-
[show abstract]
[hide abstract]
ABSTRACT: For a successful computer-aided diagnosis (CAD) approach, investigating the benefit of the output for radiologist diagnosis is as important as developing the computer algorithm itself. To evaluate the accuracy and the interobserver variability of two newly developed CAD algorithms for breast mass discrimination, eight radiologists with varied experience in breast ultrasonography (US) independently reviewed the lesions according to Breast Imaging Reporting and Data System (BI-RADS)-US. They interpreted the original ultrasound images, provided a final assessment category to indicate the probability of malignancy and then made a further diagnosis using the images processed by the proposed CAD algorithms. The receiver operating characteristic (ROC) curve and Cohen's kappa statistics were employed to evaluate the effect of the CAD algorithms on radiologist diagnoses. By using the proposed CAD approach, the quality of the images was improved and more information was provided to the observers. With the processed images, the areas under the ROC (Az) of each reader (0.86 approximately 0.89) were greater than those with the original ultrasound images (0.81 approximately 0.86) and all the radiologists improved their performance significantly (p < 0.05) except two senior radiologists (p > 0.05). The Az values of the junior radiologists with CAD were comparable to those of the senior radiologists. Cohen's kappa statistics showed that better interobserver agreement was obtained by using the processed images. We conclude that the proposed CAD method is more helpful for the junior radiologists than for the senior ones and it also showed the advantage of decreasing interobserver variability.
Ultrasound in medicine & biology 08/2010; 36(8):1273-81. · 2.02 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: To evaluate the feasibility and value of determining myocardial perfusion and regional systolic function by myocardial contrast stress echocardiography (MCSE) with computer-assisted technique in a rabbit model of ischemia/reperfusion injury.
Rabbits underwent 30-(Group I, n = 15) and 120-(Group II, n = 15) minute left ventricular branch of the left circumflex coronary artery occlusion foll owed by 60-minute reperfusion, dobutamine at increasing doses (5, 10, 15 and 20 microg.kg(-1).min(-1)) was then infused after reperfusion for 15 min. Bolus myocardial contrast agent was injected and MCSE performed at baseline, at the end of coronary occlusion and reperfusion, at the end of each dobutamine infusion. Images were analyzed by computer-assisted technique and myocardial calibrated contrast intensity (CI) of each segment was measured and a color-coded map was then obtained automatically (yellow: from 0 to -20 pix, blue:from -21 to -40 pix, green: from -41 to -70 pix, red: < -70 pix). The area at risk and infarct area obtained by red-coded map were compared with ex vivo results determined by fluorescent microsphere and triphenyl-tetrazolium chloride (TTC) staining. Percentage wall thickening (WT) of each risk segment at each stage were also measured.
(1) During occlusion, WT in the areas at risk decreased to zero or negative and the calibrated CI values were significantly lower than those at baseline. Area at risk obtained by red-coded map correlated well with that obtained by fluorescent staining (r = 0.91, P < 0.01). (2) After reperfusion and 5 microg.kg(-1).min(-1) dobutamine administration, WT and calibrated CI in all rabbits remained depressed. Calibrated CI at -70 pix was an optimal cutoff point to identify infarcted segments (sensitivity 95%, specificity 87%). The correlation between the infarct size by red-coded image and TTC was 0.89 (P < 0.01). (3) Calibrated CI and WT significantly improved in Group I rabbits while these parameters remained unchanged in Group II rabbits after increasing doses of dobutamine post ischemia.
Myocardial contrast stress echocardiography in combination with computer-assisted analysis technique are valuable techniques to quantitatively assess myocardial perfusion and regional systolic function and exactly identify stunned myocardium and infarcted myocardium.
Zhonghua xin xue guan bing za zhi [Chinese journal of cardiovascular diseases] 04/2008; 36(4):360-4.
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a comparative study of the diagnostic results of the ultrasologists with/without using a novel enhancement algorithm for breast ultrasonic images based on fuzzy entropy principle and textural information. Totally, 350 ultrasound images of 115 cases were analyzed including 59 benign and 56 malignant lesions. The original breast images were fuzzified, the edge and textural information were extracted, and the images were enhanced. The original and enhanced images were assessed and evaluated by ultrasologists using double blind method before and after enhancement. The diagnostic sensitivity and specificity were calculated by the areas (Az) under the receiver operating characteristic (ROC) curves. And the two diagnostic results before and after enhancement were compared by Chi-square test in a 2 x 2 table. The results demonstrated that the discrimination rate of breast masses had been highly improved after employing the novel enhancement algorithm. The result indicates the sensitivity could be raised from 74.3% to 89.3% with the false-positive rate 14.3%, and the area (Az) under the ROC curve of diagnosis also increased from 0.84 to 0.93. The novel enhancement algorithm can increase the classification accuracy and decrease the rate of missing and misdiagnosis, and it is useful for breast cancer control.
Medical Physics 09/2007; 34(8):3158-64. · 2.83 Impact Factor
