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

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Artificial Intelligence-Assisted Inner Ear Computed Tomography Analysis: Radiomics-Based Comparison of Affected and Unaffected Ears in Idiopathic Sudden Sensorineural Hearing Loss.

Journal of imaging informatics in medicine·2026

Same author

Building a Clinically Relevant and Technically Robust Synthetic Histopathology Dataset for Breast and Gastric Cancer.

Journal of medical systems·2026

Same author

Radiomics-Based Machine Learning for Sarcopenia Detection in Abdominal and Low-Dose CT.

Diagnostics (Basel, Switzerland)·2026

Same author

Modified Ultrafast Dynamic CT Myelography: Method, Outcomes, and Comparison With Noninvasive Imaging.

Journal of clinical neurology (Seoul, Korea)·2026

Same author

Diagnostic Value of Flow-Void Sign for Localizing Ventral Dural Defects in Spine MRI.

Journal of clinical neurology (Seoul, Korea)·2026

Same author

Deep Learning-Based Prediction System for Surgical Difficulty in Rectal Cancer Patients Using MRI Pelvimetry.

Yonsei medical journal·2026

Search research articles

Related Experiment Video

Updated: Oct 21, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Using Convolutional Neural Network with Taguchi Parametric Optimization for Knee Segmentation from X-Ray Images.

Young Jae Kim¹, Seung Ro Lee¹, Ja-Young Choi²

¹Department of Biomedical Engineering, Gil Medical Center, Gachon University College of Medicine, Incheon 21565, Republic of Korea.

Biomed Research International

|September 3, 2021

Summary

This study uses deep learning and the Taguchi method to improve knee X-ray segmentation for diagnosing cartilage loss. Optimized deep learning achieved high accuracy in segmenting femur and tibia, aiding orthopedic diagnosis.

More Related Videos

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: Oct 21, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

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:

Medical imaging
Artificial intelligence in healthcare
Orthopedics

Background:

Knee cartilage loss causes significant pain and is a prevalent global condition.
Accurate femur and tibia segmentation from X-rays is crucial for diagnosis, but knee complexity challenges automated methods.
Existing automatic knee segmentation techniques offer limited value due to these complexities.

Purpose of the Study:

To develop a robust and environmentally independent knee segmentation method using deep learning.
To optimize deep learning parameters for knee segmentation using the Taguchi method.
To enhance the accuracy of femur and tibia segmentation for improved diagnosis of knee conditions.

Main Methods:

Exploited deep learning, specifically the Dilated-Resnet architecture, for robust knee segmentation.
Applied the Taguchi method to systematically optimize deep learning parameters, including architecture, optimizer, and learning rate.
Investigated the impact and interaction of these parameters on segmentation performance.

Main Results:

Achieved high dice coefficients of 0.964 for femur and 0.942 for tibia segmentation.
The Dilated-Resnet architecture with the Adam optimizer and a learning rate of 0.001 yielded optimal results.
Demonstrated the effectiveness of the Taguchi method in optimizing deep learning for medical image segmentation.

Conclusions:

The optimized deep learning approach provides accurate femur and tibia segmentation, overcoming limitations of previous methods.
This technique can aid in precise margin determination for knee bones in X-rays.
The study lays the groundwork for developing advanced automatic diagnosis algorithms for orthopedic diseases.