Search

PURPOSE: To evaluate a computer-aided diagnosis (CAD) technique in predicting malignancy for cytologically indeterminate thyroid nodules (TNs) as compared with different experienced radiologists. METHOD: 436 patients with 436 cytologically indeterminate TNs on fine-needle aspiration cytology (FNAC) were included and all were confirmed by surgical pathology. They were retrospectively analyzed with respect to ultrasound (US) characteristics using a commercially available CAD system (AmCAD-UT; AmCad BioMed, Taiwan, China) and reviewed by one junior and one senior radiologists.The CAD system and different experienced radiologists stratified the risk of malignancy using ACR TI-RADS category. The diagnostic performance by different experienced radiologists independently and after consulting the CAD (different experienced radiologists + CAD) and by the CAD alone were compared. RESULTS: The different experienced radiologists showed significantly higher specificities than the CAD system alone. The combination of radiologist and CAD system showed improved diagnostic performance with an AUC (Area under the curve) of 0.740 in the senior radiologist and 0.677 in the junior radiologist, as compared with CAD (AUC: 0.585) alone (all P

BACKGROUND: Ultrasound-guided fine-needle aspiration (US-FNA) is the most accurate method for preoperative diagnosis of thyroid nodules, but how to deal with false negative results? OBJECTIVE: This study aimed to find preoperative diagnosis methods including Conventional Ultrasound (CUS), Shear Wave Elastography (SWE) and BRAF V600E testing to differentiate false negative nodules. METHODS: Forty-nine nodules in 49 patients with benign FNA results and pathological diagnoses were included. CUS and SWE features were evaluated. BRAF V600E analysis was performed after FNA. Diagnostic performances of three methods were analyzed in predicting malignancy in benign FNA results. RESULTS: Twenty-seven of 49 nodules were malignant, and 22 nodules were benign. Hypoechogenicity, taller-than-wider, irregular boundary, microcalcification, SWE max, SWE mean and BRAF V600E mutation were risk factors for malignancy. All 7 malignant nodules with BRAF V600E mutations and 18 of 20 malignant nodules without BRAF V600E mutations have two or more suspicious CUS features. Six of 7 malignant nodules with BRAF V600E mutations and 16 of 20 malignant nodules without BRAF V600E mutations had SWE mean value greater than the cut-off value. CONCLUSIONS: CUS, SWE and BRAF V600E were diagnostic tools for malignancy in FNA benign nodules. Further clinical decisions should be considered for nodules with two or more suspicious CUS features and SWE parameters greater than cut-off values whether BRAF V600E is mutational or not.

Background: The similar visual appearance of superficial basal cell carcinoma (sBCC) and Bowen's disease (BD) may cause confusion for diagnosis. Objective: To investigate the value of ultra-high frequency ultrasound (uHFUS) in differentiating sBCC from BD. Materials and methods: This prospective study included a pilot cohort of 110 patients (73 BDs and 37 sBCCs) from November 2016 to October 2020 and a validation cohort of 42 patients (30 BDs and 12 sBCCs) from July 2021 to December 2021. Clinical and uHFUS features of pathologically confirmed sBCC and BD were assessed. A predictive model was developed based on the HFUS features of the pilot cohort. Subsequently, the model was validated and compared with clinical diagnosis in the validation cohort. Results: uHFUS features with significant differences between sBCC and BD included lesion surface, skin layer involvement, hyperkeratosis, and hyperechoic spots (all p < 0.05). A prediction model based on the above features was established to identify sBCC and BD in the pilot and validation cohorts with the areas under the curve (AUC) of 0.908 and 0.923, sensitivity of 82.3% and 83.3%, specificity of 91.9% and 91.7%, accuracy of 85.5% and 85.7%, respectively, which was significantly higher than those obtained by clinical diagnosis based on photographic pictures of lesions, with the AUC of 0.692, sensitivity of 63.3%, specificity of 75.3%, and accuracy of 66.7% (all p < 0.05). Conclusion: uHFUS provides detailed internal features of sBCC and BD, which facilitates the differentiation between sBCC and BD and its diagnostic performance is superior to clinical diagnosis.

The similar visual appearance of high-risk basal cell carcinoma (BCC) and cutaneous squamous cell carcinoma (cSCC) may cause confusion for diagnosis. High-frequency ultrasound (HFUS) may provide additional intralesional information and thus help to distinguish them.In this retrospective study, we analyzed the clinical characteristics, HFUS grayscale, and color Doppler flow imaging (CDFI) features of pathologically confirmed high-risk BCC and cSCC lesions (n = 65 vs n = 68). Subsequently, discrimination models based on the significant HFUS features were established.Between high-risk BCC and cSCC lesions, the HFUS grayscale features of the lesion size (10.0 mm vs 17.4 mm), thickness (3.1 mm vs 5.9 mm), internal hyperechoic spots (80.0% vs 23.5%), and posterior acoustic shadowing (16.9% vs 66.2%) were statistically different (all p 0.001). As for the CDFI features, high-risk BCC lesions mainly appeared as pattern II (47.7%), while cSCC lesions mainly appeared as pattern III (66.2%). Based on the above five features, an optimal discrimination model was established with a sensitivity of 91.2%, a specificity of 87.7%, and an accuracy of 89.5%.HFUS features, including size, thickness, internal hyperechoic spots, posterior acoustic shadowing, and Doppler vascularity pattern, are useful for differential diagnosis between high-risk BCC and cSCC.

Objective To evaluate high-frequency ultrasound (HFUS) features for diagnosing cutaneous squamous cell carcinoma (cSCC) as a spectrum of progressively advanced malignancies, including precursor actinic keratosis (AK), Bowen's disease (BD), and invasive squamous cell carcinoma (iSCC). Method In this retrospective study, 160 skin lesions diagnosed histopathologically (54 AK, 54 BD, and 52 iSCC) in 160 patients were included. The HFUS features of AK, BD, and iSCC were analyzed. The obtained data were evaluated using univariate and forward multivariate logistic regression analyses. Results The most significant HFUS features in AK were regular surface (odds ratio [OR], 8.42) and irregular basal border (OR, 6.36). The most significant HFUS features in BD were crumpled surface (OR, 19.62) and layer involvement confined to the epidermis (OR, 3.96). The most significant HFUS features in iSCC were concave surface (OR, 27.06), stratum corneum (SC) detachment (OR, 14.41), irregular basal border (OR, 4.01), and convex surface (OR, 3.73). The characteristics of surface features, basal border, and layer involvement could be valuable HFUS clues in the discrimination of AK, BD, and iSCC. Conclusion High-frequency ultrasound is valuable for the differentiation of AK, BD, and iSCC, which may allow dynamic and noninvasive monitoring in the spectrum of cSCC.

The purpose of this study was to develop, validate and test a prediction model for discriminating malignant from benign breast lesions using conventional ultrasound (US), US elastography of strain elastography and contrast-enhanced ultrasound (CEUS). The study included 454 patients with breast imaging-reporting and data system (BI-RADS) category 4 breast lesions identified on histologic examinations. Firstly, 228 breast lesions (cohort 1) were analyzed by logistic regression analysis to identify the risk factors, and a breast malignancy prediction model was created. Secondly, the prediction model was validated in cohort 2 (84 patients) and tested in cohort 3 (142 patients) by using analysis of the area under the receiver operating characteristic curve (AUC). Univariate regression indicated that age ≥40 y, taller than wide shape on US, early hyperenhancement on CEUS and enlargement of enhancement area on CEUS were independent risk factors for breast malignancy (all p0.05). The logistic regression equation was established as follows: p = 1/1+Exp∑[-5.066 + 3.125 x (if age ≥40 y) + 1.943 x (if taller than wide shape) + 1.479 x (if early hyperenhancement) + 4.167 x (if enlargement of enhancement area). The prediction model showed good discrimination performance with an AUC of 0.967 in cohort 1, 0.948 in cohort 2 and 0.920 in cohort 3. By using the prediction model to selectively downgrade category 4a lesions, the re-rated BI-RADS yield an AUC of 0.880 (95% confidence interval [CI], 0.794-0.965) in cohort 2 and 0.870 (95% CI, 0.801-0.939) in cohort 3. The specificity increased from 0.0% (0/35) to 80.0% (28/35) without loss of sensitivity (from 100.0% to 95.9%, p = 0.153) in cohort 2. Similarly, the specificity increased from 0.0% (0/58) to 77.6% (45/58) without loss of sensitivity (from 100.0% to 96.4%, p = 0.081) in cohort 3. Multimodal US showed good diagnostic performance in predicting breast malignancy of BI-RADS category 4 lesions. Although the loss of sensitivity was existing, the addition of multimodal US to US BI-RADS could improve the specificity in BI-RADS category 4 lesions, which reduced unnecessary biopsies.

Objectives To compare the imaging findings of Bowen's disease (BD) between ultrasound biomicroscopy (UBM) and conventional high-frequency ultrasound (HFUS). Methods A total of 29 pathologically proven BD lesions in 28 patients were retrospectively enrolled in the study, and all were after surgery. All the lesions were imaged with both UBM and HFUS. The imaging features on HFUS and UBM were analyzed and compared. The diagnostic results of ultrasound for BD were referenced with pathology results. Results All the 29 (100%) BD lesions appeared hypoechogenicity, solid component, and superficial hyperechoic layer (ie, keratinization) on both UBM and HFUS. The typical imaging feature of BD lesions, that was, infiltration depth confined to the epidermis, was visualized in 25 (86.2%, 25/29) lesions on UBM whereas 15 (51.7%, 15/29) on HFUS (P = .002). A "wave sign," which corresponds to the surface keratinization of BD lesion, was visualized in 17 (58.6%, 17/29) of BD lesions on UBM whereas 6 (20.7%, 6/29) on HFUS (P = .001). UBM and HFUS correctly diagnosed 25 (86.2%, 25/29) and 15 (51.7%, 15/29) BD lesions, respectively (P = .002). Conclusions Bowen's disease has some typical imaging features on US. The "wave sign" of the superficial hyperechoic layer and the clear borderline between the tumor in epidermis and the slightly hyperechoic dermis layer are better depicted by UBM in comparison with HFUS, which leads to a more accurate diagnosis of BD. UBM has potential to be used as a diagnostic tool for characterization of BD on account of its high resolution.

To investigate the value of ultrasound (US) and clinicopathological features of papillary thyroid cancer (PTC) in predicting Telomerase Reverse Transcriptase (TERT) promoter mutations. Preoperative US images of 351 surgically confirmed PTCs were evaluated in terms of PTCs size and US features. The basic clinicopathological features were also retrieved. Univariate and multivariate analyses were performed to identify the risk factors for TERT promoter mutations. A scoring system was developed based on the cumulative number of risk factors. The area under the receiver operating characteristic curve (AUC) and cut-off value were calculated to evaluate the diagnostic performance of the scoring system for predicting TERT promoter mutations. TERT promoter mutations were found in 4.84% (17/351) of patients with PTCs. Patient age >50 years (OR: 6.244, P = 0.006), multifocality (OR: 21.071, P = 0.022), taller-than-wide shape (OR: 4.934, P = 0.029), microlobulated margin (OR: 4786, P = 0.032), and capsule contact or involvement (OR: 4.668, P = 0.030) were independent risk factors for TERT promoter mutations. TERT promoter mutations were relevant to more suspicious US and clinicopathological features than TERT promoter wild-type PTC (median, 4 vs. 1, P

Thyroid nodules have a high prevalence and a small percentage is malignant. Many non-invasive methods have been developed with the help of the Internet of Things to improve the detection rate of malignant nodules. These methods can be roughly categorized into two classes: radiomics based and deep learning based approaches. In general, convolutional neural networks based deep learning methods have achieved promising performance in many medical image analysis and classification applications; however, no existing comparison has been done between radiomics based and deep learning based approaches. Therefore, in this paper, we aim to compare the performance of radiomics and deep learning based methods for the classification of thyroid nodules from ultrasound images. On one hand, we developed a radiomics based method, which consists of extracting high throughput 302-dimensional statistical features from pre-processed images. Then dimension reduction was performed using mutual information and linear discriminant analysis respectively to achieve the final classification. On the other hand, a deep learning based method was also developed and tested by pre-training a VGG16 model with fine-tuning. Ultrasound images including 3120 images (1841 benign nodules and 1393 malignant nodules) from 1040 cases were retrospectively collected. The dataset was divided into 80% training and 20% testing data. The highest accuracies yielded on the testing data for radiomics and deep learning based methods were 66.81% and 74.69%, respectively. A comparison result demonstrated that the deep learning based method can achieve a better performance than using radiomics.

To evaluate the feasibility of a 5G-based telerobotic ultrasound (US) system for thyroid examination on a rural island.From September 2020 to March 2021, this prospectively study enrolled a total of 139 patients (average age, 58.6 ± 12.7 years) included 33 males and 106 females, who underwent 5G-based telerobotic thyroid US examination by a tele-doctor at Shanghai Tenth People's Hospital and a conventional thyroid US examination at Chongming Second People's Hospital 84 km away. The clinical feasibility of 5G-based telerobotic US for thyroid examination were evaluated in terms of safety, duration, US image quality, diagnostic results, and questionnaire survey.92.8% of patients had no examination-related complaints. The average duration of the 5G-based telerobotic US examination was similar as that of conventional US examination (5.57 ± 2.20 min vs. 5.23 ± 2.1 min, P = 0.164). The image quality of telerobotic US correlated well with that of conventional US (4.63 ± 0.60 vs. 4.65 ± 0.61, P = 0.102). There was no significant difference between two types of US examination methods for the diameter measurement of the thyroid, cervical lymph nodes, and thyroid nodules. Two lymphadenopathies and 20 diffuse thyroid diseases were detected in two types of US methods. 124 thyroid nodules were detected by telerobotic US and 127 thyroid nodules were detected by conventional US. Among them, 122 were the same thyroid nodules. In addition, there were good consistency in the US features (component, echogenicity, shape, and calcification) and ACR TI-RADS category of the same thyroid nodules between telerobotic and conventional US examinations (ICC = 0.788-0.863). 85.6% of patients accepted the telerobotic US, and 87.1% were willing to pay extra fee for the telerobotic US.The 5G-based telerobotic US system can be a routine diagnostic tool for thyroid examination for patients on a rural island.

BACKGROUND: To evaluate whether MicroPure imaging, an ultrasound (US) image-processing technique with computer-aided analysis, can quantitatively detect crystal dissolution during urate-lowering therapy (ULT) in gout. METHODS: This was a prospective study of gout patients requiring ULT. The first metatarsophalangeal joints were examined using US and MicroPure before and after 3 months of ULT. Elementary lesions of gout, including the double contour sign (DCS), aggregates, tophi, erosion, and other US features were recorded at baseline and 3 months. MicroPure imaging features were automatically calculated by a self-developed software. Patients were divided into goal-achieved and goal-not-achieved groups according to their urate levels at 3 months. The US and MicroPure imaging features of the two groups were analyzed at baseline and 3 months. RESULTS: A total of 55 consecutive patients were enrolled (25: goal-achieved group; 30: goal-not-achieved group). US findings demonstrated that the power Doppler signal grade decreased at 3 months, regardless of the group (both P0.05). CONCLUSIONS: In comparison with B-mode US, computer-aided MicroPure imaging can sensitively and quantitatively detect aggregate dissolution during effective ULT after only 3 months of treatment.

Combined checkpoint blockade (e.g., PD1/PD-L1) with traditional clinical therapies can be hampered by side effects and low tumour-therapeutic outcome, hindering broad clinical translation. Here we report a combined tumour-therapeutic modality based on integrating nanosonosensitizers-augmented noninvasive sonodynamic therapy (SDT) with checkpoint-blockade immunotherapy. All components of the nanosonosensitizers (HMME/R837@Lip) are clinically approved, wherein liposomes act as carriers to co-encapsulate sonosensitizers (hematoporphyrin monomethyl ether (HMME)) and immune adjuvant (imiquimod (R837)). Using multiple tumour models, we demonstrate that combining nanosonosensitizers-augmented SDT with anti-PD-L1 induces an anti-tumour response, which not only arrests primary tumour progression, but also prevents lung metastasis. Furthermore, the combined treatment strategy offers a long-term immunological memory function, which can protect against tumour rechallenge after elimination of the initial tumours. Therefore, this work represents a proof-of-concept combinatorial tumour therapeutics based on noninvasive tumours-therapeutic modality with immunotherapy., Immunotherapy for the treatment of cancer can be complicated by side effects and poor efficacy. Here, the authors use a nanoparticle-based approach in combination with a TLR7 agonist and sonodynamic therapy, and find that when used together with anti-PD-L1, tumour formation and metastases are impacted.

B-mode ultrasound (BUS) imaging is a routine tool for diagnosis of liver cancers, while contrast-enhanced ultrasound (CEUS) provides additional information to BUS on the local tissue vascularization and perfusion to promote diagnostic accuracy. In this work, we propose to improve the BUS-based computer aided diagnosis for liver cancers by transferring knowledge from the multi-view CEUS images, including the arterial phase, portal venous phase, and delayed phase, respectively. To make full use of the shared labels of paired of BUS and CEUS images to guide knowledge transfer, support vector machine plus (SVM+), a specifically designed transfer learning (TL) classifier for paired data with shared labels, is adopted for this supervised TL. A nonparallel hyperplane based SVM+ (NHSVM+) is first proposed to improve the TL performance by transferring the per-class knowledge from source domain to the corresponding target domain. Moreover, to handle the issue of multi-source TL, a multi-kernel learning based NHSVM+ (MKL-NHSVM+) algorithm is further developed to effectively transfer multi-source knowledge from multi-view CEUS images. The experimental results indicate that the proposed MKL-NHSVM+ outperforms all the compared algorithms for diagnosis of liver cancers, whose mean classification accuracy, sensitivity, and specificity are 88.18 ± 3.16 %, 86.98 ± 4.77 %, and 89.42±3.77%, respectively.

Purpose: This prospective study explored the value of synchronous tele-ultrasound (US) to aid doctors inexperienced in US with breast US examinations.Methods: In total, 99 patients were enrolled. Two trainee doctors who were inexperienced in US (trainee A [TA] and trainee B [TB]) and one doctor who was an expert in US completed the US examinations sequentially. TA completed the US examinations independently, while TB was instructed by the expert using synchronous tele-US. Subsequently, the expert performed on-site US examinations in person. Separately, they selected the most clinically significant nodule as the target nodule. Consistency with the expert and image quality were compared between TA and TB to evaluate tele-US. Furthermore, TB and the patients evaluated tele-US through questionnaires.Results: TB demonstrated higher consistency with the expert in terms of target nodule selection than TA (93.3% vs. 63.3%, P0.75) with the expert on five US features (5/9, 55.6%), while TA only did so for one (1/9, 11.1%) (P=0.046). TB’s image quality was higher than TA’s in gray value, time gain compensation, depth, color Doppler adjustment, and the visibility of key information (P=0.018, P

OBJECTIVES Pathological invasion level of extramammary Paget disease (EMPD) is strongly related with its risk staging, treatment, and prognosis. However, the current evaluation before treatments fails to evaluate pathological invasion level of EMPD. High-frequency ultrasound (HFUS) may play a key role to solve this problem. The purpose was to explore the performance of HFUS in the evaluation of pathological invasion level of EMPD. METHODS Sixty pathologically proven EMPD patients were retrospectively enrolled and divided into 2 groups as follows: in situ in the epidermis (IE) (n = 42) and invasion into the dermis or subcutaneous (ID) (n = 18) groups. Clinical and HFUS features were compared between the 2 groups. RESULTS Between the 2 groups, HFUS features (lesion shape, internal echogenicity and echotexture, surface shape, epidermal hyperechoic layer on the surface, the "pseudopod sign", and color Doppler ultrasound features) and clinical features were comparable (all P >.05). Tumor growth pattern significantly differed between the 2 groups (P

Objectives: Ultrasound-guided fine-needle aspiration (FNA) is the most accurate and economical means for the differential diagnosis of thyroid nodules, but false negative results also existed. This study aimed to predict the false negative results of FNA, reduce the missed diagnosis and improve the current management strategy of thyroid nodules. Methods: A total of 1232 consecutive patients with thyroid nodules who received FNA and BRAF V600E detection were adopted. All patients received both CUS (conventional ultrasound) and SWE (shear wave elastography) examinations and characteristics of these thyroid nodules were analyzed to evaluated the diagnostic performances of risk factors for malignancy.Results: Finally, 26 nodules with benign cytology and BRAF V600E mutations were enrolled. Undefined boundary, microcalcification and E max ratio > 1.49 were risk factors for malignancy (P 1.49 respectively. There was no difference between benign and malignant nodules in the patient age, sex and nodule sizes (P>0.05).Conclusions: Undefined boundary, microcalcification and E max ratio > 1.49 were risk factors for malignancy in benign cytology nodules. When FNA results were benign but above characteristics could be found in the thyroid nodules with BRAF V600E mutation, further clinical decisions should be carried out to reduce the missed diagnosis.

BACKGROUND Esophageal varices (EV) are the most fatal complication of chronic hepatitis B (CHB) related cirrhosis. The prognosis is poor, especially after the first upper gastrointestinal hemorrhage. AIM To construct nomograms to predict the risk and severity of EV in patients with CHB related cirrhosis. METHODS Between 2016 and 2018, the patients with CHB related cirrhosis were recruited and divided into a training or validation cohort at The First Affiliated Hospital of Wenzhou Medical University. Clinical and ultrasonic parameters that were closely related to EV risk and severity were screened out by univariate and multivariate logistic regression analyses, and integrated into two nomograms, respectively. Both nomograms were internally and externally validated by calibration, concordance index (C-index), receiver operating characteristic curve, and decision curve analyses (DCA). RESULTS A total of 307 patients with CHB related cirrhosis were recruited. The independent risk factors for EV included Child-Pugh class [odds ratio (OR) = 7.705, 95% confidence interval (CI) = 2.169-27.370, P = 0.002], platelet count (OR = 0.992, 95%CI = 0.984-1.000, P = 0.044), splenic portal index (SPI) (OR = 3.895, 95%CI = 1.630-9.308, P = 0.002), and liver fibrosis index (LFI) (OR = 3.603, 95%CI = 1.336-9.719, P = 0.011); those of EV severity included Child-Pugh class (OR = 5.436, 95%CI = 2.112-13.990, P < 0.001), mean portal vein velocity (OR = 1.479, 95%CI = 1.043-2.098, P = 0.028), portal vein diameter (OR = 1.397, 95%CI = 1.021-1.912, P = 0.037), SPI (OR = 1.463, 95%CI = 1.030-2.079, P = 0.034), and LFI (OR = 3.089, 95%CI = 1.442-6.617, P = 0.004). Two nomograms (predicting EV risk and severity, respectively) were well-calibrated and had a favorable discriminative ability, with C-indexes of 0.916 and 0.846 in the training cohort, respectively, higher than those of other predictive indexes, like LFI (C-indexes = 0.781 and 0.738), SPI (C-indexes = 0.805 and 0.714), ratio of platelet count to spleen diameter (PSR) (C-indexes = 0.822 and 0.726), King's score (C-indexes = 0.694 and 0.609), and Lok index (C-indexes = 0.788 and 0.700). The areas under the curves (AUCs) of the two nomograms were 0.916 and 0.846 in the training cohort, respectively, higher than those of LFI (AUCs = 0.781 and 0.738), SPI (AUCs = 0.805 and 0.714), PSR (AUCs = 0.822 and 0.726), King's score (AUCs = 0.694 and 0.609), and Lok index (AUCs = 0.788 and 0.700). Better net benefits were shown in the DCA. The results were validated in the validation cohort. CONCLUSION Nomograms incorporating clinical and ultrasonic variables are efficient in noninvasively predicting the risk and severity of EV.

Objectives: The aim of this study was to develop an ultrasound consolidated score (UCS) in determining the activity of Crohn’s disease (CD) and evaluate it with reference to simple endoscopic score (SES). Methods: From June 2014 to June 2017, 66 patients with CD were retrospectively enrolled in this study. Each patient underwent endoscopy and transabdominal ultrasound (US) examination. The morphological symmetry, echogenicity of bowel wall, bowel wall layer structure, echogenicity of peri-bowel fat, bowel wall thickness (BWT), and Limberg type on power Doppler US were assessed with transabdominal US, and an UCS scoring system was developed based on these characteristics. Endoscopic results were used as the reference standard and SES was calculated to determine the CD activity. Receiver operating characteristic curve analysis was performed to assess the diagnostic performance for determining CD activity and the correlation between UCS and SES was assessed using Spearman correlation analysis. Results: 330 intestinal segments in 66 patients were included. The UCS of the segments in the remission phase ranged from 3.0 to 9.0 (mean, 3.6 ± 0.9) whereas in the active phase from 3.0 to 20.0 (mean, 10.6 ± 4.0) (p < 0.001). The cut-off value of UCS was 6. The associated area under ROC curve, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.980, 88.3%, 95.5%, 93.8%, 91.3%, and 92.3%, respectively. The correlation coefficient between UCS and SES was 0.90, which was higher than the correlation coefficient of 0.83 between BWT and SES. Conclusions: The newly developed UCS with transabdominal US has a good performance and potentially provides an effective alternative for evaluating the activity of CD. Advances in knowledge: UCS is an effective method to evaluate the activity of CD because it provides comprehensive information of the disease. Therefore, it could be employed as an alternative for diagnosis of CD.

Objectives The purpose of this study was to establish a scoring system for predicting axillary lymph node metastasis (ALNM) in patients with breast invasive ductal carcinoma with negative axillary ultrasound (US) results. Methods In this retrospective study, 156 breast invasive ductal carcinoma lesions from 156 women were retrospectively enrolled. The features of conventional US and contrast-enhanced ultrasound (CEUS) qualitative enhancement patterns and quantitative enhancement parameters were analyzed. Subsequently, a scoring system was created by a multivariate logistic regression analysis. Results The results found that 60 patients (38%) showed ALNM. A scoring system was defined as risk score = 1.75 × (if lesion size ≥20 mm) + 1.93 × (if uncircumscribed margin shown on conventional US) + 1.77 × (if coarse or twisting penetrating vessels shown on CEUS). When the risk scores were less than 1.75, 1.75 to 1.93, 1.94 to 3.70, and 3.70 or higher, the risk rates of ALNM were 0% (0 of 9), 10.7% (5 of 46), 29.2% (14 of 48) and 77.4% (41 of 53), respectively. In comparison with conventional US alone, the scoring system using the combination of conventional US and CEUS showed better discrimination ability in terms of the area under the curve (0.830 versus 0.777; P = .037). Conclusions A scoring system based on conventional US and CEUS may improve the prediction of ALNM.

OBJECTIVE To compare the diagnostic performance and the unnecessary biopsy rates for recommending fine needle aspiration (FNA) of Thyroid Imaging Reporting and Data Systems proposed by American College of Radiology (ACR TI-RADS), American Thyroid Association (ATA) guidelines, TI-RADS proposed by Kwak (Kwak TI-RADS), and Korean Thyroid Association/Korean Society of Thyroid Radiology (KTA/KSThR) guidelines for malignancy risk stratification of thyroid nodules (TNs). METHODS The study included 1271 TNs whose cytologic results or surgical pathologic findings were available. Ultrasound images of these TNs were retrospectively reviewed and categorized according to the four guidelines. The diagnostic performances and the unnecessary biopsy rates for recommending FNA of the four guidelines were evaluated. RESULTS After multivariate analysis, the most significant independent predictor for malignancy was hypoechogenicity/marked hypoechogenicity (OR: 9.37, 95% CI: 5.40-16.26) (P

OBJECTIVE With the fast development of artificial intelligence techniques, we proposed a novel two-stage multi-view learning framework for the contrast-enhanced ultrasound (CEUS) based computer-aided diagnosis for liver tumors, which adopted only three typical CEUS images selected from the arterial phase, portal venous phase and late phase. MATERIALS AND METHODS In the first stage, the deep canonical correlation analysis (DCCA) was performed on three image pairs between the arterial and portal venous phases, arterial and delayed phases, and portal venous and delayed phases respectively, which then generated total six-view features. While in the second stage, these multi-view features were then fed to a multiple kernel learning (MKL) based classifier to further promote the diagnosis result. Two MKL classification algorithms were evaluated in this MKL-based classification framework. We evaluated proposed DCCA-MKL framework on 93 lesions (47 malignant cancers vs. 46 benign tumors). RESULTS The proposed DCCA-MKL framework achieved the mean classification accuracy, sensitivity, specificity, Youden index, false positive rate, and false negative rate of 90.41 ± 5.80%, 93.56 ± 5.90%, 86.89 ± 9.38%, 79.44 ± 11.83%, 13.11 ± 9.38% and 6.44 ± 5.90%, respectively, by soft margin MKL classifier. CONCLUSION The experimental results indicate that the proposed DCCA-MKL framework achieves best performance for discriminating benign liver tumors from malignant liver cancers. Moreover, it is also proved that the three-phase CEUS image based CAD is feasible for liver tumors with the proposed DCCA-MKL framework.

To evaluate the value of ultrasound (US) in differentiating the acute phase of gout from the intercritical phase, particularly using shear wave elastography (SWE). 57 gout patients were prospectively enrolled and divided into acute phase and intercritical phase groups. The patients underwent US and SWE examinations for the first metatarsophalangeal joints with the same protocol. Maximum synovial thickness was measured. US features were reviewed by two radiologists independently. The maximum (Emax) and mean (Emean) elastic moduli of synovium were calculated. Diagnostic performances of US, SWE and combined US and SWE were evaluated. US findings demonstrated that the colour Doppler flow signal grade in the acute phase was higher than that in the intercritical phase (p = 0.001), whereas no differences were found for B-mode US features between the two groups (all p > 0.05). For SWE, Emax and Emean were significantly higher in the intercritical phase than in the acute phase (both p < 0.001). The areas under the receiver operating characteristic curve (AUROCs) were 0.494–0.553 for B-mode US, 0.735 for colour Doppler US (CDUS), 0.887 for Emax and 0.882 for Emean. The combination of CDUS and SWE increased the AUROC, sensitivity and accuracy significantly in comparison with CDUS alone (all p < 0.001). However, the combined set did not show stronger diagnostic performance in comparison with SWE alone. SWE increases the diagnostic performance in differentiating the acute phase of gout from the intercritical phase in comparison with conventional US. • Colour Doppler flow signal grade is higher in acute phase of gout than in intercritical phase. • SWE demonstrates that synovium stiffness is higher in intercritical phase of gout than in acute phase. • SWE increases diagnostic performance in differentiating acute phase of gout from intercritical phase in comparison with conventional US.

To compare the sampling efficiency and diagnostic performance of ultrasound (US)-guided fine-needle aspiration cytology (FNAC) and fine-needle non-aspiration cytology (FNNAC) for thyroid nodules.629 thyroid nodules in 629 cases (477 females, 152 males) were randomly subjected to FNAC or FNNAC from Jun 2014 to Feb 2015. Diagnostic performance was calculated in reference to the histological findings or follow-up results.629 patients (152 men, 477 women) with 629 thyroid nodules were enrolled in the study. Pathological results were obtained in 173 nodules and benign nodules at FNA with more than six months' follow-up were found in 65 nodules. Tumor size for FNAC ranges from 3.0 to 51.0 mm (mean±SD; 10.2±6.9 mm); whereas FNNAC (2.0-43.0 mm; 11.9±7.7 mm). Non-diagnostic results were found in 7.59% (24/316) of FNNAC procedures and 7.59% (25/313) of FNAC (P 0.05). Determinate and indeterminate results were found in 50.63% (160/316) and 41.77% (132/316) of FNNAC procedures, whereas 58.15% (182/313) and 33.87% (106/313) of FNAC (P 0.05). In order to obtain determinate cytological results, FNAC might be more suitable than FNNAC for diagnosis of nodules with hypovascularity (51.38% vs. 41.78%, P 0.05) and macrocalcifications (9.72% vs. 6.50%, P 0.05). No US and Color-Doppler US characteristics, such as the presence of hypervascularity (P 0.05), microcalcifications (P 0.05), internal component (P 0.05), or size(P 0.05), were significantly different to obtain determinate cytological results between the FNAC and FNNAC groups. The sensitivity, specificity, positive predictive value, negative predictive value, accuracy of FNAC and FNNAC were as follows: 96.67% vs. 100%, 89.74% vs. 96.5%, 87.88% vs. 96.97%, 97.22% vs. 100%, 92.75% vs.98.36%, respectively (all P 0.05).Both FNAC and FNNAC are effective for diagnosis of thyroid nodules. However, FNAC is more effective than FNNAC to acquire determinate cytological results for nodules which US present hypovascularity and macrocalcifications.

To assess the factors associated with initial incomplete ablation (ICA) after radiofrequency ablation for benign thyroid nodules (BTNs).69 BTNs (mean volume 6.35±5.66 ml, range 1.00-25.04 ml) confirmed by fine-needle aspiration cytology (FNAC) in fifty-four patients were treated with ultrasound-guided percutaneous radiofrequency ablation (RFA) and the local treatment efficacy was immediately assessed by intra-procedural contrast-enhanced ultrasound (CEUS). The RFA was performed with a bipolar electrode (CelonProSurge 150-T20, output power: 20 W). CEUS was performed with a second generation contrast agent under low acoustic power (i.e. coded phase inversion, CPI). Characteristics of clinical factors, findings on conventional gray-scale ultrasound, color-Doppler ultrasound, and CEUS were evaluated preoperatively. Factors associated with initial ICA and initial ICA patterns on CEUS were assessed. Volume reduction ratios (VRRs) of ICA nodules were compared with those with complete ablation (CA).The RFA procedures were accomplished with a mean ablation time and mean total energy deposition of 11.13±3.39 min (range, 5.38-22.13 min) and 12612±4466 J (range, 6310-26130 J) respectively. CEUS detected initial ICA in 21 of 69 (30.8%) BTNs and 16 (76.2%) of the 21 BTNs with initial ICA achieved CA after additional RFA, leading to a final CA rate of 92.8% (64/69). The factors associated with initial ICA were predominantly solid nodule, nodule close to danger triangle area, nodule close to carotid artery, and peripheral blood flow on color-Doppler ultrasound (all P 0.05). The mean VRRs of all BTNs were 23.4%, 54.4% and 81.9% at the 1-, 3- and 6-month follow-up, respectively. All BTNs achieved therapeutic success in this series in that all had VRRs of50% at the 6-month follow-up, among which 7 nodules (10.1%) had VRRs of90%. There were significant differences in VRRs between ICA nodules and CA nodules at the 3- and 6-month follow-up (all P 0.05).The factors associated with initial ICA after RFA for BTNs were predominantly solid nodules, nodule close to danger triangle area, nodule close to carotid artery, and peripheral blood flow on color-Doppler ultrasound. CEUS assists quick treatment response evaluation and facilitates subsequent additional RFA and final CA of the nodules. Nodules with CA achieve a better outcome in terms of VRR in comparison with those with ICA.

Objectives To investigate the diagnostic performance of a 2-dimensional shear wave elastographic technique (Virtual Touch tissue imaging and quantification [VTIQ]; Siemens Medical Solutions, Mountain View, CA) for predicting thyroid malignancy. Methods A total of 302 thyroid nodules underwent conventional sonography and VTIQ before fine-needle aspiration examination or surgery. Compared with histopathologic or cytologic results in combination with follow-up, the diagnostic performance of various shear wave speed (SWS) indices (minimum [SWSmin], maximum [SWSmax], and mean [SWSmean]) on VTIQ as well as conventional sonographic features for predicting thyroid malignancy was evaluated in all of the nodules. Results Sixty-five malignant and 237 benign thyroid nodules were histopathologically or cytologically confirmed. All SWS indices on VTIQ were lower in benign nodules than thyroid malignancy (all P

Ultrasonography is a common modality for diagnosing thyroid nodules. Computer-aided classification of benign and malignant thyroid nodules in the ultrasound images is meaningful. A key challenge in this issue is that a lot of ultrasound images without obvious benign or malignant features are hindering deep learning model to extract effective features. Here, a novel method using two combined classification modules is proposed to separate and classify those images. Firstly, we adopt multi-fold cross-validation based a CNN model to pick out ultrasound images that hard to recognize. Then we add new labels to those images and put them back to the dataset that will be trained with the CNN model to form a tripartite classification module. Finally, a binary classification module will be trained exclusively to discriminate those obscure images. Experimental results on 4148 ultrasound images show that the proposed method lead to excellent performance, with an accuracy of 0.804, which demonstrate the value of this method.