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

You might also read

Related Articles

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

Sort by

Same author

Phonon Transport Mechanism of Strain-Enhanced Lattice Thermal Conductivity in Penta-NiAs<sub>2</sub> Monolayer.

Nanomaterials (Basel, Switzerland)·2026

Same author

NIR-Programmable Stealth 2D Black Phosphorus Nanobiointerfaces for Deep Tumor Penetration and Photoimmunotherapy.

ACS nano·2026

Same author

A wearable paper-based SGR/MCC microneedle array sensor for continuous glucose monitoring.

Microsystems & nanoengineering·2026

Same author

Simultaneous multi-band multi-spectral imaging using multi-band RF excitation for accelerated metal artifact reduction in MRI-guided interventions.

Medical physics·2026

Same author

Inhibition of PLA2G15 Alleviates Palmitic Acid-Induced Lysosomal Membrane Permeabilization in Human Nucleus Pulposus Cells During Intervertebral Disc Degeneration.

JOR spine·2026

Same author

An integrated electrochemical microfluidic chip for simultaneous detection of uric acid and interleukin-6.

Mikrochimica acta·2026

Search research articles

Related Experiment Video

Updated: Dec 29, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

A deep-learning-based approach for adenoid hypertrophy diagnosis.

Yi Shen¹, Xiaohu Li², Xiao Liang¹

¹Center for Biomedical Imaging, University of Science and Technology of China, 230026, Hefei, Anhui, China.

Medical Physics

|February 5, 2020

Summary

This study introduces a deep learning method for classifying adenoid hypertrophy, achieving high accuracy even with limited data. The approach uses keypoint localization and a novel VerticalLoss to improve diagnostic efficiency for this common condition.

Keywords:

adenoid hypertrophy convolutional neural networks keypoint localization

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

Related Experiment Videos

Last Updated: Dec 29, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

Area of Science:

Medical imaging analysis
Artificial intelligence in healthcare
Otorhinolaryngology

Background:

Adenoid hypertrophy can cause sleep-disordered breathing.
Current diagnosis relies on time-consuming manual measurements from lateral cephalograms.
There is a need for automated diagnostic tools for adenoid hypertrophy.

Purpose of the Study:

To develop a computer-aided diagnostic tool for adenoid hypertrophy classification.
To leverage deep learning for improved accuracy and efficiency.
To address challenges of limited training data in medical imaging.

Main Methods:

Proposed a deep learning model for adenoid hypertrophy classification.
Implemented a keypoint localization method to integrate prior information.
Introduced a novel regularized term, VerticalLoss, to enhance network performance.

Main Results:

Achieved 95.6% classification accuracy and a 0.957 macro F1-score with a full dataset.
Demonstrated strong performance with only half the training data (94% accuracy, 0.89 macro F1-score).
Obtained a low average adenoid-to-nasopharyngeal width (AN ratio) error of 0.026.

Conclusions:

The proposed deep learning method effectively classifies adenoid hypertrophy.
Incorporating prior information, particularly through VerticalLoss, is crucial for medical imaging with limited data.
The approach offers a promising solution for efficient and accurate adenoid hypertrophy diagnosis.