Search research articles

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

Related Concept Videos

Classification of Bones

Classification of Bones

The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...

You might also read

Related Articles

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

Sort by

Same author

Multi-class segmentation of aortic branches and zones in computed tomography angiography: The AortaSeg24 challenge.

Medical image analysis·2026

Same author

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026

Same author

Multi-structure segmentation in CBCT volumes: The ToothFairy2 challenge.

Medical image analysis·2026

Same author

Radiomics-based mapping of glioblastoma infiltration beyond contrast enhancement: diffusion-perfusion correlations and survival analysis in large public cohorts.

European journal of radiology·2026

Same author

Intracranial ependymoma and secondary hydrocephalus: a rare case report in a Camel (<i>Camelus bactrianus</i>).

Frontiers in veterinary science·2026

Same author

Prospective biopsy-controlled validation of an AI model for predicting glioblastoma infiltration: Results from the SupraGlio trial.

Neuro-oncology·2026

Search research articles

Related Experiment Video

Updated: Nov 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Automatic classification of canine thoracic radiographs using deep learning.

Tommaso Banzato¹, Marek Wodzinski², Silvia Burti³

¹Department of Animal Medicine, Productions, and Health, Legnaro (PD), University of Padua, 35020, Padua, Italy. tommaso.banzato@unipd.it.

Scientific Reports

|February 18, 2021

Summary

This summary is machine-generated.

A novel deep convolutional neural network (CNN) aids veterinarians in interpreting dog thoracic radiographs. The ResNet-50 based CNN demonstrated strong performance in classifying various radiographic findings, improving diagnostic accuracy.

More Related Videos

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Nov 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

Area of Science:

Veterinary Radiology
Artificial Intelligence in Medicine
Machine Learning for Medical Imaging

Background:

Thoracic radiograph interpretation is complex and prone to errors for veterinarians.
Current computer-aided diagnostic systems for veterinary radiographs are limited.
Advancements in machine learning offer potential solutions for improving diagnostic accuracy.

Purpose of the Study:

To develop a novel multi-label deep convolutional neural network (CNN) for classifying thoracic radiographs in dogs.
To evaluate the performance and generalization ability of different CNN architectures (ResNet-50 and DenseNet-121).
To identify specific radiographic findings that can be accurately classified by the developed models.

Main Methods:

Retrospective collection of dog thoracic radiographs (2010-2020) from two different acquisition systems.
Development and testing of two deep CNNs: ResNet-50 and DenseNet-121 architectures.
Training CNNs using non-mutually exclusive labels for findings: unremarkable, cardiomegaly, alveolar pattern, bronchial pattern, interstitial pattern, mass, pleural effusion, pneumothorax, and megaesophagus.

Main Results:

The ResNet-50 CNN achieved an Area Under the Receive-Operator Curve (AUC) > 0.8 for most findings on both training and testing datasets.
The DenseNet-121 CNN showed lower overall performance compared to ResNet-50.
ResNet-50 demonstrated statistically significant superior generalization for alveolar pattern, interstitial pattern, megaesophagus, and pneumothorax.

Conclusions:

A ResNet-50 based multi-label CNN shows promising performance for classifying canine thoracic radiographs.
The developed CNN can aid veterinarians in identifying various radiographic abnormalities, potentially improving diagnostic efficiency.
Further research can explore refining CNN architectures for enhanced accuracy in veterinary diagnostic imaging.