A nomogram based on combining clinical features and contrast enhanced ultrasound is not able to identify Her-2 over-expressing cancer from other breast cancers.

Objective: The aim of this study was to evaluate whether a predictive model based on a contrast enhanced ultrasound (CEUS)-based nomogram and clinical features (Clin) could differentiate Her-2-overexpressing breast cancers from other breast cancers. Methods: A total of 152 pathology-proven breast cancers including 55 Her-2-overexpressing cancers and 97 other cancers from two units that underwent preoperative CEUS examination, were included and divided into training (n = 102) and validation cohorts (n = 50). Multivariate regression analysis was utilized to identify independent indicators for developing predictive nomogram models. The area under the receiver operating characteristic (AUC) curve was also calculated to establish the diagnostic performance of different predictive models. The corresponding sensitivities and specificities of different models at the cutoff nomogram value were compared. Results: In the training cohort, 7 clinical features (menstruation, larger tumor size, higher CA153 level, BMI, diastolic pressure, heart rate and outer upper quarter (OUQ)) + enlargement in CEUS with P < 0.2 according to the univariate analysis were submitted to the multivariate analysis. By incorporating clinical information and enlargement on the CEUS pattern, independently significant indicators for Her-2-overexpression were used for further predictive modeling as follows: Model I, nomogram model based on clinical features (Clin); Model II, nomogram model combining enlargement (Clin + Enlargement); Model III, nomogram model based on typical clinical features combining enlargement (MC + BMI + diastolic pressure (DP) + outer upper quarter (OUQ) + Enlargement). Model II achieved an AUC value of 0.776 at nomogram cutoff score value of 190, which was higher than that of the other models in the training cohort without significant differences (all P>0.05). In the test cohort, the diagnostic efficiency of predictive model was poor (all AUC<0.6). In addition, the sensitivity and specificity were not significantly different between Models I and II (all P>0.05), in either the training or the test cohort. In addition, Clin exhibited an AUC similar to that of model III (P=0.12). Moreover, model III exhibited a higher sensitivity (70.0%) than the other models with similar AUC and specificity, only in the test cohort. Conclusion: The main finding of the study was that the predictive model based on a CEUS-based nomogram and clinical features could not differentiate Her-2-overexpressing breast cancers from other breast cancers.

Ultrasound-based radiomics analysis for differentiating benign and malignant breast lesions: From static images to CEUS video analysis.

Background: Continuous contrast-enhanced ultrasound (CEUS) video is a challenging direction for radiomics research. We aimed to evaluate machine learning (ML) approaches with radiomics combined with the XGBoost model and a convolutional neural network (CNN) for discriminating between benign and malignant lesions in CEUS videos with a duration of more than 1 min. Methods: We gathered breast CEUS videos of 109 benign and 81 malignant tumors from two centers. Radiomics combined with the XGBoost model and a CNN was used to classify the breast lesions on the CEUS videos. The lesions were manually segmented by one radiologist. Radiomics combined with the XGBoost model was conducted with a variety of data sampling methods. The CNN used pretrained 3D residual network (ResNet) models with 18, 34, 50, and 101 layers. The machine interpretations were compared with prospective interpretations by two radiologists. Breast biopsies or pathological examinations were used as the reference standard. Areas under the receiver operating curves (AUCs) were used to compare the diagnostic performance of the models. Results: The CNN model achieved the best AUC of 0.84 on the test cohort with the 3D-ResNet-50 model. The radiomics model obtained AUCs between 0.65 and 0.75. Radiologists 1 and 2 had AUCs of 0.75 and 0.70, respectively. Conclusions: The 3D-ResNet-50 model was superior to the radiomics combined with the XGBoost model in classifying enhanced lesions as benign or malignant on CEUS videos. The CNN model was superior to the radiologists, and the radiomics model performance was close to the performance of the radiologists.

PBL teaching in ultrasonography resident standardization training in the COVID-19 pandemic.

OBJECTIVE: To study the effect of the problem-based learning (PBL) method in ultrasonography (US) resident standardization training during the COVID-19 pandemic. METHODS: Fifty residents were divided into two groups to participate in a 30-day US training program. The residents in the observation group underwent PBL combined with the lecture-based learning (LBL) method, while the residents in the control group experienced the LBL method alone, with 25 residents in each group. A basic theoretical test, practical examination, and questionnaire were used to evaluate the teaching effect of the PBL + LBL method and the LBL method alone. RESULTS: The basic theoretical pretest score of the observation group was not significantly different from that of the control group. However, the posttest theoretical score and practical score were significantly higher in the observation group than in the control group (P < 0.01). The results of the questionnaire showed that the resident satisfaction level in the observation group with PBL combined with the LBL method was 96%, which was significantly higher than that of the control group with the LBL method alone (80%) (P < 0.05). CONCLUSION: The combination of PBL with the LBL method has obvious advantages over the LBL method alone in regard to the training of US residents during the COVID-19 pandemic.

Principal component regression-based contrast-enhanced ultrasound evaluation system for the management of BI-RADS US 4A breast masses: objective assistance for radiologists.

A portion of detected breast masses might be overrated by using the Breast Imaging-Reporting and Data System ultrasonography (BI-RADS US) lexicon. A principal component regression-based contrast-enhanced ultrasound (PCR-CEUS) evaluation system was built to quantitatively illustrate whether CEUS could help radiologists to differentiate 4A masses. The PCR-CEUS evaluation system, based on principal component analysis (PCA) and logistic regression, was verified by random assignment into training and test sets and shown to reduce the data dimension and avoid collinearity in CEUS variables. This prospective study consecutively collected 238 patients with 238 4A masses confirmed pathologically. All enrolled patients accepted CEUS examination. The diagnostic performance of senior and junior radiologists, PCR-CEUS and combined methods was compared. The PCR-CEUS system had consistent diagnostic performance in both the training and test sets, with an area under the curve (AUC) of 0.831 (0.765-0.897), 0.798 (0.7034-0.892) and 0.854 (0.765-0.943) (all P > 0.05). The AUC of the combined diagnostic model (PCR-CEUS + Senior radiologists) was higher than that of senior radiologists, and the combined model had higher sensitivity (0.875 (0.781-0.969) vs. 0.729 (0.603-0.855)) without compromising specificity. Furthermore, the AUC and specificity of the combined model (PCR-CEUS + Junior radiologists) (0.852 (0.787-0.916)) was higher than that of junior radiologists (0.665 (0.592-0.737) (P < 0.00001)). PCR-CEUS demonstrated good ability in differentiating malignant BI-RADS-US 4A masses and was helpful for both senior and junior radiologists.

Combination of contrast-enhanced ultrasound and strain elastography to assess cytologically non-diagnostic thyroid nodules.

The aim of the present study was to investigate the benefits of combining contrast-enhanced ultrasound (CEUS) and strain elastography (SE) for the diagnosis of thyroid nodules with non-diagnostic fine-needle aspiration cytology (FNAC) results. Between October 2013 and March 2017, CEUS and SE were performed in 226 patients (236 thyroid nodules) with non-diagnostic FNAC results prior to thyroidectomy. The diagnostic value of CEUS, SE and their combination (CEUS+SE) in distinguishing malignant from benign thyroid nodules was evaluated, using surgical pathology as a reference. Receiver operating characteristic curve analysis was used to assess the diagnostic performance of CEUS, SE and CEUS+SE in determining malignant thyroid nodules. Subsequently, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of CEUS, SE and CEUS + SE were calculated. The malignancy rate in patients with thyroid nodules and non-diagnostic FNAC results was 26.3% in the present study. The sensitivity, specificity, PPV, NPV, accuracy and area under the curve in predicting malignant thyroid nodules were 80.6, 85.6, 66.7, 92.5, 84.3 and 0.831%, respectively, using SE alone; 59.7, 95.9, 84.1, 86.9, 86.4 and 0.778%, respectively, using CEUS alone; and 83.9, 89.1, 73.6, 94.5, 88.1 and 0.865%, respectively, using the combination of CEUS and SE. Overall, the combination of CEUS with SE resulted in higher sensitivity, NPV and accuracy in the diagnosis of cytologically non-diagnostic thyroid nodules compared with CEUS or SE alone.

The features of contrast enhanced ultrasound and BRAF V600E in papillary thyroid carcinoma.

BACKGROUND: BRAF V600E mutation was proved to be associated with thyroid cancer. Papillary thyroid carcinoma (PTC) with positive BRAF mutation might have a more aggressive behavior. We investigated the correlation of the contrast-enhanced ultrasound (CEUS) features with BRAF 600VE in PTC. METHODS: The medical records of 1,199 patients with 1,315 nodules who underwent CEUS prior to fine needle aspiration (FNA) from January 2016 to March 2018 were retrospectively reviewed. The features of their enhancement were assessed from eight aspects: degree of enhancement, method of enhancement, homogeneity of enhancement, completeness of enhancement, boundary of the enhanced lesions, shape of the enhanced lesions, size of the enhanced lesions, and wash out period of the enhanced lesions. The patients then examined for the BRAF V600E mutation using specimens obtained from FNA. RESULTS: BRAF mutations were found in 888 of 1,315 nodules. The CEUS features were significantly different between BRAF-positive and BRAF-negative nodules. The BRAF mutation positive nodules were more often with larger size, hypo-enhancement, centripetal enhancement, inhomogeneous enhancement, complete enhancement, blurred boundary, irregular shape, and with wash out period at preoperative CEUS than those without BRAF mutations (P<0.001). However, no significant correlation was showed in Spearman's rank correlation between the CEUS features and BRAF mutation, except for degree of enhancement, method pattern of enhancement, and completeness of complete enhancement. Multivariate analysis showed that centripetal (OR: 1.465, 95% CI: 1.129-1.903) and no significant enhancement (OR: 0.790, 95% CI: 0.639-0.977) were predictive for the presence of BRAF mutations. The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of no significant enhancement and centripetal enhancement of CEUS for predicting BRAF mutation were 68.3%, 40.0%, 91.6%, 11.7%, and 72.4%, 35.1%, 37.8%, 70.0%, respectively. CONCLUSIONS: Our study indicated that preoperative thyroid nodule characteristics on CEUS might serve as a useful tool to BRAF mutation in PTC.

Role of Virtual Touch Tissue Quantification in Hashimoto's Thyroiditis.

We investigated the role of the virtual touch tissue quantification (VTQ) technique in diagnosing Hashimoto's thyroiditis (HT) and in distinguishing various HT-related thyroid dysfunctions. Two hundred HT patients and 100 healthy volunteers (the control group) were enrolled. The diagnostic performance of VTQ in predicting HT was calculated as the area under the receiver operating characteristic curve (AZ). The HT patients were further classified into three subgroups on the basis of serologic tests of thyroid function: hyperthyroidism, euthyroidism and hypothyroidism. Comparisons of shear wave velocity (SWV) between three subgroups were evaluated by analysis of variance. The mean SWV of the control group was significantly lower than that of the HT group (1.93 ± 0.33 m/s vs. 2.32 ± 0.49 m/s, p <0.001). Az was 0.734 with a cut-off value of 1.86 m/s for performance of SWV in distinguishing between HT and a healthy thyroid; the sensitivity and specificity were 82.5% and 50.0%, respectively. Mean SWV values in the three HT subgroups (hyperthyroidism [2.07 ± 0.37 cm/s] vs. euthyroidism [2.20 ± 0.40 cm/s] vs. hypothyroidism [2.49 ± 0.46 cm/s]) were significantly different (p <0.05). Our results suggest that VTQ is a promising technique for assessing HT and HT-related thyroid dysfunction.