A calibration-aware hierarchical CNN-SWIN fusion framework for robust Cross-Dataset brain MRI analysis.

Overview

1. School of Microelectronics, Tianjin University, Tianjin, China
2. Department of Data Science, National University of Computer and Emerging Sciences (FAST–NUCES), Lahore, Pakistan
3. School of Material Science and Engineering, Zhejiang University, Hangzhou, China
4. Department of Computer Science, Yobe State University, Damaturu, Nigeria
5. Center for Distance and Online Education, Lovely Professional University, Phagwara, Punjab, India
6. Department of Biomedical Engineering, School of Precision Instruments and Opto-electronics Engineering, Tianjin University, Tianjin, China

Abstract

Introduction: Deep learning approaches have become central to brain MRI analysis; however, their reliability under dataset shift remains a critical barrier to safe and scalable deployment in neuroscience and clinical research. While convolutional neural networks (CNNs) provide strong locality-driven inductive biases for robust feature extraction, they lack global contextual awareness. Conversely, transformer-based architectures capture long-range dependencies but often exhibit reduced robustness and miscalibrated confidence when applied to heterogeneous medical imaging data, particularly in Cross-Dataset settings.

Methods: In this work, we propose a calibration-aware hierarchical CNN-Transformer fusion framework designed for robust brain MRI analysis under dataset shift. The architecture integrates a pretrained multi-scale CNN backbone with a hierarchical transformer branch and performs scale-aligned fusion through cross-attention mechanisms. By allowing local convolutional features to selectively query global contextual representations, the proposed design maintains stable feature contributions during fusion and mitigates overconfident reliance on transformer features when generalization degrades across datasets. The framework is evaluated using a strict Cross-Dataset protocol, where models are trained on one dataset and tested on a distinct dataset.

Results: Experimental results demonstrate that the proposed fusion model achieves competitive classification performance while substantially improving probabilistic calibration relative to both CNN-only and transformer-only baselines. Specifically, the model attains an average accuracy of 99.20% and achieves lower Expected Calibration Error (ECE = 0.0041), Brier score (0.0028), and Negative Log-Likelihood (NLL = 0.0277) compared to a standalone Swin Transformer and a strong ResNet50 baseline.

Discussion: These findings demonstrate that calibration-aware hierarchical CNN-Transformer fusion enhances both predictive reliability and robustness under Cross-Dataset evaluation. By improving the alignment between predictive confidence and empirical correctness, the proposed method supports safer large-scale analysis of heterogeneous brain MRI data, with important implications for multi-center neuroscience studies and trustworthy clinical decision support.

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

• figshare:30533120, at figshare; found in “Data availability statement”
• kaggle.com/datasets/mohamadabouali1, at Kaggle; found in “Data availability statement”

Data availability statement

The datasets analyzed in this study are publicly available and were obtained from open-access repositories. The first dataset is the BRISC (Brain Tumor Image Segmentation and Classification) dataset, which provides annotated brain MRI scans for tumor classification and related research tasks. The dataset is publicly available via Figshare at https://doi.org/10.6084/m9.figshare.30533120 and is described in the associated publication by Fateh et al. The data are released for research use and include expert-provided diagnostic labels. The second dataset is the BT-MRI four-class brain tumor classification dataset, which contains contrast-enhanced brain MRI slices categorized into glioma, meningioma, pituitary tumor, and no-tumor classes. This dataset is publicly available on Kaggle at https://www.kaggle.com/datasets/mohamadabouali1/mri-brain-tumor-dataset-4-class-7023-images. In this study, one dataset is used exclusively for training and the other exclusively for testing, following a strict train-on-one, test-on-another cross-dataset evaluation protocol. All preprocessing steps, dataset partitions, and experimental configurations are described in the manuscript to support reproducibility.

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, 29 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 6 authors, 6 keywords, 9 references.

Cite

This paper

Younis, A., Qiang, L., Rehman, A., Hussain, H., Adamu, M. J., & Kawuwa, H. B. (2026). A calibration-aware hierarchical CNN-SWIN fusion framework for robust Cross-Dataset brain MRI analysis. Frontiers in neuroscience, 20, 1782306. https://doi.org/10.3389/fnins.2026.1782306

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:10.3389/frai.2026.1771088 [code]

Few-shot deployment of pretrained MRI transformers in brain imaging tasks.

Journal: Frontiers in artificial intelligence

In common: methods / tools, structural MRI / diffusion, 2 references

[2] doi:10.1038/s41598-026-58789-0 [code]

Metaheuristic hyperparameter optimization of deep neural networks for demographic-aware autism spectrum disorder classification.

Journal: Scientific reports

In common: structural MRI / diffusion, 2 references

[3] 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, 2 references

[4] doi:10.1038/s41598-026-48825-4

YOLO-LS: a novel deep learning framework for brain tumor segmentation in Magnetic Resonance Imaging.

Journal: Scientific reports

In common: methods / tools, structural MRI / diffusion, 1 reference

[5] doi:10.3390/jcm15145508

Region-Wise Bézier Intensity Augmentation for Domain-Generalized Brain Tumor Segmentation with a Mamba U-Net.

Journal: Journal of clinical medicine

In common: methods / tools, structural MRI / diffusion, 1 reference

[6] doi:10.3390/diagnostics16111745

Brain Tumor Classification and Segmentation in MR Images Using EfficientNet and U-Net++ Models.

Journal: Diagnostics (Basel, Switzerland)

In common: methods / tools, structural MRI / diffusion, 1 reference

[7] doi:10.1371/journal.pdig.0001316 [code]

Reliability of a convolutional neural network in segmenting multiple sclerosis lesions from MRI: Impact of data augmentation, image modality and tolerance with U-Net architecture.

Journal: PLOS digital health

In common: methods / tools, structural MRI / diffusion, 1 reference

[8] 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: methods / tools, structural MRI / diffusion, 1 reference

[9] doi:10.21037/qims-2026-0792 [code]

An nnU-Net-based framework with adaptive feature representation for 3D brain tumor segmentation.

Journal: Quantitative imaging in medicine and surgery

In common: methods / tools, structural MRI / diffusion, 1 reference

[10] doi:10.1186/s12938-026-01555-0 [code]

Incorporating normal periventricular changes for enhanced pathological white matter hyperintensity segmentation: on multiclass deep learning approaches.

Journal: Biomedical engineering online

In common: methods / tools, 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.