Search research articles

Search research articles

Related Experiment Video

Updated: Jan 3, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A novel enhanced softmax loss function for brain tumour detection using deep learning.

Sunil Maharjan¹, Abeer Alsadoon¹, P W C Prasad¹

¹Charles Sturt University, Sydney, Australia.

Journal of Neuroscience Methods

|November 18, 2019

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

Retraction Note: Comparative analysis of heart disease prediction using logistic regression, SVM, KNN, and random forest with cross-validation for improved accuracy.

Scientific reports·2026

Same author

Comparative analysis of heart disease prediction using logistic regression, SVM, KNN, and random forest with cross-validation for improved accuracy.

Scientific reports·2025

Same author

Candidate antibody reference reagents for Chlamydia trachomatis serology.

Journal of immunological methods·2024

Same author

Model based smooth super-twisting control of cancer chemotherapy treatment.

Computers in biology and medicine·2024

Same author

Enhanced cluster detection and noise reduction for geospatial time series data of COVID-19.

Multimedia tools and applications·2023

Same author

Editorial: Artificial intelligence and big data for value-based care.

Frontiers in medicine·2023

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 a deep learning model for accurate brain tumor classification from MRI images, overcoming limitations of binary classification and reducing overfitting. The enhanced system achieves higher accuracy and faster processing times compared to existing methods.

Area of Science:

Medical Imaging
Deep Learning
Computational Neuroscience

Background:

The sigmoid function's limitation to binary classification hinders multiclass brain tumor classification in deep learning.
Overfitting and processing time are significant challenges in current deep learning models for medical image analysis.

Purpose of the Study:

To enhance brain tumor classification accuracy using deep learning.
To address the limitations of binary classification inherent in the sigmoid function.
To mitigate the risk of overfitting and reduce processing time in multiclass classification tasks.

Main Methods:

Development of a convolutional neural network (CNN) architecture.
Implementation of a modified softmax loss function for multiclass classification.

Keywords:

Brain tumour detection Deep learning Loss function Multiclass classification Neural network Softmax function

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 3, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

Integration of regularization techniques to prevent overfitting.

Main Results:

The proposed system demonstrated superior performance in classifying different types of brain tumors from 3D MRI images.
Achieved classification accuracy improved by approximately 2% compared to existing solutions.
Reduced processing time to 40-50 ms, indicating significant efficiency gains.

Conclusions:

The novel deep learning approach effectively overcomes the binary classification limitation of the sigmoid function for brain tumor detection.
The system successfully reduces overfitting and processing time, offering a more efficient and accurate solution.
This method provides a robust framework for multiclass classification of brain tumors from MRI data.