Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)

By D. Gutman, Noel C. F. Codella, M. Emre Celebi, Brian Helba, M. Marchetti, N. Mishra, Allan Halpern. 2016

2,727 citations recorded by the source corpus.

This article describes the design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge. The goal is to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer. The challenge was divided into 3 tasks: lesion segmentation, feature detection, and disease classification. Participation involved 593 registrations, 81 pre-submissions, 46 finalized submissions (including a 4-page manuscript), and approximately 50 attendees, making this the largest standardized and comparative study in this field to date. While the official challenge duration and ranking of participants has concluded, the dataset snapshots remain available for further research and development.

Subfields: Artificial Intelligence, Epidemiology, Oncology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

In Oncology

Citations in the corpus

Deep learning ensembles for melanoma recognition in dermoscopy images (2016, methodology): “A detailed description of the definition of each metric is given in the ISBI challenge report [35].”
Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval (2021, methodology): “1) and hosting multiple challenges and workshops [28].”
Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC) (2019, methodology): “Evaluation criteria historically had been the Jaccard index [3,4,5], averaged over all images in the dataset.”
Towards a guideline for evaluation metrics in medical image segmentation (2022, neutral): “[35], endoscopy–endoscopic colonoscopy frames for polyp detection [36], fundus photography–vessel extraction in retinal images [37], dermoscopy–skin lesion segmentation for melanoma detection in dermoscopy images [38].”
A Survey on ensemble learning under the era of deep learning (2021, methodology): “…on ImageNet (Deng et al. 2009) and convolutional network of U-shape (U-Net) (Ronneberger et al. 2015) pretrained on lesion segmentation task (Codella et al. 2018) for feature representations, in addition to several types of traditional feature representations including color histogram (CH)…”
Seven-Point Checklist and Skin Lesion Classification Using Multitask Multimodal Neural Nets (2019, background): “For instance, the International Skin Imaging Collaboration’s skin lesion classification challenge [17], asks participants to directly classify benign from malignant lesions.”
Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation (2021, methodology): “• ISIC-2018 is a dataset composed of skin lesions with a total of 2594 images with both segmentation masks expert labels from the HAM10000 dataset [31] and ISIC-2017 dataset [4].”