Segmentation of brain magnetic resonance angiography images based on MAP–MRF with multi-pattern neighborhood system and approximation of regularization coefficient

Automated morphologic analysis of intracranial and extracranial arteries using convolutional neural networks

OBJECTIVE

To develop an automated method for 3D magnetic resonance (MR) vessel wall image analysis to facilitate morphologic quantification of intra- and extracranial arteries, including vessel centerline tracking, vessel straightening and reformation, vessel wall segmentation based on convoluted neural networks (CNNs), and morphological measurement.

METHODS

MR vessel wall images acquired using DANTE-SPACE sequences and corresponding time-of-flight-MRA images of 67 subjects (including 47 healthy volunteers and 20 patients with atherosclerosis) were included in this study. The centerline of the vessel was firstly extracted from the MRA images and copyed to the 3D MR vessel wall images through the registration relationship between the MRA images and the MR vessel wall images to extract, straighten, and reconstruct interested vessel segments into 2D slices. Then a complete CNN-based Unet-like method was used to automatically segment the vessel wall to obtain quantitative morphological measurements such as maximum wall thicknesses and normalized wall index (NWI).

RESULTS

The proposed automatic segmentation network was trained and validated with 11,735 slices and tested on 2517 slices. The method showed satisfactory agreement with manual segmentation method. The Dice coefficients of intracranial arteries were 0.90 for lumen and 0.78 for vessel wall, while the Dice coefficients of extracranial arteries were 0.90 for lumen and 0.82 for vessel wall. The maximum wall thickness and NWI obtained from the proposed automatic method were slightly larger than those obtained from the manual method for both intra- and extracranial arteries. However, there was no significant difference of the quantitative measurements between the two methods (p > 0.05). In addition, the automatically measured NWI of plaque slice was significantly larger than that of normal slice.

CONCLUSION

We propose an automatic analysis method of MR vessel wall images, which can realize automatic segmentation of intra- and extracranial vessel wall. It is expected to facilitate large-scale arterial vessel wall morphological quantification.

ADVANCES IN KNOWLEDGE

We have proposed an automatic method for analysis of intra- and extracranial MR vessel wall images simultaneously based on CNN, which can facilitate large-scale quantitative analyses of vessel walls.

Portal Vein and Hepatic Vein Segmentation in Multi-Phase MR Images Using Flow-Guided Change Detection

Segmenting portal vein (PV) and hepatic vein (HV) from magnetic resonance imaging (MRI) scans is important for hepatic tumor surgery. Compared with single phase-based methods, multiple phases-based methods have better scalability in distinguishing HV and PV by exploiting multi-phase information. However, these methods just coarsely extract HV and PV from different phase images. In this paper, we propose a unified framework to automatically and robustly segment 3D HV and PV from multi-phase MR images, which considers both the change and appearance caused by the vascular flow event to improve segmentation performance. Firstly, inspired by change detection, flow-guided change detection (FGCD) is designed to detect the changed voxels related to hepatic venous flow by generating hepatic venous phase map and clustering the map. The FGCD uniformly deals with HV and PV clustering by the proposed shared clustering, thus making the appearance correlated with portal venous flow robustly delineate without increasing framework complexity. Then, to refine vascular segmentation results produced by both HV and PV clustering, interclass decision making (IDM) is proposed by combining the overlapping region discrimination and neighborhood direction consistency. Finally, our framework is evaluated on multi-phase clinical MR images of the public dataset (TCGA) and local hospital dataset. The quantitative and qualitative evaluations show that our framework outperforms the existing methods.

Iterative stripe artifact correction framework for TOF-MRA

The purpose of this study is to develop a practical stripe artifacts correction framework on three-dimensional (3-D) time-of-flight magnetic resonance angiography (TOF-MRA) obtained by multiple overlapping thin slab acquisitions (MOTSA) technology. In this work, the stripe artifacts in TOF-MRA were considered as a part of image texture. To separate the image structure and the texture, the relative total variation (RTV) was firstly employed to smooth the TOF-MRA for generating the template image with fewer image textures. Then a residual image was generated, which was the difference between the template image and the raw TOF-MRA. The residual image was served as the image texture, which contained the image details and stripe artifacts. Then, we obtained the artifact image from the residual image via a filter in a specific direction since the image artifacts appeared as stripes. The image details were then produced from the difference between the artifact image and the image texture. To produce the corrected images, we finally compensated the image details to the RTV smoothing image. The proposed method was continued until the stripe artifacts during the iteration vary as little as possible. The digital phantom and the real patients' TOF-MRA were used to test the approach. The spatial uniformity was increased from 74% to 82% and the structural similarity was improved from 86% to 98% in the digital phantom test by using the proposed algorithm. Our approach proved to be highly successful in eliminating stripe artifacts in real patient data tests while retaining image details. The proposed iterative framework on TOF-MRA stripe artifact correction is effective and appealing for enhancing the imaging performance of multi-slab 3-D acquisitions.

Cerebrovascular segmentation from TOF-MRA based on multiple-U-net with focal loss function

BACKGROUND AND OBJECTIVE

Accurate cerebrovascular segmentation plays an important role in the diagnosis of cerebrovascular diseases. Considering the complexity and uncertainty of doctors' manual segmentation of cerebral vessels, this paper proposed an automatic segmentation algorithm based on Multiple-U-net (M-U-net) to segment cerebral vessel structures from the Time-of-flight Magnetic Resonance Angiography (TOF-MRA) data.

METHODS

First, the TOF-MRA data was normalized by volume and then divided into three groups through slices of axial, coronal and sagittal directions respectively. Three single U-nets were trained by divided dataset. To solve the problem of uneven distribution of positive and negative samples, the focal loss function was adopted in training. After obtaining the prediction results of three single U-nets, the voting feature fusion and the post-processing process based on connected domain analysis would be performed. 95 volumes of TOF-MRA provided by the MIDAS platform were applied to the experiment, among which 20 volumes were treated as the training dataset, 5 volumes were used as the validation dataset and the remaining 70 volumes were divided into 10 groups to test the trained model respectively.

RESULTS

Experiments showed that the proposed M-U-net based algorithm achieved 88.60% and 87.93% Dice Similarity Coefficient (DSC) on the verification dataset and testing dataset, which performed better than any single U-net.

CONCLUSIONS

Compared with other existing algorithms, our algorithm reached the state of the art level. The feature fusion of three single U-nets could effectively complement the segmentation results.

A Parallel Cerebrovascular Segmentation Algorithm Based on Focused Multi-Gaussians Model and Heterogeneous Markov Random Field

A complete and detailed cerebrovascular image segmented from time-of-flight magnetic resonance angiography (TOF-MRA) data is essential for the diagnosis and therapy of the cerebrovascular diseases. In recent years, three-dimensional cerebrovascular segmentation algorithms based on statistical models have been widely used, but the existed methods always perform poorly on stenotic vessels and are not robust enough. In this paper, we propose a parallel cerebrovascular segmentation algorithm based on focused multi-Gaussians model and heterogeneous Markov random field. Specifically, we present a focused multi-Gaussians (FMG) model with local fitting region to model the vascular tissue more accurately and introduce the chaotic oscillation particle swarm optimization (CO-PSO) algorithm to improve the global optimization capability in the parameter estimation. Furthermore, we design a heterogeneous Markov Random Field (MRF) in the three-dimensional neighborhood system to incorporate precise local character of image. Finally, the algorithm has been performed parallel optimization based on GPUs and obtain about 60 times speedup compared to serial execution. The experiments show that the proposed algorithm can produce more detailed segmentation result in shorter time and performs well on the stenotic vessels robustly.

Statistical modeling and knowledge-based segmentation of cerebral artery based on TOF-MRA and MR-T1

BACKGROUND AND OBJECTIVE

For cerebrovascular segmentation from time-of-flight (TOF) magnetic resonance angiography (MRA), the focused issues are segmentation accuracy, vascular network coverage ratio, and cerebral artery and vein (CA/CV) separation. Therefore, cerebral artery segmentation is a challenging work, while a complete solution is lacking so far.

METHODS

The preprocessing of skull-stripping and Hessian-based feature extraction is first implemented to acquire an indirect prior knowledge of vascular distribution and shape. Then, a novel intensity- and shape-based Markov statistical modeling is proposed for complete cerebrovascular segmentation, where our low-level process employs a Gaussian mixture model to fit the intensity histogram of the skull-stripped TOF-MRA data, while our high-level process employs the vascular shape prior to construct the energy function. To regularize the individual data processes, Markov regularization parameter is automatically estimated by using a machine-learning algorithm. Further, cerebral artery and vein (CA/CV) separation is explored with a series of morphological logic operations, which are based on a direct priori knowledge on the relationship of arteriovenous topology and brain tissues in between TOF-MRA and MR-T1.

RESULTS

We employed 109 sets of public datasets from MIDAS for qualitative and quantitative assessment. The Dice similarity coefficient, false negative rate (FNR), and false positive rate (FPR) of 0.933, 0.158, and 0.091% on average, as well as CA/CV separation results with the agreement, FNR, and FPR of 0.976, 0.041, and 0.022 on average. For clinical visual assessment, our methods can segment various sizes of the vessel in different contrast region, especially performs better on vessels of small size in low contrast region.

CONCLUSION

Our methods obtained satisfying results in visual and quantitative evaluation. The proposed method is capable of accurate cerebrovascular segmentation and efficient CA/CV separation. Further, it can stimulate valuable clinical applications on the computer-assisted cerebrovascular intervention according to the neurosurgeon's recommendation.

A vessel segmentation method for multi-modality angiographic images based on multi-scale filtering and statistical models

Background

Accurate segmentation of blood vessels plays an important role in the computer-aided diagnosis and interventional treatment of vascular diseases. The statistical method is an important component of effective vessel segmentation; however, several limitations discourage the segmentation effect, i.e., dependence of the image modality, uneven contrast media, bias field, and overlapping intensity distribution of the object and background. In addition, the mixture models of the statistical methods are constructed relaying on the characteristics of the image histograms. Thus, it is a challenging issue for the traditional methods to be available in vessel segmentation from multi-modality angiographic images.

Methods

To overcome these limitations, a flexible segmentation method with a fixed mixture model has been proposed for various angiography modalities. Our method mainly consists of three parts. Firstly, multi-scale filtering algorithm was used on the original images to enhance vessels and suppress noises. As a result, the filtered data achieved a new statistical characteristic. Secondly, a mixture model formed by three probabilistic distributions (two Exponential distributions and one Gaussian distribution) was built to fit the histogram curve of the filtered data, where the expectation maximization (EM) algorithm was used for parameters estimation. Finally, three-dimensional (3D) Markov random field (MRF) were employed to improve the accuracy of pixel-wise classification and posterior probability estimation. To quantitatively evaluate the performance of the proposed method, two phantoms simulating blood vessels with different tubular structures and noises have been devised. Meanwhile, four clinical angiographic data sets from different human organs have been used to qualitatively validate the method. To further test the performance, comparison tests between the proposed method and the traditional ones have been conducted on two different brain magnetic resonance angiography (MRA) data sets.

Results

The results of the phantoms were satisfying, e.g., the noise was greatly suppressed, the percentages of the misclassified voxels, i.e., the segmentation error ratios, were no more than 0.3%, and the Dice similarity coefficients (DSCs) were above 94%. According to the opinions of clinical vascular specialists, the vessels in various data sets were extracted with high accuracy since complete vessel trees were extracted while lesser non-vessels and background were falsely classified as vessel. In the comparison experiments, the proposed method showed its superiority in accuracy and robustness for extracting vascular structures from multi-modality angiographic images with complicated background noises.

Conclusions

The experimental results demonstrated that our proposed method was available for various angiographic data. The main reason was that the constructed mixture probability model could unitarily classify vessel object from the multi-scale filtered data of various angiography images. The advantages of the proposed method lie in the following aspects: firstly, it can extract the vessels with poor angiography quality, since the multi-scale filtering algorithm can improve the vessel intensity in the circumstance such as uneven contrast media and bias field; secondly, it performed well for extracting the vessels in multi-modality angiographic images despite various signal-noises; and thirdly, it was implemented with better accuracy, and robustness than the traditional methods. Generally, these traits declare that the proposed method would have significant clinical application.

Automatic SWI Venography Segmentation Using Conditional Random Fields

Susceptibility-weighted imaging (SWI) venography can produce detailed venous contrast and complement arterial dominated MR angiography (MRA) techniques. However, these dense reversed-contrast SWI venograms pose new segmentation challenges. We present an automatic method for whole-brain venous blood segmentation in SWI using Conditional Random Fields (CRF). The CRF model combines different first and second order potentials. First-order association potentials are modeled as the composite of an appearance potential, a Hessian-based shape potential and a non-linear location potential. Second-order interaction potentials are modeled using an auto-logistic (smoothing) potential and a data-dependent (edge) potential. Minimal post-processing is used for excluding voxels outside the brain parenchyma and visualizing the surface vessels. The CRF model is trained and validated using 30 SWI venograms acquired within a population of deep brain stimulation (DBS) patients (age range [Formula: see text] years). Results demonstrate robust and consistent segmentation in deep and sub-cortical regions (median kappa = 0.84 and 0.82), as well as in challenging mid-sagittal and surface regions (median kappa = 0.81 and 0.83) regions. Overall, this CRF model produces high-quality segmentation of SWI venous vasculature that finds applications in DBS for minimizing hemorrhagic risks and other surgical and non-surgical applications.