Automatic Lesion Boundary Segmentation in Dermoscopic Images with Ensemble Deep Learning Methods

TL;DR

This paper introduces an ensemble deep learning approach combining Mask-RCNN and DeepLabv3+ for precise skin lesion boundary segmentation in dermoscopic images, significantly outperforming existing methods on the ISIC-2017 dataset.

Contribution

The study presents a novel ensemble method that improves segmentation accuracy of skin lesions, leveraging deep learning models trained on limited annotated datasets.

Findings

Ensemble method achieved a Jaccard index of 79.58%.

Outperformed FrCN, FCN, U-Net, and SegNet in segmentation accuracy.

Achieved high classification accuracy for benign and malignant cases.

Abstract

Early detection of skin cancer, particularly melanoma, is crucial to enable advanced treatment. Due to the rapid growth in the numbers of skin cancers, there is a growing need of computerized analysis for skin lesions. The state-of-the-art public available datasets for skin lesions are often accompanied with very limited amount of segmentation ground truth labeling as it is laborious and expensive. The lesion boundary segmentation is vital to locate the lesion accurately in dermoscopic images and lesion diagnosis of different skin lesion types. In this work, we propose the use of fully automated deep learning ensemble methods for accurate lesion boundary segmentation in dermoscopic images. We trained the Mask-RCNN and DeepLabv3+ methods on ISIC-2017 segmentation training set and evaluate the performance of the ensemble networks on ISIC-2017 testing set. Our results showed that the best proposed ensemble method segmented the skin lesions with Jaccard index of 79.58% for the ISIC-2017 testing set. The proposed ensemble method outperformed FrCN, FCN, U-Net, and SegNet in Jaccard Index by 2.48%, 7.42%, 17.95%, and 9.96% respectively. Furthermore, the proposed ensemble method achieved an accuracy of 95.6% for some representative clinically benign cases, 90.78% for the melanoma cases, and 91.29% for the seborrheic keratosis cases on ISIC-2017 testing set, exhibiting better performance than FrCN, FCN, U-Net, and SegNet.