Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance

TLDR

Automatic skin lesion segmentation in dermoscopic images is challenging due to low contrast, irregular borders, artifacts, and variable acquisition conditions. The study proposes a fully automatic 19‑layer deep convolutional neural network for skin lesion segmentation that is trained end‑to‑end without relying on prior data knowledge. The authors train the network end‑to‑end using a Jaccard‑distance loss and data‑efficient strategies, and evaluate its effectiveness, efficiency, and generalization on the ISBI 2016 and PH2 datasets. The approach outperforms state‑of‑the‑art methods on both datasets and, with minimal preprocessing, is broadly applicable to medical image segmentation.

Abstract

Automatic skin lesion segmentation in dermoscopic images is a challenging task due to the low contrast between lesion and the surrounding skin, the irregular and fuzzy lesion borders, the existence of various artifacts, and various imaging acquisition conditions. In this paper, we present a fully automatic method for skin lesion segmentation by leveraging 19-layer deep convolutional neural networks that is trained end-to-end and does not rely on prior knowledge of the data. We propose a set of strategies to ensure effective and efficient learning with limited training data. Furthermore, we design a novel loss function based on Jaccard distance to eliminate the need of sample re-weighting, a typical procedure when using cross entropy as the loss function for image segmentation due to the strong imbalance between the number of foreground and background pixels. We evaluated the effectiveness, efficiency, as well as the generalization capability of the proposed framework on two publicly available databases. One is from ISBI 2016 skin lesion analysis towards melanoma detection challenge, and the other is the PH2 database. Experimental results showed that the proposed method outperformed other state-of-the-art algorithms on these two databases. Our method is general enough and only needs minimum pre- and post-processing, which allows its adoption in a variety of medical image segmentation tasks.