Texture Analysis of Supraspinatus Ultrasound Image for Computer Aided Diagnostic System.

OBJECTIVES: In this paper, we proposed an algorithm for recognizing a rotator cuff supraspinatus tendon tear using a texture analysis based on a histogram, gray level co-occurrence matrix (GLCM), and gray level run length matrix (GLRLM). METHODS: First, we applied a total of 57 features (5 first order descriptors, 40 GLCM features, and 12 GLRLM features) to each rotator cuff region of interest. Our results show that first order statistics (mean, skewness, entropy, energy, smoothness), GLCM (correlation, contrast, energy, entropy, difference entropy, homogeneity, maximum probability, sum average, sum entropy), and GLRLM features are helpful to distinguish a normal supraspinatus tendon and an abnormal supraspinatus tendon. The statistical significance of these features is verified using a t-test. The support vector machine classification showed accuracy using feature combinations. Support Vector Machine offers good performance with a small amount of training data. Sensitivity, specificity, and accuracy are used to evaluate performance of a classification test. RESULTS: From the results, first order statics features and GLCM and GLRLM features afford 95%, 85%, and 100% accuracy, respectively. First order statistics and GLCM and GLRLM features in combination provided 100% accuracy. Combinations that include GLRLM features had high accuracy. GLRLM features were confirmed as highly accurate features for classified normal and abnormal. CONCLUSIONS: This algorithm will be helpful to diagnose supraspinatus tendon tear on ultrasound images.

A case of pulmonary artery intimal sarcoma diagnosed with multislice CT scan with 3D reconstruction.

Pulmonary artery intimal sarcoma is a rare highly lethal disease, with additional retrograde extension to pulmonic valve and right ventricle being an extremely rare condition. It is frequently mistaken for pulmonary thromboembolism. We report a case of 64-year-old woman with progressive dyspnea initially suspected and treated for pulmonary thromboembolism. Her helical chest CT scan with 3 dimensional (3D) reconstruction combined with echocardiography revealed a compacting main pulmonary artery mass extending to the right ventricular outflow tract and the right pulmonary artery. After excision of the mass, the patient's condition improved dramatically, and the pathologic findings revealed pulmonary intimal sarcoma. This report emphasizes that helical chest CT with 3D reconstruction can be an important tool to differentiate the characteristics of pulmonary artery lesions, such as intimal sarcoma and thromboembolism.

B-type natriuretic Peptide predicts clinical presentations and ventricular overloading in patients with heart failure.

Brain natriuretic peptide (BNP), a neurohormone secreted from the ventricular myocardium in response to hemodynamic load/wall stress, in congestive heart failure (CHF). This study was performed to evaluate the correlation between BNP level and clinical presentations and hemodynamic parameters obtained by echo-Doppler (echo-Doppler) analysis, and its relation with disease severity and ventricular load/wall stress. CHF patients (n=246) were subgrouped by clinical presentations and echo-Doppler findings into 4 groups: diastolic HF only, chronic HF, acute HF, and chronic HF with acute exacerbation. A BNP level of 81.2 pg/ml showed a sensitivity/ specificity of 53.3%/98.4% for detecting CHF (AUC, 0.882; p < 0.0001), and was found to be closely related with the NYHA classification (p < 0.0001). Log BNP was related with LVEF (r2=0.3015, p < 0.0001) and the Meridional wall stress index (r2=0.4052, p < 0.0001). The difference between the BNP levels of the subgroups and BNP control was significant (p < 0.0001), except between the HF group and the controls; control (n=114, 20.9 +/- 31.4 pg/ml), only diastolic HF (n=84, 89.8 +/- 117.6 pg/ml), chronic HF (n=60, 208.2 +/- 210.2 pg/ml), acute HF (n=28, 477.9 +/- 498.4 pg/ml), chronic HF with acute exacerbation (n= 74, 754.1 +/- 419.2 pg/ml). The BNP level was significantly higher in the only diastolic HF group than in the asymptomatic control group with diastolic dysfunction (89.8 +/- 12.8 vs. 22.8 +/- 5.1 pg/ml, p < 0.0001). BNP may be a good indicator for the differential diagnosis of a broad spectrum of heart failures. And, elevated BNP might help to diagnose diastolic HF in patients with diastolic dysfunction.