English

Domain-Specific Foundation Model Improves AI-Based Analysis of Neuropathology

Computer Vision and Pattern Recognition 2025-12-09 v1 Artificial Intelligence

Abstract

Foundation models have transformed computational pathology by providing generalizable representations from large-scale histology datasets. However, existing models are predominantly trained on surgical pathology data, which is enriched for non-nervous tissue and overrepresents neoplastic, inflammatory, metabolic, and other non-neurological diseases. Neuropathology represents a markedly different domain of histopathology, characterized by unique cell types (neurons, glia, etc.), distinct cytoarchitecture, and disease-specific pathological features including neurofibrillary tangles, amyloid plaques, Lewy bodies, and pattern-specific neurodegeneration. This domain mismatch may limit the ability of general-purpose foundation models to capture the morphological patterns critical for interpreting neurodegenerative diseases such as Alzheimer's disease, Parkinson's disease, and cerebellar ataxias. To address this gap, we developed NeuroFM, a foundation model trained specifically on whole-slide images of brain tissue spanning diverse neurodegenerative pathologies. NeuroFM demonstrates superior performance compared to general-purpose models across multiple neuropathology-specific downstream tasks, including mixed dementia disease classification, hippocampal region segmentation, and neurodegenerative ataxia identification encompassing cerebellar essential tremor and spinocerebellar ataxia subtypes. This work establishes that domain-specialized foundation models trained on brain tissue can better capture neuropathology-specific features than models trained on general surgical pathology datasets. By tailoring foundation models to the unique morphological landscape of neurodegenerative diseases, NeuroFM enables more accurate and reliable AI-based analysis for brain disease diagnosis and research, setting a precedent for domain-specific model development in specialized areas of digital pathology.

Keywords

Cite

@article{arxiv.2512.05993,
  title  = {Domain-Specific Foundation Model Improves AI-Based Analysis of Neuropathology},
  author = {Ruchika Verma and Shrishtee Kandoi and Robina Afzal and Shengjia Chen and Jannes Jegminat and Michael W. Karlovich and Melissa Umphlett and Timothy E. Richardson and Kevin Clare and Quazi Hossain and Jorge Samanamud and Phyllis L. Faust and Elan D. Louis and Ann C. McKee and Thor D. Stein and Jonathan D. Cherry and Jesse Mez and Anya C. McGoldrick and Dalilah D. Quintana Mora and Melissa J. Nirenberg and Ruth H. Walker and Yolfrankcis Mendez and Susan Morgello and Dennis W. Dickson and Melissa E. Murray and Carlos Cordon-Cardo and Nadejda M. Tsankova and Jamie M. Walker and Diana K. Dangoor and Stephanie McQuillan and Emma L. Thorn and Claudia De Sanctis and Shuying Li and Thomas J. Fuchs and Kurt Farrell and John F. Crary and Gabriele Campanella},
  journal= {arXiv preprint arXiv:2512.05993},
  year   = {2025}
}