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
Veterinary Clinical Pathology · 2025
DOI: 10.1111/vcp.70056 ↗Kurz gefasst
Fachartikel in der Zeitschrift Veterinary Clinical Pathology, 2025. Verfasst von Christina Pacholec und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Sciences and Pathobiology, Virginia-Maryland College of Veterinary Medicine, Blacksburg, Virginia, USA. Hauptthemen laut MEDLINE: Dog Diseases, Lymph Nodes, Neural Networks, Computer, Lymphoma, Large B-Cell, Diffuse. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Morris Animal Foundation, American Kennel Club Canine Health Foundation, Virginia-Maryland College of Veterinary Medicine Veterinary Memorial Fund.
Abstract (Originalsprache)
Background
Lymph node (LN) aspirates are often obtained to distinguish large‐cell lymphoma (LCL) from non‐lymphoma (NL) in dogs with enlarged lymph nodes.
Objective
Images from cytology slides tested the effects of magnification, image type, and number on a convolutional neural network (CNN) differentiating canine LCL from NL.
Methods
Three hundred images of LCL and NL were used to train a CNN and interrogate the effects of image magnification, type, and number on the model's performance. Identified cases were imaged at 200×, 500×, and 1000× magnification in color and gray‐scale and then used to train and identify optimal magnification and image type. The impact of the image number per cohort (50, 100, 150, 200, 250, 300) on the top model's performance was then assessed.
Results
The highest performance with color images was achieved at 1000× magnification, with an accuracy of 95.8%, a Receiving Operating Characteristic (ROC) area of 0.997, and an F ‐measure of 0.958. Similarly, the best results with gray images, also at 1000× magnification, showed an accuracy of 96.67%, a ROC area of 0.994, and an F ‐measure of 0.967. Performance improvements were most significant and plateaued as the number of images per class approached 150, with an accuracy of 95%, ROC area of 0.939, and F ‐measure of 0.95.
Conclusion
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Sciences and Pathobiology, Virginia-Maryland College of Veterinary Medicine, Blacksburg, Virginia, USA.
ORCID-Profile: Christina Pacholec
Förderung
- Morris Animal Foundation
- American Kennel Club Canine Health Foundation
- Virginia-Maryland College of Veterinary Medicine Veterinary Memorial Fund
Zitieren
APA
Pacholec, C., Xie, H., Curnin, J., Lin, A., & Zimmerman, K. (2025). 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. Veterinary Clinical Pathology. https://doi.org/10.1111/vcp.70056
Vancouver
Pacholec C, Xie H, Curnin J, Lin A, Zimmerman K. 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. Veterinary Clinical Pathology. 2025. doi:10.1111/vcp.70056
BibTeX
@article{Pacholec2025,
author = {Pacholec, Christina and Xie, Hehuang and Curnin, Julianne and Lin, Amy and Zimmerman, Kurt},
title = {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},
journal = {Veterinary Clinical Pathology},
year = {2025},
doi = {10.1111/vcp.70056}
}
EUVIMED