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

Fusion of computational and experimental provenance in RO-Crate.

Journal of integrative bioinformatics·2026

Same author

Region-Aware Wasserstein Distances of Persistence Diagrams and Merge Trees.

IEEE transactions on visualization and computer graphics·2026

Same author

Effect of hip bracing on stair walking biomechanics and pain in patients with mild-to-moderate hip osteoarthritis: an intervention study.

BMC musculoskeletal disorders·2026

Same author

IQGAP1 and IQGAP3 are critical host factors for Marburg virus replication, nucleocapsid transport, and cell-to-cell spread.

Cellular and molecular life sciences : CMLS·2026

Same author

Human-centered evaluation of statistical parametric mapping and explainable machine learning for outlier detection in plantar pressure data.

Scientific reports·2026

Same author

Two-year persistence of MERS-CoV-specific antibody and T cell responses after MVA-MERS-S vaccination in healthy adults.

Nature communications·2026

Search research articles

Related Experiment Video

Updated: Sep 17, 2025

Predictive Measurement for Windlass Change in Length and Selected Treatment Outcomes in Chronic Plantar Fasciitis

Predictive Measurement for Windlass Change in Length and Selected Treatment Outcomes in Chronic Plantar Fasciitis

Published on: March 1, 2024

Toward automated plantar pressure analysis: machine learning-based segmentation and key point detection across

Carlo Dindorf¹, Jonas Dully¹, Steven Simon¹

¹Department of Sports Science, University of Kaiserslautern-Landau (RPTU), Kaiserslautern, Germany.

Frontiers in Bioengineering and Biotechnology

|July 4, 2025

Summary

Machine learning models accurately segment plantar pressure data and detect key landmarks across multiple centers. This approach standardizes analysis, reducing manual effort and bias for improved foot function assessment.

Keywords:

U-net artificial intelligence biomechanics deep learning hallux angle image segmentation intelligent systems zoning

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

Related Experiment Videos

Last Updated: Sep 17, 2025

Predictive Measurement for Windlass Change in Length and Selected Treatment Outcomes in Chronic Plantar Fasciitis

Predictive Measurement for Windlass Change in Length and Selected Treatment Outcomes in Chronic Plantar Fasciitis

Published on: March 1, 2024

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

Area of Science:

Biomechanics
Medical Imaging Analysis
Machine Learning in Healthcare

Background:

Plantar pressure analysis is crucial for evaluating foot function and gait, but traditional methods struggle with diverse data.
Existing machine learning models for plantar pressure segmentation are often limited to single-center datasets.
Automated detection of key anatomical landmarks on plantar pressure maps remains underexplored.

Purpose of the Study:

To develop and validate machine learning models for robust anatomical zone segmentation of plantar pressure data.
To explore deep learning regression for predicting key landmarks on plantar pressure profiles.
To assess the performance of these models on multicenter, multi-system datasets.

Main Methods:

Utilized a U-Net model for segmenting plantar surfaces into four regions (hallux, metatarsal areas 1 and 2-5, heel).
Employed deep learning regression models for predicting landmarks like interdigital space coordinates and metatarsal area 1 center.
Standardized and augmented 758 plantar pressure samples from 460 individuals across multiple centers and systems.

Main Results:

The U-Net model achieved expert-level accuracy (Median Dice Scores ≥ 0.88) for segmentation, especially in well-defined areas.
Direct segmentation-based prediction of metatarsal area 1 center outperformed regression or ensemble models (Median Euclidean distance = 4.47).
Regression models showed higher errors for interdigital space detection compared to metatarsal area 1 center prediction.

Conclusions:

The proposed ML framework demonstrates robustness and accuracy for plantar pressure segmentation and landmark detection across diverse multicenter datasets and hardware.
These methods enable efficient, standardized, and automated analysis of large plantar pressure datasets, reducing manual labeling and subjective bias.
The integrated approach offers significant practical value for clinical and research applications requiring consistent foot function assessment.