Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2512.05993 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908695337631744 |
|---|---|
| author | Verma, Ruchika Kandoi, Shrishtee Afzal, Robina Chen, Shengjia Jegminat, Jannes Karlovich, Michael W. Umphlett, Melissa Richardson, Timothy E. Clare, Kevin Hossain, Quazi Samanamud, Jorge Faust, Phyllis L. Louis, Elan D. McKee, Ann C. Stein, Thor D. Cherry, Jonathan D. Mez, Jesse McGoldrick, Anya C. Mora, Dalilah D. Quintana Nirenberg, Melissa J. Walker, Ruth H. Mendez, Yolfrankcis Morgello, Susan Dickson, Dennis W. Murray, Melissa E. Cordon-Cardo, Carlos Tsankova, Nadejda M. Walker, Jamie M. Dangoor, Diana K. McQuillan, Stephanie Thorn, Emma L. De Sanctis, Claudia Li, Shuying Fuchs, Thomas J. Farrell, Kurt Crary, John F. Campanella, Gabriele |
| author_facet | Verma, Ruchika Kandoi, Shrishtee Afzal, Robina Chen, Shengjia Jegminat, Jannes Karlovich, Michael W. Umphlett, Melissa Richardson, Timothy E. Clare, Kevin Hossain, Quazi Samanamud, Jorge Faust, Phyllis L. Louis, Elan D. McKee, Ann C. Stein, Thor D. Cherry, Jonathan D. Mez, Jesse McGoldrick, Anya C. Mora, Dalilah D. Quintana Nirenberg, Melissa J. Walker, Ruth H. Mendez, Yolfrankcis Morgello, Susan Dickson, Dennis W. Murray, Melissa E. Cordon-Cardo, Carlos Tsankova, Nadejda M. Walker, Jamie M. Dangoor, Diana K. McQuillan, Stephanie Thorn, Emma L. De Sanctis, Claudia Li, Shuying Fuchs, Thomas J. Farrell, Kurt Crary, John F. Campanella, Gabriele |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05993 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Domain-Specific Foundation Model Improves AI-Based Analysis of Neuropathology Verma, Ruchika Kandoi, Shrishtee Afzal, Robina Chen, Shengjia Jegminat, Jannes Karlovich, Michael W. Umphlett, Melissa Richardson, Timothy E. Clare, Kevin Hossain, Quazi Samanamud, Jorge Faust, Phyllis L. Louis, Elan D. McKee, Ann C. Stein, Thor D. Cherry, Jonathan D. Mez, Jesse McGoldrick, Anya C. Mora, Dalilah D. Quintana Nirenberg, Melissa J. Walker, Ruth H. Mendez, Yolfrankcis Morgello, Susan Dickson, Dennis W. Murray, Melissa E. Cordon-Cardo, Carlos Tsankova, Nadejda M. Walker, Jamie M. Dangoor, Diana K. McQuillan, Stephanie Thorn, Emma L. De Sanctis, Claudia Li, Shuying Fuchs, Thomas J. Farrell, Kurt Crary, John F. Campanella, Gabriele Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Domain-Specific Foundation Model Improves AI-Based Analysis of Neuropathology |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.05993 |