Application of multimodal large language models for HER2/CEN17 FISH signal detection
Computer Methods and Programs in Biomedicine · 2026-10 · 285 · 109462
DOI: 10.1016/j.cmpb.2026.109462 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2026-10. Verfasst von Kamil Stanisław Fryszkowski und 1 weiteren Autor:innen. Beteiligte Einrichtung: Warsaw University of Technology, Plac Politechniki 1, Warsaw, 00-661, Poland. Electronic address: kamil.fryszkowski.stud@pw.edu.pl. Hauptthemen laut MEDLINE: In Situ Hybridization, Fluorescence, Erb-b2 Receptor Tyrosine Kinases. Die Arbeit nennt 23 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND AND OBJECTIVE Fluorescence in situ hybridisation (FISH) is a reference technique for HER2 gene amplification assessment, yet manual signal counting is labour-intensive and subject to inter-observer variability. This study evaluates the zero and few-shot capability of multimodal large language models for automatic counting of HER2 and CEN17 signals in single-nucleus images. METHODS A data set of 240 nuclei, categorised by difficulty (simple, complex, and cluster), was extracted from clinical slides acquired at 100× magnification. Three models-Gemini 2.5 Pro, GPT-5, and Claude Sonnet 4.5 were tested using natural language prompts. In the main evaluation setting on original colour images, Gemini 2.5 Pro outperformed the others, achieving a mean absolute error (MAE) of 0.47 signals for simple nuclei and 0.92 for complex cases. RESULTS The model demonstrated high consistency across repeated runs (median absolute deviation of 0.22) and relied heavily on colour information, as the aggregated MAE worsened to 1.60 on greyscale inputs. Bland-Altman analysis revealed a systematic overcounting bias of 0.39 signals (p
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Warsaw University of Technology, Plac Politechniki 1, Warsaw, 00-661, Poland. Electronic address: kamil.fryszkowski.stud@pw.edu.pl.
- Warsaw University of Technology, Plac Politechniki 1, Warsaw, 00-661, Poland. Electronic address: tomasz.les@pw.edu.pl.
Zitieren
APA
Fryszkowski, K. S., & Les, T. (2026). Application of multimodal large language models for HER2/CEN17 FISH signal detection. Computer Methods and Programs in Biomedicine, 285, 109462. https://doi.org/10.1016/j.cmpb.2026.109462
Vancouver
Fryszkowski KS, Les T. Application of multimodal large language models for HER2/CEN17 FISH signal detection. Computer Methods and Programs in Biomedicine. 2026;285:109462. doi:10.1016/j.cmpb.2026.109462
BibTeX
@article{Fryszkowski2026,
author = {Fryszkowski, Kamil Stanisław and Les, Tomasz},
title = {Application of multimodal large language models for HER2/CEN17 FISH signal detection},
journal = {Computer Methods and Programs in Biomedicine},
year = {2026},
volume = {285},
pages = {109462},
doi = {10.1016/j.cmpb.2026.109462}
}
EUVIMED