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

Anthropogenic gadolinium contamination in tap water across the Paris megacity: Rare earth elements trace sources and mixing.

Environmental pollution (Barking, Essex : 1987)·2026

Same author

AI-driven volumetric approach for automatic chemotherapy response assessment in colorectal liver metastases.

European radiology·2026

Same author

Rare earth element abundances and gadolinium contamination in tap water worldwide.

Chemosphere·2025

Same author

Bias, accuracy, and trust: no GenAI in peer reviewing.

Journal of neuroradiology = Journal de neuroradiologie·2025

Same author

Exploring learning transferability in deep segmentation of colorectal cancer liver metastases.

Computers in biology and medicine·2025

Same author

Unveiling rare earth elements in beers:evidence for gadolinium contamination.

Food chemistry·2025

Same journal

Deep multi-modal features based spatio-temporal video regression for non-invasive hemoglobin estimation.

Medical & biological engineering & computing·2026

Same journal

Reduced mechanical strength correlates with decreased elastin content in aortic intima-media tissue: association with dissection in human ascending aortas.

Medical & biological engineering & computing·2026

Same journal

How plaque morphology and stenosis severity govern stent-artery interaction and deployment outcomes: a computational study.

Medical & biological engineering & computing·2026

Same journal

Investigating a relation between amyloid beta plaque burden and accumulated neurotoxicity caused by amyloid beta oligomers.

Medical & biological engineering & computing·2026

Same journal

A robot-assisted eye positioning method with high precision and repeatability for ocular particle therapy: mechanical and geometric assessment.

Medical & biological engineering & computing·2026

Same journal

Enhanced puncture event detection for teleoperated needle insertion robotic system.

Medical & biological engineering & computing·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 1, 2026

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

Automatic forensic identification using 3D sphenoid sinus segmentation and deep characterization.

Kamal Souadih¹, Ahror Belaid², Douraied Ben Salem^3,4

¹Medical Computing Laboratory (LIMED), University of Abderrahmane Mira, 06000, Bejaia, Algeria. kamal.souadih@univ-bejaia.dz.

Medical & Biological Engineering & Computing

|December 19, 2019

Summary

This summary is machine-generated.

This study introduces an automated method for forensic identification using 3D sphenoid sinus analysis from CT scans. The novel approach achieved 100% accuracy in identifying individuals based on unique sphenoid sinus features.

Keywords:

3D segmentation Convolutional auto-encoder Forensic identification Fuzzy C-means Mathematical morphology Sphenoidal sinus

More Related Videos

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

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: Jan 1, 2026

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

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

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:

Forensic Radiology
Medical Imaging Analysis
Biometrics

Background:

Sphenoid sinus anatomy is highly variable and can aid in radiologic identification when traditional methods are unavailable.
Accurate characterization of sphenoid sinus pneumatization is crucial for forensic identification applications.
Current forensic identification methods may be limited by the availability of dental records, fingerprints, or DNA samples.

Purpose of the Study:

To develop and validate an automated system for person identification using sphenoid sinus features from CT scans.
To investigate the potential of deep learning for extracting discriminative features from 3D sphenoid sinus reconstructions.
To establish a novel biometric identification method based on craniofacial anatomical variations.

Main Methods:

A novel approach for fully automatic 3D reconstruction and segmentation of sphenoid hemisinuses using fuzzy c-means and mathematical morphology.
Extraction of deep shape features from segmented hemisinuses via a dilated residual stacked convolutional auto-encoder.
Hierarchical mapping of segmentation masks into a low-dimensional space and recognition using the ℓ2 distance.

Main Results:

The proposed method achieved 100% identification accuracy on a dataset of 85 CT scans from 72 individuals.
Successful automatic 3D reconstruction and segmentation of sphenoid hemisinuses were demonstrated.
Deep shape features effectively captured unique sphenoid sinus characteristics for identification.

Conclusions:

Automated sphenoid sinus analysis from CT scans offers a highly accurate and novel method for forensic identification.
The combination of advanced image processing and deep learning provides a robust framework for biometric recognition.
This technique holds significant potential for forensic applications, particularly in cases with limited traditional identification data.