ISIC Skin Image Analysis Workshop
@ CVPR 2020

Hosted by the International Skin Imaging Collaboration (ISIC)

NEW (6/15/2020): Video of Opening Remarks posted

NEW (6/14/2020): Videos and Slides of Paper Presentations posted

NEW (6/14/2020): Videos of Invited Talks posted

NEW (6/14/2020): Open-Access Workshop Proceedings available

NEW (6/13/2020): CVPR Virtual Site launched



NOTICE: Paper Submission System Online

Skin is the largest organ of the human body, and is the first area of assessment performed by any clinical staff when a patient is seen, as it delivers numerous insights into a patient’s underlying health. For example, cardiac function, liver function, immune function, and physical injuries can be assessed by examining the skin. In addition, dermatologic complaints are also among the most prevalent in primary care [1].  Images of the skin are the most easily captured form of medical image in healthcare, and the domain shares qualities to other standard computer vision datasets, serving as a natural bridge between standard computer vision tasks and medical applications. However, significant and unique challenges still exist in this domain. For example, there is significant visual similarity across disease conditions, and in comparison to other medical imaging modalities, the skin is an organ which has no expected shape: varying genetics, disease states, imaging equipment, and environments can significantly change its appearance, making localization and classification in this domain unsolved tasks.

This workshop will serve as a venue to facilitate advancements and knowledge dissemination in the field of skin image analysis, raising awareness and interest for these socially valuable tasks. Invited speakers include (confirmed) major influencers in computer vision and skin imaging, and authors of accepted papers.

Topics of manuscript submissions may include:

  • Computer Vision Applied to Dermatology and Primary Care
  • Skin Analysis from Dermoscopic Images
  • Skin Analysis from Consumer-Grade Photographs
  • Skin Analysis from Video
  • Skin Analysis from Total-Body Photography and 3D Skin Reconstructions
  • Skin Analysis from Confocal Microscopy
  • Skin Analysis from Optical Coherence Tomography (OCT)
  • Skin Analysis from Histopathological Images
  • Skin Analysis from Multi-Modal Data Sources
  • Interpretable or Explainable AI Related to Skin Image Analysis
  • Algorithms to Mitigate Dataset Imbalance
  • Uncertainty Estimation Related to Skin Image Analysis
  • Application Workflows for Skin Image Analysis
  • Robustness to Bias from Clinical and User-Originating Photography
  • Few-Shot Learning in Skin Images
The workshop will give out 2 awards towards paper submissions:
  • Best Paper Award: 4,000 USD
  • Honorable Mention Award: 2,000 USD
Judging will be carried out by the workshop chairs according to paper reviews, quality of research, potential impact, and novelty.

In order to submit a paper, please refer to the following:
Paper Submissions System Link Available *NOW*! (Author Information and Template)

[1] Lowell BA, et al. “Dermatology in primary care: Prevalence and patient disposition" In: Journal of the American Academy of Dermatology (JAAD), vol. 45, no. 2. 2001.

Invited Speakers

This workshop will feature several prominent names in the field of skin image analysis, including:

Kristin Dana
Dr. Dana is a Full Professor in the Department of Electrical and Computer Engineering at Rutgers University. She is also a member of the graduate faculty of Rutgers Computer Science Department. Her work on skin image analysis has included confocal microscopy analysis, skin texture quantification, and microbiome assessment, published in top venues such as CVPR and ICPR..
Tim K. Lee
Dr. Lee is an associate professor of Dermatology and Skin Science and a senior scientist of BC Cancer Research Centre. He is one of the earliest researchers in dermoscopy image analysis, and inventor of the DullRazor algorithm, which is used for automatic hair removal.
Doug Canfield
Doug Canfield is CEO of Canfield Scientific, one of the largest developers and manufacturers of dermatology imaging equipment, including dermatoscopes, facial imaging, total body imaging, and more. Canfield researches and develops automated analysis systems for their products using machine learning and artificial intelligence.
Daniel Mark Siegel
Dr. Siegel is a Clinical Professor of Dermatology at SUNY Downstate. He is a former President of the American Academy of Dermatology (AAD) and a member of the Scientific Board of SkinVision.

Important Dates

March 22nd, 2020: Workshop Paper Submission Deadline: 11:59 PM EST
April 13th, 2020: Author final notification
April 20th, 2020: Camera-Ready Deadline
June 15, 2020: Workshop @ CVPR 2020 Virtual

Paper Submission

For paper submissions, CVPR manuscript rules are followed. All papers will be indexed in CVF and IEEE Xplore, along with other CVPR 2020 papers.

Paper Submissions System (Author Information and Template).

Research Datasets for Skin Image Analysis

  • ISIC 2018 / ISIC 2019: According to the American Cancer Society, skin cancer is the most common form of cancer. While amenable to early detection by direct inspection, visual similarity with benign lesions makes the task difficult. Dermoscopic imaging was introduced to better visualize key details in skin lesions to improve diagnostic accuracy. The International Skin Imaging Collaboration (ISIC) has organized the world's largest repository of dermoscopic images of skin (over 23,000 images), to support research and development of methods for segmentation, clinical attribute detection, and disease classification. These datasets are snapshots used for the 2018 and 2019 challenges. See also: Challenge Summary / Data Description
  • SD-198: 6,584 consumer grade photographs of skin affected by 198 disease states. See also: Paper Reference / Author Website
  • Derm7pt: Over 2,000 dermoscopic and clinical images of skin lesions, with 7-point checklist criteria and disease diagnosis annotated.

Program Schedule

Location: Monday, June 15th, 7:45-13:00 PDT, WWW

7:45: Opening Remarks (M. Emre Celebi) [Video]
8:00: Invited Talk 1: Computational Skin Texture (Kristin Dana) [Video]
8:30: Invited Talk 2: How to Advance Automated Computer-Aided Diagnostic System for Melanoma Detection (Tim K. Lee) [Video]
9:00: Invited Talk 3: 3D Total Body Photography and Change Detection (Doug Canfield) [Video]
9:30: Invited Talk 4: SkinVision: 21st Century Melanoma Screening with a Real Medical Device (Daniel Mark Siegel) [Video]
10:00: Accepted Paper Presentation Session [Workshop Proceedings]
Chairs: M. Emre Celebi, Noel C. F. Codella, Marc Combalia, Kristin Dana, Allan Halpern, Philipp Tschandl
  • 10:00 -- Illumination-Based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images. Kumar Abhishek (Simon Fraser University, Canada)*; Ghassan Hamarneh (Simon Fraser University, Canada); Mark S Drew (Simon Fraser University, Canada) [Paper] [Video] [Slides]
  • 10:12 -- Meta-DermDiagnosis: Few-Shot Skin Disease Identification using Meta-Learning. Kushagra Mahajan (TCS Research, India)*; Monika Sharma (TCS Research, India); Lovekesh Vig (TCS Research, India) [Paper] [Video] [Slides]
  • 10:24 -- On Out-of-Distribution Detection Algorithms with Deep Neural Skin Cancer Classifiers. Andre GC Pacheco (Federal University of Espírito Santo, Brazil)*; Chandramouli Sastry (Dalhousie University, Canada); Thomas Trappenberg (Dalhousie University, Canada); Sageev Oore (Dalhousie University, Canada); Renato Krohling (Federal University of Espírito Santo, Brazil) [Paper] [Video] [Slides]
  • 10:36 -- Interpreting Mechanisms of Prediction for Skin Cancer Diagnosis Using Multi-Task Learning. Davide Coppola (A*STAR, Singapore)*; Hwee Kuan Lee (A*STAR, Singapore); Cuntai Guan (Nanyang Technological University, Singapore) [Paper] [Video] [Slides]
  • 10:48 -- Agreement Between Saliency Maps and Human-Labeled Regions of Interest: Applications to Skin Disease Classification. Nalini M Singh (MIT, USA)*; Kang Lee (Google Research); David Coz (Google Research); Christof Angermueller (Google); Susan Huang (Advanced Clinical/Adecco Staffing); Aaron Loh (Google); Yuan Liu (Google) [Paper] [Video] [Slides]
  • 11:00 -- Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation. Vinicius Ribeiro (UNICAMP, Brazil)*; Sandra Avila (UNICAMP, Brazil); Eduardo Valle (UNICAMP, Brazil) [Paper] [Video] [Slides]
  • 11:12 -- Debiasing Skin Lesion Datasets and Models? Not So Fast. Alceu E Bissoto (UNICAMP, Brazil); Eduardo Valle (UNICAMP, Brazil); Sandra Avila (UNICAMP, Brazil)* [Paper] [Video] [Slides]
  • 11:24 -- How Important is Each Dermoscopy Image? Catarina Barata (IST, Portugal)*; Carlos Santiago (IST, Portugal) [Paper] [Video] [Slides]
  • 11:36 -- Uncertainty Estimation in Deep Neural Networks for Dermoscopic Image Classification. Marc Combalia (Hospital Clínic de Barcelona, Spain)*; Ferran Hueto (MIT, USA); Susana Puig (Hospital Clínic de Barcelona, Spain); Josep Malvehy (Hospital Clínic de Barcelona, Spain); Veronica Vilaplana (Technical University of Catalonia, Spain) [Paper] [Video] [Slides]
  • 11:48 -- Learning a Meta-Ensemble Technique for Skin Lesion Classification and Novel Class Detection. Subhranil Bagchi (Indian Institute of Technology Ropar, India)*; Anurag Banerjee (Indian Institute of Technology Ropar, India); Deepti Bathula (Indian Institute of Technology Ropar, India) [Paper] [Video] [Slides]
12:00: Q&A Session (Live via Zoom)
12:30: Closing Remarks (Kristin Dana)



Workshop Organizers:

Steering Committee:

Contact Email:

ISIC Skin Image Analysis Workshop
ISIC Skin Image Analysis Workshop