Torticollis, also called wryneck, is a clinical sign or symptom that could be the result of a variety of possible disorders. Among the etiologies, congenital muscular torticollis (CMT) with impairment of the sternocleidomastoid (SCM) is the most frequent cause of torticollis in infants. Infants with CMT have the symptom of head tilt to one side, which is often combined with rotation of the head to the opposite side. In this paper, we report a study on the analysis of the ultrasonic images on two sides of the neck for the CMT classification. To this end, we first apply an interactive ROI segmentation procedure, followed by the extraction of several different texture features for the classification of CMT type. We use three types of texture features, including gray-lever co-occurrence matrix, Laplacian of Gaussian, and Gabor features. In addition, three feature comparison methods, such as mutual information, Bhattacharyya Distance, and Kullback-Leibler divergence, are used to compute the distribution distances for different texture features and feed them into the support vector machine classifier for the CMT classification. Experimental results demonstrate the performance of the proposed image analysis and classification method on real ultrasonic images.