A Multi-stage Framework with Context Information Fusion Structure for Skin Lesion Segmentation
This work addresses segmentation accuracy for melanoma recognition, which is crucial for medical diagnosis, but it is incremental as it builds on existing UNet-based methods.
The authors tackled the problem of inaccurate skin lesion segmentation in computer-aided diagnosis systems by proposing a multi-stage UNet framework with context information fusion and deep supervision, achieving state-of-the-art performance on the ISBI 2016 dataset with improvements in four out of five metrics including Jaccard index and Dice coefficient.
The computer-aided diagnosis (CAD) systems can highly improve the reliability and efficiency of melanoma recognition. As a crucial step of CAD, skin lesion segmentation has the unsatisfactory accuracy in existing methods due to large variability in lesion appearance and artifacts. In this work, we propose a framework employing multi-stage UNets (MS-UNet) in the auto-context scheme to segment skin lesion accurately end-to-end. We apply two approaches to boost the performance of MS-UNet. First, UNet is coupled with a context information fusion structure (CIFS) to integrate the low-level and context information in the multi-scale feature space. Second, to alleviate the gradient vanishing problem, we use deep supervision mechanism through supervising MS-UNet by minimizing a weighted Jaccard distance loss function. Four out of five commonly used performance metrics, including Jaccard index and Dice coefficient, show that our approach outperforms the state-ofthe-art deep learning based methods on the ISBI 2016 Skin Lesion Challenge dataset.