Regressive vision transformer for dog cardiomegaly assessment

J Li, Y Zhang - Scientific Reports, 2024 - nature.com
Cardiac disease is one of the leading causes of death in dogs. Automatic cardiomegaly
detection has great significance in helping clinicians improve the accuracy of the diagnosis …

Confident Pseudo-labeled Diffusion Augmentation for Canine Cardiomegaly Detection

S Zhang, LR Polamreddy, Y Zhang - arXiv preprint arXiv:2501.07533, 2025 - arxiv.org
Canine cardiomegaly, marked by an enlarged heart, poses serious health risks if
undetected, requiring accurate diagnostic methods. Current detection models often rely on …

[PDF][PDF] Precision Veterinary Imaging: Vertebral Heart Size Measurement in Dog X-rays with EfficientNet-B7 and Self-Attention Mechanisms

LP Ramisetty - 2024 - researchgate.net
This research report details the development and implementation of a point detection model
for measuring the Vertebral Heart Size (VHS) of dogs using X-ray images. The goal is to …

[PDF][PDF] Dog Heart Keypoint Detection using EfficientNet

Y Yao - 2024 - researchgate.net
This paper presents a method for detecting keypoints in dog heart images using EfficientNet.
The aim is to accurately predict six keypoints on dog heart images, which are used to …

[PDF][PDF] EfficientNet-Based Detection of Key Points in Dog Heart X-Rays

N Patel - researchgate.net
Cardiac disease is a leading cause of mortality in dogs, and accurate detection of
cardiomegaly is essential for improving diagnostic outcomes. Automatic detection systems …

[PDF][PDF] Automated Classification of DogHeart X-Rays Using a Custom Convolutional Neural Network with Attention Mechanisms

N Patel - researchgate.net
This study presents a convolutional neural network (CNN) model specifically designed for
image classification tasks and evaluates its performance on the benchmark Dog-Heart …

[PDF][PDF] Innovating Cardiovascular Imaging: A Novel Convolutional Neural Network for Dog Heart Image Classification

LP Ramisetty - researchgate.net
This study presents the development and evaluation of a custom convolutional neural
network (CNN) for classifying dog heart images. Our novel architecture aims to surpass the …