2. Automatic detection and classification of the 2D MRI brain tumor
images using deep convolutional neural networks
• CNNs are trained using large collections of diverse images
• Convolutional neural network is composed of multiple building
blocks, such as convolution layers, pooling layers, and fully
connected layers
• The convolutional layers are used to convolve the input image
with kernels (weights) to obtain a feature map
• Extract the features using CNN and then classifying using four
machine learning classifiers such as SVM, K-NN, naïve bayes and
discriminant analysis classifiers
• Database used : Cancer imaging archive
(https://www.cancerimagingarchive.net/)
3/10/2024 Department of Biomedical Engineering, SRMIST, KTR 2
3. CNN ARCHITECTURE
• Convolution - Convolution of an image with different filters can perform
operations such as edge detection, blur and sharpen by applying filters
• Rectified Linear Unit activation - Relu activation function is used instead of
Tanh to add non-linearity. It accelerates the speed by 6 times at the same
accuracy.
The output is ƒ(x) = max(0,x)
CNN Architecture
3/10/2024 Department of Biomedical Engineering, SRMIST, KTR 3