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

ARBUTIN AS A THERAPEUTIC CANDIDATE FOR AUTISM: CURRENT EVIDENCE AND MECHANISTIC INSIGHTS INTO PI3K/Akt/mTOR and Nrf2 PATHWAYS.

European journal of pharmacology·2026

Same author

Rapid and Sustained Remission of Chronic Depression With Adjunctive Transcranial Direct Current Stimulation (tDCS): A Case Report.

The journal of ECT·2026

Same author

Brain white matter microstructural integrity differences between pre-post buprenorphine-naloxone treated individuals with opioid use disorder: Evidence from a DTI study.

Psychiatry research. Neuroimaging·2026

Same author

Update and reuse: Structure-guided nanobody evolution against SARS-CoV-2 escape.

PLoS pathogens·2026

Same author

Development of a high-copy target enhanced multiplexed crRNA-based, amplification-free detection assay (HiTECT) for Brucella spp.

Molecular biology reports·2026

Same author

Hobby horse gait in cerebral adrenoleukodystrophy.

Parkinsonism & related disorders·2026

Same journal

Retraction Note: An efficient hybrid stock trend prediction system during COVID-19 pandemic based on stacked-LSTM and news sentiment analysis.

Multimedia tools and applications·2026

Same journal

Retraction Note: Covid-19 classification using sigmoid based hyper-parameter modified DNN for CT scans and chest X-rays.

Multimedia tools and applications·2026

Same journal

Retraction Note: Smart healthcare system using integrated and lightweight ECC with private blockchain for multimedia medical data processing.

Multimedia tools and applications·2026

Same journal

Retraction Note: Modeling and prediction of KSE - 100 index closing based on news sentiments: an applications of machine learning model and ARMA (p, q) model.

Multimedia tools and applications·2026

Same journal

Retraction Note: COVID-19 Detection using adopted convolutional neural networks and high-performance computing.

Multimedia tools and applications·2026

Same journal

Human-like scene graph generation and evaluation.

Multimedia tools and applications·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 11, 2025

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

Interpreting SVM for medical images using Quadtree.

Prashant Shukla¹, Abhishek Verma¹, Abhishek¹

¹Department of IT, Indian Institute of Information Technology Allahabad, Deoghat, Jhalwa, Allahabad, UP India.

Multimedia Tools and Applications

|August 25, 2020

Summary

This summary is machine-generated.

This study introduces a quadtree method to explain nonlinear Support Vector Machine (SVM) predictions in medical imaging. It highlights discriminative regions (ROIs) for better interpretability of classification results.

Keywords:

Interpretability Localization Non linear classification Quadtree

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

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Dec 11, 2025

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

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Medical Imaging
Machine Learning
Computer Vision

Background:

Interpreting nonlinear Support Vector Machine (SVM) predictions in medical image classification is challenging due to the implicit nature of kernel mapping.
Understanding the rationale behind SVM predictions is crucial for clinical trust and adoption.

Purpose of the Study:

To develop a quadtree-based approach for capturing spatial information in medical images.
To enhance the interpretability of nonlinear SVM predictions by identifying discriminative regions.

Main Methods:

A quadtree decomposition is recursively applied to medical images.
Support Vector Machines (SVMs) are trained on sub-images generated by the quadtree decomposition.
Regions of Interest (ROIs) containing discriminative features are identified and highlighted.

Main Results:

The quadtree-based method effectively localizes discriminative regions crucial for SVM predictions.
Experiments on various medical image datasets demonstrate the approach's effectiveness in explaining predictions.
Occlusion methods were used to validate the correctness and importance of the identified ROIs.

Conclusions:

The proposed quadtree approach significantly improves the interpretability of nonlinear SVMs in medical image analysis.
Identifying and highlighting localized discriminative regions aids in understanding complex classification decisions.
This method offers a valuable tool for enhancing trust and transparency in AI-driven medical diagnostics.