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

Smartphone-Based Grading and Rehabilitation in Patients With Facial Palsy Using Computer Vision: Prospective Validation Study.

JMIR rehabilitation and assistive technologies·2026

Same author

OpenMRF: A Modular, Vendor-Neutral Open-Source Framework for Reproducible Magnetic Resonance Fingerprinting using Pulseq.

ArXiv·2026

Same author

<i>FRMPD4</i>, a causal gene for intellectual disability and epilepsy, is associated with X-linked non-syndromic hearing loss.

medRxiv : the preprint server for health sciences·2026

Same author

Fibre phantom generation using FibreSimulator: an open-source Python tool.

Journal of synchrotron radiation·2026

Same author

Probabilistic Safe Zone Mapping for S1 Screw Placement Using 1000 Lumbosacral CT Scans: A Study Protocol for a Bilateral, Two-Rater, Multi-Offset Anatomical Modeling Study.

Journal of clinical medicine·2026

Same author

Comparing image quality of synchrotron and laboratory nano-CT scans: a round robin study.

Journal of synchrotron radiation·2026

Search research articles

Related Experiment Video

Updated: Jul 11, 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

Towards fully automated inner ear analysis with deep-learning-based joint segmentation and landmark detection

Jannik Stebani^1,2,3, Martin Blaimer⁴, Simon Zabler^4,5

¹Magnetic Resonance and X-Ray Imaging Department, Fraunhofer Institute for Integrated Circuits IIS, 97074, Würzburg, Germany. jannik.stebani@iis.fraunhofer.de.

Scientific Reports

|November 5, 2023

Summary

This study introduces an automated framework for analyzing inner ear anatomy in radiological scans, significantly reducing manual assessment time. The AI model accurately segments inner ear structures and detects key landmarks, aiding surgical planning and research.

More Related Videos

Whole Neonatal Cochlear Explants as an In vitro Model

Whole Neonatal Cochlear Explants as an In vitro Model

Published on: July 28, 2023

Investigating Outer Hair Cell Motility with a Combination of External Alternating Electrical Field Stimulation and High-speed Image Analysis

Investigating Outer Hair Cell Motility with a Combination of External Alternating Electrical Field Stimulation and High-speed Image Analysis

Published on: July 18, 2011

Related Experiment Videos

Last Updated: Jul 11, 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

Whole Neonatal Cochlear Explants as an In vitro Model

Whole Neonatal Cochlear Explants as an In vitro Model

Published on: July 28, 2023

Investigating Outer Hair Cell Motility with a Combination of External Alternating Electrical Field Stimulation and High-speed Image Analysis

Investigating Outer Hair Cell Motility with a Combination of External Alternating Electrical Field Stimulation and High-speed Image Analysis

Published on: July 18, 2011

Area of Science:

Medical Imaging
Radiology
Computational Anatomy

Background:

Manual assessment of inner ear anatomy in radiological data is time-consuming and hinders preoperative planning and clinical research.
Automated analysis offers a potential solution to improve efficiency and accuracy.

Purpose of the Study:

To develop and evaluate an automated framework for joint semantic segmentation of the inner ear and anatomical landmark detection.
To assess the performance and robustness of the proposed model on both in-house and independent datasets.

Main Methods:

Implementation of a fully automated pipeline using a dual-headed volumetric 3D U-Net.
Training and evaluation on manually labeled in-house datasets (cadaveric and clinical) and three independent open-source datasets.
Ablation studies to determine optimal parameters and assess the benefits of coupled tasks.

Main Results:

Achieved high Dice scores, intersection-over-union, and low Hausdorff distances on in-house datasets for segmentation.
Demonstrated accurate automatic landmark localization with minimal average error.
Showcased robust performance on open-source datasets, albeit with reduced accuracy, and highlighted the benefits of joint segmentation and landmark detection.

Conclusions:

The proposed automated framework effectively segments inner ear anatomy and detects key landmarks, offering a valuable tool for clinical applications.
Coupling segmentation with landmark detection provides performance benefits, suggesting the framework's potential to advance preoperative planning and research in otology.