We present DeepVesselNet, an architecture tailored to the challenges to be addressed when extracting vessel networks and corresponding features in 3-D angiography using deep learning. We discuss the problems of low execution speed and high memory requirements associated with full 3-D convolutional networks, high class imbalance arising from low percentage (less than 3%) of vessel voxels, and unavailability of accurately annotated training data - and offer solutions that are the building blocks of DeepVesselNet. First, we formulate 2-D orthogonal cross-hair filters which make use of 3-D context information. Second, we introduce a class balancing cross-entropy score with false positive rate correction to handle the high class imbalance and high false positive rate problems associated with existing loss functions. Finally, we generate synthetic dataset using a computational angiogenesis model, capable of generating vascular networks under physiological constraints on local network structure and topology, and use these data for transfer learning. DeepVesselNet is optimized for segmenting vessels, predicting centerlines, and localizing bifurcations. We test the performance on a range of angiographic volumes including clinical Time-of-Flight MRA data of the human brain, as well as synchrotron radiation X-ray tomographic microscopy scans of the rat brain. Our experiments show that, by replacing 3-D filters with 2-D orthogonal cross-hair filters in our network, speed is improved by 23% while accuracy is maintained. Our class balancing metric is crucial for training the network and pre-training with synthetic data helps in early convergence of the training process.
Feature extraction is a very crucial task in image and pixel (voxel) classification and regression in biomedical image modeling. In this work we present a machine learning based feature extraction scheme based on inception models for pixel classification tasks. We extract features under multi-scale and multi-layer schemes through convolutional operators. Layers of Fully Convolutional Network are later stacked on this feature extraction layers and trained end-to-end for the purpose of classification. We test our model on the DRIVE and STARE public data sets for the purpose of segmentation and centerline detection and it out performs most existing hand crafted or deterministic feature schemes found in literature. We achieve an average maximum Dice of 0.85 on the DRIVE data set which out performs the scores from the second human annotator of this data set. We also achieve an average maximum Dice of 0.85 and kappa of 0.84 on the STARE data set. Though these datasets are mainly 2-D we also propose ways of extending this feature extraction scheme to handle 3-D datasets.