Daphne Hong1 and Yunyan Zhang1
1University of Calgary, Calgary, AB, Canada
1University of Calgary, Calgary, AB, Canada
Using Grad-CAM, it is feasible to backpropagate classification information into arbitrary layers of convolutional neural networks trained on standard brain MRI. Backpropagation into lower-level layers showed greater localization, and higher levels with greater generalization.
Heatmaps from MRI of a SPMS patient. Shown are FLAIR image slices 57-59 (left to right, top row) out of 135, and corresponding Grad-CAM heatmaps from VGG16 (left) and VGG19 with GAP (right). The CNN layers highlighted in VGG16 with GAP are: A) last convolutional layer – ‘block5_conv3’, B) second last convolutional layer – ‘block5_conv2’, and C) first convolutional layer of the last convolutional block – ‘block5_conv1’; and in VGG19 with GAP: A) last max pooling layer – ‘block5_pool’, B) last convolutional layer – ‘block5_conv4’, and C) second last convolutional layer – ‘block5_conv3’.
Further heatmaps generated from the brain MRI of the same SPMS patient using VGG19 with GAP. Shown are also MRI slices at 57-59 (left to right, top row) out of 135. The CNN layers highlighted are: A) third last convolutional layer – ‘block5_conv2’, B) first convolutional layer of last convolutional block – ‘block5_conv1’, and C) last convolutional layer of second last convolutional block – ‘block4_conv4’.
