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: Feb 25, 2026

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

Significant Anatomy Detection Through Sparse Classification: A Comparative Study.

Li Zhang, Dana Cobzas, Alan H Wilman

IEEE Transactions on Medical Imaging

|August 8, 2017

Summary

This summary is machine-generated.

Related Concept Videos

Classification of Bones

Classification of Bones

The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...

You might also read

Related Articles

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

Sort by

Same author

Susceptibility Source Separation Unveils Paramagnetic and Diamagnetic Trajectories in Healthy Brains From 5 to 90 Years.

NMR in biomedicine·2026

Same author

Myelin damage in radiologically isolated syndrome is associated with decreased processing speed.

Multiple sclerosis journal - experimental, translational and clinical·2026

Same author

DeepRelaxo: Fast Mono-Exponential Magnitude Brain R2* Mapping With Reduced Echoes Using Self-Supervised Deep Learning.

Magnetic resonance in medicine·2026

Same author

Advancing Quantitative Susceptibility Mapping With 2.5D Diffusion Models for Rapid Intracranial Hemorrhage Quantification.

Magnetic resonance in medicine·2026

Same author

The influence of prism adaptation on spatial biases is not dependent on which hand is used to adapt.

Experimental brain research·2026

Same author

Exploring the Value of Brain T2* Weighted and FLAIR Imaging for Diagnosing Amyotrophic Lateral Sclerosis.

The Canadian journal of neurological sciences. Le journal canadien des sciences neurologiques·2026

Same journal

UniOCTSeg++: Refined Hierarchical Prompt Strategy and Bi-directional Progressive Consistency Learning for Universal Retinal Layer Segmentation in OCT.

IEEE transactions on medical imaging·2026

Same journal

Volumetric Functional Ultrasound Imaging in Macaques.

IEEE transactions on medical imaging·2026

Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026

Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026

Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026

Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026

See all related articles

Total variation (TV) penalty outperforms graph net (GN) models for discriminative anatomy detection in neuroimaging. Adding an L2 penalty further enhances accuracy in sparse classification models for both methods.

Area of Science:

Neuroimaging Analysis
Computational Neuroscience
Medical Image Processing

Background:

Mass univariate approaches are common for discriminative anatomy detection in high-dimensional neuroimaging data.
Sparse classification models offer improved accuracy and variable selection over traditional methods.
Existing regularization methods include Graph Net (GN) and total variation (TV) models, enhancing classification but not region recovery accuracy.

Purpose of the Study:

To theoretically prove bounds on recovered sparse coefficients and selected image regions for GN and TV penalty models.
To practically evaluate the accuracy and stability of recovered regions using simulated and real MRI data.
To compare the performance of GN and TV regularization methods, and assess the impact of L2 penalty addition.

Main Methods:

Related Experiment Videos

Last Updated: Feb 25, 2026

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

Theoretical analysis of sparse coefficient and image region recovery bounds for four models (two GN, two TV).
Validation using simulated neuroimaging data to measure the accuracy of selected regions against ground truth.
Cross-validation on real MRI data to assess the stability of recovered regions.

Main Results:

Theoretical bounds were established for sparse coefficients and selected regions in GN and TV models.
Practical evaluation confirmed theoretical findings, demonstrating TV penalty's superiority over the GN model.
The addition of an L2 penalty was shown to improve coefficient estimation and region selection accuracy for both model types.

Conclusions:

Total Variation (TV) regularization is more effective than Graph Net (GN) for discriminative anatomy detection in neuroimaging.
Sparse classification models with image-based regularization provide accurate and interpretable results for neuroimaging analysis.
Incorporating an L2 penalty enhances the performance of both TV and GN models, leading to more precise anatomical region identification.