Robust Tracing and Visualization of Heterogeneous Microvascular Networks

Tracking the Adaptation and Compensation Processes of Patients' Brain Arterial Network to an Evolving Glioblastoma

The brain's vascular network dynamically affects its development and core functions. It rapidly responds to abnormal conditions by adjusting properties of the network, aiding stabilization and regulation of brain activities. Tracking prominent arterial changes has clear clinical and surgical advantages. However, the arterial network functions as a system; thus, local changes may imply global compensatory effects that could impact the dynamic progression of a disease. We developed automated personalized system-level analysis methods of the compensatory arterial changes and mean blood flow behavior from a patient's clinical images. By applying our approach to data from a patient with aggressive brain cancer compared with healthy individuals, we found unique spatiotemporal patterns of the arterial network that could assist in predicting the evolution of glioblastoma over time. Our personalized approach provides a valuable analysis tool that could augment current clinical assessments of the progression of glioblastoma and other neurological disorders affecting the brain.

VC-Net: Deep Volume-Composition Networks for Segmentation and Visualization of Highly Sparse and Noisy Image Data

The fundamental motivation of the proposed work is to present a new visualization-guided computing paradigm to combine direct 3D volume processing and volume rendered clues for effective 3D exploration. For example, extracting and visualizing microstructures in-vivo have been a long-standing challenging problem. However, due to the high sparseness and noisiness in cerebrovasculature data as well as highly complex geometry and topology variations of micro vessels, it is still extremely challenging to extract the complete 3D vessel structure and visualize it in 3D with high fidelity. In this paper, we present an end-to-end deep learning method, VC-Net, for robust extraction of 3D microvascular structure through embedding the image composition, generated by maximum intensity projection (MIP), into the 3D volumetric image learning process to enhance the overall performance. The core novelty is to automatically leverage the volume visualization technique (e.g., MIP - a volume rendering scheme for 3D volume images) to enhance the 3D data exploration at the deep learning level. The MIP embedding features can enhance the local vessel signal (through canceling out the noise) and adapt to the geometric variability and scalability of vessels, which is of great importance in microvascular tracking. A multi-stream convolutional neural network (CNN) framework is proposed to effectively learn the 3D volume and 2D MIP feature vectors, respectively, and then explore their inter-dependencies in a joint volume-composition embedding space by unprojecting the 2D feature vectors into the 3D volume embedding space. It is noted that the proposed framework can better capture the small/micro vessels and improve the vessel connectivity. To our knowledge, this is the first time that a deep learning framework is proposed to construct a joint convolutional embedding space, where the computed vessel probabilities from volume rendering based 2D projection and 3D volume can be explored and integrated synergistically. Experimental results are evaluated and compared with the traditional 3D vessel segmentation methods and the state-of-the-art in deep learning, by using extensive public and real patient (micro- )cerebrovascular image datasets. The application of this accurate segmentation and visualization of sparse and complicated 3D microvascular structure facilitated by our method demonstrates the potential in a powerful MR arteriogram and venogram diagnosis of vascular disease.

Three-Dimensional Microscopy by Milling with Ultraviolet Excitation

Analysis of three-dimensional biological samples is critical to understanding tissue function and the mechanisms of disease. Many chronic conditions, like neurodegenerative diseases and cancers, correlate with complex tissue changes that are difficult to explore using two-dimensional histology. While three-dimensional techniques such as confocal and light-sheet microscopy are well-established, they are time consuming, require expensive instrumentation, and are limited to small tissue volumes. Three-dimensional microscopy is therefore impractical in clinical settings and often limited to core facilities at major research institutions. There would be a tremendous benefit to providing clinicians and researchers with the ability to routinely image large three-dimensional tissue volumes at cellular resolution. In this paper, we propose an imaging methodology that enables fast and inexpensive three-dimensional imaging that can be readily integrated into current histology pipelines. This method relies on block-face imaging of paraffin-embedded samples using deep-ultraviolet excitation. The imaged surface is then ablated to reveal the next tissue section for imaging. The final image stack is then aligned and reconstructed to provide tissue models that exceed the depth and resolution achievable with modern three-dimensional imaging systems.

Accurate flow in augmented networks (AFAN): an approach to generating three-dimensional biomimetic microfluidic networks with controlled flow

In vivo, microvasculature provides oxygen, nutrients, and soluble factors necessary for cell survival and function. The highly tortuous, densely-packed, and interconnected three-dimensional (3D) architecture of microvasculature ensures that cells receive these crucial components. The ability to duplicate microvascular architecture in tissue-engineered models could provide a means to generate large-volume constructs as well as advanced microphysiological systems. Similarly, the ability to induce realistic flow in engineered microvasculature is crucial to recapitulating in vivo-like flow and transport. Advanced biofabrication techniques are capable of generating 3D, biomimetic microfluidic networks in hydrogels, however, these models can exhibit systemic aberrations in flow due to incorrect boundary conditions. To overcome this problem, we developed an automated method for generating synthetic augmented channels that induce the desired flow properties within three-dimensional microfluidic networks. These augmented inlets and outlets enforce the appropriate boundary conditions for achieving specified flow properties and create a three-dimensional output useful for image-guided fabrication techniques to create biomimetic microvascular networks.