Using Deep Learning and B-Splines to Model Blood Vessel Lumen from 3D Images

Accurate geometric modeling of blood vessel lumen from 3D images is crucial for vessel quantification as part of the diagnosis, treatment, and monitoring of vascular diseases. Our method, unlike other approaches which assume a circular or elliptical vessel cross-section, employs parametric B-splines combined with image formation system equations to accurately localize the highly curved lumen boundaries. This approach avoids the need for image segmentation, which may reduce the localization accuracy due to spatial discretization. We demonstrate that the model parameters can be reliably identified by a feedforward neural network which, driven by the cross-section images, predicts the parameter values many times faster than a reference least-squares (LS) model fitting algorithm. We present and discuss two example applications, modeling the lower extremities of artery-vein complexes visualized in steady-state contrast-enhanced magnetic resonance images (MRI) and the coronary arteries pictured in computed tomography angiograms (CTA). Beyond applications in medical diagnosis, blood-flow simulation and vessel-phantom design, the method can serve as a tool for automated annotation of image datasets to train machine-learning algorithms.

Introduction to Radiomics

Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

Image registration in dynamic renal MRI-current status and prospects

Magnetic resonance imaging (MRI) modalities have achieved an increasingly important role in the clinical work-up of chronic kidney diseases (CKD). This comprises among others assessment of hemodynamic parameters by arterial spin labeling (ASL) or dynamic contrast-enhanced (DCE-) MRI. Especially in the latter, images or volumes of the kidney are acquired over time for up to several minutes. Therefore, they are hampered by motion, e.g., by pulsation, peristaltic, or breathing motion. This motion can hinder subsequent image analysis to estimate hemodynamic parameters like renal blood flow or glomerular filtration rate (GFR). To overcome motion artifacts in time-resolved renal MRI, a wide range of strategies have been proposed. Renal image registration approaches could be grouped into (1) image acquisition techniques, (2) post-processing methods, or (3) a combination of image acquisition and post-processing approaches. Despite decades of progress, the translation in clinical practice is still missing. The aim of the present article is to discuss the existing literature on renal image registration techniques and show today’s limitations of the proposed techniques that hinder clinical translation. This paper includes transformation, criterion function, and search types as traditional components and emerging registration technologies based on deep learning. The current trend points towards faster registrations and more accurate results. However, a standardized evaluation of image registration in renal MRI is still missing.

Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging

The purpose of this study was to differentiate acute from chronic myocardial infarction using machine learning techniques and texture features extracted from cardiac magnetic resonance imaging (MRI). The study group comprised 22 cases with acute myocardial infarction (AMI) and 22 cases with chronic myocardial infarction (CMI). Cine and late gadolinium enhancement (LGE) MRI were analyzed independently to differentiate AMI from CMI. A total of 279 texture features were extracted from predefined regions of interest (ROIs): the infarcted area on LGE MRI, and the entire myocardium on cine MRI. Classification performance was evaluated by a nested cross-validation approach combining a feature selection technique with three predictive models: random forest, support vector machine (SVM) with Gaussian Kernel, and SVM with polynomial kernel. The polynomial SVM yielded the best classification performance. Receiver operating characteristic curves provided area-under-the-curve (AUC) (mean±standard deviation) of 0.86±0.06 on LGE MRI using 72 features; AMI sensitivity=0.81±0.08 and specificity=0.84±0.09. On cine MRI, AUC=0.82±0.06 using 75 features; AMI sensitivity=0.79±0.10 and specificity=0.80±0.10. We concluded that texture analysis can be used for differentiation of AMI from CMI on cardiac LGE MRI, and also on standard cine sequences in which the infarction is visually imperceptible in most cases.

Simulation of MR angiography imaging for validation of cerebral arteries segmentation algorithms

BACKGROUND AND OBJECTIVE

Accurate vessel segmentation of magnetic resonance angiography (MRA) images is essential for computer-aided diagnosis of cerebrovascular diseases such as stenosis or aneurysm. The ability of a segmentation algorithm to correctly reproduce the geometry of the arterial system should be expressed quantitatively and observer-independently to ensure objectivism of the evaluation.

METHODS

This paper introduces a methodology for validating vessel segmentation algorithms using a custom-designed MRA simulation framework. For this purpose, a realistic reference model of an intracranial arterial tree was developed based on a real Time-of-Flight (TOF) MRA data set. With this specific geometry blood flow was simulated and a series of TOF images was synthesized using various acquisition protocol parameters and signal-to-noise ratios. The synthesized arterial tree was then reconstructed using a level-set segmentation algorithm available in the Vascular Modeling Toolkit (VMTK). Moreover, to present versatile application of the proposed methodology, validation was also performed for two alternative techniques: a multi-scale vessel enhancement filter and the Chan-Vese variant of the level-set-based approach, as implemented in the Insight Segmentation and Registration Toolkit (ITK). The segmentation results were compared against the reference model.

RESULTS

The accuracy in determining the vessels centerline courses was very high for each tested segmentation algorithm (mean error rate = 5.6% if using VMTK). However, the estimated radii exhibited deviations from ground truth values with mean error rates ranging from 7% up to 79%, depending on the vessel size, image acquisition and segmentation method.

CONCLUSIONS

We demonstrated the practical application of the designed MRA simulator as a reliable tool for quantitative validation of MRA image processing algorithms that provides objective, reproducible results and is observer independent.

On The Effect Of Image Brightness And Contrast Nonuniformity On Statistical Texture Parameters

Computerized texture analysis characterizes spatial patterns of image intensity, which originate in the structure of tissues. However, a number of texture descriptors also depend on local average image intensity and/or contrast. This variations, known as image nonuniformity (inhomogeneity) artefacts often occur, e.g. in MRI. Their presence may lead to errors in tissue description. This unwanted effect is explained in this paper using statistical texture descriptors applied for MRI slices of a normal and fibrotic liver. To reduce the errors, correction of image spatial nonuniformity prior to texture analysis is performed. The issue of sensitivity of popular texture parameters to image nonuniformities is discussed. It is illustrated by classification examples of natural Brodatz textures, digitally modified to account for inhomogeneities – modeled as smooth variations of image intensity and contrast. A set of texture features is identified which represent certain immunity to image inhomogeneities.

Textural entropy as a potential feature for quantitative assessment of jaw bone healing process

INTRODUCTION

The aim of the study was to propose and evaluate textural entropy as a parameter for bone healing assessment.

MATERIAL AND METHODS

One hundred and twenty radiographs with loss of bone architecture were investigated (a bone defect was circumscribed - ROI DEF). A reference region (ROI REF) of the same surface area as the ROI DEF was placed in a field distant from the defect, where a normal, trabecular pattern of bone structure was well visualized. Data of three time points were investigated: T0 - immediately after the surgical procedure, T1 - 3 months post-op, and T2 - 12 months post-op.

RESULTS

Textural entropy as a parameter describing bone structure regeneration was selected based on Fisher coefficient (F) evaluation. F was highest in T0 (3.4) and was decreasing later in T1 (1.7) and T2 (1.0 - means final lack of difference in the structure to reference bone). Textural entropy is a measure of structure disarrangement which in a bone defect region attains minimal value due to structural homogeneity, i.e. low complexity of the texture. The calculated parameter in the investigated material revealed a gradual increase inside the bone defect (p < 0.05), i.e. increase of complexity in a time-dependent manner starting from immediate post-op (T0 = 2.51; T1 = 2.68) up to most complex 1 year post-operational (T2 = 2.73), reaching the reference level of a normal bone.

CONCLUSIONS

Textural entropy may be useful for computer assisted evaluation of bone regeneration process. The complexity of the texture corresponds to mature trabecular bone formation.

Computer simulation of magnetic resonance angiography imaging: model description and validation

With the development of medical imaging modalities and image processing algorithms, there arises a need for methods of their comprehensive quantitative evaluation. In particular, this concerns the algorithms for vessel tracking and segmentation in magnetic resonance angiography images. The problem can be approached by using synthetic images, where true geometry of vessels is known. This paper presents a framework for computer modeling of MRA imaging and the results of its validation. A new model incorporates blood flow simulation within MR signal computation kernel. The proposed solution is unique, especially with respect to the interface between flow and image formation processes. Furthermore it utilizes the concept of particle tracing. The particles reflect the flow of fluid they are immersed in and they are assigned magnetization vectors with temporal evolution controlled by MR physics. Such an approach ensures flexibility as the designed simulator is able to reconstruct flow profiles of any type. The proposed model is validated in a series of experiments with physical and digital flow phantoms. The synthesized 3D images contain various features (including artifacts) characteristic for the time-of-flight protocol and exhibit remarkable correlation with the data acquired in a real MR scanner. The obtained results support the primary goal of the conducted research, i.e. establishing a reference technique for a quantified validation of MR angiography image processing algorithms.

Texture analysis methodologies for magnetic resonance imaging

Methods for the analysis of digital-image texture are reviewed. The functions of MaZda, a computer program for quantitative texture analysis developed within the framework of the European COST (Cooperation in the Field of Scientific and Technical Research) B11 program, are introduced. Examples of texture analysis in magnetic resonance images are discussed.

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

A method is proposed for quantitative description of blood-vessel trees, which can be used for tree classification and/or physical parameters indirect monitoring. The method is based on texture analysis of 3D images of the trees. Several types of trees were defined, with distinct tree parameters (number of terminal branches, blood viscosity, input and output flow). A number of trees were computer-simulated for each type. 3D image was computed for each tree and its texture features were calculated. Best discriminating features were found and applied to 1-NN nearest neighbor classifier. It was demonstrated that (i) tree images can be correctly classified for realistic signal-to-noise ratio, (ii) some texture features are monotonously related to tree parameters, (iii) 2D texture analysis is not sufficient to represent the trees in the discussed sense. Moreover, applicability of texture model to quantitative description of vascularity images was also supported by unsupervised exploratory analysis. Eventually, the experimental confirmation was done, with the use of confocal microscopy images of rat brain vasculature. Several classes of brain tissue were clearly distinguished based on 3D texture numerical parameters, including control and different kinds of tumours - treated with NG2 proteoglycan to promote angiogenesis-dependent growth of the abnormal tissue. The method, applied to magnetic resonance imaging e.g. real neovasculature or retinal images can be used to support noninvasive medical diagnosis of vascular system diseases.

MaZda--a software package for image texture analysis

MaZda, a software package for 2D and 3D image texture analysis is presented. It provides a complete path for quantitative analysis of image textures, including computation of texture features, procedures for feature selection and extraction, algorithms for data classification, various data visualization and image segmentation tools. Initially, MaZda was aimed at analysis of magnetic resonance image textures. However, it revealed its effectiveness in analysis of other types of textured images, including X-ray and camera images. The software was utilized by numerous researchers in diverse applications. It was proven to be an efficient and reliable tool for quantitative image analysis, even in more accurate and objective medical diagnosis. MaZda was also successfully used in food industry to assess food product quality. MaZda can be downloaded for public use from the Institute of Electronics, Technical University of Lodz webpage.

[Short run length of pixels in radiotexture of jaw alveolar ridge in human]

The real bone structure can be completely described by histomorphometric analysis; however, it needs bone biopsy. The development of imaging techniques and mathematical methods of texture parameters extraction from radiographs make it possible to reveal the characteristic bone features in non-invasive manner. The aim of this study was to formulate a mathematical description of image texture for finding out whether there exist any structural differences (run-length matrix) in jaw bone depended on gender. Parameters derived from a run-length matrix are used to characterize the texture in quantity.

MATERIAL AND METHODS

319 digital, standardized, intra-oral, plain radiographs of patients qualifying to dental implantations were included into this study. Straight-line series (runs) of pixels of similar gray level were searched and analyzed in radiographs.

RESULTS

Exploring the local bone structure at particular fragments of the jaws, in females significantly more frequent the presence of short series of pixels in lower alveolar ridge than in upper alveolar ridge are observed. Only later aspects of maxillary alveolar ridge have the radiomicroarchitecture depending on patient's gender in respect to the investigated feature. In females, much more number of short series of the pixels is revealed at lateral aspect of alveolar ridge of mandible than at frontal aspect.

CONCLUSION

Quantitative description of short series of pixels is useful for evaluation of radiotexture in images of alveolar ridge.

Classification and segmentation of intracardiac masses in cardiac tumor echocardiograms

This paper describes an automatic method for classification and segmentation of different intracardiac masses in tumor echocardiograms. Identification of mass type is highly desirable, since to different treatment options for cardiac tumors (surgical resection) and thrombi (effective anticoagulant treatment) are possible. Correct diagnosis of the character of intracardiac mass in a living patient is a true challenge for a cardiologist; therefore, an objective image analysis method may be useful in heart diseases diagnosis. Image texture analysis is used to distinguish various types of masses. The presented methods assume that image texture encodes important histological features of masses and, therefore, texture numerical parameters enable the discrimination and segmentation of a mass. The recently developed technique based on the network of synchronized oscillators is proposed for the image segmentation. This technique is based on a 'temporary correlation' theory, which attempts to explain scene recognition as it would be performed by a human brain. This theory assumes that different groups of neural cells encode different properties of homogeneous image regions (e.g. shape, color, texture). Monitoring of temporal activity of cell groups leads to scene segmentation. A network of synchronized oscillators was successfully used for segmentation of Brodatz textures and medical textured images. The advantage of this network is its ability to detect texture boundaries. It can be also manufactured as a VLSI chip, for a very fast image segmentation. The accuracy of locating of analyzed tissues in the image should be assessed to evaluate a segmentation technique. The new evaluation method based on measurement of physical textured test objects was proposed. Firstly, a series of object images was obtained by the use of different devices (scanner, digital camera and TV camera). Secondly, the images were segmented using oscillator network and feedforward artificial neural network. Thirdly, geometrical test object parameters were estimated and compared to its true values. The experiment was repeated also for ultrasound images, which represented rectangular cross-section of synthetic sponge submerged in water. In addition, classification and segmentation of selected benign tumor echocardiograms were performed. Oscillator network was used with network weights defined for both whole texture region and texture boundary detection for the tumor segmentation. The latter method provides much faster segmentation with the similar accuracy. The obtained segmentation results were discussed and compared to the artificial neural network classifier. Finally, it was demonstrated that the network of synchronized oscillators is a reliable tool for the segmentation of the selected intracardiac masses, since it gives a relatively accurate location of analyzed tissues. The advantage of the proposed method is its resistance to changes of the visual information in the analyzed image and to noise and artifacts, often present in echocardiograms.

Texture analysis for tissue discrimination on T1-weighted MR images of the knee joint in a multicenter study: Transferability of texture features and comparison of feature selection methods and classifiers

PURPOSE

To investigate the reproducibility and transferability of texture features between MR centers, and to compare two feature selection methods and two classifiers.

MATERIALS AND METHODS

Coronal T1-weighted MR images of the knees of 63 patients, divided into three groups, were included in the study. MR images were obtained at three different MR centers. Regions of interest (ROIs) were drawn in the bone marrow and fat tissue. Then texture analysis (TA) of the ROIs was performed, and the most discriminant features were identified using Fisher coefficients and POE+ACC (probability of classification error and average correlation coefficients). Based on these features, artificial neural network (ANN) and k-nearest-neighbor (k-NN) classifiers were used for tissue discrimination.

RESULTS

Although the texture features differed among the MR centers, features from one center could be successfully used for tissue discrimination in texture data on MR images from other centers. The best results were achieved using the ANN classifier in combination with features selected by POE+ACC.

CONCLUSION

The differences in texture features extracted from MR images from different centers seem to have only a small impact on the results of tissue discrimination.

Two-phase active contour method for semiautomatic segmentation of the heart and blood vessels from MRI images for 3D visualization

The paper presents an active-contour segmentation method for 2D structures in MR images. The method combines two approaches to active contour segmentation, known as balloons and snakes. This makes the method shape independent and accurate. New anti-tangling features were introduced to improve segmentation of very complex object shapes, e.g. the left ventricle with papillary muscles. The method was applied to segment all large structures in the cardiovascular system and its outcome was used for 3D visualization.

Parametric signal restoration using artificial neural networks

The problem of parametric signal restoration given its blurred/nonlinearly distorted version contaminated by additive noise is discussed. It is postulated that feedforward artificial neural networks can be used to find a solution to this problem. The proposed estimator does not require iterative calculations that are normally performed using numerical methods for signal parameter estimation. Thus high speed is the main advantage of this approach. A two-stage neural network-based estimator architecture is considered in which the vector of measurements is projected on the signal subspace and the resulting features form the input to a feedforward neural network. The effect of noise on the estimator performance is analyzed and compared to the least-squares technique. It is shown, for low and moderate noise levels, that the two estimators are similar to each other in terms of their noise performance, provided the neural network approximates the inverse mapping from the measurement space to the parameter space with a negligible error. However, if the neural network is trained on noisy signal observations, the proposed technique is superior to the least-squares estimate (LSE) model fitting. Numerical examples are presented to support the analytical results. Problems for future research are addressed.