A weakly supervised approach to skin lesion segmentation

Abstract

Early detection of skin cancers greatly increases patients' chances of recovery. To support dermatologists in this diagnosis, many decision support systems based on Convolutional Neural Networks have recently been proposed to segment the lesion and classify it. The use of the information coming from the segmentation, as an additional input to the classifier, proved to be fundamental to increase its performance and, in fact, the shape of the lesion is of diagnostic importance unanimously recognized by clinicians. However, in the ISIC database, the public reference dataset that collects a huge number of skin lesion images, all samples are labeled for classification but only a very small fraction of them are also labeled for segmentation. To overcome this limitation, the present paper proposes a weakly supervised approach to extract the segmentation label maps of approximately 43,000 ISIC images, used to train a segmentation network, with very promising performance.

Deep learning techniques for biomedical data processing

“…the rupture of the innermost layer of the aorta which allows blood to flow between the layers of the aortic wall, forcing the layers to separate. On the other hand, in [85] a weakly supervised approach was implemented to realize skin lesion segmentation and identify possible harmful melanomas from benign nevi. This research topic was also further exploited, investigating a multimodal approach, i.e.…”

Deep Semantic Segmentation Models in Computer Vision

“…The use of semantic segmentation deep learning models in this context can efficiently help the human operator responsible for assessing the healthiness of a oocyte to be fertilized and returned to the uterus. Other two interesting contributions showing applications of deep learning for the task of semantics segmentation in biomedical related fields, in particular related to the dermatology fields, are represented by [44,45]. In [44] the authors presented a short survey and overview of the most used methodologies in this fields, together with the relevant datasets.…”

“…Most recent models were compared. In [45] instead, the author presented deep semantic model application to the case of skin lesions detection. The paper presents a novel application of convolutional neural networks based architecture to the case of skin lesions detection.…”