Crohn’s disease (CD) is one of inflammatory bowel diseases, characterized by lifelong relapsing-remitting clinical course. The choice of treatment protocols is based on the comprehensive evaluation of the disease. And the treatment protocols should be adjusted according to the response to the treatment and the drug tolerance. Repeated assessment of the activity of intestinal inflammation is very necessary. Each of endoscopy, Crohn’s Disease Activity Index, CT, magnetic resonance enterography, and ultrasonography (US) has its own disadvantages. US is widely used in clinical practice because of its no radiation, convenience, low cost, and high degree of patient tolerance. The two-dimensional ultrasound, Doppler ultrasound, elastosonography, and contrast-enhanced ultrasonography each provides some effective parameters for evaluation of CD activity. Some parameters are of high value, such as bowl wall thichness, bowl wall stratification, color Doppler signal, strain ratio, and relative enhancement, etc. The values of some parameters are disputed, such as the blood flow of superior mesenteric artery, time to peak, etc. Some studies combine several ultrasound parameters and calculate their respective weights to obtain an ultrasound scoring method. US, as a valid tool to evaluate CD activity, provides valuable help in solving clinical problems such as evaluation of therapeutic effect, mucosal healing, and postoperative recurrence.
Transrectal contrast-enhanced ultrasound (CEUS) is an important examination for rectal tumors. The inhomogeneity of the CEUS images has important clinical significance. However, there is no objective method to evaluate this index. In this study, a method based on gray-level co-occurrence matrix (GLCM) is proposed to extract texture features of images and grade these images according the inhomogeneity. Specific processes include compressing the gray level of the image, calculating the texture statistics of gray level co-occurrence matrix, combining feature selection and principal component analysis (PCA) for dimensionality reduction, and training and validating quadratic discriminant analysis (QDA). After ten cross-validation, the overall accuracy rate of machine classification was 87.01%, and the accuracy of each level was as follows: Grade Ⅰ 52.94%, Grade Ⅱ 96.48% and Grade Ⅲ 92.35% respectively. The proposed method has high accuracy in judging grade Ⅱ and Ⅲ images, which can help to identify the grade of inhomogeneity of contrast-enhanced ultrasound images of rectal tumors, and may be used to assist clinical doctors in judging the grade of inhomogeneity of contrast-enhanced ultrasound of rectal tumors.