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 27, 2026

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

A framework for optimal kernel-based manifold embedding of medical image data.

Veronika A Zimmer¹, Karim Lekadir¹, Corné Hoogendoorn¹

¹Information and Communication Technologies Department, Universitat Pompeu Fabra, Barcelona, Spain.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society

|July 11, 2014

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

Unlocking 3D baby face photogrammetry: Multi-view BabyMorph reconstruction from uncalibrated photographs.

Expert systems with applications·2026

Same author

Artificial intelligence for detecting fetal orofacial clefts and advancing medical education.

Nature communications·2026

Same author

Multi-omic analysis of deep learning-derived phenotypes links ophthalmic imaging to cardiovascular and neurological traits.

Nature cardiovascular research·2026

Same author

Classification of bacterial images obtained optically using some pre-trained models.

Journal of microbiological methods·2026

Same author

From pixels to polygons: A survey of deep learning approaches for medical image-to-mesh reconstruction.

Medical image analysis·2026

Same author

The Spanish transplantation model as a benchmark: clinical, societal, and economic impact of liver transplants in Spain (1984-2024).

Health economics review·2026

Selecting the right kernel function is crucial for nonlinear manifold embedding in medical imaging. This study introduces an automated method to optimize kernel selection for improved medical image analysis and data representation.

Area of Science:

Medical Image Analysis
Machine Learning
Nonlinear Dimensionality Reduction

Background:

Kernel-based dimensionality reduction is vital for analyzing complex medical image data.
Standard kernels (Gaussian, polynomial) may not always be optimal for specific medical imaging applications.
Effective nonlinear manifold embedding relies on appropriate kernel function and parameter selection.

Purpose of the Study:

To investigate the impact of kernel functions on nonlinear manifold embedding in medical imaging.
To develop and evaluate a method for automatic kernel selection and parameter optimization.
To enhance the accuracy and interpretability of medical image data analysis.

Main Methods:

Literature review of advanced kernel functions from statistics, machine learning, and signal processing.

Keywords:

Kernel principal component analysis Manifold embedding quality Multilevel kernel combinations Nonlinear dimensionality reduction

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Related Experiment Videos

Last Updated: Apr 27, 2026

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

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Implementation of kernel-based formulations for Isomap and Locally Linear Embedding (LLE).

Development of an automated kernel selection method with parameter optimization, including spatial considerations and kernel combination.

Main Results:

A unified framework for kernel-based manifold embedding was established.
The proposed method demonstrated the ability to automatically select optimal kernels and parameters.
Experiments on synthetic, phantom, and real medical data (brain, multispectral images) showed improved embedding results compared to standard approaches.

Conclusions:

Kernel selection significantly impacts the quality of nonlinear manifold embeddings in medical image analysis.
The automated kernel selection method offers a robust approach to optimize manifold embeddings.
This work provides a valuable tool for advancing the analysis of high-dimensional medical image data.