In this paper, we propose a new registration method for prone and supine computed tomographic colonography scans using graph matching. We formulate 3-D colon registration as a graph matching problem and propose a new graph matching algorithm based on mean field theory. In the proposed algorithm, we solve the matching problem in an iterative way. In each step, we use mean field theory to find the matched pair of nodes with highest probability. During iterative optimization, one-to-one matching constraints are added to the system in a step-by-step approach. Prominent matching pairs found in previous iterations are used to guide subsequent mean field calculations. The proposed method was found to have the best performance with smallest standard deviation compared with two other baseline algorithms called the normalized distance along the colon centerline (NDACC) ( p = 0.17) with manual colon centerline correction and spectral matching ( p <; 1e-5). A major advantage of the proposed method is that it is fully automatic and does not require defining a colon centerline for registration. For the latter NDACC method, user interaction is almost always needed for identifying the colon centerlines.

PURPOSE:Surface curvatures are important geometric features for the computer-aided analysis and detection of polyps in CT colonography (CTC). However, the general kernel approach for curvature computation can yield erroneous results for small polyps and for polyps that lie on haustral folds. Those erroneous curvatures will reduce the performance of polyp detection. This paper presents an analysis of interpolation's effect on curvature estimation for thin structures and its application on computer-aided detection of small polyps in CTC.METHODS:The authors demonstrated that a simple technique, image interpolation, can improve the accuracy of curvature estimation for thin structures and thus significantly improve the sensitivity of small polyp detection in CTC.RESULTS:Our experiments showed that the merits of interpolating included more accurate curvature values for simulated data, and isolation of polyps near folds for clinical data. After testing on a large clinical data set, it was observed that sensitivities with linear, quadratic B-spline and cubic B-spline interpolations significantly improved the sensitivity for small polyp detection.CONCLUSIONS:The image interpolation can improve the accuracy of curvature estimation for thin structures and thus improve the computer-aided detection of small polyps in CTC.

In this paper, we propose a new registration method for supine and prone computed tomographic colonography scans based on graph matching. We first formulated 3D colon registration as a graph matching problem and utilized a graph matching algorithm based on mean field theory. During the iterative optimization process, one-to-one matching constraints were added to the system step-by-step. Prominent matching pairs found in previous iterations are used to guide subsequent mean field calculations. The advantage of the proposed method is that it does not require a colon centerline for registration. We tested the algorithm on a CTC dataset of 19 patients with 19 polyps. The average registration error of the proposed method was 4.0cm (std. 2.1cm). The 95% confidence intervals were [3.0cm, 5.0mm]. There was no significant difference between the proposed method and our previous method based on the normalized distance along the colon centerline (p=0.1).

Purpose: To assess the effect of using computer-aided detection (CAD) in second-read mode on readers' accuracy in interpreting computed tomographic (CT) colonographic images.Materials and Methods: The contributing institutions performed the examinations under approval of their local institutional review board, with waiver of informed consent, for this HIPAA-compliant study. A cohort of 100 colonoscopy-proved cases was used: In 52 patients with findings positive for polyps, 74 polyps of 6 mm or larger were observed in 65 colonic segments; in 48 patients with findings negative for polyps, no polyps were found. Nineteen blinded readers interpreted each case at two different times, with and without the assistance of a commercial CAD system. The effect of CAD was assessed in segment-level and patient-level receiver operating characteristic (ROC) curve analyses.Results: Thirteen (68%) of 19 readers demonstrated higher accuracy with CAD, as measured with the segment-level area under the ROC curve (AUC). The readers' average segment-level AUC with CAD (0.758) was significantly greater (P = .015) than the average AUC in the unassisted read (0.737). Readers' per-segment, per-patient, and per-polyp sensitivity for all polyps of 6 mm or larger was higher (P < .011,.007,.005, respectively) for readings with CAD compared with unassisted readings (0.517 versus 0.465, 0.521 versus 0.466, and 0.477 versus 0.422, respectively). Sensitivity for patients with at least one large polyp of 10 mm or larger was also higher (P < .047) with CAD than without (0.777 versus 0.743). Average reader sensitivity also improved with CAD by more than 0.08 for small adenomas. Use of CAD reduced specificity of readers by 0.025 (P = .05).Conclusion: Use of CAD resulted in a significant improvement in overall reader performance. CAD improves reader sensitivity when measured per segment, per patient, and per polyp for small polyps and adenomas and also reduces specificity by a small amount. (C) RSNA, 2010

In this paper, we propose a new graph matching algorithm based on mean field theory. We first convert the original graph matching problem which is a quadratic integer programming problem to a spin model with quadratic interaction by dropping the matching constraints. Then the matching constraints are added to the system iteratively after each round of mean field calculation. Prominent matching pairs found in previous iterations will guide the mean field calculation in the next round. Experiments on the CMU house dataset and a CTC dataset show promising matching results.

Purpose: Pulmonary arterial hypertension (PAH) is a progressive vascular disease that results in high mortality and morbidity in sickle cell disease (SCD) patients. PAH diagnosis is invasive via right heart catheterization, but manual measurements of the main pulmonary artery (PA) diameters from computed tomography (CT) have shown promise as noninvasive surrogate marker of PAH. The authors propose a semiautomated computer-assisted diagnostic (CAD) tool to quantify the main PA size from pulmonary CT angiography (CTA).Methods: A follow-up retrospective study investigated the potential of CT and image analysis to quantify the presence of PAH secondary to SCD based on PA size. The authors segmented the main pulmonary arteries using a combination of fast marching level sets and geodesic active contours from smoothed pulmonary CTA images of 20 SCD patients with proven PAH by right heart catheterization and 20 matched negative controls. From the PA segmentation, a Euclidean distance map was calculated and an algorithm based on fast marching methods was used to compute subvoxel precise centerlines of the PA trunk (PT) and main left/right PA (PM). Maximum distentions of PT and PM were automatically quantified using the centerline and validated with manual measurements from two observers.Results: The pulmonary trunk and main were significantly larger (p < 0.001) in PAH/SCD patients (33.73 +/- 3.92 mm for PT and 25.17 +/- 2.90 for PM) than controls (27.03 +/- 2.94 mm for PT and 20.62 +/- 3.06 for PM). The discrepancy was qualitatively improved when vessels' diameters were normalized by body surface area (p < 0.001). The validation of the method showed high correlation (mean R=0.9 for PT and R=0.91 for PM) and Bland-Altman agreement (0.4 +/- 3.6 mm for PT and 0.5 +/- 2.9 mm for PM) between CAD and manual measurements. Quantification errors were comparable to intraobserver and interobserver variability. CAD measurements between two different users were robust and reproducible with correlations of R=0.99 for both PT and PM and Bland-Altman agreements of -0.13 +/- 1.33 mm for PT and -0.08 +/- 0.84 mm for PM.Conclusion: Results suggest that the semiautomated quantification of pulmonary artery has sufficient accuracy and reproducibility for clinical use. CT with image processing and extraction of PA biomarkers show great potential as a surrogate indicator for diagnosis or quantification of PAH, and could be an important tool for drug discovery and noninvasive clinical surveillance.

A multiobjective genetic algorithm is designed to optimize a computer-aided detection (CAD) system for identifying colonic polyps. Colonic polyps appear as elliptical protrusions on the inner surface of the colon. Curvature-based features for colonic polyp detection have proved to be successful in several CT colonography (CTC) CAD systems. Our CTC CAD program uses a sequential classifier to form initial polyp detections on the colon surface. The classifier utilizes a set of thresholds on curvature-based features to cluster suspicious colon surface regions into polyp candidates. The thresholds were previously chosen experimentally by using feature histograms. The chosen thresholds were effective for detecting polyps sized 10 mm or larger in diameter. However, many medium-sized polyps, 6-9 mm in diameter, were missed in the initial detection procedure. In this paper, the task of finding optimal thresholds as a multiobjective optimization problem was formulated, and a genetic algorithm to solve it was utilized by evolving the Pareto front of the Pareto optimal set. The new CTC CAD system was tested on 792 patients. The sensitivities of the optimized system improved significantly, from 61.68% to 74.71% with an increase of 13.03% (95% CI [6.57%, 19.5%], p = 7.78 x 10(-5)) for the size category of 6-9 mm polyps, from 65.02% to 77.4% with an increase of 12.38% (95% CI [6.23%, 18.53%], p = 7.95 x 10(-5)) for polyps 6 mm or larger, and from 82.2% to 90.58% with an increase of 8.38% (95% CI [0.75%, 16%], p = 0.03) for polyps 8 mm or larger at comparable false positive rates. The sensitivities of the optimized system are nearly equivalent to those of expert radiologists.

Pulmonary arterial hypertension is a known complication associated with sickle-cell disease; roughly 75% of sickle cell disease-afflicted patients have pulmonary arterial hypertension at the time of death. This prospective study investigates the potential of image analysis to act as a surrogate for presence and extent of disease, and whether the size change of the pulmonary arteries of sickle cell patients could be linked to sickle-cell associated pulmonary hypertension. Pulmonary CT-Angiography scans from sickle-cell patients were obtained and retrospectively analyzed. Randomly selected pulmonary CT-Angiography studies from patients without sickle-cell anemia were used as negative controls. First, images were smoothed using anisotropic diffusion. Then, a combination of fast marching and geodesic active contours level sets were employed to segment the pulmonary artery. An algorithm based on fast marching methods was used to compute the centerline of the segmented arteries. From the centerline, the diameters at the pulmonary trunk and first branch of the pulmonary arteries were measured automatically. Arterial diameters were normalized to the width of the thoracic cavity, patient weight and body surface. Results show that the pulmonary trunk and first right and left pulmonary arterial branches at the pulmonary trunk junction are significantly larger in diameter with increased blood flow in sickle-cell anemia patients as compared to controls (p values of 0.0278 for trunk and 0.0007 for branches). CT with image processing shows great potential as a surrogate indicator of pulmonary hemodynamics or response to therapy, which could be an important tool for drug discovery and noninvasive clinical surveillance.

Computed tomographic colonography (CTC) is a feasible and minimally invasive method for the detection of colorectal polyps and cancer screening. In current practice, a patient will be scanned twice during the CTC examination - once supine and once prone. In order to assist the radiologists in evaluating colon polyp candidates in both scans, we expect the computer aided detection (CAD) system can provide not only the locations of suspicious polyps, but also the possible matched pairs of polyps in two scans. In this paper, we propose a new automated matching method based on the extracted features of polyps by using principal component analysis (PCA) and Support Vector Machines (SVMs). Our dataset comes from the 104 CT scans of 52 patients with supine and prone positions collected from three medical centers. From it we constructed two groups of matched polyp candidates according to the size of true polyps: group A contains 12 true polyp pairs (> 9 mm) and 454 false pairs; group B contains 24 true polyp pairs (6-9 mm) and 514 false pairs. By using PCA, we reduced the dimensions of original data (with 157 attributes) to 30 dimensions. We did leave-one-patient-out test on the two groups of data. ROC analysis shows that it is easier to match bigger polyps than that of smaller polyps. On group A data, when false alarm probability is 0.18, the sensitivity of SVM achieves 0.83 which shows that automated matching of polyp candidates is practicable for clinical applications.

OBJECTIVEThe purpose of this study was to investigate the variability of CT colonography (CTC) scan quality obtained within and between institutions by using previously validated automated quality assessment (QA) software that assesses colonic distention and surface area obscured by residual fluid.MATERIALS AND METHODSThe CTC scans of 120 patients were retrospectively selected, 30 from each of four institutions. The bowel preparation included oral contrast material for fecal and fluid tagging. Patients at one institution (institution 4) drank half the amount of oral contrast material compared with the patients at the other three institutions. Fifteen of the CTC scans were from the beginning of the protocol studied at each institution and 15 scans were from the same protocol acquired approximately 1 year later in the study. We used previously validated QA software to automatically measure the mean distention and residual fluid of each of five colonic segments (ascending, transverse, descending, sigmoid, and rectum). Adequate distention was defined as a colonic diameter of at least 2 cm. Residual fluid was determined by the percentage of colonic surface area covered by fluid. We compared how the quality varied across multiple institutions and over time within the same institution.RESULTSNo significant difference in the amount of colonic distention among the four institutions was found (p = 0.19). However, the distention in the prone position was significantly greater than the distention in the supine position (p < 0.001). Patients at institution 4 had about half the amount of residual colonic fluid compared with patients at the other three institutions (p < 0.01). The sigmoid and descending colons were the least distended segments, and the transverse and descending colons contained the most fluid on the prone and supine scans, respectively. More recently acquired studies had greater distention and less residual fluid, but the differences were not statistically significant (p = 0.30 and p = 0.96, respectively).CONCLUSIONAcross institutions, a significant difference can exist in bowel preparation quality for CTC. This study reaffirms the need for standardized bowel preparation and quality monitoring of CTC examinations to reduce poor CTC performance.

This retrospective study investigates the potential of image analysis to quantify for the presence and extent of pulmonary hypertension secondary to sickle cell disease (SCD). A combination of fast marching and geodesic active contours level sets were employed to segment the pulmonary artery from smoothed CT-Angiography images from 16 SCD patients and 16 matching controls. An algorithm based on fast marching methods was used to compute the centerline of the segmented arteries to measure automatically the diameters of the pulmonary trunk and first branches of the pulmonary arteries. Results show that the pulmonary trunk and arterial branches are significantly larger in diameter in SCD patients as compared to controls (p-values of 0.002 for trunk and 0.0003 for branches). For validation, the results were compared with manually measured values and did not demonstrate significant difference (mean p-values 0.71). CT with image processing shows great potential as a surrogate indicator of pulmonary hemodynamics or response to therapy, which could be an important tool for drug discovery and noninvasive clinical surveillance.

OBJECTIVE:A computer-aided detection (CAD) system with high sensitivity in the detection of adenomatous polyps in varied CT colonography (CTC) data sets increases the utility of CAD in the clinical setting. The purpose of this study was to evaluate the standalone performance of an existing CAD system with a new set of CTC data from screening patients at an institution and geographic location different from those at which the CAD system was trained.MATERIALS AND METHODS:CTC data were collected from the records of 104 patients undergoing screening for colorectal neoplasia. Most of the patients were at average risk, had CTC findings suggestive of polyps, and underwent colonoscopy. Patients underwent cathartic bowel preparation, were given an oral contrast agent, and underwent imaging in the prone and supine positions. The patients had 86 adenomas confirmed at same-day optical colonoscopy; 47 of these tumors were 10 mm in diameter or larger, and 39 measured 6-9 mm. The CTC data were analyzed with an existing CAD system for colonography that was trained with previously acquired data. In a previous non-polyp-enriched screening cohort, the standalone performance of the CAD system was 93.3% (28/30) sensitivity for adenomatous polyps 10 mm or larger, 51.1% (47/92) sensitivity for adenomas 6-9 mm, and a mean false-positive rate of 8.6 per patient. Sensitivity comparisons were made with findings in the previous study.RESULTS:The CAD system had per-polyp sensitivities of 91.5% (43/47; 95% CI, 78.7-97.2%; p = 1.0) for adenomas 10 mm or larger and 82.1% (32/39; 65.9-91.9%; p = 0.0009) for adenomas 6-9 mm. The per-patient sensitivities were 97.6% (40/41; 85.6-99.9%; p = 0.6) for patients with adenomas 10 mm or larger and 82.4% (28/34; 64.8-92.6%; p = 0.047) for patients with adenomas 6-9 mm. The mean and median false-positive rates were 9.6 +/- 9.6 and 7.0 per patient, respectively. Common reasons for CAD misses (false-negative findings) were the presence of adherent contrast medium, flat adenomas, and adenomas located on or adjacent to normal colonic folds. In a random sample, 72.5% (29/40) of false-positive findings were attributable to folds or residual feces.CONCLUSION:The CAD system evaluated has a high level of performance in the detection of adenomatous polyps with CTC data from a polyp-enriched cohort different from that used to train the system.

Computer-aided diagnosis (CAD) systems must show sufficient versatility to produce robust analysis on a large variety of data. In the case of colonography, CAD has not been designed to cope with the presence of stool, although labeling the stool with high contrast agents replaces the use of laxatives and reduces the patient discomfort. This procedure introduces additional challenges for the diagnosis, such as poorly tagged stool, stool sticking to colonic walls, and heterogeneous stool (tagged stool mixed with air or untagged stool). Our study proposes a robust algorithm for heterogeneous stool removal to be employed as a preprocessing module for CAD systems in colonic cancer detection. Colonoscopy data are automatically cleansed of residual stool to enhance the polyp appearance for improved diagnosis. The algorithm uses expectation-maximization, quadratic regression, level sets and minimum variance. Results show stool removal accuracy on polyps which are partially or fully covered by stool. The results are robust on stool lining and large pools of heterogeneous and weakly-tagged stool. The automatic detection of colon polyps using our CAD system on cathartic-free data improves considerably with the addition of the automatic stool removal module from 74% to 86% true positive (TP) rate at 6.4 false positives (FP)/case.

In this paper, we focus on the robustness and stability of our algorithm to plot the position of an endoscopic camera (during a colonoscopy procedure) on the corresponding pre-operative CT scan of the patient. The colon has few topological landmarks, in contrast to bronchoscopy images, where a number of registration algorithms have taken advantage of features such as anatomical marks or bifurcations. Our method estimates the camera motion from the optic-flow computed from the information contained in the video stream. Optic-flow computation is notoriously susceptible to errors in estimating the motion field. Our method relies on the following features to counter this, (1) we use a small but reliable set of feature points (sparse optic-flow field) to determine the spatio-temporal scale at which to perform optic-flow computation in each frame of the sequence, (2) the chosen scales are used to compute a more accurate dense optic flow field, which is used to compute qualitative parameters relating to the main motion direction, and (3) the sparse optic-flow field and the main motion parameters are then combined to estimate the camera parameters. A mathematical analysis of our algorithm is presented to illustrate the stability of our method, as well as comparison to existing motion estimation algorithms. We present preliminary results of using this algorithm on both a virtual colonoscopy image sequence, as well as a colon phantom image sequence.

The detection of polyps in virtual colonoscopy is an active area of research. One of the critical elements in detecting cancerous polyps using virtual colonoscopy, especially in conjunction with computer-aided detection, is the accurate segmentation of the colon wall. The large CT attenuation difference between the lumen and inner, mucosal layer of the colon wall makes the segmentation of the lumen easily performed by traditional threshold segmentation techniques. However, determining the location of the colon outer wall is often difficult due to the low contrast difference between the colon wall's outer serosal layer and the fat surrounding the colon. We have developed an automatic, level set based method to determine from a CT colonography scan the location of the colon inner boundary and the colon outer wall boundary. From the location of the inner and outer colon wall boundaries, the wall thickness throughout the colon can be computed. Color mapping of the wall thickness on the colon surface allows for easy visual determination of potential regions of interest. Since the colon wall tends to be thicker at polyp locations, potential polyps also can be detected automatically at sites of increased colon wall thickness. This method was validated on several CT colonography scans containing optical colonoscopy-proven polyps. The method accurately determined thicker colonic wall regions in areas where polyps are present in the ground truth datasets and detected the polyps at a false positive rate between 44.4% and 82.8% lower than a state-of-the-art curvature-based method for initial polyp detection.

The accurate calculation of the skeleton of an object is a problem not satisfactorily solved by existing approaches. Most algorithms require a significant amount of user interaction and use a voxel grid to compute discrete and often coarse approximations of this representation of the data. We present a novel, automatic algorithm for computing subvoxel precise skeletons of volumetric data based on subvoxel precise distance fields. Most voxel based centerline and skeleton algorithms start with a binary mask and end with a list of voxels that define the centerline or skeleton. Even though subsequent smoothing may be applied, the results are inherently discrete. Our skeletonization algorithm uses as input a subvoxel precise distance field and employs a number of fast marching method propagations to extract the skeleton at subvoxel precision. We present the skeletons of various three-dimensional (3D) data sets and digital phantom models as validations of our algorithm.