Guanyu Yang

Curve-Like Structure Extraction Using Minimal Path Propagation With Backtracking

Minimal path techniques can efficiently extract geometrically curve-like structures by finding the path with minimal accumulated cost between two given endpoints. Though having found wide practical applications (e.g., line identification, crack detection, and vascular centerline extraction), minimal path techniques suffer from some notable problems. The first one is that they require setting two endpoints for each line to be extracted (endpoint problem). The second one is that the connection might fail when the geodesic distance between the two points is much shorter than the desirable minimal path (shortcut problem). In addition, when connecting two distant points, the minimal path connection might become inefficient as the accumulated cost increases over the propagation and results in leakage into some non-feature regions near the starting point (accumulation problem). To address these problems, this paper proposes an approach termed minimal path propagation with backtracking. We found that the information in the process of backtracking from reached points can be well utilized to overcome the above problems and improve the extraction performance. The whole algorithm is robust to parameter setting and allows a coarse setting of the starting point. Extensive experiments with both simulated and realistic data are performed to validate the performance of the proposed method.

A Multiscale Tracking Algorithm for the Coronary Extraction in MSCT Angiography

This paper deals with the extraction of the coronary network on dynamic volume sequences, acquired in multi-slice spiral computed tomography (MSCT). The proposed approach makes use of a tracking algorithm of the vascular structure, combining a 3D geometric moment operator with a multiscale Hessian filter to estimate the vessel central axis location, its local diameter and orientation. The method performs at the same time, a bifurcation detection to reconstitute the structure of the coronary network. The mean computation time to extract a coronary network is about 3 minutes using a P4-2.4G PC. Preliminary encouraging results are presented on one volume of a sequence

Sliding Conjugate Symmetric Sequency-Ordered Complex Hadamard Transform: Fast Algorithm and Applications

This paper presents a fast algorithm for the computation of forward and backward sliding conjugate symmetric se-quency-ordered complex Hadamard transform (CSSCHT). The forward CSSCHT algorithm calculates the values of window i+N/4 from those of window i and one length-N/4 CSSCHT, one length-N/4 Walsh Hadamard transform (WHT) and one length-N/4 modified WHT. The backward CSSCHT algorithm can be obtained by transposing the signal flow graph of that of the forward one. The proposed algorithm requires O(N) arithmetic operations, which is more efficient than the block-based algorithm and those based on the sliding FFT and the sliding DFT. The applications of the sliding CSSCHT in spectrum estimation and transform domain adaptive filtering (TDAF) are also provided with supporting simulation results.

Automatic kidney segmentation in CT images based on multi-atlas image registration.

Kidney segmentation is an important step for computer-aided diagnosis or treatment in urology. In this paper, we present an automatic method based on multi-atlas image registration for kidney segmentation. The method mainly relies on a two-step framework to obtain coarse-to-fine segmentation results. In the first step, down-sampled patient image is registered with a set of low-resolution atlas images. A coarse kidney segmentation result is generated to locate the left and right kidneys. In the second step, the left and right kidneys are cropped from original images and aligned with another set of high-resolution atlas images to obtain the final results respectively. Segmentation results from 14 CT angiographic (CTA) images show that our proposed method can segment the kidneys with a high accuracy. The average Dice similarity coefficient and surface-to-surface distance between segmentation results and reference standard are 0.952 and 0.913mm. Furthermore, the kidney segmentation in CT urography (CTU) and CTA images of 12 patients were performed to show the feasibility of our method in CTU images.

An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework

PURPOSE The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD) events. In clinical practice, CAC is manually identified and automatically quantified in cardiac CT using commercially available software. This is a tedious and time-consuming process in large-scale studies. Therefore, a number of automatic methods that require no interaction and semiautomatic methods that require very limited interaction for the identification of CAC in cardiac CT have been proposed. Thus far, a comparison of their performance has been lacking. The objective of this study was to perform an independent evaluation of (semi)automatic methods for CAC scoring in cardiac CT using a publicly available standardized framework. METHODS Cardiac CT exams of 72 patients distributed over four CVD risk categories were provided for (semi)automatic CAC scoring. Each exam consisted of a noncontrast-enhanced calcium scoring CT (CSCT) and a corresponding coronary CT angiography (CCTA) scan. The exams were acquired in four different hospitals using state-of-the-art equipment from four major CT scanner vendors. The data were divided into 32 training exams and 40 test exams. A reference standard for CAC in CSCT was defined by consensus of two experts following a clinical protocol. The framework organizers evaluated the performance of (semi)automatic methods on test CSCT scans, per lesion, artery, and patient. RESULTS Five (semi)automatic methods were evaluated. Four methods used both CSCT and CCTA to identify CAC, and one method used only CSCT. The evaluated methods correctly detected between 52% and 94% of CAC lesions with positive predictive values between 65% and 96%. Lesions in distal coronary arteries were most commonly missed and aortic calcifications close to the coronary ostia were the most common false positive errors. The majority (between 88% and 98%) of correctly identified CAC lesions were assigned to the correct artery. Linearly weighted Cohens kappa for patient CVD risk categorization by the evaluated methods ranged from 0.80 to 1.00. CONCLUSIONS A publicly available standardized framework for the evaluation of (semi)automatic methods for CAC identification in cardiac CT is described. An evaluation of five (semi)automatic methods within this framework shows that automatic per patient CVD risk categorization is feasible. CAC lesions at ambiguous locations such as the coronary ostia remain challenging, but their detection had limited impact on CVD risk determination.

Motion Compensated Tomography Reconstruction of Coronary Arteries in Rotational Angiography

This paper deals with the 3-D reconstruction of the coronary tree from a rotational X-ray projection sequence. It describes the following three stages: the reconstruction of the 3-D coronary tree at different phases of the cardiac cycle, the motion estimation, and the motion-compensated tomographic reconstruction of the 3-D coronary tree at one given phase using all the available projections. Our method is tested on a series of simulated images computed from the projection of a segmented dynamic volume sequence acquired in multislice computed tomography imaging. Performances are comparable to those obtained by reconstruction of a statical coronary tree using an algebraic reconstruction technique algorithm.

Dual-source CT coronary angiography involving injection protocol with iodine load tailored to patient body weight and body mass index: estimation of optimal contrast material dose.

Background Body mass index (BMI) has a positive linear influence on arterial attenuation at coronary CT angiography involving injection protocol with dose linearly tailored to body weight (BW). Excessive contrast material may inadvertently be given in heavier patients when the dose is determined by BW only. Purpose To investigate the effect of injection protocol with dose of contrast material (CM) tailored to BW and BMI on coronary arterial attenuation, contrast-to-noise ratio, and image noise at dual-source CT coronary angiography (DSCT-CA). Material and Methods A total of 233 consecutive patients (mean age, 60.2 years) undergoing DSCT-CA were included. Image acquisition protocol was standardized (120 kV, 380 mAs, and retrospective electrocardiograph-triggered DSCT-CA). CM dosage calculation was randomly categorized into groups: a BW group and a BW-BMI group. CM flow rate in both groups was calculated as dosage divided by scan time plus 8 s. Correlations between BW, BMI, and attenuations of ascending aorta (AA) above coronary ostia, left main coronary artery (LM), proximal right coronary artery (RCA), left anterior descending (LAD), and left circumflex artery (LCX), contrast to noise ratio of LM (LMCNR) and RCA (RCACNR), and image noise were evaluated with simple linear regression for two groups individually. Results In BW group, attenuations of AA and coronary arteries showed positive linear correlations to BW and BMI. In contrast, no relationships were found in BW-BMI group. LMCNR and RCACNR were inversely determined by BW and BMI in both groups. Image noise increased with BW and BMI increasing in two groups. Conclusion BMI has a positive linear influence on arterial attenuation with fixed iodine per BW. The injection protocol with CM dose tailored to BW and BMI is reasonable during DSCT-CA.

CT-based renal volume measurements: correlation with renal function in patients with renal tumours

AIM To evaluate the correlations between renal cortical volume (RCV), renal parenchymal volume (RPV), and renal function in patients with renal tumours before and after laparoscopic partial nephrectomy (LPN). MATERIALS AND METHODS Thirty-five patients with a single unilateral renal tumour who had undergone contrast-enhanced computed tomography (CT) and renal nuclear scintigraphy before and after LPN were retrospectively studied. RCV and RPV were calculated as renal volume, excluding tumours or cysts, using a semi-automatic segmentation program. The correlations between RCV, RPV, and glomerular filtration rate (GFR) were undertaken preoperatively and postoperatively using the Pearson correlation coefficient. RESULTS Preoperatively, the correlations between RCV and GFR, and RPV and GFR for the operated kidneys was r=0.502 (p=0.002) and 0.527 (p=0.001), respectively, whereas the correlations for the contralateral side were r=0.384 (p=0.023) and r=0.412 (p=0.014). The mean RCV and RPV of the operated kidneys decreased by 27.4% and 24.8%. The mean split GFR of the operated kidneys decreased by 36.4%. Postoperatively, residual RCV (r=0.619, p<0.001) and RPV (r=0.593, p<0.001) correlated moderately with the GFR of the operated kidneys. CONCLUSIONS Renal volume, both RCV and RPV, had a moderate relationship with renal function before and after operation. CT-based renal volume measurements could serve as a simple and effective method for estimation of postoperative renal function.

Sparse reconstruction from a limited projection number of the coronary artery tree in X-ray rotational imaging

This paper deals with the 3D reconstruction of sparse data in X-ray rotational imaging. Due to the cardiac motion, the number of available projections for this reconstruction is equal to four, which leads to a strongly under-sampled reconstruction problem. We address thus this illness problem through a regularized iterative method. The whole algorithm is divided into two steps. Firstly, a minimal path segmentation step extracts artery tree boundaries. Secondly, a MAP reconstruction comparing L0-norm and L1-norm priors is applied on this extracted coronary tree. The reconstruction optimization process relies on a separable paraboloidal (SPS) algorithm. Some preliminary results are provided on simulated rotational angiograms.

Automatic coronary calcium scoring using noncontrast and contrast CT images

PURPOSE Calcium scoring is widely used to assess the risk of coronary heart disease (CHD). Accurate coronary artery calcification detection in noncontrast CT image is a prerequisite step for coronary calcium scoring. Currently, calcified lesions in the coronary arteries are manually identified by radiologists in clinical practice. Thus, in this paper, a fully automatic calcium scoring method was developed to alleviate the work load of the radiologists or cardiologists. METHODS The challenge of automatic coronary calcification detection is to discriminate the calcification in the coronary arteries from the calcification in the other tissues. Since the anatomy of coronary arteries is difficult to be observed in the noncontrast CT images, the contrast CT image of the same patient is used to extract the regions of the aorta, heart, and coronary arteries. Then, a patient-specific region-of-interest (ROI) is generated in the noncontrast CT image according to the segmentation results in the contrast CT image. This patient-specific ROI focuses on the regions in the neighborhood of coronary arteries for calcification detection, which can eliminate the calcifications in the surrounding tissues. A support vector machine classifier is applied finally to refine the results by removing possible image noise. Furthermore, the calcified lesions in the noncontrast images belonging to the different main coronary arteries are identified automatically using the labeling results of the extracted coronary arteries. RESULTS Forty datasets from four different CT machine vendors were used to evaluate their algorithm, which were provided by the MICCAI 2014 Coronary Calcium Scoring (orCaScore) Challenge. The sensitivity and positive predictive value for the volume of detected calcifications are 0.989 and 0.948. Only one patient out of 40 patients had been assigned to the wrong risk category defined according to Agatston scores (0, 1-100, 101-300, >300) by comparing with the ground truth. CONCLUSIONS The calcified lesions in the noncontrast CT images can be detected automatically by using the segmentation results of the aorta, heart, and coronary arteries obtained in the contrast CT images with a very high accuracy.