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
Related Experiment Video
Updated: Jan 17, 2026
Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma
Published on: January 9, 2019
Christina Pacholec1, Hehuang Xie1, Julianne Curnin1
1Department of Biomedical Sciences and Pathobiology, Virginia-Maryland College of Veterinary Medicine, Blacksburg, Virginia, USA.
Insights
This study shows that 1000× magnification and at least 150 images are optimal for convolutional neural networks (CNNs) to accurately diagnose canine large-cell lymphoma (LCL) from lymph node aspirates. Image color did not significantly impact diagnostic performance.
Area of Science:
- Veterinary Pathology
- Machine Learning in Diagnostics
- Canine Oncology
Background:
- Lymph node aspirates are crucial for differentiating canine large-cell lymphoma (LCL) from non-lymphoma (NL).
- Accurate diagnosis is essential for appropriate treatment of canine lymphoma.
Purpose of the Study:
- To evaluate the impact of image magnification, type, and number on a convolutional neural network (CNN) for diagnosing canine LCL.
- To determine optimal parameters for CNN-based canine lymphoma diagnosis using cytology images.
Main Methods:
- A CNN was trained using 300 canine lymph node aspirate images (LCL and NL).
- Images were acquired at 200×, 500×, and 1000× magnification in color and grayscale.
- The effect of image number per class (50-300) on CNN performance was assessed.
Main Results:
- Optimal performance was achieved at 1000× magnification for both color (95.8% accuracy) and grayscale (96.67% accuracy) images.
- CNN performance significantly improved and plateaued around 150 images per class.
- Color versus grayscale image type did not substantially affect diagnostic accuracy.
Conclusions:
- 1000× magnification is optimal for CNN-based differentiation of canine LCL from NL.
- A minimum of 150 images per class is recommended for initial CNN studies in this diagnostic task.
- CNNs show promise for improving the accuracy and efficiency of canine lymphoma diagnosis.
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.
