Brain Tumor Detection in MRI Scans Using a Deep CNN

Enhancement of brain tumor detection is achieved through deep learning-based image analysis. Existing systems use methods like manual segmentation, traditional machine learning, and pre-trained models, but they often struggle with small datasets, low contrast in MRI scans, or high false-negative rates. Many approaches also fail to generalize across diverse medical imaging devices, limiting real-world applicability. Our project addresses these challenges by developing a custom Convolutional Neural Network (CNN) optimized for brain MRI analysis. The system automatically detects tumors by analysing structural patterns in MRI scans with high accuracy and a high F1-score, minimizing diagnostic errors. By incorporating data augmentation and lightweight architecture, the model achieves high precision without relying on transfer learning, making it suitable for resource-constrained clinical environments.

environmental analysis, soil factors, agricultural productivity, sustainable farming, data-driven insights.

1. Ronneberger et al. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI. [Google Scholar] [Crossref]

2. Ioffe & Szegedy (2015). Batch Normalization: Accelerating Deep Network Training. ICML. [Google Scholar] [Crossref]

3. Zeiler & Fergus (2014). Visualizing and Understanding Convolutional Networks. ECCV. [Google Scholar] [Crossref]

4. Menze et al. (2015). The Multimodal Brain Tumor Segmentation (BraTS) Benchmark. IEEE TMI. [Google Scholar] [Crossref]

5. Litjens et al. (2017). A Survey on Deep Learning in Medical Image Analysis. MIA. [Google Scholar] [Crossref]

6. Litjens et al. (2017). A Survey on Deep Learning in Medical Image Analysis. MIA. [Google Scholar] [Crossref]

7. Howard et al. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv. [Google Scholar] [Crossref]

8. Wang et al. (2020). Deep Learning for Brain Tumor Segmentation: A Survey. IEEE Access. [Google Scholar] [Crossref]

9. Çiçek et al. (2016). 3D U-Net: Learning Dense Volumetric Segmentation. MICCAI. [Google Scholar] [Crossref]

10. .Dosovitskiy et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition. ICLR. [Google Scholar] [Crossref]

11. Li et al. (2022). Federated Learning for Medical Image Analysis. Nature Digital Medicine. [Google Scholar] [Crossref]

12. .Our implementation (2024). Lightweight CNN for Edge Deployment. [GitHub] [Google Scholar] [Crossref]

13. Isensee et al. (2021). nnU-Net: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation. Nature Methods. [Google Scholar] [Crossref]

14. Abadi et al. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. [URL: tensorflow.org] [Google Scholar] [Crossref]

15. Paszke et al. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. NeurIPS. [Google Scholar] [Crossref]

16. Kingma & Ba (2015). Adam: A Method for Stochastic Optimization. ICLR. [Google Scholar] [Crossref]

17. Selvaraju et al. (2017). Grad-CAM: Visual Explanations from Deep Networks. ICCV. [Google Scholar] [Crossref]

18. He et al. (2016). Deep Residual Learning for Image Recognition. CVPR. [Google Scholar] [Crossref]

19. M. Gupta and K. Sasidhar (2020). Non-invasive Brain Tumor Detection using Magnetic Resonance Imaging based Fractal Texture Features and Shape Measures. ICETCE. [Google Scholar] [Crossref]

• Measuring Waste of Patient Time in Health Care at Non-Digitized Hospital: An Observational Study in Bangabandhu Sheikh Mujib Medical University, Bangladesh
• Reaffirming Clinical Confidence in Atorvastatin Therapy: A Digital Outreach Case Study from Tamil Nadu, India
• Clinical Manifestations and Therapeutic Response in a Patient with Hypothyroidism: A Case Report
• Eranda (Ricinus Communis) In Gridhrasi (Sciatica): Classical Rationale, Pharmacology and Clinical Evidence- A Narrative Literature Review
• Magnetotherapy in Pain Management: Mechanisms, Clinical Applications, and Future Perspectives – A Review