Challenges of automatic processing of large amount of skin lesion multispectral data

I. Lihacova, E. Cibulska, A. Lihachev, M. Lange, E. V. Plorina, D. Bliznuks, A. Derjabo, N. Kiss

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work will describe the challenges involved in setting up automatic processing for a large differentiated data set. In this study, a multispectral (skin diffuse reflection images using 526nm (green), 663nm (red), and 964nm (infrared) illumination and autofluorescence (AF) image using 405 nm excitation) data set with 756 lesions (3024 images) was processed. Previously, using MATLAB software, finding markers, correctly segmenting images with dark edges and image alignment were the main causes of the problems in automatic data processing. To improve automatic processing and eliminate the use of licensed software, the latter was substituted with the open source Python environment. For more precise segmentation of skin markers and skin lesions, as well for image alignment, the processing of artificial neural networks was utilized. The resulting processing method solves most of the issues of the MATLAB script. However, for even more accurate results, it is necessary to provide more accurate ground-truth segmentation masks and generate more input data to increase the training image database by using data augmentation.

Original languageEnglish
Title of host publicationBiophotonics - Riga 2020
EditorsJanis Spigulis
PublisherSPIE
ISBN (Electronic)9781510639997
DOIs
Publication statusPublished - 2020
Externally publishedYes
EventBiophotonics - Riga 2020 - Riga, Latvia
Duration: 24 Aug 202025 Aug 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11585
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceBiophotonics - Riga 2020
Country/TerritoryLatvia
CityRiga
Period24/08/2025/08/20

Keywords*

  • artificial neural networks
  • multispectral melanoma diagnostics
  • skin lesion segmentation

Field of Science*

  • 3.2 Clinical medicine
  • 1.3 Physical sciences

Publication Type*

  • 3.1. Articles or chapters in proceedings/scientific books indexed in Web of Science and/or Scopus database

Fingerprint

Dive into the research topics of 'Challenges of automatic processing of large amount of skin lesion multispectral data'. Together they form a unique fingerprint.

Cite this