skin lesion analysis, achieving high accuracy and robustness on standard datasets.

Contribution

It introduces a joint detection and segmentation framework using Faster-RCNN and SkinNet, outperforming existing methods on benchmark datasets.

Findings

Achieved Dice coefficient >0.93 and Jaccard index >0.88.

Outperformed state-of-the-art methods in accuracy and sensitivity.

Validated on ISBI 2017 and PH2 datasets with five-fold cross validation.

Abstract

Early detection and segmentation of skin lesions is crucial for timely diagnosis and treatment, necessary to improve the survival rate of patients. However, manual delineation is time consuming and subject to intra- and inter-observer variations among dermatologists. This underlines the need for an accurate and automatic approach to skin lesion segmentation. To tackle this issue, we propose a multi-task convolutional neural network (CNN) based, joint detection and segmentation framework, designed to initially localize the lesion and subsequently, segment it. A `Faster region-based convolutional neural network' (Faster-RCNN) which comprises a region proposal network (RPN), is used to generate bounding boxes/region proposals, for lesion localization in each image. The proposed regions are subsequently refined using a softmax classifier and a bounding-box regressor. The refined bounding boxes are finally cropped and segmented using `SkinNet', a modified version of U-Net. We trained and evaluated the performance of our network, using the ISBI 2017 challenge and the PH2 datasets, and compared it with the state-of-the-art, using the official test data released as part of the challenge for the former. Our approach outperformed others in terms of Dice coefficients ($>0.93$), Jaccard index ($>0.88$), accuracy ($>0.96$) and sensitivity ($>0.95$), across five-fold cross validation experiments.