Segmentation in Echocardiographic Sequences using Shape-based Snake Model Combined with Generalized Hough Transformation

Simultaneous Analysis of 2D Echo Views for Left Atrial Segmentation and Disease Detection

We propose a joint information approach for automatic analysis of 2D echocardiography (echo) data. The approach combines a priori images, their segmentations and patient diagnostic information within a unified framework to determine various clinical parameters, such as cardiac chamber volumes, and cardiac disease labels. The main idea behind the approach is to employ joint Independent Component Analysis of both echo image intensity information and corresponding segmentation labels to generate models that jointly describe the image and label space of echo patients on multiple apical views, instead of independently. These models are then both used for segmentation and volume estimation of cardiac chambers such as the left atrium and for detecting pathological abnormalities such as mitral regurgitation. We validate the approach on a large cohort of echoes obtained from 6,993 studies. We report performance of the proposed approach in estimation of the left-atrium volume and detection of mitral-regurgitation severity. A correlation coefficient of 0.87 was achieved for volume estimation of the left atrium when compared to the clinical report. Moreover, we classified patients that suffer from moderate or severe mitral regurgitation with an average accuracy of 82%.

Using the Hough transform to segment ultrasound images of longitudinal and transverse sections of the carotid artery

Automatic segmentation of the arterial lumen from ultrasound images is an important task in clinical diagnosis. In this paper, the Hough transform (HT) was used to automatically extract straight lines and circles from sequences of B-mode ultrasound images of longitudinal and transverse sections, respectively, of the carotid artery. In 10 normal subjects, the specificity and accuracy of HT-based segmentation were on average higher than 0.96 for both sections, whereas the sensitivity was higher than 0.96 in longitudinal and higher than 0.82 in transverse sections. The intima-media thickness (IMT) was also estimated from images of longitudinal sections; the corresponding validation parameters were generally higher than 0.90. To further validate the results, arterial distension waveforms (ADW) were estimated from sequences of images using the HT technique as well as motion analysis using block matching (BM). In longitudinal sections, diastolic and systolic diameters and relative diameter changes using HT and BM were not significantly different. In transverse sections, diastolic and systolic diameters were significantly lower using the HT technique; the differences were <7%. Relative diameter changes in transverse sections were not significantly different from BM-estimated ones. The HT technique was also applied to four subjects with atherosclerosis, in which sensitivity, specificity and accuracy were comparable to those of normal subjects; the low values of sensitivity in transverse sections may reflect departure from the circular model because of the presence of plaque. In conclusion, the HT technique provides a reliable way to segment ultrasound images of the carotid artery and can be used in clinical practice to estimate indices of arterial wall physiology, such as the IMT and the ADW.