Predicting Ethanol Drinking Status from Nonhuman Primate Liver Histology: A Proof of Concept for Parameter-efficient Fine-tuning in Few-Shot Vision-Language Modeling
Combining vision-language models (VLMs) with parameter-efficient fine-tuning (PEFT) offers a promising approach to few-shot whole-slide image (WSI) classification in computational pathology. This study evaluates this approach for predicting ethanol drinking status from nonhuman primate liver histology. Adapters are evaluated against non-PEFT configurations on a subset of the Monkey Alcohol Tissue Research Resource (MATRR). All evaluated PEFT configurations achieve higher mean balanced accuracy than the non-PEFT baselines. For example, in the four-shot setting, attention-based multiple instance learning (ABMIL) alone achieves 43.5% mean balanced accuracy, compared with 78.1% after adding an adapter. Qualitative attention analysis shows that textual pathway adaptations produce localized attention heatmaps, while visual pathway adaptations produce more diffuse ones. A pathologist's review identified similar histological features across adaptations.
Authors
- Mary Lauren Benton (ORCID: https://orcid.org/0000-0002-5485-1041)
- Kathleen A. Grant (ORCID: https://orcid.org/0000-0002-0380-7219)
- Amirmohammad Mohammadi (ORCID: https://orcid.org/0000-0002-7558-1706)
- Rupak Khadka (ORCID: https://orcid.org/0009-0003-7838-450X)
- Joshua Peeples
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-12
- DOI
- https://doi.org/10.48550/arxiv.2611.17105
- Primary Topic
- AI in cancer detection
- Type
- preprint