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

The role of ferroptosis regulators in the prognosis, immune activity and gemcitabine resistance of pancreatic cancer.

Annals of translational medicine·2020
Same author

The vascular endothelial growth factor trap aflibercept induces vascular dysfunction and hypertension via attenuation of eNOS/NO signaling in mice.

Acta pharmacologica Sinica·2020
Same author

MBNL1 regulates isoproterenol-induced myocardial remodelling in vitro and in vivo.

Journal of cellular and molecular medicine·2020
Same author

Platelets Stimulate Liver Regeneration in a Rat Model of Partial Liver Transplantation.

Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society·2020
Same author

Mutant p53 in Cancer Progression and Targeted Therapies.

Frontiers in oncology·2020
Same author

Downregulation of astrocyte elevated gene-1 expression inhibits the development of vasculogenic mimicry in gliomas.

Experimental and therapeutic medicine·2020

Related Experiment Video

Updated: Aug 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

472

MsgeCNN: Multiscale geometric embedded convolutional neural network for ONFH segmentation and grading.

Xiang Li1, Songcen Lv2, Chuanxin Tong2

  • 1Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China.

Medical Physics
|February 22, 2023
PubMed
Summary

A new AI framework accurately segments femoral head and necrosis regions for osteonecrosis of the femoral head (ONFH) grading. This automated approach aids in clinical diagnosis and treatment planning for ONFH.

Keywords:
ONFH gradingONFH segmentationconvolutional neural networksgeometric loss function

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

599
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

Related Experiment Videos

Last Updated: Aug 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

472
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

599
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

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Orthopedic surgery

Background:

  • Osteonecrosis of the femoral head (ONFH) incidence is rising, necessitating rapid and accurate grading.
  • Current Steinberg staging relies on subjective estimation of necrosis and femoral head areas.
  • Objective assessment is crucial for effective clinical management of ONFH.

Purpose of the Study:

  • To develop an automated two-stage framework for segmenting femoral head and necrosis regions in ONFH.
  • To improve the accuracy and objectivity of ONFH grading compared to traditional methods.
  • To provide quantitative pathological information for clinical decision-making.

Main Methods:

  • A multiscale geometric embedded convolutional neural network (MsgeCNN) was developed for precise femoral head segmentation.
  • Necrosis regions were segmented using an adaptive threshold method with the segmented femoral head as background.
  • The framework calculates area and proportion for automated ONFH grading.

Main Results:

  • The MsgeCNN achieved high accuracy (97.73%) and Dice score (93.34%) for femoral head segmentation.
  • Segmentation performance surpassed existing algorithms.
  • The overall diagnostic accuracy of the framework reached 90.80%.

Conclusions:

  • The proposed framework accurately segments femoral head and necrosis regions in ONFH.
  • Quantitative outputs (area, proportion) offer valuable auxiliary information for clinical treatment.
  • This automated approach enhances diagnostic accuracy and supports treatment strategies for ONFH.