EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Fusion of Multimodal MRI Features for Brain Tumor Detection

Bakhita Salman, Eithar Yassin, Deepak Ganta, Hermes Luna

Applied Sciences · 15.12.2025 · 15 (24) · 13155

DOI: 10.3390/app152413155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.12.2025. Verfasst von Bakhita Salman und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: TAMIU University research grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite advances in deep learning, brain tumor detection from MRI continues to face major challenges, including the limited robustness of single-modality models, the computational burden of transformer-based architectures, opaque fusion strategies, and the lack of efficient binary screening tools. To address these issues, we propose a lightweight multimodal CNN framework that integrates T1, T2, and FLAIR MRI sequences using modality-specific encoders and a channel-wise fusion module (concatenation followed by a 1 × 1 convolution). The pipeline incorporates U-Net-based segmentation for tumor-focused patch extraction, improving localization and reducing irrelevant background. Evaluated on the BraTS 2020 dataset (7500 slices; 70/15/15 patient-level split), the proposed model achieves 93.8% accuracy, 94.1% F1-score, and 19 ms inference time. It outperforms all single-modality ablations by up to 5% and achieves competitive or superior performance to transformer-based baselines while using over 98% fewer parameters. Grad-CAM and LIME visualizations further confirm clinically meaningful tumor-region activation. Overall, this efficient and interpretable multimodal framework advances scalable brain tumor screening and supports integration into real-time clinical workflows.

Förderung

  • TAMIU University research grant

Zitieren

APA

Salman, B., Yassin, E., Ganta, D., & Luna, H. (2025). Deep Learning-Based Fusion of Multimodal MRI Features for Brain Tumor Detection. Applied Sciences, 15(24), 13155. https://doi.org/10.3390/app152413155

Vancouver

Salman B, Yassin E, Ganta D, Luna H. Deep Learning-Based Fusion of Multimodal MRI Features for Brain Tumor Detection. Applied Sciences. 2025;15(24):13155. doi:10.3390/app152413155

BibTeX
@article{Salman2025,
  author = {Salman, Bakhita and Yassin, Eithar and Ganta, Deepak and Luna, Hermes},
  title = {Deep Learning-Based Fusion of Multimodal MRI Features for Brain Tumor Detection},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {24},
  pages = {13155},
  doi = {10.3390/app152413155}
}
Kostenlos starten →