Learning to Detect Blue-white Structures in Dermoscopy Images with Weak Supervision

TL;DR

This paper introduces a weakly-supervised learning method for detecting and localizing Blue-whitish structures in dermoscopy images, aiding melanoma diagnosis with only image-level labels.

Contribution

It presents a novel Multiple Instance Learning framework that localizes dermoscopic features using weak supervision, advancing automated skin lesion analysis.

Findings

Outperforms state-of-the-art methods on a challenging dataset

Successfully localizes dermoscopic features with only image-level labels

Enhances automated analysis of skin lesions

Abstract

We propose a novel approach to identify one of the most significant dermoscopic criteria in the diagnosis of Cutaneous Melanoma: the Blue-whitish structure. In this paper, we achieve this goal in a Multiple Instance Learning framework using only image-level labels of whether the feature is present or not. As the output, we predict the image classification label and as well localize the feature in the image. Experiments are conducted on a challenging dataset with results outperforming state-of-the-art. This study provides an improvement on the scope of modelling for computerized image analysis of skin lesions, in particular in that it puts forward a framework for identification of dermoscopic local features from weakly-labelled data.