Image Processing: Brain Tumour Detection

Our team dipped our hands into the scene of medical imaging and image processing machine learning algorithms in this project. We were exposed to image pre-processing techniques such as data augmentation to artificially increase the size of our dataset, and image feature extraction techniques such as the Canny, Sobel Edge and Prewitt Operator algorithms.

​

Multiple models were built with the aim to improve current existing ones. Other than individual models like SVM, kNN and CNN, we also explored several ensemble methods like Bagging with kNN / Decision Trees and AdaBoost with Decision Tress / Gaussian Naive Bayes to help us in detecting the presence as well as type of tumour present in brain scans.