Segmentation of lumen and outer wall of abdominal aortic aneurysms from 3D black-blood MRI with a registration based geodesic active contour model

VWI-APP: Vessel wall imaging-dedicated automated processing pipeline for intracranial atherosclerotic plaque quantification

BACKGROUND

Quantitative plaque assessment based on 3D magnetic resonance (MR) vessel wall imaging (VWI) has been shown to provide valuable numerical markers of the burden and risk of intracranial atherosclerotic disease (ICAD). However, plaque quantification is currently time-consuming and observer-dependent due to the demand for heavy manual effort. A VWI-dedicated automated processing pipeline (VWI-APP) is desirable.

PURPOSE

To develop and evaluate a VWI-APP for end-to-end quantitative analysis of intracranial atherosclerotic plaque.

METHODS

We retrospectively enrolled 91 subjects with ICAD (80 for pipeline development, 10 for an end-to-end pipeline evaluation, and 1 for demonstrating longitudinal plaque assessment) who had undergone VWI and MR angiography. In an end-to-end evaluation, diameter stenosis (DS), normalized wall index (NWI), remodeling ratio (RR), plaque wall contrast ratio (CR), and total plaque volume (TPV) were quantified at each culprit lesion using the developed VWI-APP and a computer-aided manual approach by a neuroradiologist, respectively. The time consumed in each quantification approach was recorded. Two-sided paired t-tests and intraclass correlation coefficient (ICC) were used to determine the difference and agreement in each plaque metric between VWI-APP and manual quantification approaches.

RESULTS

There was no significant difference between VWI-APP and manual quantification in each plaque metric. The ICC was 0.890, 0.813, 0.827, 0.891, and 0.991 for DS, NWI, RR, CR, and TPV, respectively, suggesting good to excellent accuracy of the pipeline method in plaque quantification. Quantitative analysis of each culprit lesion on average took 675.7 s using the manual approach but shortened to 238.3 s with the aid of VWI-APP.

CONCLUSIONS

VWI-APP is an accurate and efficient approach to intracranial atherosclerotic plaque quantification. Further clinical assessment of this automated tool is warranted to establish its utility in the risk assessment of ICAD lesions.

3D carotid artery segmentation using shape-constrained active contours

Reconstruction of the carotid artery is demanded in the detection and characterization of atherosclerosis. This study proposes a shape-constrained active contour model for segmenting the carotid artery from MR images, which embeds the output of the deep learning network into the active contour. First the centerline of the carotid artery is localized and then modified active contour initialized from the centerline is used to extract the vessel lumen, finally the probability atlas generated by the deep learning network in polar representation domain is integrated into the active contour as a prior information to detect the outer wall. The results showed that the proposed active contour model was efficient and comparable to manual segmentation.

Intracranial vessel wall segmentation with deep learning using a novel tiered loss function incorporating class inclusion

PURPOSE

To develop an automated vessel wall segmentation method on T1-weighted intracranial vessel wall magnetic resonance images, with a focus on modeling the inclusion relation between the inner and outer boundaries of the vessel wall.

METHODS

We propose a novel method that estimates the inner and outer vessel wall boundaries simultaneously, using a network with a single output channel resembling the level-set function height. The network is driven by a unique tiered loss that accounts for data fidelity of the lumen and vessel wall classes and a length regularization to encourage boundary smoothness.

RESULTS

Implemented with a 2.5D UNet with a ResNet backbone, the proposed method achieved Dice similarity coefficients (DSC) in 2D of 0.925 ± 0.048, 0.786 ± 0.084, Hausdorff distance (HD) of 0.286 ± 0.436, 0.345 ± 0.419 mm, and mean surface distance (MSD) of 0.083 ± 0.037 and 0.103 ± 0.032 mm for the lumen and vessel wall, respectively, on a test set; compared favorably to a baseline UNet model that achieved DSC 0.924 ± 0.047, 0.794 ± 0.082, HD 0.298 ± 0.477, 0.394 ± 0.431 mm, and MSD 0.087 ± 0.056, 0.119 ± 0.059 mm. Our vessel wall segmentation method achieved substantial improvement in morphological integrity and accuracy compared to benchmark methods.

CONCLUSIONS

The proposed method provides a systematic approach to model the inclusion morphology and incorporate it into an optimization infrastructure. It can be applied to any application where inclusion exists among a (sub)set of classes to be segmented. Improved feasibility in result morphology promises better support for clinical quantification and decision.

A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm

Abdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentation task will be addressed automatically using a deep learning based approach which has been proved to successfully solve several medical imaging problems with excellent performances. This article therefore proposes a new solution of AAA segmentation using deep learning in a type of 3D convolutional neural network (CNN) architecture that also incorporates coordinate information. The tested CNNs are UNet, AG-DSV-UNet, VNet, ResNetMed and DenseVoxNet. The 3D-CNNs are trained with a dataset of high resolution (256 × 256) non-contrast and post-contrast CT images containing 64 slices from each of 200 patients. The dataset consists of contiguous CT slices without augmentation and no post-processing step. The experiments show that incorporation of coordinate information improves the segmentation results. The best accuracies on non-contrast and contrast-enhanced images have average dice scores of 97.13% and 96.74%, respectively. Transfer learning from a pre-trained network of a pre-operative dataset to post-operative endovascular aneurysm repair (EVAR) was also performed. The segmentation accuracy of post-operative EVAR using transfer learning on non-contrast and contrast-enhanced CT datasets achieved the best dice scores of 94.90% and 95.66%, respectively.

Computer-aided quantification of non-contrast 3D black blood MRI as an efficient alternative to reference standard manual CT angiography measurements of abdominal aortic aneurysms

BACKGROUND

Non-contrast 3D black blood MRI is a promising tool for abdominal aortic aneurysm (AAA) surveillance, permitting accurate aneurysm diameter measurements needed for patient management.

PURPOSE

To evaluate whether automated AAA volume and diameter measurements obtained from computer-aided segmentation of non-contrast 3D black blood MRI are accurate, and whether they can supplant reference standard manual measurements from contrast-enhanced CT angiography (CTA).

MATERIALS AND METHODS

Thirty AAA patients (mean age, 71.9 ± 7.9 years) were recruited between 2014 and 2017. Participants underwent both non-contrast black blood MRI and CTA within 3 months of each other. Semi-automatic (computer-aided) MRI and CTA segmentations utilizing deformable registration methods were compared against manual segmentations of the same modality using the Dice similarity coefficient (DSC). AAA lumen and total aneurysm volumes and AAA maximum diameter, quantified automatically from these segmentations, were compared against manual measurements using Pearson correlation and Bland-Altman analyses. Finally, automated measurements from non-contrast 3D black blood MRI were evaluated against manual CTA measurements using the Wilcoxon test, Pearson correlation and Bland-Altman analyses.

RESULTS

Semi-automatic segmentations had excellent agreement with manual segmentations (lumen DSC: 0.91 ± 0.03 and 0.94 ± 0.03; total aneurysm DSC: 0.92 ± 0.02 and 0.94 ± 0.03, for black blood MRI and CTA, respectively). Automated volume and maximum diameter measurements also had excellent correlation to their manual counterparts for both black blood MRI (volume: r = 0.99, P < 0.001; diameter: r = 0.97, P < 0.001) and CTA (volume: r = 0.99, P < 0.001; diameter: r = 0.97, P < 0.001). Compared to manual CTA measurements, bias and limits of agreement (LOA) for automated MRI measurements (lumen volume: 1.49, [-4.19 7.17] cm³; outer wall volume: -2.46, [-14.05 9.13] cm³; maximal diameter: 0.08, [-6.51 6.67] mm) were largely equivalent to those of manual MRI measurements, particularly for maximum AAA diameter (lumen volume: 0.73, [-6.47 7.93] cm³; outer wall volume: 0.98, [-10.54 12.5] cm³; maximal diameter: 0.08, [-3.67 3.83] mm).

CONCLUSION

Semi-automatic segmentation of non-contrast 3D black blood MRI efficiently provides reproducible morphologic AAA assessment yielding accurate AAA diameters and volumes with no clinically relevant differences compared to either automatic or manual measurements based on CTA.

Outer Wall Segmentation of Abdominal Aortic Aneurysm by Variable Neighborhood Search Through Intensity and Gradient Spaces

Aortic aneurysm segmentation remains a challenge. Manual segmentation is a time-consuming process which is not practical for routine use. To address this limitation, several automated segmentation techniques for aortic aneurysm have been developed, such as edge detection-based methods, partial differential equation methods, and graph partitioning methods. However, automatic segmentation of aortic aneurysm is difficult due to high pixel similarity to adjacent tissue and a lack of color information in the medical image, preventing previous work from being applicable to difficult cases. This paper uses uses a variable neighborhood search that alternates between intensity-based and gradient-based segmentation techniques. By alternating between intensity and gradient spaces, the search can escape from local optima of each space. The experimental results demonstrate that the proposed method outperforms the other existing segmentation methods in the literature, based on measurements of dice similarity coefficient and jaccard similarity coefficient at the pixel level. In addition, it is shown to perform well for cases that are difficult to segment.

Surveillance of abdominal aortic aneurysm using accelerated 3D non-contrast black-blood cardiovascular magnetic resonance with compressed sensing (CS-DANTE-SPACE)

BACKGROUND

3D non-contrast high-resolution black-blood cardiovascular magnetic resonance (CMR) (DANTE-SPACE) has been used for surveillance of abdominal aortic aneurysm (AAA) and validated against computed tomography (CT) angiography. However, it requires a long scan time of more than 7 min. We sought to develop an accelerated sequence applying compressed sensing (CS-DANTE-SPACE) and validate it in AAA patients undergoing surveillance.

METHODS

Thirty-eight AAA patients (all males, 73 ± 6 years) under clinical surveillance were recruited for this study. All patients were scanned with DANTE-SPACE (scan time 7:10 min) and CS-DANTE-SPACE (scan time 4:12 min, a reduction of 41.4%). Nine 9 patients were scanned more than 2 times. In total, 50 pairs of images were available for comparison. Two radiologists independently evaluated the image quality on a 1-4 scale, and measured the maximal diameter of AAA, the intra-luminal thrombus (ILT) and lumen area, ILT-to-muscle signal intensity ratio, and the ILT-to-lumen contrast ratio. The sharpness of the aneurysm inner/outer boundaries was quantified.

RESULTS

CS-DANTE-SPACE achieved comparable image quality compared with DANTE-SPACE (3.15 ± 0.67 vs. 3.03 ± 0.64, p = 0.06). There was excellent agreement between results from the two sequences for diameter/area and ILT ratio measurements (ICCs> 0.85), and for quantifying growth rate (3.3 ± 3.1 vs. 3.3 ± 3.4 mm/year, ICC = 0.95.) CS-DANTE-SPACE showed a higher ILT-to-lumen contrast ratio (p = 0.01) and higher sharpness than DANTE-SPACE (p = 0.002). Both sequences had excellent inter-reader reproducibility for quantitative measurements (ICC > 0.88).

CONCLUSION

CS-DANTE-SPACE can reduce scan time while maintaining image quality for AAA imaging. It is a promising tool for the surveillance of patients with AAA disease in the clinical setting.

Extending Cardiac Functional Assessment with Respiratory-Resolved 3D Cine MRI

This study aimed to develop a cardiorespiratory-resolved 3D magnetic resonance imaging (5D MRI: x-y-z-cardiac-respiratory) approach based on 3D motion tracking for investigating the influence of respiration on cardiac ventricular function. A highly-accelerated 2.5-minute sparse MR protocol was developed for a continuous acquisition of cardiac images through multiple cardiac and respiratory cycles. The heart displacement along respiration was extracted using a 3D image deformation algorithm, and this information was used to cluster the acquired data into multiple respiratory phases. The proposed approach was tested in 15 healthy volunteers (7 females). Cardiac function parameters, including the end-systolic volume (ESV), end-diastolic volume (EDV), stroke volume (SV), and ejection fraction (EF), were measured for the left and right ventricle in both end-expiration and end-inspiration. Although with the proposed 5D cardiac MRI, there were no significant differences (p > 0.05, t-test) between end-expiration and end-inspiration measurements of the cardiac function in volunteers, incremental respiratory motion parameters that were derived from 3D motion tracking, such as the depth, expiration and inspiration distribution, correlated (p < 0.05, correlation coefficient, Mann-Whitney) with those volume-based parameters of cardiac function and varied between genders. The obtained initial results suggested that this new approach allows evaluation of cardiac function during specific respiratory phases. Thus, it can enable investigation of effects related to respiratory variability and better assessment of cardiac function for studying respiratory and/or cardiac dysfunction.

Deep Learning Deformation Initialization for Rapid Groupwise Registration of Inhomogeneous Image Populations

Groupwise image registration tackles biases that can potentially arise from inappropriate template selection. It typically involves simultaneous registration of a cohort of images to a common space that is not specified a priori. Existing groupwise registration methods are computationally complex and are only effective for image populations without large anatomical variations. In this paper, we propose a deep learning framework to rapidly estimate large deformations between images to significantly reduce structural variability. Specifically, we employ a multi-level graph coarsening method to agglomerate similar images into clusters, each represented by an exemplar image. We then use a deep learning framework to predict the initial deformations between images. Warping with the estimated deformations brings the images closer in the image manifold and their alignment can be further refined using conventional groupwise registration algorithms. We evaluated the effectiveness of our method in groupwise registration of MR brain images and compared it against state-of-the-art groupwise registration methods. Experimental results indicate that deformation initialization enables groupwise registration to converge significantly faster with competitive accuracy, therefore facilitates large-scale imaging studies.

Imaging of Thoracoabdominal Aortic Aneurysms

Untreated thoracoabdominal aortic aneurysms are associated with an exceedingly high mortality rate, and surgery carries a high complication rate. Crawford's classification system of thoracoabdominal aortic aneurysms describes aneurysm morphology and stratifies patients on the basis of risk of major postoperative complications including mortality, spinal cord injury, and renal failure. Computed tomography and magnetic resonance angiography are essential for classifying thoracoabdominal aortic aneurysms and identifying other important features that impact prognosis and surgical management. Four-dimensional flow-sensitive magnetic resonance imaging is an emerging technique that may help predict complications and further impact timing of intervention.

3D segmentation of exterior wall surface of abdominal aortic aneurysm from CT images using variable neighborhood search

A 3D model of abdominal aortic aneurysm (AAA) can provide useful anatomical information for clinical management and simulation. Thin-slice contiguous computed tomographic (CT) angiography is the best source of medical images for construction of 3D models, which requires segmentation of AAA in the images. Existing methods for segmentation of AAA rely on either manual process or 2D segmentation in each 2D CT slide. However, a traditional manual segmentation is a time consuming process which is not practical for routine use. The construction of a 3D model from 2D segmentation of each CT slice is not a fully satisfactory solution due to rough contours that can occur because of lack of constraints among segmented slices, as well as missed segmentation slices. To overcome such challenges, this paper proposes the 3D segmentation of AAA using the concept of variable neighborhood search by iteratively alternating between two different segmentation techniques in the two different 3D search spaces of voxel intensity and voxel gradient. The segmentation output of each method is used as the initial contour to the other method in each iteration. By alternating between search spaces, the technique can escape local minima that naturally occur in each search space. Also, the 3D search spaces provide more constraints across CT slices, when compared with the 2D search spaces in individual CT slices. The proposed method is evaluated with 10 easy and 10 difficult cases of AAA. The results show that the proposed 3D segmentation technique achieves the outstanding segmentation accuracy with an average dice similarity value (DSC) of 91.88%, when compared to the other methods using the same dataset, which are the 2D proposed method, classical graph cut, distance regularized level set evolution, and registration based geometric active contour with the DSCs of 87.57 ± 4.52%, 72.47 ± 8.11%, 58.50 ± 8.86% and 76.21 ± 10.49%, respectively.

Evaluation of the distribution and progression of intraluminal thrombus in abdominal aortic aneurysms using high-resolution MRI

BACKGROUND

Intraluminal thrombus (ILT) signal intensity on MRI has been studied as a potential marker of abdominal aortic aneurysm (AAA) progression.

PURPOSE

1) To characterize the relationship between ILT signal intensity and AAA diameter; 2) to evaluate ILT change over time; and 3) to assess the relationship between ILT features and AAA growth.

STUDY TYPE

Prospective.

SUBJECTS

Eighty AAA patients were imaged, and a subset (n = 41) were followed with repeated MRI for 16 ± 9 months.

FIELD STRENGTH/SEQUENCE

3D black-blood fast-spin-echo sequence at 3 T.

ASSESSMENT

ILT was designated as "bright" if the signal was greater than 1.2 times that of adjacent psoas muscle. AAAs were divided into three groups based on ILT: Type 1: bright ILT; Type 2: isointense ILT; Type 3: no ILT. During follow-up, an active ILT change was defined as new ILT formation or an increase in ILT signal intensity to bright; stable ILT was defined as no change in ILT type or ILT became isointense from bright previously.

STATISTICAL TESTS

Shapiro-Wilk test; Mann-Whitney U-test; Fisher's exact test; Kruskal-Wallis test; Spearman's r; intraclass correlation coefficient (ICC), Cohen's kappa.

RESULTS

AAAs with Type 1 ILT were larger than those with Types 2 and 3 ILT (5.1 ± 1.1 cm, 4.4 ± 0.9 cm, 4.2 ± 0.8 cm, P = 0.008). The growth rate of AAAs with Type 1 ILT was significantly greater than that of AAAs with Types 2 and 3 ILT (2.6 ± 2.5, 0.6 ± 1.3, 1.5 ± 0.6 mm/year, P = 0.01). During follow-up, AAAs with active ILT changes had a 3-fold increased growth rate compared with AAAs with stable ILT (3.6 ± 3.0 mm/year vs. 1.2 ± 1.5 mm/year, P = 0.008).

DATA CONCLUSION

AAAs with bright ILT are larger in diameter and grow faster. Active ILT change is associated with faster AAA growth. Black-blood MRI can characterize ILT features and monitor their change over time, which may provide new insights into AAA risk assessment.

LEVEL OF EVIDENCE

2 Technical Efficacy Stage: 5 J. Magn. Reson. Imaging 2019;50:994-1001.

Fully automatic segmentation of 4D MRI for cardiac functional measurements

PURPOSE

Segmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semiautomatically. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV) as well as the myocardium of three-dimensional (3D) magnetic resonance (MR) images throughout the entire cardiac cycle (four-dimensional, 4D), remains challenging. This study proposes a deformable-based segmentation methodology for efficiently segmenting 4D (3D + t) cardiac MR images.

METHODS

The proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images. Following this, a novel level set-based shape prior method was applied to generate the LV epicardial contours and the RV boundary.

RESULTS

This automatic image segmentation approach has been applied to studies on 17 subjects. The results demonstrated that the proposed method was efficient compared to manual segmentation, achieving a segmentation accuracy with average Dice values of 88.62 ± 5.47%, 87.35 ± 7.26%, and 82.63 ± 6.22% for the LV endocardial, LV epicardial, and RV contours, respectively.

CONCLUSIONS

We have presented a method for accurate LV and RV segmentation. Compared to three existing methods, the proposed method can successfully segment the LV and yield the highest Dice value. This makes it an option for clinical assessment of the volume, size, and thickness of the ventricles.

Towards optimal flow diverter porosity for the treatment of intracranial aneurysm

PURPOSE

Low-porosity endovascular stents, known as flow diverters (FDs), have been proposed as an effective and minimally invasive treatment for sidewall intracranial aneurysms (IAs). Although it has been reported that the efficacy of a FD is substantially influenced by its porosity, clinical doctors would clearly prefer to do their interventions optimally based on refined quantitative data. This study focuses on the association between the porosity configurations and the FD efficacy, in order to provide practical data to help the clinical doctors optimize the interventions.

METHOD

Numerical simulations in fluid dynamics were performed using four patient-specific IA geometries, pulsatile velocity profiles and braided fully resolved FDs. The variation of velocity and wall shear stress within the IAs, were investigated in this study. Lattice Boltzmann method (LBM) was used to solve the main challenge centered on the diversity of spatial scales since the typical diameter of struts of FDs is only 25μm while the artery normally can be larger by a hundred times.

RESULTS

Numerical simulations revealed that the blood flow within IA sac was substantially reduced when the porosity is less than 86%. In particular, the flow condition within each IA sac is favorite to initialize thrombus formation when porosity is less than 70%.

CONCLUSION

Our study suggests the existence of a porosity threshold below which the efficacy of a FD will be sufficient for the patients to initialize the thrombus formation. Therefore, by estimating the porosity of FD on patient-specific information, it may be potentially to predict whether or the blood flow condition will successfully become prothrombotic after the FD intervention.

Unsupervised morphological segmentation of tissue compartments in histopathological images

Algorithmic segmentation of histologically relevant regions of tissues in digitized histopathological images is a critical step towards computer-assisted diagnosis and analysis. For example, automatic identification of epithelial and stromal tissues in images is important for spatial localisation and guidance in the analysis and characterisation of tumour micro-environment. Current segmentation approaches are based on supervised methods, which require extensive training data from high quality, manually annotated images. This is often difficult and costly to obtain. This paper presents an alternative data-independent framework based on unsupervised segmentation of oropharyngeal cancer tissue micro-arrays (TMAs). An automated segmentation algorithm based on mathematical morphology is first applied to light microscopy images stained with haematoxylin and eosin. This partitions the image into multiple binary ‘virtual-cells’, each enclosing a potential ‘nucleus’ (dark basins in the haematoxylin absorbance image). Colour and morphology measurements obtained from these virtual-cells as well as their enclosed nuclei are input into an advanced unsupervised learning model for the identification of epithelium and stromal tissues. Here we exploit two Consensus Clustering (CC) algorithms for the unsupervised recognition of tissue compartments, that consider the consensual opinion of a group of individual clustering algorithms. Unlike most unsupervised segmentation analyses, which depend on a single clustering method, the CC learning models allow for more robust and stable detection of tissue regions. The proposed framework performance has been evaluated on fifty-five hand-annotated tissue images of oropharyngeal tissues. Qualitative and quantitative results of the proposed segmentation algorithm compare favourably with eight popular tissue segmentation strategies. Furthermore, the unsupervised results obtained here outperform those obtained with individual clustering algorithms.