EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Low-Cost Lung Cancer Classification in WSIs Using a Foundation Model and Evolving Prototypes

Soroush Oskouei, André Pedersen, Marit Valla, Vibeke Grotnes Dale, Sissel Gyrid Freim Wahl, Mats Dehli Haugum, Borgny Ytterhus, Maria Paula Ramnefjell, Lars Andreas Akslen, Gabriel Kiss, Hanne Sorger

Algorithms · 06.12.2025 · 18 (12) · 769

DOI: 10.3390/a18120769 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 06.12.2025. Verfasst von Soroush Oskouei und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Liaison Committee for Education, Research, and Innovation in Central Norway, Research Council of Norway.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Whole slide imaging has transformed the field of pathology by enabling high-resolution digitization of histopathological slides. However, the large image size and variability in morphology, tissue processing, and imaging can pose challenges for robust computational analysis. When working with specific tasks in digital pathology, conventional feature extractors pretrained on general images may not provide features as relevant as those trained on histopathological images. To address this, foundation models pretrained on histopathological images have been developed. Yet, their large size and computational demands might limit widespread adoptions to specific tasks. To facilitate the low-cost adoption of these models, we utilized low-rank adaptation for finetuning the model and developed evolving prototype-based multiple instance learning (EP-MIL). Our method’s capabilities were demonstrated by applying it to the classification of two histological subtypes of lung cancer. The results show that our approach achieves competitive performance when benchmarked against a state-of-the-art technique (CLAM), while offering improvements in efficiency. Specifically, our proposed method requires 8.3 times less training runtime compared with CLAM, uses less than 200.0 MB of memory during training, and enables 73.8 times faster inference runtime. These efficiency gains, combined with competitive performance, suggest that utilizing evolving prototypes with LoRA-tuned foundation models offers a more efficient and practical approach for broader use of foundation models in resource-constrained clinical settings.

Förderung

  • The Liaison Committee for Education, Research, and Innovation in Central Norway
  • Research Council of Norway

Zitieren

APA

Oskouei, S., Pedersen, A., Valla, M., Dale, V. G., Wahl, S. G. F., Haugum, M. D., Ytterhus, B., Ramnefjell, M. P., Akslen, L. A., Kiss, G., & Sorger, H. (2025). Low-Cost Lung Cancer Classification in WSIs Using a Foundation Model and Evolving Prototypes. Algorithms, 18(12), 769. https://doi.org/10.3390/a18120769

Vancouver

Oskouei S, Pedersen A, Valla M, Dale VG, Wahl SGF, Haugum MD, et al. Low-Cost Lung Cancer Classification in WSIs Using a Foundation Model and Evolving Prototypes. Algorithms. 2025;18(12):769. doi:10.3390/a18120769

BibTeX
@article{Oskouei2025,
  author = {Oskouei, Soroush and Pedersen, André and Valla, Marit and Dale, Vibeke Grotnes and Wahl, Sissel Gyrid Freim and Haugum, Mats Dehli and Ytterhus, Borgny and Ramnefjell, Maria Paula and Akslen, Lars Andreas and Kiss, Gabriel and Sorger, Hanne},
  title = {Low-Cost Lung Cancer Classification in WSIs Using a Foundation Model and Evolving Prototypes},
  journal = {Algorithms},
  year = {2025},
  volume = {18},
  number = {12},
  pages = {769},
  doi = {10.3390/a18120769}
}
Kostenlos starten →