Dense Volume-to-Volume Vascular Boundary Detection

In this work, we tackle the important problem of dense 3D volume labeling in medical imaging. We start by introducing HED-3D, a 3D extension of the state-of-the-art 2D edge detector (HED). Next, we develop a novel 3D-Convolutional Neural Network (CNN) architecture, I2I-3D, that predicts boundary location in volumetric data. Our fine-to-fine, deeply supervised framework addresses three critical issues to 3D boundary detection: (1) efficient, holistic, end-to-end volumetric label training and prediction (2) precise voxel-level prediction to capture fine scale structures prevalent in medical data and (3) directed multi-scale, multi-level feature learning. We evaluate our approaches on a dataset consisting of 93 medical image volumes with a wide variety of anatomical regions and vascular structures. We show that our deep learning approaches out-perform the current state-of-the-art in 3D vascular boundary detection (structured forests 3D), by a large margin, as well as HED applied to slices. Prediction takes about one minute on a typical \(512\,\times \,512\,\times \,512\) volume, when using GPU.