Przegląd Dermatologiczny
facebook
eISSN: 2084-9893
ISSN: 0033-2526
Dermatology Review/Przegląd Dermatologiczny
Bieżący numer Archiwum Artykuły zaakceptowane O czasopiśmie Zeszyty specjalne Rada naukowa Bazy indeksacyjne Prenumerata Kontakt Zasady publikacji prac Standardy etyczne i procedury
Panel Redakcyjny
Zgłaszanie i recenzowanie prac online
SCImago Journal & Country Rank
1/2025
vol. 112
 
Poleć ten artykuł:
Udostępnij:
streszczenie artykułu:
Opis przypadku

Use of Machine Learning Tools for Post-Processing of Digital Dermoscopic Images: a Case Series

Marian Voloshynovych
1, 2
,
Tetiana Boychuk
2
,
Iryna Blaha
1, 2
,
Oleksandr Berezkin
3
,
Natalia Matkovska
4
,
Volodymyr Voloshynovych
5

  1. Department of Dermatology and Venereology, Ivano-Frankivsk National Medical University, Ivano-Frankivsk, Ukraine
  2. Lux Skin, Ivano-Frankivsk, Ukraine
  3. Bogomolets dermpathlab, Kyiv, Ukraine
  4. Department of Therapy, Family and Emergency Medicine of Postgraduate Education, Ivano-Frankivsk National Medical University, Ivano-Frankivsk, Ukraine
  5. Department of Forensic Medicine, Medical and Pharmaceutical Law, Ivano-Frankivsk National Medical University, Ivano-Frankivsk, Ukraine
Dermatol Rev/Przegl Dermatol 2025, 112, 59-63
Data publikacji online: 2025/05/20
Pełna treść artykułu Pobierz cytowanie
 
Metryki PlumX:


The use of electronic photographic recording has greatly facilitated the process of photo post-processing. Digital camera-based fixation enables extensive manipulation of captured images, potentially uncovering diagnostically relevant features and improving the visualization of dermoscopic structures.

This article aims to illustrate the potential utility of digital image post-processing in selected diagnostic contexts. A series of clinical dermoscopic images are presented, demonstrating pre- and post-processing comparisons, with annotated regions highlighting key diagnostic structures.

Digital post-processing may offer diagnostic support in certain cases, particularly when used in conjunction with artificial intelligence and machine learning algorithms, which facilitate analysis with minimal user intervention. However, validation of the diagnostic reliability of post-processed images necessitates multicenter, retrospective comparative studies.


© 2025 Termedia Sp. z o.o.
Developed by Bentus.