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

Search research articles

Home
The Application Of Mask Region-based Convolutional Neural Networks In The Detection Of Nasal Septal Deviation Using Cone Beam Computed Tomography Images: Proof-of-concept Study.

Home
The Application Of Mask Region-based Convolutional Neural Networks In The Detection Of Nasal Septal Deviation Using Cone Beam Computed Tomography Images: Proof-of-concept Study.

Related Experiment Video

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

The Application of Mask Region-Based Convolutional Neural Networks in the Detection of Nasal Septal Deviation Using

Shishir Shetty¹, Auwalu Saleh Mubarak², Leena R David³

¹Department of Oral and Craniofacial Health Sciences, College of Dental Medicine, University of Sharjah, Sharjah, United Arab Emirates.

JMIR Formative Research

|September 3, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

Keywords:

CNN ResNet artificial intelligence cone beam computed tomography convolutional neural networks face facial image imagery images nasal nasal septal deviation neural network neural networks nose tomographic tomography

More Related Videos

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 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

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 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

This study developed an AI model to detect nasal septal deviation (NSD) in cone beam CT scans. The model achieved high accuracy, demonstrating AI

Area of Science:

Radiology and Medical Imaging
Artificial Intelligence in Healthcare
Computational Anatomy

Background:

Artificial intelligence (AI) models are increasingly utilized for detecting pathologies in medical imaging.
Nasal septal deviation (NSD) is a clinically significant anatomical variation, yet AI-based radiographic detection remains unexplored.
Cone beam computed tomography (CBCT) provides detailed anatomical data crucial for diagnosing conditions like NSD.

Purpose of the Study:

To develop and evaluate a real-time AI model for detecting probable nasal septal deviation (NSD).
To utilize cone beam computed tomography (CBCT) images for AI-driven NSD identification.
To establish a benchmark for AI performance in diagnosing NSD from radiographic data.

Main Methods:

Trained and tested AI models using coronal CBCT images from 204 patients, classified by radiologists.

Employed Mask region-based convolutional neural networks (Mask R-CNNs) with ResNet50, ResNet101, and MobileNet backbones.

Incorporated contrast enhancement (CEH) preprocessing to optimize detection accuracy.

Main Results:

The CEH-ResNet101 model demonstrated superior performance in detecting NSD.
Achieved a mean average precision of 0.911 and an area under the curve of 0.921.
Indicated high capability of the AI model in identifying nasal septal deviation.

Conclusions:

The developed AI model is effective for detecting nasal septal deviation (NSD) in CBCT images.
Suggests potential for AI in routine radiological assessment of NSD.
Recommends future research focusing on advanced preprocessing and 3D multi-planar analysis for NSD detection.