Global-local feature fusion: a robust hybrid deep learning model for multiclass brain tumor classification with Grad-CAM++ interpretation.

Overview

1. Department of Computer Science and Engineering, Bipin Tripathi Kumaon Institute of Technology, Dwarahat, Uttarakhand, India
2. School of Computer Applications and Technology, Galgotias University, Greater Noida, Uttar Pradesh, India
3. Center for Precision Health, McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
4. Department of Health Information Management and Technology, College of Applied Medical Sciences, King Faisal University, Al-Ahsa, Saudi Arabia

Abstract

Background: Accurate classification of brain tumors in MRI scans is critical for effective clinical decision making, yet manual assessment is labor-intensive and subject to variability. Although deep learning models, particularly CNNs and Transformers, have shown potential, each architecture alone has limitations: CNNs excel at local feature extraction but lack global context awareness, while Transformers capture global relationships but may overlook fine-grained details.

Objectives: To develop a hybrid Transfer Learning–Transformer model that integrates CNN-driven local feature modeling with Transformer-based global reasoning to enhance multi-class brain tumor classification.

Methods: The proposed workflow comprises three stages: (1) benchmarking standalone CNN (ResNet50, VGG19, ConvNeXtBase, EfficientNetV2B0) and Transformer models (ViT, Swin, DeiT, PoolFormer); (2) constructing two intra-family hybrids—HTL (ResNet50 + ConvNeXtBase) and HTF (PoolFormer + ViT); and (3) fusing them into a final hybrid model (HF). Two public MRI datasets (Figshare, Kaggle) were used. Models were trained, validated, and tested on the Kaggle dataset, while the Figshare dataset was used exclusively for external validation. Performance was assessed using accuracy, precision, recall, F1-score, AUC, Friedman’s aligned-rank test, Kendall’s W, Holm post hoc analysis, TOPSIS-based ranking, calibration analysis (Brier score), and Grad-CAM++ for interpretability.

Results: The HF model achieved near-perfect classification (∼99.4% on Kaggle and up to 100% on Figshare), significantly outperforming all baseline and single-architecture models. Statistical and multi-criteria analyses consistently ranked HF as the top-performing model, while calibration results confirmed reliable probability estimation. Grad-CAM++ further indicated tumor-focused decision-making.

Conclusion: The proposed hybrid model delivers high accuracy, strong generalizability, and reliable, interpretable predictions across MRI datasets, positioning it as a promising solution for AI-assisted brain tumor diagnosis.

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

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in 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

• figshare:1512427 — at figshare; found in the references
• github.com/kirti-pant/convnext-base-for-brain-tumor-classification--data — at github.com; found in “Data availability statement”

Data availability statement

The datasets used in the experiment are publicly available at https://github.com/Kirti-Pant/ConvNeXT-Base-for-Brain-Tumor-Classification--Data.git.

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 2, 28 September 2026

• Funding: added University of Texas Health Science Center at Houston; King Faisal University

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 5 authors, 8 keywords, 69 references.

Cite

This paper

Pant, K., Dutta Pramanik, P. K., Ganie, S. M., Saha, A., & Zhao, Z. (2026). Global-local feature fusion: a robust hybrid deep learning model for multiclass brain tumor classification with Grad-CAM++ interpretation. Frontiers in genetics, 17, 1814786. https://doi.org/10.3389/fgene.2026.1814786

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:10.1186/s42492-026-00230-4

Hierarchical two-stage ensemble of dilated U-net models for brain tumor segmentation.

Journal: Visual computing for industry, biomedicine, and art

In common: figshare 1512427, other condition, 4 references

[2] doi:10.3390/jimaging12060233 [code]

Brain Tumor Classification in MRI Images Using Combined Transfer Learning and Convolutional Neural Networks.

Journal: Journal of imaging

In common: figshare 1512427, structural MRI / diffusion, other condition, 2 references

[3] doi:10.3390/diagnostics16172806

Brain Tumor Segmentation and Grading on MRI Using Deep Learning: A Systematic Literature Review and Benchmark-Driven Comparative Analysis.

Journal: Diagnostics (Basel, Switzerland)

In common: structural MRI / diffusion, other condition, 4 references

[4] doi:10.1038/s41598-026-46803-4 [code]

BrainGraphNet-ViT model: a hybrid model combining vision transformers and graph convolutional networks for brain tumor diagnosis.

Journal: Scientific reports

In common: figshare 1512427, structural MRI / diffusion, other condition, 1 reference

[5] doi:10.1186/s40708-026-00325-x

CAE-BrainNet: a statistically validated class-adaptive attention ensemble model for explainable brain tumor classification from MRI.

Journal: Brain informatics

In common: figshare 1512427, structural MRI / diffusion, other condition, 1 reference

[6] doi:10.1371/journal.pone.0346821

LHW-Net: An ensemble-based machine learning framework for brain tumor classification.

Journal: PloS one

In common: figshare 1512427, other condition, 1 reference

[7] doi:10.3389/fonc.2026.1834400

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

In common: structural MRI / diffusion, other condition, 3 references

[8] doi:10.1371/journal.pone.0352353

Deep convolutional GAN and hypernet-based neural architecture search for brain tumor diagnosis detection and classification.

Journal: PloS one

In common: structural MRI / diffusion, other condition, 3 references

[9] doi:10.1038/s41598-026-51236-0

A minimal-net CNN model for an IoT-based brain tumor detection and monitoring system.

Journal: Scientific reports

In common: structural MRI / diffusion, other condition, 3 references

[10] doi:10.1038/s41598-026-52658-6

A multi-level attention CNN-transformer based framework for the detection of brain tumor using regional dual-score explainability.

Journal: Scientific reports

In common: 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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

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