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

Publisher Correction: Response to: "Distinct associations of blood pressure phenotypes with subclinical cerebrovascular disease and coronary artery calcification in Japanese men".

Hypertension research : official journal of the Japanese Society of Hypertension·2026

Same author

Machine learning-based morphological brain analysis in schizophrenia and unaffected siblings: a multisite study of potential risk markers.

Frontiers in neuroscience·2026

Same author

Response to: "Distinct associations of blood pressure phenotypes with subclinical cerebrovascular disease and coronary artery calcification in Japanese men".

Hypertension research : official journal of the Japanese Society of Hypertension·2026

Same author

Distinct associations of blood pressure phenotypes with subclinical cerebrovascular disease and coronary artery calcification in Japanese men.

Hypertension research : official journal of the Japanese Society of Hypertension·2026

Same author

Impairment of novelty-dependent hippocampal behavioural tagging in Septin5-deficient mice.

Molecular brain·2026

Same author

Septin5 deficiency impairs both recent and remote contextual fear memory.

Molecular brain·2025

Search research articles

Related Experiment Video

Updated: Apr 21, 2026

Abbiategrasso Brain Bank Protocol for Collecting, Processing and Characterizing Aging Brains

Abbiategrasso Brain Bank Protocol for Collecting, Processing and Characterizing Aging Brains

Published on: June 3, 2020

Advancing brain age estimation: normative deviation mapping (NDM) for sensitive detection of pathological aging.

Akihiko Shiino¹, Kenji Tanigaki², Maya Oki³

¹Department of Neurosurgery, Shiga University of Medical Science, Otsu, Shiga, 520-2192, Japan.

|April 19, 2026

Summary

A new normative deviation mapping (NDM) model offers a superior method for calculating brain age, outperforming traditional machine learning. This advanced brain age biomarker enhances detection of neurodegenerative diseases and correlates better with cognitive function.

Keywords:

Brain age Brain function Machine learning Normative deviation mapping Voxel-based morphometry

More Related Videos

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

Published on: May 7, 2014

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse

Published on: May 19, 2015

Related Experiment Videos

Last Updated: Apr 21, 2026

Abbiategrasso Brain Bank Protocol for Collecting, Processing and Characterizing Aging Brains

Abbiategrasso Brain Bank Protocol for Collecting, Processing and Characterizing Aging Brains

Published on: June 3, 2020

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

Published on: May 7, 2014

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse

Published on: May 19, 2015

Area of Science:

Neuroimaging
Biomarkers
Brain Health

Background:

Brain age, estimated via machine learning (ML), is a key neuroimaging biomarker for brain health.
Conventional ML models exhibit bias and can obscure age-related biological variations, limiting their ability to detect subtle aging.
This necessitates the development of more sensitive and less biased methods for brain age estimation.

Purpose of the Study:

To introduce and validate a novel Normative Deviation Mapping (NDM) model as an alternative to conventional ML for brain age estimation.
To assess the NDM model's efficacy in reducing bias and improving the detection of pathological changes compared to standard ML approaches.
To evaluate the NDM model's correlation with cognitive function and its ability to capture biological brain aging.

Main Methods:

Analysis of MRI-derived volumes from 223 brain regions in 10,539 participants (aged 4-98 years).
Development of the NDM model, assuming normal distribution of age-specific volumes to calculate regional deviations for brain age estimation.
Comparison of NDM model performance against standard ML models (e.g., neural networks, extreme gradient boosting).

Main Results:

The NDM model effectively eliminated regression bias, unlike standard ML models.
NDM mitigated the underestimation of brain age in older adults, significantly improving detection of neurodegenerative diseases like Alzheimer's.
In healthy individuals, NDM showed a stronger correlation with cognitive function than chronological age.
Data harmonization using ComBat-GAM may obscure pathological associations, requiring careful application.

Conclusions:

The NDM model provides a more robust and biologically meaningful brain age biomarker than conventional ML.
NDM enhances the detection of pathological changes and better reflects biological brain aging.
The model reveals impacts of amyloid accumulation and lifestyle on brain health, offering insights for future research and clinical applications.