Breast tumor classification using different features of quantitative ultrasound parametric images.

RATIONALE AND OBJECTIVES: The ultrasound B-mode-based morphological and texture analysis and Nakagami parametric imaging have been proposed to characterize breast tumors. Since these three feature categories of ultrasonic tissue characterization supply information on different physical characteristics of breast tumors, by combining the above methods is expected to provide more clues for classifying breast tumors. MATERIALS AND METHODS: To verify the validity of the concept, raw data were obtained from 160 clinical cases. Six different types of morphological-feature parameters, four texture features, and the Nakagami parameter of benignancy and malignancy were extracted for evaluation. The Pearson's correlation matrix was used to calculate the correlation between different feature parameters. The fuzzy c-means clustering and stepwise regression techniques were utilized to determine the optimal feature set, respectively. The logistic regression, receiver operating characteristic curve, and support vector machine were used to estimate the diagnostic ability. RESULTS: The best performance was obtained by combining morphological-feature parameter (e.g., standard deviation of the shortest distance), texture feature (e.g., variance), and the Nakagami parameter, with an accuracy of 89.4%, a specificity of 86.3%, a sensitivity of 92.5%, and an area under receiver operating characteristic curve of 0.96. There was no significant difference between using fuzzy c-means clustering, logistic regression, and support vector machine based on the optimal feature set for breast tumors classification. CONCLUSION: Therefore, we verified that different physical ultrasonic features are functionally complementary and thus improve the performance in diagnosing breast tumors. Moreover, the optimal feature set had the maximum discriminating performance should be irrelative to the power of classifiers.

Clinical analysis of contributors to the delayed gallbladder opacification following the use of water-soluble contrast medium.

OBJECTIVES: Gallbladder opacification (GBO) on computed tomography (CT) imaging may obscure certain pathological or emergent conditions in the gallbladder, such as neoplasms, stones, and hemorrhagic cholecystitis. This study aimed to investigate the clinical contributing factors that could predict the presence of delayed GBO determined by CT. METHODS: This study retrospectively evaluated 243 consecutive patients who received enhanced CT or intravenous pyelography imaging and then underwent abdominal CT imaging within 5 days. According to the interval between imaging, the patients were divided into group A (1 day), group B (2 or 3 days), and group C (4 or 5 days). Three radiologists evaluated CT images to determine GBO. Fisher's exact test and multivariate backward stepwise elimination logistic regression were performed. RESULTS: Positive GBO was significantly associated with the interval between imaging studies, contrast type, contrast volume, renal function, and hypertransaminasemia (P<0.05). Multivariate backward stepwise elimination logistic regression analysis of the three groups identified contrast type and hypertransaminasemia as independent predictors of GBO in group B patients (odds ratio [OR], 13.52, 95% confidence interval [CI], 1.72-106.38 and OR, 3.43, 95% CI, 1.31-8.98, respectively; P<0.05). Hypertransaminasemia was the only independent predictor of GBO in group C patients with an OR of 7.2 (95% CI, 1.62-31.73). Hypertransaminasemia was noted in three patients (100%) who initially underwent imaging 5 days prior to GBO. CONCLUSION: Delayed GBO on CT imaging may be associated with laboratory hypertransaminasemia, particularly in patients receiving contrast medium over a period of ≥4 days. A detailed clinical history, physical examination, and further workup are of paramount importance for investigating the underlying cause behind the hypertransaminasemia.

Case report: lateral capsular release for acute extension deficit in a child with congenital radioulnar synostosis.

Acute elbow extension deficit is an unusual phenomenon that has been observed in patients with congenital radioulnar synostosis. We report the case of an 11-year-old girl with congenital radioulnar synostosis who developed acute extension deficit of the right elbow and whose elbow range of motion was restored following lateral capsular release.

Imaging of dermatofibrosarcoma protuberans of breast.

Dermatofibrosarcoma protuberans (DFSP) is a rare superficial soft tissue malignancy. We report a 45-year-old woman diagnosed with DFSP involving the breast. Ultrasound of DFSP revealed a heteroechogenetic breast mass, which showed normal adjacent dermis. Mammography disclosed a high-density mass without microcalcification. MRI showed an enhancing lobulated lesion with small area of cystic change and hemorrhage. The patient underwent excision biopsy and pathology revealed DFSP of the breast. DFSP involving the breast is rare and preoperative diagnosis by imaging could be a challenge for clinicians. A solitary mixed echogenicity and ill-defined soft tissue with no microcalcification located in the subdermal region could indicate the presence of DFSP.