3D image texture analysis of simulated and real-world vascular trees

Artificial vascular image generation using blood vessel texture maps

BACKGROUND

Current methods for identifying blood vessels in digital images typically involve training neural networks on pixel-wise annotated data. However, manually outlining whole vessel trees in images tends to be very costly. One approach for reducing the amount of manual annotation is to pre-train networks on artificially generated vessel images. Recent pre-training approaches focus on generating proper artificial geometries for the vessels, while the appearance of the vessels is defined using general statistics of the real samples or generative networks requiring an additional training procedure to be defined. In contrast, we propose a methodology for generating blood vessels with realistic textures extracted directly from manually annotated vessel segments from real samples. The method allows the generation of artificial images having blood vessels with similar geometry and texture to the real samples using only a handful of manually annotated vessels.

METHODS

The first step of the method is the manual annotation of the borders of a small vessel segment, which takes only a few seconds. The annotation is then used for creating a reference image containing the texture of the vessel, called a texture map. A procedure is then defined to allow texture maps to be placed on top of any smooth curve using a piecewise linear transformation. Artificial images are then created by generating a set of vessel geometries using Bézier curves and assigning vessel texture maps to the curves.

RESULTS

The method is validated on a fluorescence microscopy (CORTEX) and a fundus photography (DRIVE) dataset. We show that manually annotating only 0.03% of the vessels in the CORTEX dataset allows pre-training a network to reach, on average, a Dice score of 0.87 ± 0.02, which is close to the baseline score of 0.92 obtained when all vessels of the training split of the dataset are annotated. For the DRIVE dataset, on average, a Dice score of 0.74 ± 0.02 is obtained by annotating only 0.29% of the vessels, which is also close to the baseline Dice score of 0.81 obtained when all vessels are annotated.

CONCLUSION

The proposed method can be used for disentangling the geometry and texture of blood vessels, which allows a significant improvement of network pre-training performance when compared to other pre-training methods commonly used in the literature.

A visual framework to create photorealistic retinal vessels for diagnosis purposes

The methods developed in recent years for synthesising an ocular fundus can be been divided into two main categories. The first category of methods involves the development of an anatomical model of the eye, where artificial images are generated using appropriate parameters for modelling the vascular networks and fundus. The second type of method has been made possible by the development of deep learning techniques and improvements in the performance of hardware (especially graphics cards equipped with a large number of cores). The methodology proposed here to produce high-resolution synthetic fundus images is intended to be an alternative to the increasingly widespread use of generative adversarial networks to overcome the problems that arise in producing slightly modified versions of the same real images. This will allow the simulation of pathologies and the prediction of eye-related diseases. The proposed approach is based on the principle of least action and correctly places the vessels on the simulated eye fundus without using real morphometric information. An a posteriori analysis of the average characteristics such as the size, length, bifurcations, and endpoint positioning confirmed the substantial accuracy of the proposed approach compared to real data. A graphical user interface allows the user to make any changes in real time by controlling the positions of control points.

3D Printable Vascular Networks Generated by Accelerated Constrained Constructive Optimization for Tissue Engineering

One of the greatest challenges in fabricating artificial tissues and organs is the incorporation of vascular networks to support the biological requirements of the embedded cells, encouraging tissue formation and maturation. With the advent of 3D printing technology, significant progress has been made with respect to generating vascularized artificial tissues. Current algorithms to generate arterial/venous trees are computationally expensive and offer limited freedom to optimize the resulting structures. Furthermore, there is no method for algorithmic generation of vascular networks that can recapitulate the complexity of the native vasculature for more than two trees, and export directly to a 3D printing format. Here, we report such a method, using an accelerated constructive constrained optimization approach, by decomposing the process into construction, optimization, and collision resolution stages. The new approach reduces computation time to minutes at problem sizes where previous implementations have reported days. With the optimality criterion of maximizing the volume of useful tissue which could be grown around such a network, an approach of alternating stages of construction and batch optimization of all node positions is introduced and shown to yield consistently more optimal networks. The approach does not place a limit on the number of interpenetrating networks that can be constructed in a given space; indeed we demonstrate a biomimetic, liver-like tissue model. Methods to account for the limitations of 3D printing are provided, notably the minimum feature size and infill at sharp angles, through padding and angle reduction, respectively.

Application of Gray Level Co-Occurrence Matrix Analysis as a New Method for Enzyme Histochemistry Quantification

Enzyme histochemistry is a valuable histological method which provides a connection between morphology, activity, and spatial localization of investigated enzymes. Even though the method relies purely on arbitrary evaluations performed by the human eye, it is still wildly accepted and used in histo(patho)logy. Texture analysis emerged as an excellent tool for image quantification of subtle differences reflected in both spatial discrepancies and gray level values of pixels. The current study of texture analysis utilizes the gray-level co-occurrence matrix as a method for quantification of differences between ecto-5'-nucleotidase activities in healthy hippocampal tissue and tissue with marked neurodegeneration. We used the angular second moment, contrast (CON), correlation, inverse difference moment (INV), and entropy for texture analysis and receiver operating characteristic analysis with immunoblot and qualitative assessment of enzyme histochemistry as a validation. Our results strongly argue that co-occurrence matrix analysis could be used for the determination of fine differences in the enzyme activities with the possibility to ascribe those differences to regions or specific cell types. In addition, it emerged that INV and CON are especially useful parameters for this type of enzyme histochemistry analysis. We concluded that texture analysis is a reliable method for quantification of this descriptive technique, thus removing biases and adding it a quantitative dimension.

Vascular amounts and dispersion of caliber-classified vessels as key parameters to quantitate 3D micro-angioarchitectures in multiple myeloma experimental tumors

Blood vessel micro-angioarchitecture plays a pivotal role in tumor progression, metastatic dissemination and response to therapy. Thus, methods able to quantify microvascular trees and their anomalies may allow a better comprehension of the neovascularization process and evaluation of vascular-targeted therapies in cancer. To this aim, the development of a restricted set of indexes able to describe the arrangement of a microvascular tree is eagerly required. We addressed this goal through 3D analysis of the functional microvascular network in sulfo-biotin-stained human multiple myeloma KMS-11 xenografts in NOD/SCID mice. Using image analysis, we show that amounts, spatial dispersion and spatial relationships of adjacent classes of caliber-filtered microvessels provide a near-linear graphical “fingerprint” of tumor micro-angioarchitecture. Position, slope and axial projections of this graphical outcome reflect biological features and summarize the properties of tumor micro-angioarchitecture. Notably, treatment of KMS-11 xenografts with anti-angiogenic drugs affected position and slope of the specific curves without degrading their near-linear properties. The possibility offered by this procedure to describe and quantify the 3D features of the tumor micro-angioarchitecture paves the way to the analysis of the microvascular tree in human tumor specimens at different stages of tumor progression and after pharmacologic interventions, with possible diagnostic and prognostic implications.

Three-dimensional solid texture analysis in biomedical imaging: review and opportunities

Three-dimensional computerized characterization of biomedical solid textures is key to large-scale and high-throughput screening of imaging data. Such data increasingly become available in the clinical and research environments with an ever increasing spatial resolution. In this text we exhaustively analyze the state-of-the-art in 3-D biomedical texture analysis to identify the specific needs of the application domains and extract promising trends in image processing algorithms. The geometrical properties of biomedical textures are studied both in their natural space and on digitized lattices. It is found that most of the tissue types have strong multi-scale directional properties, that are well captured by imaging protocols with high resolutions and spherical spatial transfer functions. The information modeled by the various image processing techniques is analyzed and visualized by displaying their 3-D texture primitives. We demonstrate that non-convolutional approaches are expected to provide best results when the size of structures are inferior to five voxels. For larger structures, it is shown that only multi-scale directional convolutional approaches that are non-separable allow for an unbiased modeling of 3-D biomedical textures. With the increase of high-resolution isotropic imaging protocols in clinical routine and research, these models are expected to best leverage the wealth of 3-D biomedical texture analysis in the future. Future research directions and opportunities are proposed to efficiently model personalized image-based phenotypes of normal biomedical tissue and its alterations. The integration of the clinical and genomic context is expected to better explain the intra class variation of healthy biomedical textures. Using texture synthesis, this provides the exciting opportunity to simulate and visualize texture atlases of normal ageing process and disease progression for enhanced treatment planning and clinical care management.

Personalized identification of abdominal wall hernia meshes on computed tomography

An abdominal wall hernia is a protrusion of the intestine through an opening or area of weakness in the abdominal wall. Correct pre-operative identification of abdominal wall hernia meshes could help surgeons adjust the surgical plan to meet the expected difficulty and morbidity of operating through or removing the previous mesh. First, we present herein for the first time the application of image analysis for automated identification of hernia meshes. Second, we discuss the novel development of a new entropy-based image texture feature using geostatistics and indicator kriging. Third, we seek to enhance the hernia mesh identification by combining the new texture feature with the gray-level co-occurrence matrix feature of the image. The two features can characterize complementary information of anatomic details of the abdominal hernia wall and its mesh on computed tomography. Experimental results have demonstrated the effectiveness of the proposed study. The new computational tool has potential for personalized mesh identification which can assist surgeons in the diagnosis and repair of complex abdominal wall hernias.

3D texture analysis reveals imperceptible MRI textural alterations in the thalamus and putamen in progressive myoclonic epilepsy type 1, EPM1

Progressive myoclonic epilepsy type 1 (EPM1) is an autosomal recessively inherited neurodegenerative disorder characterized by young onset age, myoclonus and tonic-clonic epileptic seizures. At the time of diagnosis, the visual assessment of the brain MRI is usually normal, with no major changes found later. Therefore, we utilized texture analysis (TA) to characterize and classify the underlying properties of the affected brain tissue by means of 3D texture features. Sixteen genetically verified patients with EPM1 and 16 healthy controls were included in the study. TA was performed upon 3D volumes of interest that were placed bilaterally in the thalamus, amygdala, hippocampus, caudate nucleus and putamen. Compared to the healthy controls, EPM1 patients had significant textural differences especially in the thalamus and right putamen. The most significantly differing texture features included parameters that measure the complexity and heterogeneity of the tissue, such as the co-occurrence matrix-based entropy and angular second moment, and also the run-length matrix-based parameters of gray-level non-uniformity, short run emphasis and long run emphasis. This study demonstrates the usability of 3D TA for extracting additional information from MR images. Textural alterations which suggest complex, coarse and heterogeneous appearance were found bilaterally in the thalamus, supporting the previous literature on thalamic pathology in EPM1. The observed putamenal involvement is a novel finding. Our results encourage further studies on the clinical applications, feasibility, reproducibility and reliability of 3D TA.

A generalized mathematical framework for estimating the residue function for arbitrary vascular networks

The microvasculature plays a vital part in the cardiovascular system. Any impairment to its function can lead to significant pathophysiological effects, particularly in organs such as the brain where there is a very tight coupling between structure and function. However, it is extremely difficult to quantify the health of the microvasculature in vivo, other than by assessing perfusion, using techniques such as arterial spin labelling. Recent work has suggested that the flow distribution within a voxel could also be a valuable measure. This can also be measured clinically, but as yet has not been related to the properties of the microvasculature due to the difficulties in modelling and characterizing these strongly inter-connected networks. In this paper, we present a new technique for characterizing an existing physiologically accurate model of the cerebral microvasculature in terms of its residue function. A new analytical mathematical framework for calculation of the residue function, based on the mass transport equation, of any arbitrary network is presented together with results from simulations. We then present a method for characterizing this function, which can be directly related to clinical data, and show how the resulting parameters are affected under conditions of both reduced perfusion and reduced network density. It is found that the residue function parameters are affected in different ways by these two effects, opening up the possibility of using such parameters, when acquired from clinical data, to infer information about both the network properties and the perfusion distribution. These results open up the possibility of obtaining valuable clinical information about the health of the microvasculature in vivo, providing additional tools to clinicians working in cerebrovascular diseases, such as stroke and dementia.

(3)D [corrected] quantification of tumor vasculature in lymphoma xenografts in NOD/SCID mice allows to detect differences among vascular-targeted therapies

Quantitative characterization of the in vivo effects of vascular-targeted therapies on tumor vessels is hampered by the absence of useful 3D vascular network descriptors aside from microvessel density. In this study, we extended the quantification of planar vessel distribution to the analysis of vascular volumes by studying the effects of antiangiogenic (sorafenib and sunitinib) or antivascular (combretastatin A4 phosphate) treatments on the quantity and spatial distributions of thin microvessels. These observations were restricted to perinecrotic areas of treated human multiple myeloma tumors xenografted in immunodeficient mice and to microvessels with an approximate cross-sectional area lower than 75 µm². Finally, vessel skeletonization minimized artifacts due to possible differential wall staining and allowed a comparison of the various treatment effects. Antiangiogenic drug treatment reduced the number of vessels of every caliber (at least 2-fold fewer vessels vs. controls; p<0.001, n = 8) and caused a heterogeneous distribution of the remaining vessels. In contrast, the effects of combretastatin A4 phosphate mainly appeared to be restricted to a homogeneous reduction in the number of thin microvessels (not more than 2-fold less vs. controls; p<0.001, n = 8) with marginal effects on spatial distribution. Unexpectedly, these results also highlighted a strict relationship between microvessel quantity, distribution and cross-sectional area. Treatment-specific changes in the curves describing this relationship were consistent with the effects ascribed to the different drugs. This finding suggests that our results can highlight differences among vascular-targeted therapies, providing hints on the processes underlying sample vascularization together with the detailed characterization of a pathological vascular tree.

An attempt toward objective assessment of brain tumor vascularization using susceptibility weighted imaging and dedicated computer program - a preliminary study

Background:

Susceptibility weighted imaging (SWI) is a novel MRI sequence which demonstrates the susceptibility differences between adjacent tissues and it is promising to be a sequence useful in the assessment of brain tumors vascularity. The aim of our study was to demonstrate usefulness of SWI in evaluation of intratumoral vessels in comparison to CET1 sequence in a standardized, objective manner.

Material/Methods:

10 patients with supratentorial brain tumors were included in the study. All of them underwent conventional MRI examination with a 1,5 T scanner. SWI sequence was additionally performed using the following parameters: TR 49 ms,TE 40 ms. We used authors’ personal computer software – Vessels View, to assess the vessels number.

Results:

Comparison of SWI and CET1 sequences was performed using our program. Analysis of all 26 ROIs demonstrated predominance of SWI in the amount of white pixels (vessel cross-sectional) and a similar number of elongated structures (blood vessels).

Conclusions:

To conclude, the results of this study are encouraging; they confirm the added value of SWI as an appropriate and useful sequence in the process of evaluation of intratumoral vascularity. Using our program significantly improved visualization of blood vessels in cerebral tumors. The Vessel View application assists radiologists in demonstrating the vessels and facilitates distinguishing them from adjacent tissues in the image.