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

Explanation-Guided Reconstruction of Missing Clinical Features for Survival Prediction in Pancreatic Cancer.

IEEE journal of biomedical and health informatics·2026

Same author

MammoDenseSegNet: A Context-Aware Deep Learning Model for Dense Tissue Segmentation in Digital Mammograms.

Journal of imaging informatics in medicine·2026

Same author

Improved pancreatic imaging with photon-counting CT: a retrospective comparison with conventional CT.

Acta radiologica (Stockholm, Sweden : 1987)·2026

Same author

Revisiting multi-nodal radiomics with advanced feature learning for lymphoma classification: a multi-center study.

Physics in medicine and biology·2026

Same author

Reduced beam hardening in urogenital imaging with photon-counting CT: a retrospective direct comparison with conventional CT.

Acta radiologica (Stockholm, Sweden : 1987)·2026

Same author

Dosimetric assessment of deep learning based organ-at-risk segmentation: insights from the HaN-Seg challenge.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026

Search research articles

Related Experiment Video

Updated: Sep 29, 2025

Quantification of Levator Ani Hiatus Enlargement by Magnetic Resonance Imaging in Males and Females with Pelvic Organ Prolapse

Quantification of Levator Ani Hiatus Enlargement by Magnetic Resonance Imaging in Males and Females with Pelvic Organ Prolapse

Published on: April 17, 2019

Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification.

Imad Eddine Ibrahim Bekkouch¹, Bulat Maksudov², Semen Kiselev³

¹Sorbonne Center for Artificial Intelligence, Sorbonne University, Paris, France; Institute of Data Science and Artificial Intelligence, Innopolis University, Innopolis, Russia.

Medical Image Analysis

|March 24, 2022

Summary

This study introduces an automated framework using reinforcement learning for detecting hip abnormalities from MRI scans. The system accurately quantifies joint angles, achieving 95% agreement with expert radiologists.

Keywords:

landmark detection magnetic resonance pelvic abnormalities reinforcement learning

More Related Videos

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Related Experiment Videos

Last Updated: Sep 29, 2025

Quantification of Levator Ani Hiatus Enlargement by Magnetic Resonance Imaging in Males and Females with Pelvic Organ Prolapse

Quantification of Levator Ani Hiatus Enlargement by Magnetic Resonance Imaging in Males and Females with Pelvic Organ Prolapse

Published on: April 17, 2019

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Area of Science:

Medical Imaging
Musculoskeletal Disorders
Artificial Intelligence

Background:

Femoroacetabular (hip) joint abnormalities are common musculoskeletal disorders.
These abnormalities often develop asymptomatically in early, treatable stages.

Purpose of the Study:

To propose an automated framework for landmark-based detection and quantification of hip abnormalities using magnetic resonance (MR) images.
To quantitatively estimate landmark contributions using multi-landmark environment analysis and reinforcement learning.

Main Methods:

Utilized convolutional neural networks (CNNs) for initial landmark proposal via image segmentation.
Formulated landmark detection as a reinforcement learning (RL) problem for position optimization.
Integrated graphical lasso and Morris sensitivity analysis with deep neural networks.

Main Results:

Validated on MR images from 260 patients, measuring key hip angles (LCEA, NSA, AASA, PASA).
Achieved a low overall landmark detection error of 1.5 mm and angle measurement error of 1.4°.
Demonstrated 95% agreement between automated and expert radiologist abnormality labels.

Conclusions:

The proposed framework offers superior performance for automated hip abnormality detection and quantification.
This AI-driven approach facilitates early diagnosis and treatment of hip joint disorders.
The method shows high accuracy and strong agreement with expert radiological assessments.