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

Search research articles

Related Experiment Video

Updated: Apr 20, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

The Assessment of Coronal Plane Lower-Limb Alignment on Pre- and Postoperative Long-Leg Radiographs Using Deep

Kellen L Mulford¹, Monty Khela¹, Eric Wang¹

¹Department of Orthopedic Surgery, Orthopedic Surgery Artificial Intelligence Laboratory, Mayo Clinic, Rochester, Minnesota.

The Journal of Arthroplasty

|April 18, 2026

Summary

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 AAHKS Clinical Research Award: Maximizing Bearing Size Markedly Reduces Dislocations in Primary Total Hip Arthroplasty.

The Journal of arthroplasty·2026

Same author

Endoscopic resection of knosp grade 0-2 growth hormone-secreting pituitary adenomas with routine medial cavernous sinus wall excision.

Acta neurochirurgica·2026

Same author

Time to Reimplantation: Waiting Longer May Increase the Risk of Subsequent Failure.

The Journal of arthroplasty·2026

Same author

Design, Preclinical Evaluation, and Clinical Translation of [68Ga]Ga/[177Lu]Lu-JH120061, A Novel Radiopharmaceutical Targeting CXCR4.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026

Same author

Estimating temporal treatment-effect patterns of radiotherapy and chemotherapy in lower-grade gliomas using causal machine learning.

Scientific reports·2026

Same author

Differential epigenetic regulation of glucose-induced alteration of miR-9 in retinal and cardiac endothelial cells.

PloS one·2026

Same journal

Preoperative Pneumonia and Its Association With Periprosthetic Joint Infection and Postoperative Complications After Total Hip and Knee Arthroplasty.

The Journal of arthroplasty·2026

Same journal

Conversion Total Hip Arthroplasty Following Prior Internal Fixation: A Comparison with Primary and Revision Total Hip Arthroplasty.

The Journal of arthroplasty·2026

Same journal

The Relationship Between Patient Satisfaction and the Degree of Valgus Deformity in Lateral Unicompartmental Knee Arthroplasty at a Mean 3-Year Follow-Up.

The Journal of arthroplasty·2026

Same journal

Kneeling After Total Knee Arthroplasty: Does Resurfacing the Patella Affect the Ability to Kneel?

The Journal of arthroplasty·2026

Same journal

Integrating Robotic-Assisted Arthroplasty into Orthopaedic Education: The Fellows' Perspective.

The Journal of arthroplasty·2026

Same journal

A Systematic Review of Registry and Large Database Studies Comparing Contemporary Cementless and Cemented Total Knee Arthroplasty.

The Journal of arthroplasty·2026

See all related articles

This summary is machine-generated.

A new deep learning algorithm accurately measures lower-limb alignment angles like hip-knee-ankle angle (HKAA) on long-leg radiographs. This tool aids surgical planning and assessment, regardless of joint operative status.

Area of Science:

Orthopedic surgery
Medical imaging analysis
Artificial intelligence in healthcare

Background:

Coronal lower-limb alignment is critical for knee arthroplasty surgical planning and assessment.
Key metrics include hip-knee-ankle angle (HKAA), lateral distal femoral angle (LDFA), and medial proximal tibial angle (MPTA).

Purpose of the Study:

To develop and validate a flexible deep learning algorithm for accurate measurement of HKAA, LDFA, and MPTA.
The algorithm should be independent of the operative status of any joint in long-leg radiographs.

Main Methods:

A deep learning algorithm was trained on 2,419 annotated long-leg radiographs.
A two-stage process involved joint detection/operative status labeling and key point localization for angle calculation.
Performance was evaluated using mean absolute error (MAE) on a test set of 239 images.

Keywords:

coronal alignment coronal plane alignment of the knee (CPAK)deep learning hip-knee-ankle angle (HKAA)long-leg radiographs

Related Experiment Videos

Last Updated: Apr 20, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

Main Results:

The algorithm achieved high accuracy comparable to manual measurements.
Mean absolute errors were 0.38° for HKAA, 1.45° for LDFA, and 1.17° for MPTA.
95% of HKAA measurements were within 1° of manual measurements; 91-99% of all measurements were within 3°.

Conclusions:

A flexible deep learning algorithm accurately measures lower-limb alignment angles (HKAA, LDFA, MPTA) on radiographs, regardless of joint implant status.
The tool's high accuracy and low MAE support its use in preoperative and postoperative alignment assessments.
Further training could enhance performance on postoperative images.