ISIC project

From dermoscopedia

0.00
(0 votes)
Annotations
Description This page has not yet been summarized.
Author(s) Ofer Reiter
Owner Ash Marghoob→ send e-mail
Status released
Status update August 13, 2018
Status by Ralph P. Braun


User=

The International Skin Imaging Collaboration (ISIC) is a combined academia and industry effort aimed at improving melanomaThis glossary term has not yet been described. diagnoses and reducing melanoma mortality by facilitating the application of digital skin imaging technologies.

Standardization of DermoscopyThe examination of [skin lesions] with a 'dermatoscope'. This traditionally consists of a magnifier (typically x10), a non-polarised light source, a transparent plate and a liquid medium between the instrument and the skin, and allows inspection of skin lesions unobstructed by skin surface reflections. Modern dermatoscopes dispense with the use of liquid medium and instead use polarised light to cancel out skin surface reflections.

Sponsored by the International Society for Digital Imaging of the Skin (ISDIS), ISIC working groups are developing proposed standards to address the technologies, techniques, and terminology used in skin imaging with special attention to the issues of privacy and interoperability (i.e., the ability to share imagesA representation of a person, animal or thing, photographed, painted or otherwise made visible. across technology and clinical platforms). Some of the articles published by the groups include Standardization of terminology in dermoscopyThe examination of [skin lesions] with a 'dermatoscope'. This traditionally consists of a magnifier (typically x10), a non-polarised light source, a transparent plate and a liquid medium between the instrument and the skin, and allows inspection of skin lesions unobstructed by skin surface reflections. Modern dermatoscopes dispense with the use of liquid medium and instead use polarised light to cancel out skin surface reflections./dermatoscopyThe examination of [skin lesions] with a 'dermatoscope'. This traditionally consists of a magnifier (typically x10), a non-polarised light source, a transparent plate and a liquid medium between the instrument and the skin, and allows inspection of skin lesions unobstructed by skin surface reflections. Modern dermatoscopes dispense with the use of liquid medium and instead use polarised light to cancel out skin surface reflections. [1] in 2016 and Technique Standards for Skin Lesion Imaging [2] in 2017.

ISIC archive

In addition, ISIC has developed and is expanding a public archive containing the largest publicly available collection of quality controlled dermoscopic images of skin lesions. Presently, the ISIC Archive contains over 23,500 dermoscopic images, which were collected from leading clinical centers across the globe and acquired from a variety of devices within each center. Broad international participation in image contribution is intended to insure a representative, clinically relevant sample.

All incoming images to the ISIC Archive are screened for both privacy and quality assurance. Most images have associated clinical metadataData or information that provides information about other data., which has been vetted by recognized melanoma experts.

A subset of the images has undergone annotation and markup by recognized skin cancerThis glossary term has not yet been described. experts. These markups include dermoscopic features (i.e., global and focal morphologic elements in the image known to discriminate between types of skin lesions).

All images on ISIC are available for everyone to access and to use for teaching purposes. In addition, ISIC is now linked to dermoscopediaDermoscopedia is the name of this website and is providing state of knowledge information concerning dermoscopy - a non invasive diagnostic method.. ImagesA representation of a person, animal or thing, photographed, painted or otherwise made visible. from dermoscopedia are uploaded to ISICISIC stands for the International Skin Imaging Collaboration project., and images from ISIC are available for use in dermoscopedia website.

The software infrastructure of the ISIC archive is based on the open-source Girder platform, and the source code for the Archive itself is freely available on GitHub.

Machine Learning Challenges

Since 2016, the ISIC Project has conducted an annual challenge for developers of artificial intelligenceThis glossary term has not yet been described. (AI) algorithms in the diagnosisis the identification of the nature and cause of a certain phenomenon. Diagnosis is used in many different disciplines with variations in the use of logic, analytics, and experience to determine "cause and effect". In systems engineering and computer science, it is typically used to determine the causes of symptoms, mitigations, and solutions of melanoma. In the first step of each challenge, a ‘training set’ of ISIC images matched to their diagnosis is used to train the algorithms. In the second stage, a ‘testThis glossary term has not yet been described. set’ of ISIC images is used to evaluate the algorithms’ diagnostic accuracyThis glossary term has not yet been described. and to compare the result with dermatologists’ diagnostic accuracy. Each year the challenges include more participants, more images, and more lesion types – While the 2016 challenge included only melanomas and pigmented neviThis glossary term has not yet been described., the 2017 included melanomas, pigmented nevi, and seborrheic keratosesThis glossary term has not yet been described., and the 2018 challenge includeded 8 different lesion types.

The 2016 challenge included 900 images in the ‘training’ set and 350 images in the ‘test’ set. The dermoscopic features that were examined were only globules and streakslines radial (always at periphery) streaks Reed nevus melanoma recurrent nevus. The average sensitivityThis glossary term has not yet been described. and specificityThis glossary term has not yet been described. of dermatologists in classifying pigmented lesions was 82 % and 59 %, respectively. At 82 % sensitivity, dermatologist specificity was similar to the top individual algorithmIn mathematics and computer science, an algorithm (Listeni/ˈælɡərɪðəm/ AL-gə-ri-dhəm) is a self-contained sequence of actions to be performed. Algorithms can perform calculation, data processing and automated reasoning tasks. (59 % vs. 62 %, P = .68) but lower than the best-performing fusion algorithm (a fusion of 16 automated predictions from the 25 participating teams, including both non-learned and machine-learning methods) that had a specificity of 76 % (P = .02) [3].

The 2017 challenge included 2000 images in the ‘training’ set and 600 images in the ‘test’ set. The dermoscopic features that were examined were pigment networkGrid-like pattern consisting of interconnecting pigmented lines surrounding hypopigmented holes., negative networkSerpiginous interconnecting broadened hypopigmented lines that surround elongated and curvilinear globules., streaks and mili-like cysts. The specificity achieved by the top algorithm for melanoma diagnosis at a sensitivity level of 82% was 74.7%. Results of the dermatologists’ sensitivity and specificity will be published soon.

The 2018 challenge includes 2594 images in the ‘training’ set and 1000 images in the ‘test’ set. It is still ongoing and will hopefully include several hundred participating dermatologists who will ‘compete’ with AI algorithms in accurately diagnosing pigmented skin lesions.



ReferencesThis is material contained in a footnote or bibliography holding further information.
  1. Kittler et al.: Standardization of terminology in dermoscopy/dermatoscopy: Results of the third consensus conference of the International Society of Dermoscopy. J. Am. Acad. Dermatol. 2016;74:1093-106. PMID: 26896294. DOI.
  2. Katragadda et al.: Technique Standards for Skin Lesion ImagingThis glossary term has not yet been described.: A Delphi Consensus Statement. JAMA Dermatol 2016;. PMID: 27892996. DOI.
  3. Marchetti et al.: Results of the 2016 International Skin Imaging CollaborationThis glossary term has not yet been described. International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J. Am. Acad. Dermatol. 2018;78:270-277.e1. PMID: 28969863. DOI.