EUVIMEDEUVIMED entdecken
Crossref

Automated Brain Tumor Detection Using Deep Learning-Based Models

Dr. Pravin Gopalrao Sarpate

International Scientific Journal of Engineering and Management · 29.10.2025 · 04 (10) · 1-9

DOI: 10.55041/isjem05132 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Scientific Journal of Engineering and Management, online erschienen am 29.10.2025. Verfasst von Dr. Pravin Gopalrao Sarpate.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain tumor detection remains one of the most challenging tasks in the field of medical image analysis, primarily due to the complexity, variability, and subtle appearance of tumors in brain imaging modalities such as Magnetic Resonance Imaging (MRI). Accurate and early identification of brain tumors is crucial for effective treatment planning and improving patient survival rates. Traditionally, radiologists rely on manual inspection of MRI scans, which is not only time-intensive but also subject to human error and inter-observer variability. To address these limitations, this study proposes an automated brain tumor detection system based on deep learning techniques. The proposed approach utilizes Convolutional Neural Networks (CNNs) to automatically learn hierarchical and discriminative features directly from MRI images without the need for manual feature extraction. The system involves several stages, including image preprocessing, data augmentation, feature extraction, and classification. Preprocessing techniques such as normalization, resizing, and noise reduction are applied to enhance image quality and ensure consistency across the dataset. Data augmentation methods, including rotation, flipping, and scaling, are employed to increase dataset diversity and improve model generalization. The deep learning model is trained on a labeled dataset of brain MRI images, categorized into tumor and non-tumor classes. The architecture consists of multiple convolutional layers followed by pooling layers to capture spatial features, and fully connected layers for classification. The model is optimized using the Adam optimizer and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that the proposed model achieves high classification accuracy and robustness compared to traditional machine learning methods. The system effectively distinguishes between normal and abnormal brain tissues, making it a valuable tool for assisting medical professionals in diagnosis. Furthermore, this study highlights the potential of deep learning in reducing diagnostic time and improving consistency in clinical decision-making. Despite its promising performance, the proposed approach faces challenges such as dependency on large annotated datasets and limited interpretability of deep learning models. Future work aims to incorporate explainable artificial intelligence techniques and extend the model for multi-class tumor classification and real-time clinical applications. Keywords Brain Tumor Detection, Deep Learning, Convolutional Neural Network (CNN), Magnetic Resonance Imaging (MRI), Medical Image Processing, Artificial Intelligence (AI), Image Classification, Tumor Segmentation, Feature Extraction, Transfer Learning, Computer-Aided Diagnosis (CAD), Neural Networks

Zitieren

APA

Sarpate, D. P. G. (2025). Automated Brain Tumor Detection Using Deep Learning-Based Models. International Scientific Journal of Engineering and Management, 04(10), 1-9. https://doi.org/10.55041/isjem05132

Vancouver

Sarpate DPG. Automated Brain Tumor Detection Using Deep Learning-Based Models. International Scientific Journal of Engineering and Management. 2025;04(10):1-9. doi:10.55041/isjem05132

BibTeX
@article{Sarpate2025,
  author = {Sarpate, Dr. Pravin Gopalrao},
  title = {Automated Brain Tumor Detection Using Deep Learning-Based Models},
  journal = {International Scientific Journal of Engineering and Management},
  year = {2025},
  volume = {04},
  number = {10},
  pages = {1--9},
  doi = {10.55041/isjem05132}
}
Kostenlos starten →