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

Ankle Joint

Ankle Joint

The ankle is formed by the talocrural joint (crural = leg). It consists of the articulations between the talus bone of the foot and the distal ends of the tibia and fibula of the leg. The superior aspect of the talus bone is square-shaped and has three areas of articulation. The top of the talus articulates with the inferior tibia. This is the portion of the ankle joint that carries the body weight between the leg and foot. The sides of the talus are firmly held in position by the articulations...

You might also read

Related Articles

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

Sort by

Same author

Relationship Between Ankle Plantar Flexion Angle and Tendon Gap in Achilles Tendon Rupture: A Prospective Study Using Portable Handheld Ultrasonography.

Cureus·2026

Same author

Comparison of portable ultrasound and arthroscopy for assessing sagittal fibular translation for assessment of syndesmotic instability.

Journal of ISAKOS : joint disorders & orthopaedic sports medicine·2026

Same author

Improving subtalar arthrodesis with a skin-matched patient-specific surgical guide: A comparative cadaveric study.

Acta orthopaedica et traumatologica turcica·2026

Same author

Application of patient-specific surgical guides in foot and ankle surgery.

Acta orthopaedica et traumatologica turcica·2026

Same author

Deep Learning Enhances Weightbearing CT Detection of Lisfranc Instability: A FIXUS-AI Ankle Insight 3D Algorithm.

Cureus·2026

Same author

Weight-bearing computed tomography volumetric analysis for diagnosis of syndesmotic instability: A new standard of care?

Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA·2026

Same journal

Revision arthrodesis after first metatarsophalangeal joint arthroplasty: A nationwide analysis of implant type and revision-related factors.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2026

Same journal

Percutaneous distal metatarsal osteotomy with K-wire fixation into the medial cuneiform for hallux valgus: A case series including severe deformity.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2026

Same journal

Transitional talalgia after medial gastrocnemius lengthening using the Strayer technique in chronic plantar fasciitis.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2026

Same journal

Amputation risk after total ankle arthroplasty: A national database study with verified continued patient enrollment.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2026

Same journal

Accuracy of radiology MRI reports in predicting syndesmotic injuries: An intraoperative correlation study.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2026

Same journal

Weightbearing after ankle fracture fixation; A systematic review and meta-analysis of randomised controlled trials, a modern perspective.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 21, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Detection of ankle fractures using deep learning algorithms.

Soheil Ashkani-Esfahani¹, Reza Mojahed Yazdi², Rohan Bhimani²

¹Foot & Ankle Research and Innovation Laboratory, Massachusetts General Hospital, Harvard Medical School, Boston 02114, MA, USA; Department of Orthopaedic Surgery, Amsterdam University Medical Center, University of Amsterdam, Amsterdam Movement Sciences, Amsterdam, the Netherlands; Foot & Ankle Service, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston 02114, MA, USA.

Foot and Ankle Surgery : Official Journal of the European Society of Foot and Ankle Surgeons

|June 6, 2022

Summary

This summary is machine-generated.

Deep convolutional neural networks (DCNNs) accurately detect ankle fractures from radiographs. Using three-view images significantly improved DCNN performance for faster and more precise clinical diagnosis.

Keywords:

Ankle radiograph Artificial intelligence Convolutional neural network Image analysis Machine learning

More Related Videos

A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation

A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation

Published on: September 14, 2017

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Related Experiment Videos

Last Updated: Sep 21, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation

A Method to Estimate Cadaveric Femur Cortical Strains During Fracture Testing Using Digital Image Correlation

Published on: September 14, 2017

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Area of Science:

Medical imaging analysis
Artificial intelligence in radiology
Orthopedic diagnostics

Background:

Early and accurate detection of ankle fractures is critical for effective treatment and complication reduction.
Radiographs are the primary imaging modality for fracture assessment.
Deep learning (DL) methods, specifically deep convolutional neural networks (DCNNs), offer potential for automated, rapid, and accurate radiographic image analysis.

Purpose of the Study:

To evaluate the performance of two distinct DCNNs in detecting ankle fractures from radiographs.
To compare the diagnostic accuracy of DCNNs utilizing single-view versus multi-view radiographic data.
To establish a benchmark for DCNN performance against ground truth in ankle fracture identification.

Main Methods:

A retrospective case-control study trained DCNNs on radiographs from 1050 patients with ankle fractures and 1050 controls.
Inception V3 and ResNet-50 pretrained models were employed. Danis-Weber classification was utilized.
Radiographs were analyzed using single-view (anteroposterior) and 3-view (anteroposterior, mortise, lateral) datasets, including 72 occult fractures.

Main Results:

DCNNs demonstrated superior performance with 3-view images compared to single-view, evidenced by higher accuracy, F-score, and Area Under the Curve (AUC).
The Inception V3 model achieved the highest sensitivity (98.7%) and specificity (98.6%) for ankle fracture detection using 3-view radiographs.
This advanced DCNN model correctly identified all but one fracture in the evaluated radiographs.

Conclusions:

The evaluated DCNNs exhibit high performance in detecting ankle fractures from radiographic images.
These DCNN models show promise for integration into current image interpretation software or as standalone clinical decision support tools.
The findings suggest DCNNs can enhance the speed and precision of ankle fracture diagnosis for clinicians.