Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Can Deep Learning Methods Differentiate Temporomandibular Joint Disorders From Healthy Joints? A 3D Artificial Intelligence Algorithm Study Based on CBCT Images.

Journal of oral rehabilitation·2026
Same author

Multi-class anatomical landmark detection in periapical radiographs with deep learning.

Odontology·2026
Same author

Deep learning detection of ectopic canines and molars in mixed dentition.

Scientific reports·2026
Same author

Evaluation of the relationship between the gonial angle and the pattern of the impacted mandibular third molar by cone beam computed tomography.

Surgical and radiologic anatomy : SRA·2026
Same author

Volumetric dimensions of the maxillary sinus affect infraorbital canal configurations? A CBCT study.

Oral radiology·2026
Same author

Comparative Performance of YOLO Models in the Automated Segmentation of Dental Traumas on Panoramic Radiographs.

Dental traumatology : official publication of International Association for Dental Traumatology·2025
Same journal

Image sharpening improves the visibility of reference points on low-dose lateral cephalometric radiographs: a phantom study.

Dento maxillo facial radiology·2026
Same journal

AI-Based Detection of Proximal Caries Across Radiographic Modalities: A Systematic Review and Meta-Analysis.

Dento maxillo facial radiology·2026
Same journal

Cranial Base Characteristics in Adults with Obstructive Sleep Apnoea and Matched Controls: A Retrospective CBCT Study.

Dento maxillo facial radiology·2026
Same journal

Dual-Circle: a new way of assessing Temporomandibular joint (TMJ) disc position at coronal MRI.

Dento maxillo facial radiology·2026
Same journal

Quantification of Supracrestal Tissue Attachment Using High-Frequency Ultrasound.

Dento maxillo facial radiology·2026
Same journal

Radiological-pathological correlation of tumour size and depth of invasion of oral squamous cell carcinoma using Dual-Energy CT in comparison to MRI and the impact on T-stage.

Dento maxillo facial radiology·2026
See all related articles

Related Experiment Video

Updated: Sep 13, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.2K

Artificial intelligence-based fully automatic 3D paranasal sinus segmentation.

Meryem Kaygısız Yiğit1, Alp Pınarbaşı1, Meryem Etöz1

  • 1Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Erciyes University, Kayseri, 38039, Turkey.

Dento Maxillo Facial Radiology
|July 25, 2025
PubMed
Summary
This summary is machine-generated.

A novel nnU-Net v2 algorithm accurately segments paranasal sinuses in 3D from cone-beam CT scans. This automated approach enhances diagnostic precision for clinical decision-making.

Keywords:
artificial intelligencedeep learningnnU-Netparanasal sinusessegmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.9K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.9K

Related Experiment Videos

Last Updated: Sep 13, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.9K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Accurate 3D segmentation of paranasal sinuses is critical for effective diagnosis and treatment planning.
  • Current segmentation methods may be time-consuming or lack precision.

Purpose of the Study:

  • To develop and evaluate a fully automated segmentation algorithm for paranasal sinuses using the nnU-Net v2 architecture.
  • To assess the performance of the automated algorithm against expert-generated ground truth.

Main Methods:

  • Developed a segmentation algorithm utilizing the nnU-Net v2 architecture with Python and PyTorch.
  • Evaluated the algorithm on 97 cone-beam computed tomography (CBCT) scans.
  • Performance was quantified using Dice Coefficient, accuracy, Jaccard Index, and 95% Hausdorff Distance.

Main Results:

  • Achieved high segmentation accuracy (>99%) and Dice Coefficients (0.88-0.97) across all paranasal sinuses.
  • Demonstrated low 95% Hausdorff Distances (0.51-1.17 mm), indicating precise boundary delineation.
  • Jaccard indices ranged from 0.80 to 0.94, confirming robust segmentation performance.

Conclusions:

  • The nnU-Net v2-based model provides highly accurate and precise automated segmentation of paranasal sinuses from CBCT images.
  • This automated approach has the potential to significantly aid clinical decision-making in diagnosis and treatment.
  • The proposed CNN model offers a valuable tool for improving efficiency and accuracy in paranasal sinus evaluation.