Ultrasonic imaging is the noninvasive clinical imaging modality of choice for diagnosing heart disease. At present, two-dimensional ultrasonic grayscale images provide a relatively cheap, fast, bedside method to study the morphology of the heart. Several methods have been proposed to assess myocardial function. These have been based on either grayscale or motion (velocity) information measured in real-time. However, the quantitative assessment of regional myocardial function remains an important goal in clinical cardiology. To do this, ultrasonic strain and strain-rate imaging have been introduced. In the clinical setting, these techniques currently only allow one component of the true three-dimensional deformation to be measured. Clinical, multidimensional strain (rate) information can currently thus only be obtained by combining data acquired using different transducer positions. Nevertheless, given the appropriate postprocessing, the clinical value of these techniques has already been shown. Moreover, multidimensional strain and strain-rate estimation of the heart in vivo by means of a single ultrasound acquisition has been shown to be feasible. In this paper, the new techniques of ultrasonic strain rate and strain imaging of the heart are reviewed in terms of definitions, data acquisition, strain-rate estimation, postprocessing, and parameter extraction. Their clinical validation and relevance will be discussed using clinical examples on relevant cardiac pathology. Based on these examples, suggestions are made for future developments of these techniques.

The recognition of the coronary blood vessels on single angiograms is addressed. Recognizing blood vessels on digital subtraction angiograms is a prerequisite to automatic diagnosis and quantification of blood-vessel pathologies. It is shown how stereoscopic angiograms can improve the interpretation process. The computational strategy recommended to solve the problem has the following important characteristics. First, the model is hierarchically instantiated, starting from a partial model and working up to the final complete model. Second, the contact with the image is never broken during the interpretation process. Missing model attributes are instantiated by returning to the image. Third, delineation (segmentation and image partitioning), interpretation, and stereoscopic matching are not sequential but integrated processes. Fourth, the knowledge representation is partially iconic. The iconic memory is used to guide the search for missing or incomplete attributes in the image.>