Saliency-Based Lesion Segmentation Via Background Detection in Dermoscopic Images

Abstract

The segmentation of skin lesions in dermoscopic images is a fundamental step in automated computer-aided diagnosis of melanoma. Conventional segmentation methods, however, have difficulties when the lesion borders are indistinct and when contrast between the lesion and the surrounding skin is low. They also perform poorly when there is a heterogeneous background or a lesion that touches the image boundaries; this then results in under- and oversegmentation of the skin lesion. We suggest that saliency detection using the reconstruction errors derived from a sparse representation model coupled with a novel background detection can more accurately discriminate the lesion from surrounding regions. We further propose a Bayesian framework that better delineates the shape and boundaries of the lesion. We also evaluated our approach on two public datasets comprising 1100 dermoscopic images and compared it to other conventional and state-of-the-art unsupervised (i.e., no training required) lesion segmentation methods, as well as the state-of-the-art unsupervised saliency detection methods. Our results show that our approach is more accurate and robust in segmenting lesions compared to other methods. We also discuss the general extension of our framework as a saliency optimization algorithm for lesion segmentation.

Segmentation of Melanoma Skin Lesion Using Perceptual Color Difference Saliency with Morphological Analysis

“…However, the application of saliency methods for segmentation of skin lesion is relatively new [13,17,37]. Saliency segmentation computes the most informative region in an image based on human vision perception such that salient and nonsalient parts become foreground region (skin lesion) and background region (healthy skin), respectively.…”

“…However, many of the improved saliency segmentation algorithms still face difficulty when salient objects share similar color features with the background pixels. These algorithms often lack the ability to effectively handle complicated images with low contrast [18,20,37]. Complementing the methods of saliency computation with other useful analysis methods such as the morphological analysis can significantly improve image segmentation results.…”

Feature of Interest‐Based Direct Volume Rendering Using Contextual Saliency‐Driven Ray Profile Analysis

“…Research in saliency by the computer vision research community has shown promising accuracy in object (feature) detection for medical images and scientific data [MTY*11, BMSH16, AKB*17]. These medical and scientific images tend to have salient object composition, that is differentiation between the foreground and background objects, for example, the lungs, heart, abdominal organs and bony skeleton are the foreground and empty space is the background.…”

Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation

“…Even experienced dermatologists may produce the inconsistent diagnosis results [7]. During recent decades, computer-aided diagnosis systems (CADs) have been developed and already demonstrated strengths for assisting dermatologists in enhancing their clinical diagnosis of melanoma [8], [9].…”