Brain Stroke Classification Using CT Scans with Transformer-Based Models and Explainable AI.
Source check: Source checked. Not independent scientific confirmation.
Finding: Three-class CT classification results are reported; MaxViT+cGAN achieved 98.00% accuracy and AUC 0.9975. ImageNet-pretrained MaxViT/transformer classifiers were fine-tuned on CT images; cGAN synthesis was used only for training augmentation. Testing: The paper specifies a stratified 80/20 train/test split, with synthetic images excluded from validation/test. This is internal image-set validation only; source does not establish external clinical or outcome benefit.. A transformer-based CT model classified no stroke, ischemic stroke and hemorrhagic stroke in a Turkish Ministry of Health image dataset; MaxViT with cGAN augmentation reported 98% accuracy on the held-out test set. Source affiliation was not stated in the reviewed case checks and was unavailable in the local bibliographic cache.
Technology: ImageNet-pretrained MaxViT/transformer classifiers were fine-tuned on CT images; cGAN synthesis was used only for training augmentation.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- ImageNet-pretrained MaxViT/transformer classifiers were fine-tuned on CT images; cGAN synthesis was used only for training augmentation.
- Test and result
- The paper specifies a stratified 80/20 train/test split, with synthetic images excluded from validation/test. This is internal image-set validation only; source does not establish external clinical or outcome benefit.
- Limitation / still unknown
- A transformer-based CT model classified no stroke, ischemic stroke and hemorrhagic stroke in a Turkish Ministry of Health image dataset; MaxViT with cGAN augmentation reported 98% accuracy on the held-out test set.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.mdpi.com/2075-4418/15/19/2486
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.