An approach to image classification in ultrasound

Ultrasound is an attractive diagnostic medical imaging modality because of its safety, speed, relative low cost, and versatility. It is used successfully in imaging of shape, structure, and size in two and three dimensions; in the measurement of blood flow, and in quantitative characterization of tissue. The paper examines some of the models and processing techniques that make those applications possible. For example, quantitative ultrasound tissue characterization requires the estimation of parameters from the observed ultrasound radio-frequency signal. First, those parameters must be identified, second, algorithms used to extract those parameters from the observed signal must be developed; third, the classifier must be chosen; and finally, those extracted parameters are used to train the classifier, which is then tested to estimate classification performance. The methods are applied to the imaging of several kinds of liver tissue.