Improved quantification and normal limits for myocardial perfusion stress-rest change.

UNLABELLED: We aimed to improve the quantification of myocardial perfusion stress-rest changes in myocardial perfusion SPECT (MPS) studies for the optimal automatic detection of ischemia and coronary artery disease (CAD). METHODS: Rest-stress (99m)Tc MPS studies (997 cases; 651 consecutive cases with correlating angiography and 346 cases with less than 5% likelihood (low likelihood [LLK]) of CAD) were analyzed. Normal limits for stress-rest changes were derived from additional LLK patients (40 women, 40 men). We computed the global stress-rest change (C-SR) by integrating direct stress-rest changes for each polar map pixel. Additionally, stress-rest change and total perfusion deficit (TPD) at stress were combined in 1 variable (C-TPD) for the optimal detection of CAD. RESULTS: The area under the receiver-operating-characteristic curve (AUC) for C-SR (0.92) was larger than that for stress TPD-rest TPD (0.88) for the identification of stenosis of 70% or more (P < 0.0001). AUC (0.94) and sensitivity (90%) for C-TPD were higher than those for stress TPD (0.91 and 83%, respectively) (P < 0.0001), whereas specificity remained the same (81%). CONCLUSION: C-SR and C-TPD provide higher diagnostic performance than difference between stress and rest TPD or stress hypoperfusion analysis.

Quantification of 3D regional myocardial wall thickening from gated magnetic resonance images.

PURPOSE: To develop 3D quantitative measures of regional myocardial wall motion and thickening using cardiac magnetic resonance imaging (MRI) and to validate them by comparison to standard visual scoring assessment. MATERIALS AND METHODS: In all, 53 consecutive subjects with short-axis slices and mid-ventricular 2-chamber/4-chamber views were analyzed. After correction for breath-hold-related misregistration, 3D myocardial boundaries were fitted to images and edited by an imaging cardiologist. Myocardial thickness was quantified at end-diastole and end-systole by computing the 3D distances using Laplace's equation. 3D thickening was represented using the standard 17-segment polar coordinates. 3D thickening was compared with 3D wall motion and with expert visual scores (6-point visual scoring of wall motion and wall thickening; 0 = normal; 5 = greatest abnormality) assigned by imaging cardiologists. RESULTS: Correlation between ejection fraction and thickening measurements was (r = 0.84; P < 0.001) compared to correlation between ejection fraction and motion measurements (r = 0.86; P < 0.001). Good negative correlation between summed visual scores and global wall thickening and motion measurements were also obtained (r(thick) = -0.79; r(motion) = -0.74). Additionally, overall good correlation between individual segmental visual scores with thickening/wall motion (r(thick) = -0.69; r(motion) = -0.65) was observed (P < 0.0001). CONCLUSION: 3D quantitative regional thickening and wall motion measures obtained from MRI correlate strongly with expert clinical scoring.

Multi-level classification of emphysema in HRCT lung images using delegated classifiers.

Emphysema is a common chronic respiratory disorder characterized by the destruction of lung tissue. It is a progressive disease where the early stages are characterized by diffuse appearance of small air spaces and later stages exhibit large air spaces called bullae. A bullous region is a sharply demarcated region of emphysema. In this paper, we show that an automated texture-based system based on delegated classifiers is capable of achieving multiple levels of emphysema extraction in High Resolution Computed Tomography (HRCT) images. The key idea of delegation is that a cautious classifier makes predictions that meet a minimum level of confidence, and delegates the difficult or uncertain predictions to a more specialized classifier. In this paper, we design a two-step scenario where a first classifier chooses the examples to classify on and delegates the more difficult examples to a second classifier. We compare this technique to well known emphysema classification techniques and ensemble methods such as bagging and boosting. Comparison of the results shows that the techniques presented here are more accurate. From a medical standpoint, the classifiers built at different iterations appear to show an interesting correlation with different levels of emphysema.

Automatic segmentation of lung parenchyma in the presence of diseases based on curvature of ribs.

RATIONALE AND OBJECTIVES: Segmentation of lungs using high-resolution computer tomographic images in the setting of diffuse lung diseases is a major challenge in medical image analysis. Threshold-based techniques tend to leave out lung regions that have increased attenuation, such as in the presence of interstitial lung disease. In contrast, streak artifacts can cause the lung segmentation to "leak" into the chest wall. The purpose of this work was to perform segmentation of the lungs using a technique that selects an optimal threshold for a given patient by comparing the curvature of the lung boundary to that of the ribs. METHODS: Our automated technique goes beyond fixed threshold-based approaches to include lung boundary curvature features. One would expect the curvature of the ribs and the curvature of the lung boundary around the ribs to be very close. Initially, the ribs are segmented by applying a threshold algorithm followed by morphologic operations. The lung segmentation scheme uses a multithreshold iterative approach. The threshold value is verified until the curvature of the ribs and the curvature of the lung boundary are closely matched. The curve of the ribs is represented using polynomial interpolation, and the lung boundary is matched in such a way that there is minimal deviation from this representation. Performance of this technique was compared with conventional (fixed threshold) lung segmentation techniques on 25 subjects using a volumetric overlap fraction measure. RESULTS: The performance of the rib segmentation technique was significantly different from conventional techniques with an average higher mean volumetric overlap fraction of about 5%. CONCLUSIONS: The technique described here allows for accurate quantification of volumetric computed tomography and more advanced segmentation of abnormal areas.

Three-dimensional mapping of gallbladder wall thickness on computed tomography using Laplace's equation.

RATIONALE AND OBJECTIVES: Traditionally, maximum gallbladder wall thickness is measured at a single point on ultrasonography. The purpose of this work was to develop an automated technique to measure the thickness of the gallbladder wall over the entire gallbladder surface using computer tomography (CT). MATERIALS AND METHODS: Subjects who had (5-mm) thick and thin (2.5-mm) reconstruction through the abdomen were selected from a research database. Their volumetric computed tomographic images were acquired using a multidetector GE Medical Systems LightSpeed 16 scanner at 120 kVp, approximately 250 mAs, with standard filter reconstruction algorithm and segmented in three dimensions. Two segmentation boundaries were obtained, an inner and an outer boundary of the gallbladder wall. The thickness of the wall was quantified by computing the distance between the boundaries over the entire volume using Laplace's equation from mathematical physics. The distance between the surfaces is found by computing normalized gradients that form a vector field, representing tangent vectors along field lines connecting both boundaries. The Laplacian technique was compared with the well-known Euclidean distance transformation (EDT) technique that provides a three-dimensional Euclidean distance mapping between the two extracted surfaces. RESULTS: The technique was tested on 10 subjects who had thin- and thick-section computed tomographic datasets reconstructed from a single scan. The mean thickness for the thick- and thin-section CT using Laplace was 3.18 and 2.93 mm, respectively. The smooth transition between surfaces resulting from the Laplace technique resulted in a coefficient of variation that was less than 1% compared to EDT. CONCLUSIONS: EDT technique is very sensitive to imperfect segmentations, resulting in higher variation compared to the Laplacian technique. The smooth transition between surfaces makes the Laplacian technique more robust compared to EDT for the measurement of CT gallbladder thickness.

Automatic detection of bronchial dilatation in HRCT lung images.

Bronchiectasis is an airway disease caused by the dilatation of the bronchial tree, and a bronchovascular pair is formed between a bronchus and a vessel. An abnormal bronchovascular pair is one that has a larger bronchus compared to its accompanying vessel. Typically, bronchi and vessels running perpendicular to the plane of section appear as near-circular rings on computed tomography (CT) scans. This paper describes BV_pairs, a system capable of detecting abnormal bronchovascular pairs in high-resolution CT scans of sparse datasets using a three-stage process: (1) detection of potential bronchovascular pairs, (2) detection of discrete pairs, where there exists no ambiguity as to the artery that accompanies a bronchus, and (3) identification of abnormal pairs with severity levels. The system was evaluated at every stage. The automated scoring for the presence and severity of bronchial abnormalities was demonstrated to be comparable to that of an experienced radiologist (i.e., kappa statistics kappa > 0.5). In addition, BV_pairs was also evaluated on images containing honeycombing regions, since honeycombing cysts appear very similar to bronchi, and the system could successfully differentiate honeycombing cysts from bronchi.