Search

To establish a breast lesion risk stratification system using ultrasound images to predict breast malignancy and assess Breast Imaging Reporting and Data System (BI-RADS) categories simultaneously.This multicenter study prospectively collected a dataset of ultrasound images for 5012 patients at thirty-two hospitals from December 2018 to December 2020. A deep learning (DL) model was developed to conduct binary categorization (benign and malignant) and BI-RADS categories (2, 3, 4a, 4b, 4c, and 5) simultaneously. The training set of 4212 patients and the internal test set of 416 patients were from thirty hospitals. The remaining two hospitals with 384 patients were used as an external test set. Three experienced radiologists performed a reader study on 324 patients randomly selected from the test sets. We compared the performance of the DL model with that of three radiologists and the consensus of the three radiologists.In the external test set, the DL model achieved areas under the receiver operating characteristic curve (AUCs) of 0.980 and 0.945 for the binary categorization and six-way categorizations, respectively. In the reader study set, the DL BI-RADS categories achieved a similar AUC (0.901 vs. 0.933, p = 0.0632), sensitivity (90.98% vs. 95.90%, p = 0.1094), and accuracy (83.33% vs. 79.01%, p = 0.0541), but higher specificity (78.71% vs. 68.81%, p = 0.0012) than those of the consensus of the three radiologists.The DL model performed well in distinguishing benign from malignant breast lesions and yielded outcomes similar to experienced radiologists. This indicates the potential applicability of the DL model in clinical diagnosis.• The DL model can achieve binary categorization for benign and malignant breast lesions and six-way BI-RADS categorizations for categories 2, 3, 4a, 4b, 4c, and 5, simultaneously. • The DL model showed acceptable agreement with radiologists for the classification of breast lesions. • The DL model performed well in distinguishing benign from malignant breast lesions and had promise in helping reduce unnecessary biopsies of BI-RADS 4a lesions.

Objective To investigate the relationship between shear wave elastography (SWE) elasticity indices of papillary thyroid carcinoma (PTC) and central lymph node metastasis (CLNM) and to evaluate the value of SWE combined with gray-scale ultrasound (US) for predicting preoperative CLNM. Method This study included 172 patients with a pathology diagnosis of PTC who underwent preoperative gray-scale US and SWE evaluation. Patients were divided into CLNM-positive and CLNM-negative groups. We analyzed the association between SWE elasticity indices (Emax, Emean and Emin) and CLNM, compared the diagnostic efficacy of gray-scale US alone versus SWE combined with gray-scale US for predicting CLNM, and analyzed the influence of Hashimoto's thyroiditis (HT) on the diagnostic efficacy of CLNM. Results SWE elasticity values Emax, Emean and Emin were significantly higher in CLNM-positive patients (P=0.000, 0.000 and 0.003, respectively). The AUC of Emax was higher than that of other SWE indices for predicting CLNM (AUC = 0.749; 95% CI = 0.676–0.822). In multivariate analysis, microcalcification (OR = 5.254; 95% CI = 2.496–11.061), extrathyroidal extension (OR = 4.210; 95% CI = 1.423–12.456), multifocality (OR = 3.084; 95% CI = 1.190–7.991) and Emax >59.0 kpa (OR = 4.934; 95% CI = 2.318–10.500) were independent risk factors for predicting CLNM. The AUC of SWE combined with gray-scale US for predicting CLNM (AUC = 0.825; 95% CI = 0.760–0.879) was significantly higher (P = 0.011) than that for gray-scale US alone (AUC = 0.774; 95% CI = 0.704–0.834). There was no significant difference in AUC between the HT and non-HT subgroups in predicting CLNM (0.798 vs. 0.833, P = 0.640). Conclusions SWE can be used to predict CLNM in PTC patients. SWE combined with gray-scale US can improve the prediction of CLNM.

Objective To assess the performance of conventional ultrasound (US) combined with strain elastography (SE) in the Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions on mammography. Methods Women with breast lesions identified as having mammography BI-RADS 4 lesions and underwent US examination were included in China. US features and US BI-RADS assessment were recorded in real-time and prospectively reported. The pathological result was referred to as the gold standard. The performance of US in the mammographic BI-RADS category 4 lesions was evaluated. Diagnostic performances of US BI-RADS, SE and combined both were compared. Results 751 women with 751 breast lesions classified as mammographic BI-RADS category 4 were included. For mammographic findings, 530 (70.6%) were true-positive and 221 (29.4%) were false-positive. Conventional US achieved higher positive predictive value (PPV) than mammography (78.5% vs 70.6%, p=0.001). The specificity increased from 34.4% to 47.1% (p Conclusions Conventional US combined with SE is a helpful tool for the non-invasive examination of breast lesions classified as BI-RADS category 4 on mammography. It helped increase the PPV and had the potential to avoid unnecessary biopsies of BI-RADS category 4 lesions detected on mammography. Micro Abstract We assessed the performance of conventional ultrasound (US) combined with strain elastography (SE) in the Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions on mammography. 751 women with 751 breast lesions classified as mammographic BI-RADS category 4 were included. Conventional US combined with SE helped increase the PPV and had the potential to avoid unnecessary biopsies of BI-RADS category 4 lesions detected on mammography.

Primary mucinous tumors of the testis and paratestis are very rare, with only 29 reported cases detected in a PubMed search. The histopathological characteristics of primary testicular mucinous tumors are similar to their ovarian counterparts, and the diagnosis and naming criteria refer to the criteria for female ovarian mucinous tumors. However, the clinical and imaging features of primary testicular mucinous tumors are poorly understood, and they are thus frequently undiagnosed or misdiagnosed. We present the case of a patient with a primary testicular mucinous tumor. A 52-year-old man presented with a 1-year history of painless enlargement of the left scrotum. Ultrasound examination revealed a cystic mass in the left testis, with viscous fluid areas and calcified spots, irregular solid bulges on the cyst wall, and a small blood supply. Serum alpha-fetoprotein, β-human chorionic gonadotropin, lactate dehydrogenase, renal function, inflammatory markers, and routine urine and blood examinations were all normal. The patient underwent radical resection of the left testis. Postoperative pathology showed a multilocular cystic mass, with the inner wall of the sac lined with mucous columnar epithelial cells, some with mild nuclear atypia, and no interstitial infiltration. The pathological diagnosis was testicular mucinous tumor. Postoperative abdominal and pelvic computed tomography, colonoscopy, and gastroscopy showed no suspicious lesions. The final diagnosis was primary testicular borderline mucinous tumor. The patient underwent postoperative follow-up examinations once a year for 4 years. Serum tumor markers, scrotal ultrasound, abdominal and pelvic computed tomography scans, and colonoscopy and gastroscopy revealed no evidence of metastases or other primary adenocarcinoma. This case highlights the clinical and imaging characteristics of primary testicular mucinous tumors, which might aid their differential diagnosis.

To investigate the effectiveness of shear-wave elastography (SWE) based on e-health in diagnosing liver fibrosis in patients infected with hepatitis B virus (HBV) and provide theoretical basis for early diagnosis and treatment of patients with chronic HBV infection, in this study, 73 patients with chronic HBV infection who underwent e-health SWE examination were divided into chronic hepatitis B group (51 cases) and hepatitis B cirrhosis group (22 cases), and another 20 healthy volunteers were introduced as control. The contents of second liver two half-and-half, hyaluronic acid (HA) of liver fibrosis, laminin (LN), pAUVollagen III N terminal peptide (PIII NP), collage type IV (CIV), and HBV-DNA were detected. SWE was used to measure the elastic modulus in the S2 and S3 segments of the left outer lobe of the liver, S4 segment of the left inner lobe of the liver, S5 and S8 segments of the right anterior lobe of the liver, and S6 and S7 segments of the right posterior lobe of the liver. Finally, the correlations between the four examination results of liver fibrosis and the elastic modulus values were compared, and the receiver operator characteristic curve (ROC) for SWE technical diagnosis was drawn. The results showed that there was no significant difference in HBV-DNA content between the two groups ( P > 0.05 ); the contents of alanine transaminase (ALT) and aspartate aminotransferase (AST) in the blood of chronic hepatitis B group were significantly higher than those in the liver cirrhosis group ( P < 0.05 ); HA, PIII NP, and CIV contents were significantly lower than the liver cirrhosis group ( P < 0.05 ); the success rates of SWE detection in S5 and S6 segments of the two groups were 100.00%, and the elastic modulus of the hepatitis B cirrhosis group was significantly higher than that of the chronic hepatitis B group ( P < 0.05 ); correlation results showed HA, PIII NP, and CIV of two groups of patients and elastic modulus value in S5 and S6 segments showed positive correlation ( P < 0.05 ); ROC curve analysis showed that AUC (area under the curve) was 0.866, the sensitivity was 89.59%, and the specificity was 76.49%, which indicated that the liver elastic modulus value measured by e-health SWE technology can quantitatively show liver fibrosis in patients with chronic HBV infection, and its application in the diagnosis of clinical liver fibrosis was real and feasible.

Background/aim: This study aimed to investigate the impact of blood pressure and sex on heart-vessel coupling in patients with essential hypertension via ultrasound. Materials and methods: We studied 76 patients with essential hypertension (48 males and 28 females) and 65 healthy controls (33 males and 32 females). Coupling parameters were obtained using ultrasound technology combined with brachial artery blood pressure measurement. Results: The Ea and Ees were higher in the hypertension group than in the control group (P < 0.01), with no statistically significant difference in Ea/Ees between the two groups (P >0.05). After subjects were classified by sex, the Ea and Ees of males and females in the hypertension group were higher than those in the control group (P < 0.05 or P < 0.01), while the Ea/Ees was lower in hypertensive females than in control females (P < 0.05). Conclusion: In female patients with essential hypertension, heart-vessel coupling was easily damaged, and systolic blood pressure was associated with heart-vessel coupling damage to some extent.

INTRODUCTION The aim of the study was to investigate the structure and function of the carotid artery in patients with hyperthyroidism by ultrasound radio frequency data technology (RF data) and the effect of (131)I on them. MATERIAL AND METHODS Seventy patients with primary hyperthyroidism and 74 healthy volunteers were enrolled in this study. Structural and functional parameters of the common carotid artery were measured in every patient before and after (131)I treatment through the RF data, such as intima media thickness (IMT), functional compliance coefficient (CC), stiffness index (β), and pulse wave velocity (PWV). We also analyzed the correlation between these parameters and patients' age, body mass index, hemodynamic parameters (blood pressure, heart rate), thyroid hormone levels and other risk factors. RESULTS There was a significant difference in IMT between hyperthyroid patients and the control group at baseline (483.6 vs. 443.3 µm, p < 0.01); after treatment, the IMT decreased significantly (428.7 vs. 483.6 µm, p < 0.001). Furthermore, the IMT was correlated with patients' age and systolic blood pressure (r = 0.525, p < 0.01 and r = 0.289, p < 0.05, respectively). The β and PWV were also higher than the control group (7.26 vs.5.87, 6.27 vs. 5.57 m/s, respectively; all p < 0.001); CC was lower than the control group (0.98 vs. 1.19 mm(2)/KPa, p < 0.01); after treatment, PWV and β were lower than baseline (5.66 vs. 6.27, 5.81 vs. 7.26 m/s, respectively; all p < 0.01), and CC was higher than baseline. In addition, they were significantly correlated with age (r = 0.525, p < 0.01 and r = 0.289, p < 0.05, respectively). However, these parameters were not correlated with the level of thyroid hormones. CONCLUSIONS Six-month (131)I treatment for patients with hyperthyroidism reverses the structural and functional damage in the carotid artery, which is sensitively evaluated by the RF data technique.

The aim of the present study was to evaluate the changes in radiofrequency ultrasound local estimator (RULES) images with different instrument settings. An Esaote Technos MPX Color Doppler Ultrasound Machine and RULES were used to capture images of a gallbladder model. The percentages of various colored areas (color filling rates) within the area of interest were calculated using different instrument gains, transducer frequencies and scan depths. Blue was predominant in the lumen of the model gallbladder, while red and green were primarily located near the inner edge of the lumen. When the depth was set at 62 mm and the gain at 105, the total color filling rates did not vary with different transducer frequencies. The blue color filling rate was greatest with a transducer frequency of 8.0 MHz, and the red and green color filling rates were greatest with a frequency of 12.5 MHz. Color variety was greatest when the transducer frequency was 12.5 MHz. When the transducer frequency was 12.5 MHz and the depth was 62 mm, the blue color filling rate was greatest with gains of 105 and 110, the red color filling rate was greatest with gains of 95 and 100 and the green color filling rate was greatest when the gain was 100. The total color filling rate was greatest at gains of 100 and 105. In conclusion, images obtained using RULES may be affected by the instrument gain and, to a certain extent, by transducer frequency.

Objectives We sought to summarize the features of radiofrequency ultrasonic local estimator (RULES) images of benign and malignant masses and to explore the diagnostic value of RULES scores to identify breast lumps. Methods A total of 81 women with a mean age ± SD of 41.33 ± 12.03 years (range, 19-68 years) with 82 lesions seen at our hospital were included in this study. Inclusion criteria were Breast Imaging Reporting and Data System grade 2 to 5 breast lesions, preoperative 2-dimensional (2D) ultrasound (US) examinations and RULES image acquisition, no treatment before the US examinations, surgical resection in our hospital, and histopathologic results. Each RULES characteristic was scored on the basis of expected values for malignant characteristics, and this RULES scoring system was assessed by a receiver operating characteristic curve. Results Of the 82 lesions, 45 were benign, and 37 were malignant. Malignancy was associated with multiple colors, red as the main color, colors distributed in 3 or more locations, aggregated colors, and more than half of the area filled with colors. A RULES score of 7 had the highest sum of sensitivity (67.6%) and specificity (95.6%) and the highest accuracy (82.9%) for diagnosis of malignancy. When 2D US imaging a Breast Imaging Reporting and Data System category of 4 was combined with a RULES score of 4 to detect breast cancer, the sensitivity was 83.8%; the specificity was 93.3%; and the accuracy increased to 89.0%. Conclusions The use of RULES images and characteristics is helpful in differentiating benign and malignant breast lesions. Diagnostic accuracy can be improved by combining 2D US imaging and RULES.

Background: The purpose of this study is to evaluate the intima-media thickness (IMT) and arterial elasticity of the common carotid artery (CCA) in patients with cerebral small vessel disease (SVD) by applying radiofrequency (RF) ultrasound technology. Methods: Fifty SVD subjects (SVD group) and fifty-three matched controls (Control group) were enrolled in the study. Structural and functional changes in the common carotid arterial wall were investigated by quality intima-media thickness (QIMT) and quanlity arterial stiffness (QAS) with a Mylab Twice ultrasound instrument. The vessel related variables between these two groups were analyzed. Results: There was a significant higher value of CCA-IMT in SVD group than that in control group (P0.05) and control group (P>0.05). Conclusions: Decreased arterial elasticity of the CCA in patients with SVD compared with normal subjects. Ultrasound RF technology can be used to non-invasively and quantitatively detect the change in the structure and function of the CCA in SVD subjects for evaluating preclinical atherosclerosis.

The purpose of this study was to investigate the effects of ultrasonic instrument gain, transducer frequency, and depth on the color variety and color filling of radiofrequency ultrasonic local estimators (RULES) images which indicated specific physical representation of liquid-containing lesions in order to find the optimal settings for the clinical application of RULES in liquid-containing lesions. Changing the ultrasonic instrument gain, transducer frequency, and depth affected the color filling and color variety of 21 pathologically-confirmed liquid-containing lesion images analyzed by RULES. Blue colored fill dominated the RULES images to represent the liquid-containing lesions. A frequency of 12.5 MHz led to red and green colors along the inner edges of the liquid-containing lesions. Changing the gain resulted in significantly different blue colored filling that was highest when the gain was 90 to 100. Changing the frequency also significantly changed the blue color filling, with the highest filling occurring at 12.5 MHz. Changing the depth did not affect the blue color filling. The liquid components of the lesions may be identified by their characteristic manifestations in RULES, where color variety is affected by transducer frequency and blue color filling which represent liquid-containing lesions in RULES images is affected by frequency and gain.