Künstliche Intelligenz in der ex‑vivo konfokalen Laserscanmikroskopie

Hartmann, Daniela (2021): Künstliche Intelligenz in der ex‑vivo konfokalen Laserscanmikroskopie. In: Hautarzt, Bd. 72, Nr. 12: S. 1066-1070

Abstract

Background Visual data, such as clinical photographs or pictures from imaging examination methods, such as ex vivo confocal laser scanning microscopy (CLSM), are particularly suitable for machine learning techniques. Objectives The aim was to find out whether data have already been published on this innovative application in ex vivo CLSM and what potential challenges and limitations could arise. Material and methods Review of the literature and summary of current knowledge and personal experience on the use of artificial intelligence (AI) in ex vivo CLSM. Results Successful integration of digital hematoxylin-eosin-like staining has made ex vivo CLSM significantly more accessible for digital assessments. Several machine learning techniques have been developed to date in such a way that they have been able to identify malignant skin lesions on clinical photographs and pathological microscopic images with similar accuracy compared to experts, or even find visual patterns that have been overlooked by experts and that correlate with certain dermatological diseases. One study on the use of AI in ex vivo CLSM for automated tumor detection has been published to date. Several challenges and limitations can arise when using AI in ex vivo CLSM. Conclusions The already digitized ex vivo CLSM, which was established for rapid section examination purposes, is a predestined method for the development and use of new applications with machine learning in the healthcare sector. The results of further studies on this topic are anticipated with great hope.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Medizin
• Themengebiete: 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISSN: 0017-8470
• Sprache: Deutsch