Projects ⚙️

Developed a machine learning model for automatic brain tumor detection from MRI scans, enabling early diagnosis and aiding medical professionals in decision-making. The project utilizes deep learning techniques to classify MRI images into two categories: tumor and no tumor (Healthy).

Key Contributions:

● Built a Convolutional Neural Network (CNN) model using PyTorch to classify brain MRI images with high accuracy.

● Preprocessed MRI scan data by applying image resizing, normalization, and augmentation techniques to enhance model performance.

● Implemented automated image classification, distinguishing between tumor and non-tumor MRI scans with significant precision.

● Integrated visualization tools using Matplotlib and Seaborn to analyze model performance through confusion matrices and accuracy metrics.

● Optimized training and validation strategies, employing techniques like dropout, batch normalization, and data augmentation to reduce overfitting.

● Collaborated with domain experts and researchers to align the model’s functionality with real-world medical imaging applications.

Skills Used: Deep Learning, Computer Vision, PyTorch, Convolutional Neural Networks (CNN), Image Processing, Data Augmentation, Model Evaluation, Python, OpenCV, Matplotlib, Scikit-learn.