Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Detecting acromegaly: screening for disease with a morphable model.

Erik Learned-Miller1, Qifeng Lu, Angela Paisley

  • 1University of Massachusetts, Amherst, Massachusetts, USA. elm@cs.umass.edu

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 16, 2007
PubMed
Summary
This summary is machine-generated.

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

Effects of dietary phytic acid on growth, antioxidant status, hepatic metabolism, and immune-related gene expression in Nile tilapia (Oreochromis niloticus).

Fish physiology and biochemistry·2026
Same author

Effects of faba beans (Vicia faba L.) on the growth, amino and fatty acids compositions, flesh quality and oxidative stability of African catfish, Clarias gariepinus.

Journal of fish biology·2026
Same author

A Bilayer Hydrogel Sensor for Elderly Oriented Human-Machine Interaction.

ACS applied materials & interfaces·2026
Same author

Organic-engineered MXenes enabling digital-to-analog switching for neuromorphic application.

Journal of colloid and interface science·2025
Same author

Toward Unified Expertise: Learning a Single Vision Model From Diverse Perception.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

A hot-humid tolerant and antibacterial MXene-based hydrogel sensor for real-time cardiorespiratory monitoring in endurance sports.

Microsystems & nanoengineering·2025

This study introduces a novel semi-automated method for detecting acromegaly using support vector machines and a 3D morphable face model. Early detection of this rare disorder can lead to timely treatment and prevent permanent changes.

Area of Science:

  • Biomedical Engineering
  • Medical Imaging
  • Machine Learning

Background:

  • Acromegaly is a rare endocrine disorder caused by excess growth hormone, leading to characteristic facial changes.
  • Delayed diagnosis of acromegaly can result in significant morbidity and irreversible physical alterations.
  • Current diagnostic methods may miss early signs, necessitating improved detection strategies.

Purpose of the Study:

  • To develop and evaluate a semi-automated approach for the early detection of acromegaly.
  • To leverage machine learning and 3D facial modeling for improved diagnostic accuracy.

Main Methods:

  • Utilized a novel combination of support vector machines (SVMs) and a 3D morphable face model.
  • Trained a classifier on 24 frontal photographs of acromegaly patients and 25 controls.

Related Experiment Videos

  • Employed an analysis-by-synthesis loop with the Blanz and Vetter 3D morphable face model to extract facial shape parameters.

    • Main Results:

    • The developed classifier demonstrated encouraging performance in distinguishing between acromegaly patients and healthy subjects.
    • Model parameters effectively captured 3D head shape features from single photographs for classification.
    • The semi-automated approach showed potential for aiding in acromegaly diagnosis.

    Conclusions:

    • A semi-automated method combining SVMs and 3D morphable models shows promise for acromegaly detection.
    • This approach could facilitate earlier diagnosis and intervention for acromegaly patients.
    • Further validation with larger datasets is warranted to confirm clinical utility.