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

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Diagnosis and Staging of Patients with Prostate Cancer: Report from the 2025 Advanced Prostate Cancer Consensus Conference (APCCC) Diagnostics.

European urology·2026

Same author

ESR Essentials: imaging of melanoma-practice recommendations by the European Society of Oncologic Imaging.

European radiology·2026

Same author

Focal Small Bowel FDG Uptake in Cancer Patients Undergoing PET/CT: Prevalence and Etiology.

Clinical nuclear medicine·2026

Same author

Histological response dynamics in gastric extranodal marginal zone B-cell lymphoma of the mucosa-associated lymphoid tissue after helicobacter-pylori eradication: a singlecenter longitudinal analysis.

Haematologica·2026

Same author

Multiparametric MRI assessment of 6-month Post-Treatment response following Real-Time adaptive stereotactic body radiotherapy for prostate cancer: Correlation with Post-Treatment PSA kinetics.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026

Same author

Staging and imaging-based prognostication in renal cell carcinoma: current guidelines and practical considerations.

Abdominal radiology (New York)·2026

Search research articles

Related Experiment Video

Updated: Aug 7, 2025

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

ComBat Harmonization for MRI Radiomics: Impact on Nonbinary Tissue Classification by Machine Learning.

Doris Leithner¹, Rachel B Nevin¹, Peter Gibbs¹

¹From the Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY.

Investigative Radiology

|March 10, 2023

Summary

This summary is machine-generated.

ComBat harmonization significantly improved multiclass radiomics tissue classification in heterogeneous MRI data. The ComBat variant without empirical Bayes estimation (ComBat-NB) demonstrated superior performance for radiomics classification tasks.

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Aug 7, 2025

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

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Radiomics
Medical Imaging
Biostatistics

Background:

Technical heterogeneity in multi-center MRI datasets can impede radiomics analysis.
Harmonization techniques are crucial for standardizing data across different scanners and vendors.

Purpose of the Study:

To evaluate the effectiveness of ComBat harmonization in improving multiclass radiomics-based tissue classification.
To compare the performance of two ComBat variants (ComBat-B and ComBat-NB) for MRI radiomics data.

Main Methods:

Retrospective analysis of T1-weighted 3D gradient echo Dixon MRI data from 100 patients across two scanners.
Extraction of radiomic features (GLH, GLCM, GLRLM, GLSZM) from liver, spleen, and paraspinal muscle.
Tissue classification using Linear Discriminant Analysis and a Multilayer Perceptron neural network with and without ComBat harmonization.

Main Results:

ComBat harmonization significantly increased classification accuracies for both Linear Discriminant Analysis and Multilayer Perceptron.
ComBat-NB harmonization yielded higher accuracies (e.g., 92.7% LDA, 89.4% GLSZM MLP) compared to ComBat-B and unharmonized data.
Improvements varied across radiomic feature categories and classification methods.

Conclusions:

ComBat harmonization is beneficial for multicenter MRI radiomics studies involving nonbinary classification.
The choice of ComBat variant (ComBat-NB recommended) and feature category impacts classification performance.