OSCR

BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images.

Overview

Authors: Sankari Chidambaram1, Jamuna Venugopal2
  1. Department of Electrical and Electronics Engineering (EEE), Chennai Institute of Technology, Chennai, India
  2. Department of Electrical and Electronics Engineering (EEE), Jerusalem College of Engineering, Chennai, India
Journal: Frontiers in oncology, volume 16, article 1834400
Dates: received 19 March 2026; accepted 30 June 2026; published online 31 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3389/fonc.2026.1834400 · PMID 42601923 · PMCID PMC13472811 · OpenAlex W7171959749
Open access: gold, a free copy (OpenAlex)
Categories: structural MRI / diffusion (modality), other condition (population), methods / tools (subfield)
Methods: Machine learning
Keywords: brain tumour classification, CBAM attention, deep learning, EfficientNet-B4, focal loss, Grad-CAM, medical image analysis, MRI
Topic: Brain Tumor Detection and Classification (Computer Vision and Pattern Recognition, Computer Science), according to OpenAlex
Citations: not cited yet (Europe PMC); 67 references in the paper

Abstract

Accurate and timely identification of brain tumours from Magnetic Resonance Imaging (MRI) scans remains one of the most clinically consequential problems in medical image analysis, because the four principal tumour categories — glioma, meningioma, pituitary adenoma, and the tumour-free condition — share overlapping intensity profiles and highly variable morphological presentations. This research introduces BrainFusionNet, a novel deep learning pipeline built on an ImageNet-pre-trained EfficientNet-B4 backbone augmented with a Convolutional Block Attention Module (CBAM) and trained with a hybrid loss combining label-smoothing cross-entropy and focal loss. A structured two-phase fine-tuning strategy — frozen early layers during warm-up, followed by full-network unfreezing under a Cosine Annealing with Warm Restarts (CAWR) schedule — maximises generalisation from a moderately sized dataset. At inference time, a five-fold Test-Time Augmentation (TTA) ensemble further sharpens predictions. Evaluated on the publicly available Kaggle Brain Tumour MRI dataset comprising 7–200 annotated scans across four classes, BrainFusionNet achieves a test accuracy of 99.81%, a macro-averaged F1-score of 99.78%, and a mean AUC of 0.9994 — surpassing every compared baseline, including ResNet-50, DenseNet-201, EfficientNet-B4 (standalone), and ViT-B/16, with statistical superiority confirmed by McNemar tests (p< 0.0001 for all comparisons). Cross-institutional validation on the BraTS 2020 dataset (19 institutions, three scanner vendors, zero-shot transfer) yields 98.25% accuracy and AUC = 0.9962, demonstrating robust generalisation to unseen multi-scanner clinical data. Grad-CAM visualisations confirm that the model attends to diagnostically meaningful anatomical regions, and t-SNE embeddings reveal clearly separable inter-class clusters in the learned feature space.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability statement

The original contributions presented in the study are included in the article/supplementary material. Further inquiries can be directed to the corresponding author.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 2 authors, 8 keywords, 60 references.

Cite

This paper

Chidambaram, S., & Venugopal, J. (2026). BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images. Frontiers in oncology, 16, 1834400. https://doi.org/10.3389/fonc.2026.1834400

BibTeX

@article{chidambaram2026brainfusionnet,
author = {Chidambaram, Sankari and Venugopal, Jamuna},
title = {{BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images}},
journal = {Frontiers in oncology},
year = {2026},
month = jul,
volume = {16},
pages = {1834400},
publisher = {Frontiers Media SA},
issn = {2234-943X},
doi = {10.3389/fonc.2026.1834400},
url = {https://doi.org/10.3389/fonc.2026.1834400},
pmid = {42601923},
pmcid = {PMC13472811}
}

RIS

TY - JOUR
AU - Chidambaram, Sankari
AU - Venugopal, Jamuna
TI - BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images
T2 - Frontiers in oncology
J2 - Front Oncol
PY - 2026
DA - 2026/07/31
VL - 16
SP - 1834400
SN - 2234-943X
PB - Frontiers Media SA
DO - 10.3389/fonc.2026.1834400
UR - https://doi.org/10.3389/fonc.2026.1834400
LA - en
ER -

CSL-JSON

{
"id": "10.3389/fonc.2026.1834400",
"type": "article-journal",
"title": "BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images",
"container-title": "Frontiers in oncology",
"author": [
{
"family": "Chidambaram",
"given": "Sankari"
},
{
"family": "Venugopal",
"given": "Jamuna"
}
],
"container-title-short": "Front Oncol",
"volume": "16",
"page": "1834400",
"DOI": "10.3389/fonc.2026.1834400",
"PMID": "42601923",
"PMCID": "PMC13472811",
"ISSN": "2234-943X",
"publisher": "Frontiers Media SA",
"URL": "https://doi.org/10.3389/fonc.2026.1834400",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
31
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/diagnostics14040383
A Novel Ensemble Framework for Multi-Classification of Brain Tumors Using Magnetic Resonance Imaging.
Journal: Diagnostics (Basel, Switzerland)
In common: kaggle.com/datasets/masoudnickparvar, methods / tools, structural MRI / diffusion, other condition, 7 references
[2] doi:10.3389/fonc.2026.1806663
A denoising autoencoder-enhanced ResNet 50 framework for explainable brain tumor classification using MRI.
Journal: Frontiers in oncology
In common: kaggle.com/datasets/masoudnickparvar, methods / tools, structural MRI / diffusion, other condition, 6 references
[3] doi:10.7717/peerj-cs.2556
Hybrid deep learning approach for brain tumor classification using EfficientNetB0 and novel quantum genetic algorithm.
Journal: PeerJ. Computer science
In common: methods / tools, other condition, 8 references
[4] doi:10.2196/76344
Trade-Off Analysis of Classical Machine Learning and Deep Learning Models for Robust Brain Tumor Detection: Benchmark Study.
Journal: JMIR AI
In common: methods / tools, other condition, 8 references
[5] doi:10.1155/2022/7897669
A Novel and Effective Brain Tumor Classification Model Using Deep Feature Fusion and Famous Machine Learning Classifiers.
Journal: Computational intelligence and neuroscience
In common: other condition, 8 references
[6] doi:10.7717/peerj-cs.2920 [code]
A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis.
Journal: PeerJ. Computer science
In common: methods / tools, structural MRI / diffusion, other condition, 7 references
[7] doi:10.3390/cancers17010121
Advanced Brain Tumor Classification in MR Images Using Transfer Learning and Pre-Trained Deep CNN Models.
Journal: Cancers
In common: kaggle.com/datasets/masoudnickparvar, structural MRI / diffusion, other condition, 4 references
[8] doi:10.7717/peerj-cs.1878 [code]
Enhancing brain tumor diagnosis: an optimized CNN hyperparameter model for improved accuracy and reliability.
Journal: PeerJ. Computer science
In common: kaggle.com/datasets/masoudnickparvar, other condition, 4 references
[9] doi:10.1371/journal.pone.0361135
A method for brain tumor detection and localization by means of deep learning and reliable prediction explainability.
Journal: PloS one
In common: kaggle.com/datasets/masoudnickparvar, methods / tools, structural MRI / diffusion, other condition, 4 references
[10] doi:10.1016/j.mex.2025.103769
BRAIN-META: A reproducible CNN-vision transformer meta-ensemble pipeline for explainable brain tumor classification.
Journal: MethodsX
In common: kaggle.com/datasets/masoudnickparvar, methods / tools, structural MRI / diffusion, other condition, 3 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.