Automated Ventricle Assessment via Three-dimensional Anatomical Reconstruction (AVA-TAR): a computational toolkit for autonomous lateral ventricle assessment in preclinical hydrocephalus models
This study introduces a deep learning tool for automated segmentation and morphological analysis of lateral ventricles in rodent MRIs. The tool's efficiency and accuracy in quantifying ventricle morphology offers significant utility in preclinical hydrocephalus research with potential future application in the clinical setting.
Authors
- Shelei Pan (ORCID: https://orcid.org/0000-0002-7318-1944)
- James D. Quirk (ORCID: https://orcid.org/0000-0002-6118-7097)
- Moe R. Mahjoub (ORCID: https://orcid.org/0000-0001-8129-7464)
- Grace L. Halupnik
- Owen W Limbrick
- Maneesha Pandey
- Sundeep Chakladar
- Jennifer M Strahle
- Annie Zhao
- Arash Nazeri
Institutions
- Washington University in St. Louis (US)
- Mallinckrodt (United States) (US)
Publication Details
- Journal
- bioRxiv (Cold Spring Harbor Laboratory)
- Published
- 2026-02-05
- DOI
- https://doi.org/10.64898/2026.02.02.703412
- Primary Topic
- Cerebrospinal fluid and hydrocephalus
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Rudi Schulte Research Institute
- National Institutes of Health