Impact of Magnification, Image Type, and Number on Convolutional Neural Network Performance in Differentiating Canine Large Cell Lymphoma From Non‐Lymphoma via Lymph Node Cytology
The analysis across models suggests that color versus greyscale did not significantly impact overall performance to distinguish LCL or NL. Optimal magnification was 1000×. A minimum of 150 images per class is recommended for pilot CNN studies in this 2-class problem.
Authors
- Kathy Zimmerman (ORCID: https://orcid.org/0000-0002-8899-2301)
- Amy Lin (ORCID: https://orcid.org/0000-0001-9783-1270)
- Hehuang Xie (ORCID: https://orcid.org/0000-0001-5739-1653)
- Christina Pacholec (ORCID: https://orcid.org/0000-0002-0535-1569)
- Julianne Curnin
Institutions
- Virginia–Maryland College of Veterinary Medicine (US)
Publication Details
- Journal
- Veterinary Clinical Pathology
- Published
- 2025-09-22
- DOI
- https://doi.org/10.1111/vcp.70056
- Citations
- 2
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- American Kennel Club Canine Health Foundation
- Virginia-Maryland College of Veterinary Medicine