Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Moral distress and quality of nursing work life: Mediating roles of compassion fatigue and resilience.

Nursing ethics·2026

Same author

Changes in Health Care Utilization and Costs During the 2024 Medical Strike in Korea: Evidence From a Specialty-Level Analysis.

Asia-Pacific journal of public health·2026

Same author

Surgical Ablation of Atrial Fibrillation Using the Left Atrial Roof Approach.

Journal of chest surgery·2026

Same author

Life cycle greenhouse gas reduction in bioenergy with carbon capture and storage processes for green hydrogen production.

Bioresource technology·2026

Same author

Germline Mutations Related to Complete Remission After Neoadjuvant Chemotherapy in Patients With Triple-negative Breast Cancer.

Journal of breast cancer·2026

Same author

Final adult height in male patients with central precocious puberty after gonadotropin-releasing hormone agonist treatment.

Annals of pediatric endocrinology & metabolism·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 6, 2026

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

CNN-based diagnosis models for canine ulcerative keratitis.

Joon Young Kim¹, Ha Eun Lee¹, Yeon Hyung Choi¹

¹Veterinary Medical Teaching Hospital, Konkuk University, Seoul, 05029, Republic of Korea.

Scientific Reports

|October 4, 2019

Summary

This study developed a convolutional neural network (CNN) to accurately classify canine corneal ulcer severity. The deep learning model achieved over 90% accuracy, offering a promising tool for veterinary diagnostics.

More Related Videos

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Published on: January 12, 2022

Establishing a Severe Corneal Inflammation Model in Rats Based on Corneal Epithelium Curettage Combined with Corneal Sutures

Establishing a Severe Corneal Inflammation Model in Rats Based on Corneal Epithelium Curettage Combined with Corneal Sutures

Published on: November 22, 2024

Related Experiment Videos

Last Updated: Jan 6, 2026

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Published on: January 12, 2022

Establishing a Severe Corneal Inflammation Model in Rats Based on Corneal Epithelium Curettage Combined with Corneal Sutures

Establishing a Severe Corneal Inflammation Model in Rats Based on Corneal Epithelium Curettage Combined with Corneal Sutures

Published on: November 22, 2024

Area of Science:

Veterinary ophthalmology
Artificial intelligence in veterinary medicine
Deep learning for image analysis

Background:

Corneal ulcers in dogs require accurate severity assessment for effective treatment.
Current diagnostic methods rely on subjective interpretation of corneal images.
Advancements in deep learning offer potential for objective image-based diagnostics.

Purpose of the Study:

To develop and evaluate a convolutional neural network (CNN) for classifying canine corneal ulcer severity.
To assess the diagnostic performance of different CNN architectures (GoogLeNet, ResNet, VGGNet) using veterinary ophthalmology data.
To establish an automated method for determining corneal ulcer severity in dogs.

Main Methods:

Training CNN models using a dataset of canine corneal images classified by veterinary ophthalmologists.
Utilizing TensorFlow and TFRecord format for image data processing and model development.
Employing data augmentation techniques including flipping and rotation to enhance model robustness.

Main Results:

Multiple CNN models achieved over 90% accuracy in classifying superficial and deep corneal ulcers.
ResNet and VGGNet models demonstrated high accuracy (>90%) in classifying normal, superficial, and deep corneal ulcers.
The developed CNN approach proved effective in determining corneal ulcer severity.

Conclusions:

Convolutional neural networks offer an effective method for assessing canine corneal ulcer severity.
Deep learning-based image classification models show significant potential for application in veterinary diagnostics.
This study supports the integration of AI tools for improved accuracy and efficiency in veterinary ophthalmology.