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: Jun 4, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Automatic anatomy recognition via multiobject oriented active shape models.

Xinjian Chen¹, Jayaram K Udupa, Abass Alavi

¹Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Room 1C515, Building 10, Bethesda, Maryland 20892-1182, USA.

Medical Physics

|February 10, 2011

Summary

This study demonstrates a feasible automatic anatomy recognition system for radiology, improving accuracy by including more objects in the model. The system consistently finds optimal solutions for identifying anatomical structures in 2D images.

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

PET-Based Personalized Management in Clinical Oncology: An Unavoidable Path for the Foreseeable Future.

PET clinics·2016

Same author

Personalized Management Approaches in Lymphoma: Utility of Fluorodeoxyglucose-PET Imaging.

PET clinics·2016

Same author

Evolving Role of Molecular Imaging with (18)F-Sodium Fluoride PET as a Biomarker for Calcium Metabolism.

Current osteoporosis reports·2016

Same author

Ocular Melanoma and Other Unusual Sites.

PET clinics·2016

Same author

Other PET Tracers and Prospects for the Future.

PET clinics·2016

Same author

Normal Variants and Effects of Aging on the Gastrointestinal Tract.

PET clinics·2016

Area of Science:

Medical Imaging
Radiology
Computer-Aided Diagnosis

Background:

Automatic anatomy recognition (AAR) is crucial for clinical radiology.
Developing robust AAR systems for 2D clinical images presents significant challenges.

Purpose of the Study:

To assess the feasibility and efficacy of an automatic anatomy recognition (AAR) system.
To demonstrate the system's operation on clinical 2D radiological images.

Main Methods:

A multiobject generalization of the OASM algorithm was developed.
A three-level dynamic programming approach was used for boundary delineation.
Object recognition strategies identified pose vectors for optimal model arrangement.

Main Results:

More Related Videos

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Related Experiment Videos

Last Updated: Jun 4, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Delineation accuracy improved to 97%-98% TPVF with low FPVF (0.1%-0.2%) when multiple objects were modeled.
Recognition accuracy of >= 90% typically resulted in TPVF >= 95% and FPVF <= 0.5%.
The proposed method achieved global optimum solutions in 97% of cases across diverse datasets.

Conclusions:

The developed AAR system is feasible and effective for clinical radiology.
Increasing model complexity (more, larger, and spread-out objects) enhances accuracy.
The system demonstrates high reliability in finding globally optimal anatomical recognition solutions.