A Dual-Branch Frequency-Aware Attention Framework for Rare Neurological Disease Classification from Brain MRI.

Overview

1. Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Aljouf, Saudi Arabia
2. Department of Information Systems, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Aljouf, Saudi Arabia

Abstract

Background: Rare neurological diseases are challenging to diagnose from brain MRI because of their low prevalence, heterogeneous imaging patterns, and limited annotated datasets. Deep learning may support image-level recognition, but results from curated datasets without complete patient-level identifiers require cautious interpretation. Objectives: This study proposes RareNeuroXNet, a frequency-aware multi-branch attention framework for image-level classification of rare neurological diseases from brain MRI. The objective was to assess whether combining global anatomical, local fine-grained, and frequency-domain representations improves benchmark performance, calibration, and interpretability. Methods: RareNeuroXNet uses three complementary branches: a global branch for whole-image representation, a local branch for regional feature extraction, and an FFT magnitude-based frequency branch. Features are refined using CBAM attention, fused, and classified through a fully connected head. The model was evaluated on a balanced curated dataset with five rare neurological disease classes using five-fold cross-validation, ablation analysis, calibration metrics, internal baseline comparison, paired testing against DenseNet121 local-only, and Grad-CAM visualization. MCND was also used as a complementary cross-dataset neurological MRI benchmark, not as same-task external validation. Results: RareNeuroXNet achieved strong image-level internal benchmark performance, with accuracy of 0.9924±0.0061, macro F1-score of 0.9924±0.0061, macro AUROC of 0.9998±0.0002, and macro AUPR of 0.9992±0.0007. Calibration was favorable, with ECE of 0.0052±0.0029 and NLL of 0.0276±0.0159. Ablation results showed that the local branch was the dominant contributor, while FFT and CBAM provided supportive refinement. Compared with DenseNet121 local-only, RareNeuroXNet showed modest classification gains and clearer calibration improvements. Conclusions: RareNeuroXNet demonstrated strong controlled image-level benchmark performance with high discrimination, stable cross-validation behavior, favorable calibration, and Grad-CAM interpretability. However, possible correlated slices, duplicate images, or subject overlap cannot be excluded. Future work should use patient-level, same-task, multi-center external validation and 3D multimodal MRI analysis.

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.

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

• doi:10.17632/d73rs38yk6.1 — at the source; found in the references
• kaggle.com/datasets/ahsanneural — at Kaggle; found in “Data Availability Statement”
• kaggle.com/datasets/alifatahi — at Kaggle; found in “Data Availability Statement”

Data Availability Statement

https://www.kaggle.com/datasets/ahsanneural/rare-neurological-diseases-mri-curated-edition/data (accessed on 5 March 2026), https://www.kaggle.com/datasets/alifatahi/multi-class-neurological-disorder-mcnd-dataset (accessed on 15 March 2026).

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, issue, pages, dates, 2 authors, 12 keywords, 1 funder, 34 references.

Cite

This paper

Alruwaili, M., & Mahmood, M. A. (2026). A Dual-Branch Frequency-Aware Attention Framework for Rare Neurological Disease Classification from Brain MRI. Diagnostics (Basel, Switzerland), 16(11), 1749. https://doi.org/10.3390/diagnostics16111749

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/diagnostics16121791

An Explainable Multi-Scale Deep Learning Framework for Multi-Class Brain MRI Classification.

Journal: Diagnostics (Basel, Switzerland)

In common: kaggle.com/datasets/alifatahi, structural MRI / diffusion, 2 references, author Mahmood A Mahmood

[2] 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, 3 references

[3] 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, 2 references

[4] doi:10.1038/s41598-026-45675-y [code]

Multi-class classification of brain tumor using a ResNet101 backbone integrated with multi-scale deformable attention module and advanced data augmentations.

Journal: Scientific reports

In common: structural MRI / diffusion, 2 references

[5] doi:10.3390/biomedicines14071475 [code]

ETDACVO: Structural-Fidelity-Aware Evolutionary Co-Optimization for Robust and Explainable Brain Tumor MRI Classification.

Journal: Biomedicines

In common: structural MRI / diffusion, 2 references

[6] doi:10.3389/fgene.2026.1814786

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

Journal: Frontiers in genetics

In common: structural MRI / diffusion, 2 references

[7] doi:10.3390/s26092822

Multi-Chaotic HEOA for Hardware-Aware Neural Architecture Search: Brain Tumor Classification on FPGA.

Journal: Sensors (Basel, Switzerland)

In common: structural MRI / diffusion, 2 references

[8] doi:10.1038/s41598-026-60525-7

Superfast prediction of brain tumours through adaptive incremental pre-training and re-training through transfer learning using state-of-the-art ResNet18 architectural model.

Journal: Scientific reports

In common: structural MRI / diffusion, 1 reference

[9] doi:10.3390/diagnostics16152428

PCA-Enhanced Deep Features for Alzheimer's Disease Stage Classification with EFMM.

Journal: Diagnostics (Basel, Switzerland)

In common: structural MRI / diffusion, 1 reference

[10] doi:10.3389/fnins.2026.1875642

Convolutional neural networks in brain disease diagnosis: a unified review of Alzheimer's, Parkinson's, and brain tumor classification.

Journal: Frontiers in neuroscience

In common: structural MRI / diffusion, 1 reference

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.