Search research articles

Search research articles

Related Experiment Video

Updated: Jan 12, 2026

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

An explainable modified convolutional mixer neural network-based deep learning framework for accurate brain tumor

S Selva Birunda¹, M Kaliappan¹, R Ramana¹

¹Department of Artificial Intelligence and Data Science, Ramco Institute of Technology, Rajapalayam, India.

Neurological Research

|October 31, 2025

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

Banana Plant Disease Classification Using Hybrid Convolutional Neural Network.

Computational intelligence and neuroscience·2022

Same author

Cervical Cancer Identification with Synthetic Minority Oversampling Technique and PCA Analysis using Random Forest Classifier.

Journal of medical systems·2019

Same author

Development of Big Data Predictive Analytics Model for Disease Prediction using Machine learning Technique.

Journal of medical systems·2019

Same author

Secure and fair cluster head selection protocol for enhancing security in mobile ad hoc networks.

TheScientificWorldJournal·2014

Same author

Aftercare of depressed inpatients--service delivery and unmet needs.

Social psychiatry and psychiatric epidemiology·2003

Same author

Medication received by patients with depression following the acute episode: adequacy and relation to outcome.

The British journal of psychiatry : the journal of mental science·1999

Same journal

Does early gastrostomy tube placement after stroke improve functional recovery and quality of life? A literature-informed pathway-decomposition analysis.

Neurological research·2026

Same journal

Predictive ability of cardiac biomarkers for early risk stratification and 3-month functional outcomes after reperfusion therapy in acute ischemic stroke.

Neurological research·2026

Same journal

Luteolin reduces sciatic nerve damage and modulates TRPV1 and TRPM2 expression in diabetic rats.

Neurological research·2026

Same journal

Cholinergic regulation of memory retrieval: scopolamine reduces hippocampal neurotrophic and metabolic support.

Neurological research·2026

Same journal

Effect of intravenous thrombolysis on arterial and venous profiles in large-vessel occlusion stroke: a retrospective propensity score-matched study.

Neurological research·2026

Same journal

Association between post-treatment neuroimaging markers of cerebral small vessel disease and short-term efficacy of recombinant tissue plasminogen activator in acute stroke patients.

Neurological research·2026

See all related 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

This study introduces an Explainable Modified Convolutional Mixer Neural Network (EM-ConvMixer+Net) for efficient and accurate brain tumor detection and classification using MRI images. The novel model achieves high accuracy, offering a reliable tool for clinical diagnosis.

Area of Science:

Medical Imaging
Artificial Intelligence
Computational Neuroscience

Background:

Brain tumors (BTs) present a significant health challenge due to their complexity and associated low survival rates.
Traditional diagnostic models are often computationally intensive and require prolonged training periods, hindering timely clinical application.
There is a need for advanced, efficient, and interpretable AI models for brain tumor analysis.

Purpose of the Study:

To develop and validate a novel Explainable Modified Convolutional Mixer Neural Network (EM-ConvMixer+Net) for brain tumor detection and classification.
To improve the computational efficiency and interpretability of AI models in neuro-oncology.
To enhance the accuracy and reliability of automated brain tumor diagnosis from MRI data.

Main Methods:

Keywords:

Brain tumor detection cross attention network external attention network gradient-weighted class activation mapping modified artificial neural network segmentation and region growing

More Related Videos

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

Related Experiment Videos

Last Updated: Jan 12, 2026

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

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

Utilized a dataset of 10,087 MRI images from two public sources, employing preprocessing techniques like denoising and augmentation.
Implemented tumor segmentation via the Adopted Region Growing method, followed by feature enhancement using a convolutional operations mixer block (ConvMixer+).
Employed Cross Attention Network (CANet) and External Attention Network (EANet) for feature fusion and refinement, with classification performed by a Modified Artificial Neural Network (M-ANN) and explainability via Grad-CAM.

Main Results:

The EM-ConvMixer+Net model achieved a high accuracy of 98.86% and an F1-score of 98.44% in experimental validation.
Comparative and ablation studies confirmed the model's effectiveness and robustness.
The Gradient-weighted Class Activation Mapping (Grad-CAM) provided visual explanations, enhancing model interpretability.

Conclusions:

The proposed EM-ConvMixer+Net framework offers a computationally efficient and interpretable solution for brain tumor diagnosis.
This technique demonstrates significant potential for advancing clinical decision-making in neuro-oncology.
The model's high performance and explainability pave the way for more reliable AI-assisted medical diagnostics.