A deep learning approach to bone segmentation in CT scans

This thesis proposes a deep learning approach to bone segmentation in abdominal CT scans. Segmentation is a common initial step in medical images analysis, often fundamental for computer-aided detection and diagnosis systems. The extraction of bones in CT scans is a challenging task, which if done manually by experts requires a time consuming process and that has not today a broadly recognized automatic solution. The method presented is based on a convolutional neural network, inspired by the U-Net and trained end-to-end, that performs a semantic segmentation of the data. The training dataset is made up of 21 abdominal CT scans, each one containing between 403 and 994 2D transversal images. Those images are in full resolution, 512x512 voxels, and each voxel is classified by the network into one of the following classes: background, femoral bones, hips, sacrum, sternum, spine and ribs. The output is therefore a bone mask where the bones are recognized and divided into six different classes. In the testing dataset, labeled by experts, the best model achieves a Dice coefficient as average of all bone classes of 0.93. This work demonstrates, to the best of my knowledge for the first time, the feasibility of automatic bone segmentation and classification for CT scans using a convolutional neural network.