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.