Related Experiment Video
Updated: Jun 10, 2025
Intravital Imaging of Intraepithelial Lymphocytes in Murine Small Intestine
Published on: June 24, 2019
Artificial intelligence-based quantification of lymphocytes in feline small intestinal biopsies
Judit M Wulcan1, Paula R Giaretta2, Sai Fingerhood3
1University of California, Davis, Davis, CA.
Insights
An artificial intelligence (AI) model was developed to quantify feline intestinal lymphocytes, improving diagnostic accuracy for chronic enteropathy (CE). This AI tool offers a reproducible, objective assessment, enhancing consistency in diagnosing this complex feline condition.
Area of Science:
- Veterinary Pathology
- Computational Pathology
- Feline Medicine
Background:
- Feline chronic enteropathy (CE) is a complex gastrointestinal disease in cats.
- Accurate histological classification of CE relies on quantifying lymphocytes in small intestinal biopsies.
- Current histological methods suffer from low interobserver agreement, impacting diagnostic reliability.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI) model for detecting and quantifying intraepithelial and lamina propria lymphocytes.
- To assess the AI model's performance against veterinary pathologists' assessments.
- To evaluate the AI model's potential to improve diagnostic consistency for feline CE.
Main Methods:
- Development of an AI model using hematoxylin and eosin-stained small intestinal biopsies from cats.
- Validation of the AI model by comparing its performance (sensitivity, positive predictive value, F1 score) against the consensus of 11 veterinary pathologists.
- Analysis of AI-derived lymphocyte counts and their correlation with semiquantitative grading.
Main Results:
- The AI model demonstrated high median sensitivity for both intraepithelial (100%) and lamina propria (89%) lymphocytes.
- Median F1 scores were 67% for intraepithelial and 70% for lamina propria lymphocytes.
- The AI model showed potential in overcoming the low interobserver agreement observed in traditional semiquantitative grading.
Conclusions:
- The AI model provides a reproducible, objective, and quantitative method for assessing feline intestinal lymphocytes.
- Supervised by a pathologist, the AI model can enhance diagnostic accuracy and consistency in feline chronic enteropathy.
- This AI approach addresses the limitations of conventional histological grading for CE.
Abstract:
Feline chronic enteropathy is a poorly defined condition of older cats that encompasses chronic enteritis to low-grade intestinal lymphoma. The histological evaluation of lymphocyte numbers and distribution in small intestinal biopsies is crucial for classification and grading. However, conventional histological methods for lymphocyte quantification have low interobserver agreement, resulting in low diagnostic reliability. This study aimed to develop and validate an artificial intelligence (AI) model to detect intraepithelial and lamina propria lymphocytes in hematoxylin and eosin-stained small intestinal biopsies from cats. The median sensitivity, positive predictive value, and F1 score of the AI model compared with the majority opinion of 11 veterinary anatomic pathologists, were 100% (interquartile range [IQR] 67%-100%), 57% (IQR 38%-83%), and 67% (IQR 43%-80%) for intraepithelial lymphocytes, and 89% (IQR 71%-100%), 67% (IQR 50%-82%), and 70% (IQR 43%-80%) for lamina propria lymphocytes, respectively. Errors included false negatives in whole-slide images with faded stain and false positives in misidentifying enterocyte nuclei. Semiquantitative grading at the whole-slide level showed low interobserver agreement among pathologists, underscoring the need for a reproducible quantitative approach. While semiquantitative grade and AI-derived lymphocyte counts correlated positively, the AI-derived lymphocyte counts overlapped between different grades. Our AI model, when supervised by a pathologist, offers a reproducible, objective, and quantitative assessment of feline intestinal lymphocytes at the whole-slide level, and has the potential to enhance diagnostic accuracy and consistency for feline chronic enteropathy.
