Evaluation of contrast-enhanced ultrasonography breast predictive model in optimizing breast lesions BI-RADS classification / 中华超声影像学杂志

Objective To explore the value of contrast-enhanced ultrasonography ( CEUS ) breast predictive model in the optimization of BI-RADS classification of breast lesions . Methods A total of 1049 BI-RADS 4 ,5 breast lesions were obtained from 1039 patients in 8 centers . CEUS examination was performed prior to biopsy or surgery . According to the classification of the model ,class 3 ,4A ,4B and 4C were selected as biopsy thresholds ,and the ROC curve was drawn . The diagnostic sensitivity ,specificity , accuracy ,positive predictive value ,negative predictive value and Jordanian index were calculated for the biopsy threshold . The biopsy rate of breast lesions before and after angiography ,cancer detection rate , follow-up cases of malignant risk were compared . Results There were benign lesions 586 ( 55 .9％ ) , malignant lesions 463 (44 .1％ ) in the 1049 breast lesions . The area of ROC with thresholds of 3 ,4A ,4B and 4C were 0 .695 ,0 .838 ,0 .847 and 0 .757 ,respectively ( all P < 0 .01) . Ultrasonography had a certain diagnostic effect on benign and malignant breast lesions . The diagnostic sensitivity ,specificity ,accuracy , positive predictive value and negative predictive value with class 4A after CEUS set as the biopsy threshold were 93 .32％ ,75 .65％ ,82 .75％ ,75 .57％ and 93 .35％ ,respectively ,and the Jordanian index was 0 .690 . When chass 3 after CEUS was set as the biopsy threshold ,the biopsy rate was reduced from 100％ to 76 .74％ ,the detection rate was increased from 44 .23％ to 56 .77％ ,and the risk of cancer was only 0 .67％ in the follow-up cases . When class 4A was set as the biopsy threshold ,the biopsy rate was reduced from 100％ to 55 .58％ after CEUS . The detection rate of cancer increased from 44 .23％ to 74 .44％ . The risk of cancer was 2 .96％ . Conclusions The biopsy rate of breast lesions in category 4 and 5 would be reduced and cancer detection rate of them would be increased after CEUS ,however ,the risk of malignancy in the follow -up cases would be controlled as low as category 3 and 4A in previous BI-RADS . Thus ,CEUS has a good prospect of in optimizing BI-RADS and reducing biopsy rate in unnecessary lesions .

Consistency of different physicians in diagnosis of malignant breast lesions with breast CEUS predictive model: A multicenter study / 中国医学影像技术

Objective To explore the consistency of different physicians in diagnosis of malignant breast lesions with breast CEUS predictive model.Methods Totally 953 patients with solitary breast nodule from multicenter who underwent ultrasound and CEUS were collected.The research team was composed by the initial group (one junior physician from each hospital),check group (one or two physicians who had at least two-year experience of CEUS examination from each hospital),research group (two senior physicians from Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital) and cross-blinded group (one or two vice directors or chief physicians from each hospital).At first,the lesions were classified according to the breast imaging reporting and data system (BI RADS) by the initial group and the check group,then new BI RADS classifications were performed by research group and cross blind group with breast CEUS predictive model.The consistency of different physicians in diagnosis of malignant breast lesions was analyzed.Results Among 953 patients,benign lesions were found in 451 patients (451/953,47.32％),malignant lesions were found in 435 patients (435/953,45.65％),and precancerous lesions were found in 67 patients (67/953,7.03％).The accuracy of the initial group,check group,research group and cross-blinded group was 71.67％(683/953),74.92％(714/953),80.17％ (764/953) and 83.42 ％ (795/953),respectively.The consistency of different physicians for diagnosis of malignant breast lesions between initial group and check group was good (Kappa =0.82,P＜0.001),while between initial group and crossblinded group,initial group and research group were both moderate (Kappa =0.56,0.41;all P＜0.001).The consistency of different physicians for diagnosis of malignant breast lesions between cheek group and cross-blinded group,between check group and research group were both moderate (Kappa =0.68,0.51;all P＜0.001).The consistency between research group and cross-blinded group with breast CEUS predictive model was moderate (Kappa =0.74,P＜ 0.001).Conclusion The consistency of different physicians in diagnosis of malignant breast lesions with breast CEUS predictive model was moderate.

Diagnostic value of contrast-enhanced ultrasound in breast precancerous lesions / 中华超声影像学杂志

Objective To evaluate the diagnostic value of contrast-enhanced ultrasound in breast precancerous lesions . Methods Retrospectively analyzed the contrast-enhanced ultrasound model and angiographic predictive model of 465 cases of the A prospective multicenter study of breast nodules contrast-enhanced ultrasound" that led the Sichuan Provincial People′s Hospital from January 2016 to April 2017 ,which included 69 cases of breast precancerous lesions and 396 other types benign lesions ,and the sensitivity ,specificity and accuracy of the diagnosis of breast precancerous lesions were calculated . Results The sensitivity of ultrasound predictive model for the diagnosis of precancerous lesions was 60 .9％ and AUC was 0 .681 . Precancerous lesions mainly showed non-concentricity , increased homogeneity , and increased lesions;other types of benign lesions mainly showed non-centripetal ,high uniformity enhancement and lesion size unchanged . Conclusions Contrast-enhanced ultrasound shows a potential value in the differential diagnosis of precancerous lesions and other types of benign lesions ,that can help clinicians to take early intervention measures for breast precancerous lesions ,but there are still many problems to be solved .

Computer-aided diagnosis of fatty liver based on ultrasonic images / 生物医学工程学杂志

This study aims to provide a computer-aided method for the diagnosis of fatty liver by B-scan ultrasonic imaging. Fatty liver is referred to the infiltration of triglycerides and other fats of the liver cells, which affected the texture of liver tissue. In this paper, some features including mean intensity ratio, as well as angular second moment, entropy and inverse differential moment of gray level co-occurrence matrix were extracted from B-scan ultrasonic liver images. Feature vectors which indicated two classes of images were created with the four features. Then we used kappa-means clustering algorithm, self-organized feature mapping (SOFM) artificial neural network and back-propagation (BP) artificial neural network to classify these vectors. The accuracy rate of kappa-means clustering algorithm was 100% for normal liver and 63.6% for fatty liver. The results of SOFM neural network showed that the accuracy rate was 84.8% for normal liver and 90.9% for fatty liver. The accuracy rate of neural network was 100% both for normal liver and fatty liver. This technology could detect the characteristics of B-scan images of normal liver and fatty liver more accurately. It could greatly improve the accuracy of the diagnosis of fatty liver.