Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis.

To assist the ultrasound (US) differential diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we retrospectively reviewed 111 medical records of digitized US images of breast pathologies. They were pathologically proved benign breast tumors from 40 patients (i.e., 40 fibroadenomas) and malignant breast tumors from 71 patients (i.e., 71 infiltrative ductal carcinomas). Radiologists, before analysis by the computer-aided diagnosis (CAD) system, segmented the tumors manually. The contour features were calculated by measuring the radial length of tumor boundaries. The features selection process was accomplished using a stepwise analysis procedure. Then, an SLR model with contour features was used to classify tumors as benign or malignant. In this experiment, cases were sampled with "leave-one-out" test methods to evaluate the SLR performance using a receiver operating characteristic (ROC) curve. The accuracy of our SLR model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40), the positive predictive value was 89.6% (69 of 77), and the negative predictive value was 94.1% (32 of 34). The CAD system using SLR can differentiate solid breast nodules with relatively high accuracy and its high negative predictive value could potentially help inexperienced operators to avoid misdiagnoses. Because the SLR model is trainable, it could be optimized if a larger set of tumor images were supplied.

Sonography of acute right side colonic diverticulitis.

BACKGROUND: To describe the prevalence and sonographic findings and ultrasound diagnostic accuracy of the right side colonic diverticulitis in patients having right lower abdominal pain with indeterminate nature. METHODS: A total of 934 patients with acute right lower abdominal pain of clinically indeterminate nature were referred for ultrasound examination (US). US studies were performed with 3.5 to 7.0 (or occasionally 10) MHz transducers using graded compression method. Twenty-three patients were finally diagnosed to have an uncomplicated acute diverticulitis of the right colon. The gray-scale sonographic images were reviewed. A retrospective study was undertaken to evaluate diagnostic contribution of US. RESULTS: The prevalence of acute right side colonic diverticulitis was 2.5% in patients with clinically indeterminate acute right lower abdominal pain. Locations of the inflamed diverticula include cecum in 6 patients, proximal ascending colon in 15 patients, and distal ascending colon in only 2 patients. Sonography detected 21 inflamed diverticula with 1 false positive and 2 false negative results. The most typical sonographic feature of an inflamed diverticulum of right side colon was a rounded or oval-shaped hypoechoic or nearly anechoic structure (52%) protruding out from the segmentally thickened colonic wall. Some of them might contain strong echoes representing gas or feces (43%), or stone in the lumen (5%). Regional pericolic or peridiverticular fat thickening was noted in 57% of patients, and segmental colon wall thickening in 38%. US examination yielded a sensitivity of 91.3%, a specificity of 99.8%, an overall accuracy of 99.5%, a positive predictive value of 95.5%, and a negative predictive value of 99.7%. A positive sonogram made the likelihood of acute right side diverticulitis 456.5 times greater compared with the pretest clinical impression. US differentiated acute right side colonic diverticulitis from acute appendicitis with a 100% accuracy. CONCLUSIONS: Ultrasound can be extremely useful in diagnosing acute right side colonic diverticulitis. Careful ultrasound evaluation of the right colon and the cecum may facilitate a correct diagnosis and help differentiate from acute appendicitis, and steer the surgeon to a more effective management.