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

Deep Learning-Based Identification of Surgical Candidacy for Cervical Spinal Cord Decompression.

International journal of spine surgery·2026

Same author

Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage.

EBioMedicine·2024

Same author

Machine Learning Predicts Cerebral Vasospasm in Subarachnoid Hemorrhage Patients.

Research square·2024

Same author

Lumbar Spinal Canal Segmentation in Cases with Lumbar Stenosis Using Deep-U-Net Ensembles.

World neurosurgery·2023

Same author

Harmonization of multi-site functional connectivity measures in tangent space improves brain age prediction.

Proceedings of SPIE--the International Society for Optical Engineering·2023

Same author

Tau-Neurodegeneration <i>mismatch</i> reveals vulnerability and resilience to comorbidities in Alzheimer's continuum.

medRxiv : the preprint server for health sciences·2023

Search research articles

Related Experiment Video

Updated: May 3, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

CLASSIFYING MEDICAL IMAGES USING MORPHOLOGICAL APPEARANCE MANIFOLDS.

Erdem Varol¹, Bilwaj Gaonkar¹, Christos Davatzikos¹

¹University of Pennsylvania, Section of Biomedical Image Analysis, Department of Radiology, 3600 Market Street, Philadelphia, PA, 19104, USA.

Proceedings. IEEE International Symposium on Biomedical Imaging

|January 21, 2014

Summary

This summary is machine-generated.

This study introduces a novel method for medical image classification by sampling image appearances across varying registration parameters. This approach enhances classification accuracy compared to conventional fixed-parameter methods.

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: May 3, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical image analysis
Computational neuroanatomy
Computer vision

Background:

Medical image classification relies on preprocessing steps like nonlinear registration to a template space.
Parametric registration methods are sensitive to parameter choices, affecting classification performance.
Variations in image appearance due to parameters can compromise classifier robustness.

Purpose of the Study:

To address the vulnerability of medical image classifiers to variations in registration parameters.
To propose a methodology that improves classification accuracy by accounting for parameter-induced appearance changes.

Main Methods:

Developed a methodology to sample image appearances by varying nonlinear registration parameters.
Integrated this sampling approach into the feature extraction pipeline for medical image classification.

Main Results:

Demonstrated that sampling image appearances across registration parameter variations yields improved classification accuracies.
Showcased the proposed method's superiority over conventional approaches using fixed registration parameters.

Conclusions:

Varying registration parameters and sampling resulting image appearances enhances medical image classification robustness and accuracy.
This approach offers a more reliable method for feature extraction in computational neuroanatomy and functional brain mapping.