EUVIMEDEUVIMED entdecken
Crossref

Transforming Medical Laboratory Science with Vision-Language Models: A Focus on Microscopy in Microbiology, Hematology, and Histopathology

Okoroafor Dorcas Okayo, Nanmet Ephraim Panwal, Okeoma Obiageri Ihuarulam, Markus Saerimam Nzunde, Franca Aminci Nyimwadang, Tosin Ayodeji Oladosu, Adesuwa Benedicta Osunde.

Oncology, Nuclear Medicine and Transplantology · 2025

DOI: 10.63946/onmt/17316 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Oncology, Nuclear Medicine and Transplantology, 2025. Verfasst von Okoroafor Dorcas Okayo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in artificial intelligence—particularly Vision–Language Models (VLMs)—offer promising avenues for enhancing microscopic diagnostics. This review synthesizes the current landscape of VLM applications across microbiology, hematology, cytology, and histopathology, spanning tasks such as Gram stain classification, cell-type recognition, feature localization, captioning, and report drafting. We outline how VLMs integrate visual features with domain-specific prompts to support triage, decision support, and quality control, while highlighting opportunities for few-shot and zero-shot generalization to rare findings. In parallel, we compare conventional convolutional pipelines with VLM-enhanced workflows, emphasizing gains in scalability, reproducibility, and explainability through multimodal rationales and grounded visual evidence. Key challenges include data curation and harmonization across laboratories, domain shift from variable staining and optics, bias and safety risks, limited task-relevant benchmarks, and the need for rigorous human-in-the-loop evaluation in clinical contexts. We propose a practical roadmap for deployment—covering dataset governance, prompt and template standardization, uncertainty reporting, and audit trails—alongside research priorities in robust evaluation, privacy-preserving learning, and alignment with clinical guidelines. Overall, VLMs are poised to complement expert microscopy by accelerating routine workflows and improving documentation, provided their adoption is guided by transparent validation and fit-for-purpose governance.

Zitieren

APA

Okayo, O. D., Panwal, N. E., Ihuarulam, O. O., Nzunde, M. S., Nyimwadang, F. A., Oladosu, T. A., & Osunde., A. B. (2025). Transforming Medical Laboratory Science with Vision-Language Models: A Focus on Microscopy in Microbiology, Hematology, and Histopathology. Oncology, Nuclear Medicine and Transplantology. https://doi.org/10.63946/onmt/17316

Vancouver

Okayo OD, Panwal NE, Ihuarulam OO, Nzunde MS, Nyimwadang FA, Oladosu TA, et al. Transforming Medical Laboratory Science with Vision-Language Models: A Focus on Microscopy in Microbiology, Hematology, and Histopathology. Oncology, Nuclear Medicine and Transplantology. 2025. doi:10.63946/onmt/17316

BibTeX
@article{Okayo2025,
  author = {Okayo, Okoroafor Dorcas and Panwal, Nanmet Ephraim and Ihuarulam, Okeoma Obiageri and Nzunde, Markus Saerimam and Nyimwadang, Franca Aminci and Oladosu, Tosin Ayodeji and Osunde., Adesuwa Benedicta},
  title = {Transforming Medical Laboratory Science with Vision-Language Models: A Focus on Microscopy in Microbiology, Hematology, and Histopathology},
  journal = {Oncology, Nuclear Medicine and Transplantology},
  year = {2025},
  doi = {10.63946/onmt/17316}
}
Kostenlos starten →