Features of image analysis under UV-video dermoscopy

2020

Closed access Metadata (CSL-JSON)
DOI 10.1117/12.2569774
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The work is devoted to the modern method of diagnosing skin diseases - video dermoscopy in the ultraviolet spectrum. The main features of the method are considered. The features of image processing and analysis for HC-video dermatoscopy are proposed for consideration. The main stages of processing HC-video dermoscopic images are considered. The main emphasis is placed on the methods of automated segmentation of HC-videodermoscopic images and the analysis of the errors that arise in this case. The stages of preliminary and post-processing of UVvideodermoscopic images are examined in detail. The main aspects of the automated analysis of dermoscopic image processing and the prospects of using such systems in medical practice are considered.