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

Clinical and Radiologic Outcomes of the Bankart Repair Using Mason-Allen (BRUMA) Technique for Small Bony Bankart Lesions: An Objective, Performance Criteria-Referenced, Single-Surgeon Case Series.

Orthopaedic journal of sports medicine·2026

Same author

Recent Updates on Allograft Selection for Reconstruction of Massive Rotator Cuff Tears.

Clinics in orthopedic surgery·2026

Same author

Citrated Kaolin Reaction Time on Thromboelastography 6s Identifies Bleeding-Prone Phenotypes in Older Adults with Atrial Fibrillation Receiving Direct Oral Anticoagulant Therapy.

Cardiovascular drugs and therapy·2026

Same author

Inhibiting muscle degeneration in rotator cuff tears: integrative biologic approaches targeting regeneration, fibrosis, and metabolism.

Stem cells translational medicine·2026

Same author

Repair of the medial meniscus posterior root tear using an all-inside meniscal repair device is not necessary during open-wedge high tibial osteotomy.

Journal of orthopaedic surgery (Hong Kong)·2026

Same author

Early Fracture Alignment Correction and Its Association with Neurologic Recovery in Pediatric Supracondylar Humeral Fractures.

Clinics in orthopedic surgery·2026

Search research articles

Related Experiment Video

Updated: Jul 30, 2025

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Automated 3-dimensional MRI segmentation for the posterosuperior rotator cuff tear lesion using deep learning

Su Hyun Lee¹, JiHwan Lee², Kyung-Soo Oh³

¹Department of Orthopaedic Surgery, Seoul Red Cross Hospital, Seoul, Korea.

|May 18, 2023

Summary

A deep learning algorithm accurately segments rotator cuff tears (RCT) on 3D MRI scans. This 3D U-Net CNN model shows high precision and sensitivity, aiding in the diagnosis of this common musculoskeletal condition.

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

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 30, 2025

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

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

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Area of Science:

Orthopedics
Radiology
Artificial Intelligence

Background:

Rotator cuff tear (RCT) is a prevalent and challenging musculoskeletal condition.
Magnetic resonance imaging (MRI) is crucial for RCT diagnosis, but interpretation can be difficult and unreliable.
Accurate segmentation of RCT lesions is essential for effective diagnosis and treatment planning.

Purpose of the Study:

To evaluate the accuracy and efficacy of a 3D MRI segmentation technique for rotator cuff tears (RCT) using a deep learning algorithm.
To develop and validate a 3D U-Net convolutional neural network (CNN) for automated RCT lesion detection, segmentation, and visualization.
To assess the performance of the deep learning model in segmenting RCT lesions on 3D MRI data.

Main Methods:

A 3D U-Net CNN was developed to analyze 3D MRI data from 303 patients with RCTs.
RCT lesions were meticulously labeled by two shoulder specialists.
The model was trained and validated using an augmented dataset with a 6:2:2 ratio for training, validation, and testing, respectively.

Main Results:

The 3D U-Net CNN successfully detected, segmented, and visualized RCT lesions in 3D.
The model achieved a high Dice coefficient of 94.3%, sensitivity of 97.1%, and specificity of 95.0%.
Additional performance metrics included precision of 84.9%, F1-score of 90.5%, and Youden index of 91.8%.

Conclusions:

The developed 3D segmentation model using deep learning demonstrates high accuracy and effective 3D visualization of RCT lesions on MRI.
The algorithm shows significant potential for improving the diagnostic process of rotator cuff tears.
Further research is warranted to confirm its clinical applicability and impact on patient care and outcomes.