Résumé:
In modern medical practice, precise detection and classification of tumors are critical for early
diagnosis and effective treatment planning. Despite advancements in medical imaging, challenges
persist in accurately identifying subtle abnormalities in early stages, often leading to delays in
treatment. Our research addresses these challenges by leveraging advanced image processing
techniques and artificial intelligence (AI) algorithms. Using Magnetic Resonance Imaging (MRI)
as a non-invasive diagnostic tool, our framework focuses on automating the segmentation of
abnormal tissues. We have developed and implemented a comprehensive methodology using
MATLAB, incorporating Gaussian filtering for pre-processing to enhance image quality and
reduce noise. Subsequently, image segmentation was performed using thresholding techniques.
For feature extraction, we utilized Discrete Wavelet Transform (DWT), Principal Component
Analysis (PCA), and Gray-Level Co-occurrence Matrix (GLCM). These features were then fed
into a Support Vector Machine (SVM) for accurate tumor detection and classification,
distinguishing between benign and malignant tumors. Our study includes the creation of a robust
local database of MRI scans and demonstrates the adaptability of our framework across various
organ systems beyond brain tumors. Through extensive experimentation and validation, we
showcase the effectiveness of our approach in real-world clinical scenarios, contributing to
enhanced medical imaging capabilities and improved patient outcomes
