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

Total Synthesis of Nineteen-Carbon Picrotoxane Terpenoid Picrodendrin L.

Journal of the American Chemical Society·2026

Same author

Mid- to Long-Term Outcomes of the MESOCOLIC Trial Evaluating Extensive vs Limited Mesenteric Excision in Crohn's Disease.

Gastroenterology·2026

Same author

[Preliminary exploration of CT evaluation system for tracheostomy of cervical or upper thoracic kyphosis].

Lin chuang er bi yan hou tou jing wai ke za zhi = Journal of clinical otorhinolaryngology head and neck surgery·2026

Same author

Uncovering the metabolic variations of sulfur dioxide in the brain of Parkinson's disease and air pollution: From imaging to therapeutic evaluations.

Journal of hazardous materials·2026

Same author

Enzyme-Guided Assembly Enables Precision Delivery of a Singlet Oxygen Battery for Membrane Lipid Peroxidation Therapy.

Angewandte Chemie (International ed. in English)·2026

Same author

Efficacy analysis of the Turnbull-Cutait procedure in refractory perianal Crohn's disease: a two-centre retrospective study.

International journal of colorectal disease·2026

Search research articles

Related Experiment Video

Updated: Nov 20, 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

Automatic segmentation of temporal bone structures from clinical conventional CT using a CNN approach.

Yi Lv¹, Jia Ke², Ying Xu¹

¹School of Mechanical Engineering and Automation, Beihang University, Beijing, China.

The International Journal of Medical Robotics + Computer Assisted Surgery : MRCAS

|January 19, 2021

Summary

This study introduces W-Net, a novel deep learning model for segmenting temporal bone structures in CT scans. W-Net achieves human-level accuracy, improving image-guided cochlear implant surgery.

Keywords:

cochlear implant surgery convolutional neural network medical image segmentation temporal bone structure

More Related Videos

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Nov 20, 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

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Medical Imaging
Artificial Intelligence
Neurosurgery

Background:

Accurate segmentation of temporal bone structures is crucial for image-guided cochlear implant surgery.
Conventional computed tomography (CT) data is used for segmentation.
Existing convolutional neural network (CNN) methods struggle with small, tubular structures.

Purpose of the Study:

To develop a novel deep learning model for accurate segmentation of temporal bone structures.
To improve segmentation accuracy for small tubular structures in CT images.
To evaluate the proposed method against state-of-the-art approaches.

Main Methods:

A light-weight three-dimensional CNN, W-Net, was developed for multiobjective segmentation.
Segmentation targets include the cochlear labyrinth, ossicular chain, and facial nerve.
Data augmentation with morphological enhancement was employed to boost accuracy for small structures.

Main Results:

The W-Net model achieved high mean Dice similarity coefficients (DSCs): 0.90 for the cochlear labyrinth, 0.85 for the ossicular chain, and 0.77 for the facial nerve.
These DSCs are comparable to those obtained by human expert annotators (0.91, 0.91, and 0.72, respectively).

Conclusions:

The proposed W-Net method demonstrates human-level accuracy in segmenting critical temporal bone structures.
This advancement holds significant potential for enhancing image-guided cochlear implant surgery outcomes.