Population-based Stroke Atlas for outcome prediction: method and preliminary results for ischemic stroke from CT.

BACKGROUND AND PURPOSE: Knowledge of outcome prediction is important in stroke management. We propose a lesion size and location-driven method for stroke outcome prediction using a Population-based Stroke Atlas (PSA) linking neurological parameters with neuroimaging in population. The PSA aggregates data from previously treated patients and applies them to currently treated patients. The PSA parameter distribution in the infarct region of a treated patient enables prediction. We introduce a method for PSA calculation, quantify its performance, and use it to illustrate ischemic stroke outcome prediction of modified Rankin Scale (mRS) and Barthel Index (BI). METHODS: The preliminary PSA was constructed from 128 ischemic stroke cases calculated for 8 variants (various data aggregation schemes) and 3 case selection variables (infarct volume, NIHSS at admission, and NIHSS at day 7), each in 4 ranges. Outcome prediction for 9 parameters (mRS at 7th, and mRS and BI at 30th, 90th, 180th, 360th day) was studied using a leave-one-out approach, requiring 589,824 PSA maps to be analyzed. RESULTS: Outcomes predicted for different PSA variants are statistically equivalent, so the simplest and most efficient variant aiming at parameter averaging is employed. This variant allows the PSA to be pre-calculated before prediction. The PSA constrained by infarct volume and NIHSS reduces the average prediction error (absolute difference between the predicted and actual values) by a fraction of 0.796; the use of 3 patient-specific variables further lowers it by 0.538. The PSA-based prediction error for mild and severe outcomes (mRS  =  [2]-[5]) is (0.5-0.7). Prediction takes about 8 seconds. CONCLUSIONS: PSA-based prediction of individual and group mRS and BI scores over time is feasible, fast and simple, but its clinical usefulness requires further studies. The case selection operation improves PSA predictability. A multiplicity of PSAs can be computed independently for different datasets at various centers and easily merged, which enables building powerful PSAs over the community.

Feasibility of using the marginal blood vessels as reference landmarks for CT colonography.

OBJECTIVE: The purpose of this study was to show the spatial relationship of the colonic marginal blood vessels and the teniae coli on CT colonography (CTC) and the use of the marginal blood vessels for supine-prone registration of polyps and for determination of proper connectivity of collapsed colonic segments. MATERIALS AND METHODS: We manually labeled the marginal blood vessels on 15 CTC examinations. Colon segmentation, centerline extraction, teniae detection, and teniae identification were automatically performed. For assessment of their spatial relationships, the distances from the marginal blood vessels to the three teniae coli and to the colon were measured. Student t tests (paired, two-tailed) were performed to evaluate the differences among these distances. To evaluate the reliability of the marginal vessels as reference points for polyp correlation, we analyzed 20 polyps from 20 additional patients who underwent supine and prone CTC. The average difference of the circumferential polyp position on the supine and prone scans was computed. Student t tests (paired, two-tailed) were performed to evaluate the supine-prone differences of the distance. We performed a study on 10 CTC studies from 10 patients with collapsed colonic segments by manually tracing the marginal blood vessels near the collapsed regions to resolve the ambiguity of the colon path. RESULTS: The average distances (± SD) from the marginal blood vessels to the tenia mesocolica, tenia omentalis, and tenia libera were 20.1 ± 3.1 mm (95% CI, 18.5-21.6 mm), 39.5 ± 4.8 mm (37.1-42.0 mm), and 36.9 ± 4.2 mm (34.8-39.1 mm), respectively. Pairwise comparison showed that these distances to the tenia libera and tenia omentalis were significantly different from the distance to the tenia mesocolica (p < 0.001). The average distance from the marginal blood vessels to the colon wall was 15.3 ± 2.0 mm (14.2-16.3 mm). For polyp localization, the average difference of the circumferential polyp position on the supine and prone scans was 9.6 ± 9.4 mm (5.5-13.7 mm) (p = 0.15) and expressed as a percentage of the colon circumference was 3.1% ± 2.0% (2.3-4.0%) (p = 0.83). We were able to trace the marginal blood vessels for 10 collapsed colonic segments and determine the paths of the colon in these regions. CONCLUSION: The marginal blood vessels run parallel to the colon in proximity to the tenia mesocolica and enable accurate supine-prone registration of polyps and localization of the colon path in areas of collapse. Thus, the marginal blood vessels may be used as reference landmarks complementary to the colon centerline and teniae coli.

Mesenteric vasculature-guided small bowel segmentation on 3-D CT.

Due to its importance and possible applications in visualization, tumor detection and preoperative planning, automatic small bowel segmentation is essential for computer-aided diagnosis of small bowel pathology. However, segmenting the small bowel directly on computed tomography (CT) scans is very difficult because of the low image contrast on CT scans and high tortuosity of the small bowel and its close proximity to other abdominal organs. Motivated by the intensity characteristics of abdominal CT images, the anatomic relationship between the mesenteric vasculature and the small bowel, and potential usefulness of the mesenteric vasculature for establishing the path of the small bowel, we propose a novel mesenteric vasculature map-guided method for small bowel segmentation on high-resolution CT angiography scans. The major mesenteric arteries are first segmented using a vessel tracing method based on multi-linear subspace vessel model and Bayesian inference. Second, multi-view, multi-scale vesselness enhancement filters are used to segment small vessels, and vessels directly or indirectly connecting to the superior mesenteric artery are classified as mesenteric vessels. Third, a mesenteric vasculature map is built by linking vessel bifurcation points, and the small bowel is segmented by employing the mesenteric vessel map and fuzzy connectness. The method was evaluated on 11 abdominal CT scans of patients suspected of having carcinoid tumors with manually labeled reference standard. The result, 82.5% volume overlap accuracy compared with the reference standard, shows it is feasible to segment the small bowel on CT scans using the mesenteric vasculature as a roadmap.

Serum tight-junction proteins predict hemorrhagic transformation in ischemic stroke patients.

OBJECTIVE: To evaluate the significance of circulating tight-junction (TJ) proteins as predictors of hemorrhagic transformation (HT) in ischemic stroke patients. METHODS: We examined 458 consecutive ischemic stroke patients, 7.2% of whom had clinically evident HT. None of the patients was treated with thrombolytic drugs. Serum levels of standard markers of blood-brain barrier (BBB) breakdown (S100B, neuron-specific enolase), TJ proteins (occludin [OCLN], claudin 5 [CLDN5], zonula occludens 1 [ZO1]), and molecules involved in BBB disintegration (matrix metalloproteinase 9 and vascular endothelial growth factor [VEGF]) were assessed upon admission to the emergency department. A clinical deterioration caused by HT (cdHT) was defined as an increase of ≥4 points in the NIH Stroke Scale score in combination with a visible HT on a CT scan performed immediately after the onset of new neurologic symptoms. RESULTS: Patients with cdHT had higher concentrations of OCLN, S100B, and the CLDN5/ZO1 ratio, and a lower level of VEGF than those without cdHT. CLDN5 levels also correlated with cdHT occurrence when estimated within 3 hours of stroke onset. We also demonstrated correlations between the levels of circulating TJ molecules and the level of S100B, which is a previously established marker of BBB disruption. CONCLUSIONS: Analyzing serum levels of TJ proteins, like CLDN5, OCLN, and CLDN5/ZO1 ratio, as well as S100B and VEGF, is an effective way to screen for clinical deterioration caused by HT in ischemic stroke patients, both within and after the IV thrombolysis time window.

Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique.

PURPOSE: An automatic, accurate and fast segmentation of hemorrhage in brain Computed Tomography (CT) images is necessary for quantification and treatment planning when assessing a large number of data sets. Though manual segmentation is accurate, it is time consuming and tedious. Semi-automatic methods need user interactions and might introduce variability in results. Our study proposes a modified distance regularized level set evolution (MDRLSE) algorithm for hemorrhage segmentation. METHODS: Study data set (from the ongoing CLEAR-IVH phase III clinical trial) is comprised of 200 sequential CT scans of 40 patients collected at 10 different hospitals using different machines/vendors. Data set contained both constant and variable slice thickness scans. Our study included pre-processing (filtering and skull removal), segmentation (MDRLSE which is a two-stage method with shrinking and expansion) with modified parameters for faster convergence and higher accuracy and post-processing (reduction in false positives and false negatives). RESULTS: Results are validated against the gold standard marked manually by a trained CT reader and neurologist. Data sets are grouped as small, medium and large based on the volume of blood. Statistical analysis is performed for both training and test data sets in each group. The median Dice statistical indices (DSI) for the 3 groups are 0.8971, 0.8580 and 0.9173 respectively. Pre- and post-processing enhanced the DSI by 8 and 4% respectively. CONCLUSIONS: The MDRLSE improved the accuracy and speed for segmentation and calculation of the hemorrhage volume compared to the original DRLSE method. The method generates quantitative information, which is useful for specific decision making and reduces the time needed for the clinicians to localize and segment the hemorrhagic regions.

Use of normative distribution of gray to white matter ratio in orthogonal planes in human brain studies and computer-assisted neuroradiology.

PURPOSE: Although the brain has been extensively studied, relationships of gray (GM) to white (WM) matters in individual sections as typically acquired and read radiologically have not yet been examined. A novel GM/WM-based approach with a compact whole brain representation is introduced and applied to study the brain and perform neuroimage processing. METHODS: The gray to white matter ratio GWR defined as GM/(GM+WM) was calculated for 3T T1-weighted axial, coronal, and sagittal sections of 75 normal subjects. The mean (normative) GWR curves were employed to describe the normal brain and quantify aging and to illustrate pathology detection and characterization. RESULTS: The mean GWR curves characterize the normal brain by only six, neuroanatomy-related numbers. The regions with a significant GWR decline with age surround the ventricular system. The GWR decline rate in males is higher (-0.17%/year) than females (-0.14%/year); moreover, males show a significantly higher decline in middle to elder group. The GWR decline from young (≤25 years) to middle (26-40 years) age group (males/females -0.31%/-0.34%/year) is significantly higher than that from middle to elder (>40 years) group (males/females -0.13/-0.07%/year). CONCLUSION: The GWR-based analysis is useful to characterize normal brain, determine significant regions of interest, and quantify healthy aging. It has potential applications in brain compression, comparison, morphometry, normalization, and detecting and quantifying pathologies, which open new avenues in computer-assisted neuroradiology from screening to large brain databases searching.

Robust calculation of the midsagittal plane in CT scans using the Kullback-Leibler's measure.

OBJECTIVE: The identification of the interhemispheric fissure (IF) is important in clinical applications for brain landmark identification, registration, symmetry assessment, and pathology detection. The IF is usually approximated by the midsagittal plane (MSP) separating the brain into two hemispheres. We present a fast accurate, automatic, and robust algorithm for finding the MSP for CT scans acquired in emergency room (ER) with a large slice thickness, high partial volume effect, and substantial head tilt. MATERIALS AND METHODS: An earlier algorithm for MSP identification from MRI using the Kullback-Leibler's measure was extended for CT by estimating patient's head orientation using model fitting, image processing, and atlas-based techniques. The new algorithm was validated on 208 clinical scans acquired mainly in the ER with slice thickness ranging from 1.5 to 6 mm and severe head tilt. RESULTS: The algorithm worked robustly for all 208 cases. An angular discrepancy (degrees) and maximum distance (mm) between the calculated MSP and ground truth have the mean value (SD) 0.0258 degrees (0.9541 degrees) and 0.1472 (0.7373) mm, respectively. In average, the algorithm takes 10 s to process of a typical CT case. CONCLUSION: The proposed algorithm is robust to head rotation, and correctly identifies the MSP for a standard clinical CT scan with a large slice thickness. It has been applied in our several CT stroke CAD systems.

Automatic segmentation of the human brain ventricles from MR images by knowledge-based region growing and trimming.

Automatic segmentation of the human brain ventricular system from MR images is useful in studies of brain anatomy and its diseases. Existing intensity-based segmentation methods are adaptive to large shape and size variations of the ventricular system, but may leak to the non-ventricular regions due to the non-homogeneity, noise and partial volume effect in the images. Deformable model-based methods are more robust to noise and alleviate the leakage problem, but may generate wrong results when the shape or size of the ventricle to be segmented in the images has a large difference in comparison to its model. In this paper, we propose a knowledge-based region growing and trimming approach where: (1) a model of a ventricular system is used to define regions of interest (ROI) for the four ventricles (i.e., left, right, third and fourth); (2) to segment a ventricle in its ROI, a region growing procedure is first applied to obtain a connected region that contains the ventricle, and (3) a region trimming procedure is then employed to trim the non-ventricle regions. A hysteretic thresholding is developed for the region growing procedure to cope with the partial volume effect and minimize non-ventricular regions. The domain knowledge on the shape and intensity features of the ventricular system is used for the region trimming procedure. Due to the joint use of the model-based and intensity-based approaches, our method is robust to noise and large shape and size variations. Experiments on 18 simulated and 58 clinical MR images show that the proposed approach is able to segment the ventricular system accurately with the dice similarity coefficient ranging from 91% to 99%.

A model-based, semi-global segmentation approach for automatic 3-D point landmark localization in neuroimages.

The existing differential approaches for localization of 3-D anatomic point landmarks in 3-D images are sensitive to noise and usually extract numerous spurious landmarks. The parametric model-based approaches are not practically usable for localization of landmarks that can not be modeled by simple parametric forms. Some dedicated methods using anatomic knowledge to identify particular landmarks are not general enough to cope with other landmarks. In this paper, we propose a model-based, semi-global segmentation approach to automatically localize 3-D point landmarks in neuroimages. To localize a landmark, the semi-global segmentation (meaning the segmentation of a part of the studied structure in a certain neighborhood of the landmark) is first achieved by an active surface model, and then the landmark is localized by analyzing the segmented part only. The joint use of global model-to-image registration, semi-global structure registration, active surface-based segmentation, and point-anchored surface registration makes our method robust to noise and shape variation. To evaluate the method, we apply it to the localization of ventricular landmarks including curvature extrema, centerline intersections, and terminal points. Experiments with 48 clinical and 18 simulated magnetic resonance (MR) volumetric images show that the proposed approach is able to localize these landmarks with an average accuracy of 1 mm (i.e., at the level of image resolution). We also illustrate the use of the proposed approach to cortical landmark identification and discuss its potential applications ranging from computer-aided radiology and surgery to atlas registration with scans.

Extraction of the midsagittal plane from morphological neuroimages using the Kullback-Leibler's measure.

A theoretically simple and computationally efficient method to extract the midsagittal plane (MSP) from volumetric neuroimages is presented. The method works in two stages (coarse and fine) and is based on calculation of the Kullback and Leibler's (KL) measure, which characterizes the difference between two distributions. Slices along the sagittal direction are analyzed with respect to a reference slice to determine the coarse MSP. To calculate the final MSP, a local search algorithm is applied. The proposed method does not need any preprocessing, like reformatting, skull stripping, etc. The algorithm was validated quantitatively on 75 MRI datasets of different pulse sequences (T1WI, T2WI, FLAIR and SPGR) and MRA. The angular and distance errors between the calculated MSP and the ground truth lines marked by the expert were calculated. The average distance and angular deviation were 1.25 pixels and 0.63 degrees , respectively. In addition, the algorithm was tested qualitatively on PD, FLAIR, MRA, and CT datasets. To analyze the robustness of the method against rotation, inhomogeneity and noise, the phantom data were used.

A virtual reality simulator for remote interventional radiology: concept and prototype design.

We present a virtual reality simulator to realize interventional radiology (IR) procedures remotely. The simulator contains two subsystems: one at the local site and the other at the remote site. At the local site, the interventional radiologist interacts with a three-dimensional (3-D) vascular model extracted from the patient's data and inserts IR devices through the Motion Tracking Box (MTB), which converts physical motion (translation and rotation) of IR devices into digital signal. This signal is transferred to the Actuator Box (AB) at the remote site that drives the IR devices in the patient. The status of the IR devices is subsequently fed back to the local site and displayed on the vascular model. To prove the concept, the prototype developed employs a physical angiography phantom (mimicking the patient) and its corresponding 3-D digital model. A magnetic tracking system provides information about positioning of the IR devices in the phantom. The initial results are encouraging. The AB controlled remotely drives IR devices with resolution of 0.00288 mm/step in translation and 0.079 deg/step in rotation.

IVME: a tool for editing, manipulation, quantification, and labeling of cerebrovascular models.

Three-dimensional (3D) vascular models are important in medical education, interventional radiology and vascular surgery. Because of a limited quality of angiographic images and inaccuracies introduced during their processing, interactive enhancement of the resulting models is required. We introduce here a novel tool, the interactive vascular modeling environment (IVME) for editing, manipulation, quantification, and labeling of cerebrovascular models. We describe the IVME architecture and design along with the functionality supporting anatomy terminology linking, 2D and 3D labeling, editing, 2D-3D cross-referencing, measurements, and quantification. The IVME is a useful platform in education, research, and clinics to explore and manipulate the angiography data in 2D and 3D.

Toward atlas-assisted automatic interpretation of MRI morphological brain scans in the presence of tumor.

RATIONALE AND OBJECTIVES: Determination of distorted brain anatomy surrounding a tumor causing a mass effect is much more difficult than interpretation of normal brain scans, particularly because this distortion is not easily predictable a tumor may be located in any place and vary substantially in size, shape, and radiological appearance. The objective of our work is to provide a qualitative means for rapid estimation of brain anatomy distorted by tumor. MATERIALS AND METHODS: Toward achieving this objective, we use an electronic and deformable brain atlas of gross anatomy along with a fast atlas-to-data warping technique. The deformed atlas determines the distorted anatomy surrounding a tumor and can be used for structure labeling (naming). The warping algorithm uses the Talairach transformation followed by three-dimensional nonlinear tumor deformation based on a geometric assumption that the tumor, delineated on radiological images, compresses its surrounding tissues radially. RESULTS: The approach is implemented and a dedicated application is developed. It processes the data automatically in five steps: (1) load data, (2) set the Talairach landmarks and perform the Talairach transformation, (3) segment the tumor, (4) warp the scan nonlinearly in three dimensions, and (5) explore the scan. The approach is very fast, and a magnetic resonance imaging scan is processed in 10-15 seconds on a standard personal computer. It is fully automatic and gives the user control over the entire process. CONCLUSION: Despite its limitations in modeling and validation, this practical solution provides a rapid and potentially useful qualitative assessment of anatomy deformed by a mass effect tumor.

Geometric modeling of the human normal cerebral arterial system.

We propose an anatomy-based approach for an efficient construction of a three-dimensional human normal cerebral arterial model from segmented and skeletonized angiographic data. The centerline-based model is used for an accurate angiographic data representation. A vascular tree is represented by tubular segments and bifurcations whose construction takes into account vascular anatomy. A bifurcation is defined quantitatively and the algorithm calculating it is given. The centerline is smoothed by means of a sliding average filter. As the vessel radius is sensitive to quality of data as well as accuracy of segmentation and skeletonization, radius outlier removal and radius regression algorithms are formulated and applied. In this way, the approach compensates for some inaccuracies introduced during segmentation and skeletonization. To create the frame of vasculature, we use two different topologies: tubular and B-subdivision based. We also propose a technique to prevent vessel twisting. The analysis of the vascular model is done on a variety of data containing 258 vascular segments and 131 bifurcations. Our approach gives acceptable results from anatomical, topological and geometrical standpoints as well as provides fast visualization and manipulation of the model. The approach is applicable for building a reference cerebrovascular atlas, developing applications for simulation and planning of interventional radiology procedures and vascular surgery, and in education.

A knowledge-driven algorithm for a rapid and automatic extraction of the human cerebral ventricular system from MR neuroimages.

A knowledge-driven algorithm for a rapid, robust, accurate, and automatic extraction of the human cerebral ventricular system from MR neuroimages is proposed. Its novelty is in combination of neuroanatomy, radiological properties, and variability of the ventricular system with image processing techniques. The ventricular system is divided into six 3D regions: bodies and inferior horns of the lateral ventricles, third ventricle, and fourth ventricle. Within each ventricular region, a 2D region of interest (ROI) is defined based on anatomy and variability. Each ventricular region is further subdivided into subregions, and conditions detecting and preventing leakage into the extra-ventricular space are specified for each subregion. The algorithm extracts the ventricular system by (1) processing each ROI (to calculate its local statistics, determine local intensity ranges of cerebrospinal fluid and gray and white matters, set a seed point within the ROI, grow region directionally in 3D, check anti-leakage conditions, and correct growing if leakage occurred) and (2) connecting all unconnected regions grown by relaxing growing conditions. The algorithm was validated qualitatively on 68 and quantitatively on 38 MRI normal and pathological cases (30 clinical, 20 MGH Brain Repository, and 18 MNI BrainWeb data sets). It runs successfully for normal and pathological cases provided that the slice thickness is less than 3.0 mm in axial and less than 2.0 mm in coronal directions, and the data do not have a high inter-slice intensity variability. The algorithm also works satisfactorily in the presence of up to 9% noise and up to 40% RF inhomogeneity for the BrainWeb data. The running time is less than 5 s on a Pentium 4, 2.0 GHz PC. The best overlap metric between the results of a radiology expert and the algorithm is 0.9879 and the worst 0.9527; the mean and standard deviation of the overlap metric are 0.9723 and 0.01087, respectively.

An algorithm for rapid calculation of a probabilistic functional atlas of subcortical structures from electrophysiological data collected during functional neurosurgery procedures.

The paper introduces an optimal algorithm for rapid calculation of a probabilistic functional atlas (PFA) of subcortical structures from data collected during functional neurosurgery procedures. The PFA is calculated based on combined intraoperative electrophysiology, pre- and intraoperative neuroimaging, and postoperative neurological verification. The algorithm converts the coordinates of the neurologically most effective contacts into probabilistic functional maps taking into account the geometry of a stimulating electrode. The PFA calculation comprises the reconstruction of the contact coordinates from two orthogonal projections, normalizing (warping) the contacts modeled as cylinders, voxelizing the contact models, calculating the atlas, and computing probability. In addition, an analytical representation of the PFA is formulated based on Gaussian modeling. The initial PFA has been calculated from the data collected during the treatment of 274 Parkinson's disease patients, most of them operated bilaterally (487 operated hemispheres). It contains the most popular stereotactic targets, the subthalamic nucleus, globus pallidus internus, and ventral intermedius nucleus. The key application of the algorithm is targeting in stereotactic and functional neurosurgery, and it also can be employed in human and animal brain research.

Knowledge-driven automated extraction of the human cerebral ventricular system from MR images.

This work presents an efficient and automated method to extract the human cerebral ventricular system from MRI driven by anatomic knowledge. The ventricular system is divided into six three-dimensional regions; six ROIs are defined based on the anatomy and literature studies regarding variability of the cerebral ventricular system. The distribution histogram of radiological properties is calculated in each ROI, and the intensity thresholds for extracting each region are automatically determined. Intensity inhomogeneities are accounted for by adjusting intensity threshold to match local situation. The extracting method is based on region-growing and anatomical knowledge, and is designed to include all ventricular parts, even if they appear unconnected on the image. The ventricle extraction method was implemented on the Window platform using C++, and was validated qualitatively on 30 MRI studies with variable parameters.