Learning to Detect Blue-white Structures in Dermoscopy Images with Weak Supervision
This work addresses a critical need in dermatology by enabling automated feature detection with weak supervision, though it is incremental in applying existing frameworks to a specific medical domain.
The paper tackled the problem of detecting blue-white structures in dermoscopy images for melanoma diagnosis using only image-level labels, achieving results that outperform state-of-the-art methods.
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.