Subtype prediction of intrahepatic cholangiocarcinoma using dynamic contrast-enhanced ultrasound

OBJECTIVE

The study aimed to investigate the predictive value of dynamic contrast-enhanced ultrasound (DCE-US) in differentiating small-duct (SD) and large-duct (LD) types of intrahepatic cholangiocarcinoma (ICC).

METHODS

This study retrospectively enrolled 110 patients with pathologically confirmed ICC lesions who were subject to preoperative contrast-enhanced ultrasound (CEUS) examinations between January 2022 and February 2023. Patients were further classified according to the subtype: SD-type and LD-type, and an optimal predictive model was established and validated using the above pilot cohort. The test cohort, consisting of 48 patients prospectively enrolled from March 2023 to September 2023, was evaluated.

RESULTS

In the pilot cohort, compared with SD-type ICCs, more LD-type ICCs showed elevated carcinoembryonic antigen (p < 0.001), carbohydrate antigen 19-9 (p = 0.004), ill-defined margin (p = 0.018), intrahepatic bile duct dilation (p < 0.001). Among DCE-US quantitative parameters, the wash-out area under the curve (WoAUC), wash-in and wash-out area under the curve (WiWoAUC), and fall time (FT) at the margin of lesions were higher in the SD-type group (all p < 0.05). Meanwhile, the mean transit time (mTT) and wash-out rate (WoR) at the margin of the lesion were higher in the LD-type group (p = 0.041 and 0.007, respectively). Logistic regression analysis showed that intrahepatic bile duct dilation, mTT, and WoR were significant predictive factors for predicting ICC subtypes, and the AUC of the predictive model achieved 0.833 in the test cohort.

CONCLUSIONS

Preoperative DCE-US has the potential to become a novel complementary method for predicting the pathological subtype of ICC.

CRITICAL RELEVANCE STATEMENT

DCE-US has the potential to assess the subtypes of ICC lesions quantitatively and preoperatively, which allows for more accurate and objective differential diagnoses, and more appropriate treatments and follow-up or additional examination strategies for the two subtypes.

KEY POINTS

Preoperative determination of intrahepatic cholangiocarcinoma (ICC) subtype aids in surgical decision-making. Quantitative parameters from dynamic contrast-enhanced US (DCE-US) allow for the prediction of the ICC subtype. DCE-US-based imaging has the potential to become a novel complementary method for predicting ICC subtypes.

Predicting the malignancy of extremity soft-tissue tumors by an ultrasound-based radiomics signature

BACKGROUND

Accurate differentiation of extremity soft-tissue tumors (ESTTs) is important for treatment planning.

PURPOSE

To develop and validate an ultrasound (US) image-based radiomics signature to predict ESTTs malignancy.

MATERIAL AND METHODS

A dataset of US images from 108 ESTTs were retrospectively enrolled and divided into the training cohort (78 ESTTs) and validation cohort (30 ESTTs). A total of 1037 radiomics features were extracted from each US image. The most useful predictive radiomics features were selected by the maximum relevance and minimum redundancy method, least absolute shrinkage, and selection operator algorithm in the training cohort. A US-based radiomics signature was built based on these selected radiomics features. In addition, a conventional radiologic model based on the US features from the interpretation of two experienced radiologists was developed by a multivariate logistic regression algorithm. The diagnostic performances of the selected radiomics features, the US-based radiomics signature, and the conventional radiologic model for differentiating ESTTs were evaluated and compared in the validation cohort.

RESULTS

In the validation cohort, the area under the curve (AUC), sensitivity, and specificity of the US-based radiomics signature for predicting ESTTs malignancy were 0.866, 84.2%, and 81.8%, respectively. The US-based radiomics signature had better diagnostic predictability for predicting ESTT malignancy than the best single radiomics feature and the conventional radiologic model (AUC = 0.866 vs. 0.719 vs. 0.681 for the validation cohort, all P <0.05).

CONCLUSION

The US-based radiomics signature could provide a potential imaging biomarker to accurately predict ESTT malignancy.

Automatic detection of thyroid nodules with a real-time artificial intelligence system in a real clinical scenario and the associated influencing factors

BACKGROUND

At present, most articles mainly focused on the diagnosis of thyroid nodules by using artificial intelligence (AI), and there was little research on the detection performance of AI in thyroid nodules.

OBJECTIVE

To explore the value of a real-time AI based on computer-aided diagnosis system in the detection of thyroid nodules and to analyze the factors influencing the detection accuracy.

METHODS

From June 1, 2022 to December 31, 2023, 224 consecutive patients with 587 thyroid nodules were prospective collected. Based on the detection results determined by two experienced radiologists (both with more than 15 years experience in thyroid diagnosis), the detection ability of thyroid nodules of radiologists with different experience levels (junior radiologist with 1 year experience and senior radiologist with 5 years experience in thyroid diagnosis) and real-time AI were compared. According to the logistic regression analysis, the factors influencing the real-time AI detection of thyroid nodules were analyzed.

RESULTS

The detection rate of thyroid nodules by real-time AI was significantly higher than that of junior radiologist (P = 0.013), but lower than that of senior radiologist (P = 0.001). Multivariate logistic regression analysis showed that nodules size, superior pole, outside (near carotid artery), close to vessel, echogenicity (isoechoic, hyperechoic, mixed-echoic), morphology (not very regular, irregular), margin (unclear), ACR TI-RADS category 4 and 5 were significant independent influencing factors (all P < 0.05). With the combination of real-time AI and radiologists, junior and senior radiologist increased the detection rate to 97.4% (P < 0.001) and 99.1% (P = 0.015) respectively.

CONCLUSONS

The real-time AI has good performance in thyroid nodule detection and can be a good auxiliary tool in the clinical work of radiologists.

A 5G-based telerobotic ultrasound system provides qualified abdominal ultrasound services for patients on a rural island: a prospective and comparative study of 401 patients

PURPOSE

To explore the feasibility of a 5G-based telerobotic ultrasound (US) system for providing qualified abdominal US services on a rural island.

METHODS

This prospective study involved two medical centers (the tele-radiologist site's hospital and the patient site's hospital) separated by 72 km. Patients underwent 5G-based telerobotic US by tele-radiologists and conventional US by on-site radiologists from September 2020 to March 2021. The clinical feasibility and diagnostic performance of the 5G-based telerobotic abdominal US examination were assessed based on safety, duration, image quality, diagnostic findings, and questionnaires.

RESULTS

A total of 401 patients (217 women and 184 men; mean age, 54.96 ± 15.43 years) were enrolled. A total of 90.1% of patients indicated no discomfort with the telerobotic US examination. For the examination duration, telerobotic US took longer than conventional US (12.54 ± 3.20 min vs. 7.23 ± 2.10 min, p = 0.001). For image quality scores, the results of the two methods were similar (4.54 ± 0.63 vs. 4.57 ± 0.61, p = 0.112). No significant differences were found between the two methods in measurements for the aorta, portal vein, gallbladder, kidney (longitudinal diameter), prostate, and uterus; however, telerobotic US underestimated the transverse diameter of the kidney (p < 0.05). A total of 504 positive results, including 31 different diseases, were detected. Among them, 455 cases were identified by the two methods; 17 cases were identified by telerobotic US only; and 32 cases were identified by conventional US only. There was good consistency in the diagnosis of 29 types of disease between the two methods (κ = 0.773-1.000). Furthermore, more than 90% of patients accepted the telerobotic US examination and agreed to pay additional fees in future.

CONCLUSION

The 5G-based telerobotic US system can expand access to abdominal US services for patients in rural areas, thereby reducing health care disparities.

A multi-parameter intrahepatic cholangiocarcinoma scoring system based on modified contrast-enhanced ultrasound LI-RADS M criteria for differentiating intrahepatic cholangiocarcinoma from hepatocellular carcinoma

PURPOSE

To develop a multi-parameter intrahepatic cholangiocarcinoma (ICC) scoring system and compare its diagnostic performance with contrast-enhanced ultrasound (CEUS) liver imaging reporting and data system M (LR-M) criteria for differentiating ICC from hepatocellular carcinoma (HCC).

METHODS

This retrospective study enrolled 62 high-risk patients with ICCs and 62 high-risk patients with matched HCCs between January 2022 and December 2022 from two institutions. The CEUS LR-M criteria was modified by adjusting the early wash-out onset (within 45 s) and the marked wash-out (within 3 min). Then, a multi-parameter ICC scoring system was established based on clinical features, B-mode ultrasound features, and modified LR-M criteria.

RESULT

We found that elevated CA 19-9 (OR=12.647), lesion boundary (OR=11.601), peripheral rim-like arterial phase hyperenhancement (OR=23.654), early wash-out onset (OR=7.211), and marked wash-out (OR=19.605) were positive predictors of ICC, whereas elevated alpha-fetoprotein (OR=0.078) was a negative predictor. Based on these findings, an ICC scoring system was established. Compared with the modified LR-M and LR-M criteria, the ICC scoring system showed the highest area under the curve (0.911 vs. 0.831 and 0.750, both p<0.05) and specificity (0.935 vs. 0.774 and 0.565, both p<0.05). Moreover, the numbers of HCCs categorized as LR-M decreased from 27 (43.5%) to 14 (22.6%) and 4 (6.5%) using the modified LR-M criteria and ICC scoring system, respectively.

CONCLUSION

The modified LR-M criteria-based multi-parameter ICC scoring system had the highest specificity for diagnosing ICC and reduced the number of HCC cases diagnosed as LR-M category.

Quantitative analysis of pre-treatment dynamic contrast-enhanced ultrasound for assessing the response of colorectal liver metastases to chemotherapy plus targeted therapy: a dual-institutional study

OBJECTIVES

To investigate the clinical value of pre-treatment quantitative contrast-enhanced ultrasound (CEUS) in assessing the response of colorectal liver metastases (CRLM) to chemotherapy plus targeted therapy.

METHODS

This study retrospectively enrolled 50 CRLM patients from the Zhongshan Hospital, Fudan University as the training cohort and 14 patients from Shanghai Tenth People's Hospital as the testing cohort. Patients underwent the CEUS examination before receiving chemotherapy (CAPOX, FOLFOX, FOLFIRI, or FOLFOXIRI) plus targeted therapy (Bevacizumab or Cetuximab). The therapy response was determined according to Response Evaluation Criteria in Solid Tumors version 1.1 based on pre-treatment CT and 3-month follow-up CT after therapy. Dynamic analysis was performed by VueBox® software. Time-intensity curves with quantitative perfusion parameters were obtained. In the training cohort, univariable and multivariable logistic regression analyses were used to develop the predictive model of therapy response. The predictive performance of the developed model was validated in the testing cohort.

RESULTS

After the logistic regression analyses, the peak enhancement (PE) (odds ratio = 1.640; 95% confidence intervals [CI] 1.022-2.633) and time to peak (TTP) (odds ratio = 0.495; 95% CI 0.246-0.996) were determined as independent predictive factors. PE and TTP generated from VueBox® were not affected by ultrasound instruments and contrast agent dosage in therapy response evaluation (P > 0.05). The logistic regression model achieved satisfactory prediction performance (area under the curve: 0.923 in the training cohort and 0.854 in the testing cohort).

CONCLUSION

CEUS with dynamic quantitative perfusion analysis, which presents high consistency, has potential practical value in predicting the response of CRLM to chemotherapy plus targeted therapy.

Response Evaluation Using Contrast-Enhanced Ultrasound for Unresectable Advanced Hepatocellular Carcinoma Treated With Tyrosine Kinase Inhibitors Plus Anti-PD-1 Antibody Therapy

OBJECTIVE

The aim of the work described here was to evaluate the role of contrast-enhanced ultrasound (CEUS) in response evaluation for unresectable advanced hepatocellular carcinoma (HCC) treated with tyrosine kinase inhibitors (TKIs) plus anti-programmed cell death protein-1 (PD-1) antibody therapy.

METHODS

A prospective cohort of consecutive patients with HCC who received combined TKI/anti-PD-1 antibody treatment for unresectable HCC between January 2022 and October 2022 was included in this study. The patients underwent unenhanced ultrasound (US) and CEUS examinations before treatment and at follow-up. Changes in the largest diameters of the target tumor on unenhanced US and the largest diameters of the enhancing target tumors on CEUS were evaluated. Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 with unenhanced US and magnetic resonance imaging/computed tomography (MRI/CT) and modified RECIST (mRECIST) with CEUS and CEMRI/CT were used to assess treatment response.

RESULTS

A total of 24 HCC patients (23 men and 1 woman; mean age: 56.5 ± 8.5 y; Barcelona Clinic Liver Cancer stage C, 62.5%; 29 intrahepatic target tumors) were studied. Calculations of degree of necrosis in the target tumors revealed no significant differences between CEUS and CEMRI/CT (44.5 ± 36.2% vs. 45.3 ± 36.8%, p = 0.862). As for the differentiation of responders from non-responders, the agreement between RECIST version 1.1 of unenhanced US and mRECIST-CEUS was poor (κ coefficient = 0.233). Meanwhile, there was a high degree of concordance between mRECIST-CEUS and mRECIST-CEMRI/CT (κ coefficient = 0.812).

CONCLUSION

CEUS proved to be superior to baseline US and is comparable to CEMRI/CT in defining treatment outcome for combined TKI/anti-PD-1 antibody therapy.

Risk stratification of gallbladder masses by machine learning-based ultrasound radiomics models: a prospective and multi-institutional study

OBJECTIVE

This study aimed to evaluate the diagnostic performance of machine learning (ML)-based ultrasound (US) radiomics models for risk stratification of gallbladder (GB) masses.

METHODS

We prospectively examined 640 pathologically confirmed GB masses obtained from 640 patients between August 2019 and October 2022 at four institutions. Radiomics features were extracted from grayscale US images and germane features were selected. Subsequently, 11 ML algorithms were separately used with the selected features to construct optimum US radiomics models for risk stratification of the GB masses. Furthermore, we compared the diagnostic performance of these models with the conventional US and contrast-enhanced US (CEUS) models.

RESULTS

The optimal XGBoost-based US radiomics model for discriminating neoplastic from non-neoplastic GB lesions showed higher diagnostic performance in terms of areas under the curves (AUCs) than the conventional US model (0.822-0.853 vs. 0.642-0.706, p < 0.05) and potentially decreased unnecessary cholecystectomy rate in a speculative comparison with performing cholecystectomy for lesions sized over 10 mm (2.7-13.8% vs. 53.6-64.9%, p < 0.05) in the validation and test sets. The AUCs of the XGBoost-based US radiomics model for discriminating carcinomas from benign GB lesions were higher than the conventional US model (0.904-0.979 vs. 0.706-0.766, p < 0.05). The XGBoost-US radiomics model performed better than the CEUS model in discriminating GB carcinomas (AUC: 0.995 vs. 0.902, p = 0.011).

CONCLUSIONS

The proposed ML-based US radiomics models possess the potential capacity for risk stratification of GB masses and may reduce the unnecessary cholecystectomy rate and use of CEUS.

CLINICAL RELEVANCE STATEMENT

The machine learning-based ultrasound radiomics models have potential for risk stratification of gallbladder masses and may potentially reduce unnecessary cholecystectomies.

KEY POINTS

• The XGBoost-based US radiomics models are useful for the risk stratification of GB masses. • The XGBoost-based US radiomics model is superior to the conventional US model for discriminating neoplastic from non-neoplastic GB lesions and may potentially decrease unnecessary cholecystectomy rate for lesions sized over 10 mm in comparison with the current consensus guideline. • The XGBoost-based US radiomics model could overmatch CEUS model in discriminating GB carcinomas from benign GB lesions.

Dense Swin Transformer for Classification of Thyroid Nodules

As an early sign of thyroid cancer, thyroid nodules are the most common nodular lesions. As a non-invasive imaging method, ultrasound is widely used in the diagnosis of benign and malignant thyroid nodules. As there is no obvious difference in appearance between the two types of thyroid nodules, and the contrast with the surrounding muscle tissue is too low, it is difficult to distinguish the benign and malignant nodules. Therefore, a dense nodal Swin-Transformer(DST) method for the diagnosis of thyroid nodules is proposed in this paper. Image segmentation is carried out through patch, and feature maps of different sizes are constructed in four stages, which consider different information of each layer of features. In each stage block, a dense connection mechanism is used to make full use of multi-layer features and effectively improve the diagnostic performance. The experimental results of multi-center ultrasound data collected from 17 hospitals show that the accuracy of the proposed method is 87.27%, the sensitivity is 88.63%, and the specific effect is 85.16%, which verifies that the proposed algorithm has the potential to assist clinical practice.

Three-dimensional convolutional neural network model to identify clinically significant prostate cancer in transrectal ultrasound videos: a prospective, multi-institutional, diagnostic study

Background

Identifying patients with clinically significant prostate cancer (csPCa) before biopsy helps reduce unnecessary biopsies and improve patient prognosis. The diagnostic performance of traditional transrectal ultrasound (TRUS) for csPCa is relatively limited. This study was aimed to develop a high-performance convolutional neural network (CNN) model (P-Net) based on a TRUS video of the entire prostate and investigate its efficacy in identifying csPCa.

Methods

Between January 2021 and December 2022, this study prospectively evaluated 832 patients from four centres who underwent prostate biopsy and/or radical prostatectomy. All patients had a standardised TRUS video of the whole prostate. A two-dimensional CNN (2D P-Net) and three-dimensional CNN (3D P-Net) were constructed using the training cohort (559 patients) and tested on the internal validation cohort (140 patients) as well as on the external validation cohort (133 patients). The performance of 2D P-Net and 3D P-Net in predicting csPCa was assessed in terms of the area under the receiver operating characteristic curve (AUC), biopsy rate, and unnecessary biopsy rate, and compared with the TRUS 5-point Likert score system as well as multiparametric magnetic resonance imaging (mp-MRI) prostate imaging reporting and data system (PI-RADS) v2.1. Decision curve analyses (DCAs) were used to determine the net benefits associated with their use. The study is registered at https://www.chictr.org.cn with the unique identifier ChiCTR2200064545.

Findings

The diagnostic performance of 3D P-Net (AUC: 0.85-0.89) was superior to TRUS 5-point Likert score system (AUC: 0.71-0.78, P = 0.003-0.040), and similar to mp-MRI PI-RADS v2.1 score system interpreted by experienced radiologists (AUC: 0.83-0.86, P = 0.460-0.732) and 2D P-Net (AUC: 0.79-0.86, P = 0.066-0.678) in the internal and external validation cohorts. The biopsy rate decreased from 40.3% (TRUS 5-point Likert score system) and 47.6% (mp-MRI PI-RADS v2.1 score system) to 35.5% (2D P-Net) and 34.0% (3D P-Net). The unnecessary biopsy rate decreased from 38.1% (TRUS 5-point Likert score system) and 35.2% (mp-MRI PI-RADS v2.1 score system) to 32.0% (2D P-Net) and 25.8% (3D P-Net). 3D P-Net yielded the highest net benefit according to the DCAs.

Interpretation

3D P-Net based on a prostate grayscale TRUS video achieved satisfactory performance in identifying csPCa and potentially reducing unnecessary biopsies. More studies to determine how AI models better integrate into routine practice and randomized controlled trials to show the values of these models in real clinical applications are warranted.

Funding

The National Natural Science Foundation of China (Grants 82202174 and 82202153), the Science and Technology Commission of Shanghai Municipality (Grants 18441905500 and 19DZ2251100), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), Shanghai Science and Technology Innovation Action Plan (21Y11911200), and Fundamental Research Funds for the Central Universities (ZD-11-202151), Scientific Research and Development Fund of Zhongshan Hospital of Fudan University (Grant 2022ZSQD07).

A multiparametric clinic-ultrasomics nomogram for predicting extremity soft-tissue tumor malignancy: a combined retrospective and prospective bicentric study

OBJECTIVE

We aimed at building and testing a multiparametric clinic-ultrasomics nomogram for prediction of malignant extremity soft-tissue tumors (ESTTs).

MATERIALS AND METHODS

This combined retrospective and prospective bicentric study assessed the performance of the multiparametric clinic-ultrasomics nomogram to predict the malignancy of ESTTs, when compared with a conventional clinic-radiologic nomogram. A dataset of grayscale ultrasound (US), color Doppler flow imaging (CDFI), and elastography images for 209 ESTTs were retrospectively enrolled from one hospital, and divided into the training and validation cohorts. A multiparametric ultrasomics signature was built based on multimodal ultrasomic features extracted from the grayscale US, CDFI, and elastography images of ESTTs in the training cohort. Another conventional radiologic score was built based on multimodal US features as interpreted by two experienced radiologists. Two nomograms that integrated clinical risk factors and the multiparameter ultrasomics signature or conventional radiologic score were respectively developed. Performance of the two nomograms was validated in the retrospective validation cohort, and tested in a prospective dataset of 51 ESTTs from the second hospital.

RESULTS

The multiparametric ultrasomics signature was built based on seven grayscale ultrasomic features, three CDFI ultrasomic features, and one elastography ultrasomic feature. The conventional radiologic score was built based on five multimodal US characteristics. Predictive performance of the multiparametric clinic-ultrasomics nomogram was superior to that of the conventional clinic-radiologic nomogram in the training (area under the receiver operating characteristic curve [AUC] 0.970 vs. 0.890, p = 0.006), validation (AUC: 0.946 vs. 0.828, p = 0.047) and test (AUC: 0.934 vs. 0.842, p = 0.040) cohorts, respectively. Decision curve analysis of combined training, validation and test cohorts revealed that the multiparametric clinic-ultrasomics nomogram had a higher overall net benefit than the conventional clinic-radiologic model.

CONCLUSION

The multiparametric clinic-ultrasomics nomogram can accurately predict the malignancy of ESTTs.

5G-Based Telerobotic Ultrasound System Improves Access to Breast Examination in Rural and Remote Areas: A Prospective and Two-Scenario Study

OBJECTIVE

Ultrasound (US) plays an important role in the diagnosis and management of breast diseases; however, effective breast US screening is lacking in rural and remote areas. To alleviate this issue, we prospectively evaluated the clinical availability of 5G-based telerobotic US technology for breast examinations in rural and remote areas.

METHODS

Between September 2020 and March 2021, 63 patients underwent conventional and telerobotic US examinations in a rural island (Scenario A), while 20 patients underwent telerobotic US examination in a mobile car located in a remote county (Scenario B) in May 2021. The safety, duration, US image quality, consistency, and acceptability of the 5G-based telerobotic US were assessed.

RESULTS

In Scenario A, the average duration of the telerobotic US procedure was longer than that of conventional US (10.3 ± 3.3 min vs. 7.6 ± 3.0 min, p = 0.017), but their average imaging scores were similar (4.86 vs. 4.90, p = 0.159). Two cases of gynecomastia, one of lactation mastitis, and one of postoperative breast effusion were diagnosed and 32 nodules were detected using the two US methods. There was good interobserver agreement between the US features and BI-RADS categories of the identical nodules (ICC = 0.795-1.000). In Scenario B, breast nodules were detected in 65% of the patients using telerobotic US. Its average duration was 10.1 ± 2.3 min, and the average imaging score was 4.85. Overall, 90.4% of the patients were willing to choose telerobotic US in the future, and tele-sonologists were satisfied with 85.5% of the examinations.

CONCLUSION

The 5G-based telerobotic US system is feasible for providing effective breast examinations in rural and remote areas.

Ultrasound-based computer-aided diagnosis for cytologically indeterminate thyroid nodules with different radiologists

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 < 0.05). The combination of senior radiologist and CAD system had the highest diagnostic performance (AUC: 0.740) and specificity (68.9%) compared to the others (all P < 0.05).

CONCLUSION

The CAD system may play the potential role as a decision-making assistant alongside radiologists for differential diagnosis of TNs with indeterminate cytology.

[Artificial intelligence technology enables ultrasonography in precision diagnosisand treatment of liver diseases]

Liver disease is one of the major problems affecting human health. Ultrasound plays an important role in diagnosis and treatment of diffuse and focal liver diseases. However, conventional ultrasound evaluation is subjective and provides limited information. Artificial intelligence (AI) technology may supplement the disadvantages of conventional ultrasound and has been widely used in the field of ultrasound in liver diseases. To date, remarkable progress has been achieved for the use of AI technology in the diagnosis, assessment of therapeutic efficacy and prognosis prediction of liver diseases. This paper reviews the research progress of ultrasound image-based AI technology in the diagnosis and treatment of diffuse and focal liver diseases.

Clinical application of a 5G-based telerobotic ultrasound system for thyroid examination on a rural island: a prospective study

PURPOSE

To evaluate the feasibility of a 5G-based telerobotic ultrasound (US) system for thyroid examination on a rural island.

METHODS

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.

RESULTS

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.

CONCLUSION

The 5G-based telerobotic US system can be a routine diagnostic tool for thyroid examination for patients on a rural island.

Improving the diagnosis of AUS/FLUS thyroid nodules using an algorithm with combination of BRAFV600E mutation analysis and ultrasound pattern-based risk stratification

PURPOSE

To propose a diagnostic algorithm for improving the diagnosis of atypia of undetermined significance or follicular lesion of undetermined significance (AUS/FLUS) thyroid nodules.

METHODS

This study retrospectively enrolled 77 consecutive patients with 81 AUS/FLUS nodules who underwent preoperative BRAFV600E mutation analysis. A new diagnostic algorithm was proposed that BRAFV600E mutation analysis for the Fine-needle aspiration cytology specimen was firstly carried out, in which positive BRAFV600E mutation indicated malignancy and classification of the nodules with negative BRAFV600E mutation was further performed based on ultrasound pattern-based risk stratification of American Thyroid Association Guidelines. The diagnostic performance of the new diagnostic algorithm was evaluated.

RESULTS

The sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and area under the receiver operating characteristic curve (AUROC) of new diagnostic algorithm were 94.6%, 84.0%, 91.4%, 86.9%, 90.1%, and 0.893, respectively. The proposed diagnostic algorithm significantly increased the diagnostic performances (AUROC: 0.893 vs. 0.837 and 0.795), sensitivity (94.6% vs. 71.4% and 75.0%), and accuracy (90.1% vs. 79.0% and 77.8%) compared with BRAFV600E mutation analysis alone and ultrasound pattern-based risk stratification alone (all P < 0.05).

CONCLUSION

The proposed diagnostic algorithm is helpful for improving the diagnosis of AUS/FLUS nodules, which might be as a routine approach.

A Comparative Analysis of Two Machine Learning-Based Diagnostic Patterns with Thyroid Imaging Reporting and Data System for Thyroid Nodules: Diagnostic Performance and Unnecessary Biopsy Rate

Background: The risk stratification system of the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) for thyroid nodules is affected by low diagnostic specificity. Machine learning (ML) methods can optimize the diagnostic performance in medical image analysis. However, it is unknown which ML-based diagnostic pattern is more effective in improving diagnostic performance for thyroid nodules and reducing nodule biopsies. Therefore, we compared ML-assisted visual approaches and radiomics approaches with ACR TI-RADS in diagnostic performance and unnecessary fine-needle aspiration biopsy (FNAB) rate for thyroid nodules. Methods: This retrospective study evaluated a data set of ultrasound (US) and shear wave elastography (SWE) images in patients with biopsy-proven thyroid nodules (≥1 cm) from the Shanghai Tenth People's Hospital (743 nodules in 720 patients from September 2017 to January 2019) and an independent test data set from the Ma'anshan People's Hospital (106 nodules in 102 patients from February 2019 to April 2019). Six US features and five SWE parameters from the radiologists' interpretation were used for building the ML-assisted visual approaches. The radiomics features extracted from the US and SWE images were used with ML methods for developing the radiomics approaches. The diagnostic performance for differentiating thyroid nodules and the unnecessary FNAB rate of the ML-assisted visual approaches and the radiomics approaches were compared with ACR TI-RADS. Results: The ML-assisted US visual approach had the best diagnostic performance than the US radiomics approach and ACR TI-RADS (area under the curve [AUC]: 0.900 vs. 0.789 vs. 0.689 for the validation data set, 0.917 vs. 0.770 vs. 0.681 for the test data set). After adding SWE, the ML-assisted visual approach had a better diagnostic performance than US alone (AUC: 0.951 vs. 0.900 for the validation data set, 0.953 vs. 0.917 for the test data set). When applying the ML-assisted US+SWE visual approach, the unnecessary FNAB rate decreased from 30.0% to 4.5% in the validation data set and from 37.7% to 4.7% in the test data set in comparison to ACR TI-RADS. Conclusions: The ML-assisted dual modalities visual approach can assist radiologists to diagnose thyroid nodules more effectively and considerably reduce the unnecessary FNAB rate in the clinical management of thyroid nodules.

Conventional ultrasound characteristics, TI-RADS category and shear wave speed measurement between follicular adenoma and follicular thyroid carcinoma

The purpose of the study was to explore the differences of conventional ultrasound characteristics, thyroid imaging reporting and data system (TI-RADS) category and shear wave speed (SWS) measurement between follicular adenoma (FA) and follicular thyroid carcinoma (FTC). Twenty-eight FTCs and 67 FAs proven by surgery were retrospectively included for analysis. Conventional ultrasound and point-shear wave elastography (p-SWE) were performed in all of the included patients. The ultrasound features, American Thyroid Association (ATA) TI-RADS category and American College of Radiology (ACR) TI-RADS category, SWS measurement were compared between the two groups. Receiver operating characteristic (ROC) curve was performed and area under ROC curve (AUC) was obtained for significant features. There were no statistical differences in mean age (46.9±15.7years vs. 48.6±13.6years, P = 0.639), gender (9 males, 32.1% vs. 18 males, 29.0%, P = 0.766) and mean diameter (28.3±16.2 mm vs. 33.8±11.9 mm, P = 0.077) between FTCs and FAs. Hypoechogenicity, lobulated or irregular margin, macrocalcification were more common in FTCs than FAs (all P < 0.05). Mean SWS of FTCs (2.29±0.64 m/s) was slightly higher than that of FAs (1.94±0.68 m/s) (P = 0.023). The AUCs were 0.655, 0.744, and 0.744 with the cut-off SWS≥1.89 m/s, ACR TI-RADS category 4 and intermediate suspicion of ATA TI-RADS category. The sensitivity and AUC were 82.1% and 0.812 with combined ultrasound features of hypoechogenicity, lobulated or irregular margin and macrocalcification. In Conclusion, SWS measurement and TI-RADS categories were useful for the identification of FTCs from FAs.

Comparisons of ACR TI-RADS, ATA guidelines, Kwak TI-RADS, and KTA/KSThR guidelines in malignancy risk stratification of thyroid nodules

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 < 0.001) among the suspicious ultrasound images features. For all nodules and two subgroups (i.e. nodules <10 mm group and nodules ≥10 mm group), ACR TI-RADS demonstrated higher specificities (all P < 0.05) and lower sensitivities (all P < 0.001) than the other guidelines. In the all nodules group and the nodules<10 mm group, ACR TI-RADS and Kwak TI-RADS had higher Azs than the other guidelines (all P < 0.01). The unnecessary biopsy rates for recommending FNA of ACR TI-RADS in the all nodules (≥10 mm) group and the subgroup (10∼19 mm) were all lower than those of the others guidelines (P < 0.001 for all). For the subgroup (≥20 mm), the unnecessary biopsy rate of ACR was lower than that of ATA guidelines and KTA/KSThR guidelines (P < 0.001).

CONCLUSIONS

The four guidelines have good diagnostic efficiency in differentiating TNs. ACR TI-RADS and Kwak TI-RADS have better diagnostic performance than the other guidelines in the all nodules group and the nodules<10 mm group. Considering the comprehensive diagnostic efficacy and unnecessary biopsy rate, ACR TI-RADS is a more desirable classification guideline in clinical practice.

Ultrasound validation of predictive model for central cervical lymph node metastasis in papillary thyroid cancer on BRAF

Aim: To compare the value of predictive power of the models for central cervical lymph node metastasis (CLNM) in papillary thyroid carcinomas (PTCs). Patients & methods: 220 PTCs were prospectively enrolled into the study with pathological examination. We established a new risk model with univariate and multivariate analyses and receiver-operating characteristic curves were plotted. Z-test was performed to compare the area under two curves and validated the predictive model for central CLNM in PTCs. The comparison of previous and new predictive model was analyzed. Results: Microcalcification, capsule contact or involvement, internal flow and BRAF^V600E mutation were four independent risk factors for PTCs with central CLNMs. The area under the curves for the new and the previous model were 0.948 and 0.934 (p = 0.572), respectively. Conclusion: Two predictive models showed strong consistency in predicting central CLNM in PTCs. The predictive model may be helpful in selecting appropriate treatment method in PTCs.

Suspicious ultrasound and clinicopathological features of papillary thyroid carcinoma predict the status of TERT promoter

PURPOSE

To investigate the value of ultrasound (US) and clinicopathological features of papillary thyroid cancer (PTC) in predicting Telomerase Reverse Transcriptase (TERT) promoter mutations.

METHODS

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.

RESULTS

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 < 0.001). The cut-off value was 2.5 and the associated AUC was 0.908 (P < 0.001).

CONCLUSIONS

The probability of TERT promoter mutations increases along with the suspicious US features and clinicopathological characteristics, which may help to recognize patients who deserve a different approach, in terms of management and follow-up, in view of the worst outcome associated to this mutation.

Imaging findings of Bowen's disease: A comparison between ultrasound biomicroscopy and conventional high-frequency ultrasound

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.

Correlation between ultrasound consolidated score and simple endoscopic score for determining the activity of Crohn's disease

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.

Usefulness of Strain Elastography, ARFI Imaging, and Point Shear Wave Elastography for the Assessment of Crohn Disease Strictures

OBJECTIVES

The aim of this study was to evaluate the diagnostic performance of strain elastography, acoustic radiation force impulse (ARFI) imaging and point shear wave elastography (p-SWE) for assessment of the predominant types of intestinal stenosis in Crohn disease.

METHODS

Twenty-five patients were enrolled in this study, among whom 25 suspicious stenoses in 25 intestinal segments were studied using gray scale ultrasonography. All 3 elastography methods were performed, and all patients underwent endoscopy within 24 hours with pathologic biopsy. The sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Youden index, and area under the receiver operating characteristic curve (AUROC) were calculated. Pathologic findings were regarded as the gold standard.

RESULTS

For SE, the optimal cutoff value was a score of 4 or greater (sensitivity, 75%; specificity, 66.7%; accuracy, 68%; PPV, 30%; NPV, 93.3%; AUROC, 0.708; however, P > .05). The results of ARFI imaging were similar: the optimal cutoff value was a score of 4 or greater (sensitivity, 50%; specificity, 81%; accuracy, 76%; PPV, 33.3%; NPV, 89.4%; AUROC, 0.669; P < .05). However, for p-SWE, the optimal cutoff value was reached when the shear wave velocity exceeded 2.73 m/s (sensitivity, 75%; specificity, 100%; accuracy, 96%; PPV, 100%; NPV, 95.5%; AUROC, 0.833; P < .05).

CONCLUSIONS

p-SWE had the best performance for evaluating and differentiating intestinal stenosis in Crohn disease, while neither SE nor ARFI imaging achieved satisfactory outcomes for evaluating inflammatory stenosis and fibrotic stenosis of Crohn disease.

BRAFV600E mutation analysis in fine-needle aspiration cytology specimens for diagnosis of thyroid nodules: The influence of false-positive and false-negative results

Background

The accurate evaluation of BRAF^V600E mutation in preoperative fine‐needle aspiration cytology (FNAC) specimens is important for making management decisions in thyroid nodules (TNs). The aim of this study was to assess the false‐positive and false‐negative BRAF^V600E mutations in thyroid FNAC specimens and their influence on diagnosis of TN.

Methods

This prospective study enrolled 292 nodules in 269 patients who underwent BRAF^V600E mutation analysis using amplification refractory mutation system‐quantitative real‐time polymerase chain reaction (ARMS‐qPCR) both in FNAC specimens and formalin‐fixed, paraffin‐embedded (FFPE) tissue samples after surgery. The false‐positive and false‐negative mutations for BRAF^V600E analysis using ARMS‐qPCR in FNAC specimens were recorded, with reference to the results of BRAF^V600E mutation analysis using ARMS‐qPCR in FFPE tissue sample. Diagnostic performances of FNAC, BRAF^V600E mutation analysis in FNAC specimens, BRAF^V600E mutation analysis in FFPE tissue sample, and the combination of FNAC and BRAF^V600E mutation analysis for predicting thyroid malignancy were assessed.

Results

The false‐positive and false‐negative mutations for BRAF^V600E analysis using ARMS‐qPCR in FNAC specimens were 10.1% (19/189) and 7.1% (7/98), respectively. FNAC combined with preoperative BRAF^V600E mutation analysis significantly increased the diagnostic sensitivity from 75.7% to 92.3%, and accuracy from 78.7% to 90.6% in comparison with FNAC alone (both P < .001). No significant differences were found between the combination of FNAC and BRAF^V600E mutation analysis in FNAC specimens and the combination of FNAC and BRAF^V600E mutation analysis in FFPE tissue sample (sensitivity: 92.3% vs 91.9%; accuracy: 90.6% vs 91.3%; both P > .05).

Conclusions

FNAC combined with preoperative BRAF^V600E mutation analysis can significantly increase the diagnostic performance in comparison with FNAC alone. False‐positive and false‐negative BRAF^V600E mutation results are found in preoperative FNAC specimens, whereas it does not affect the overall auxiliary diagnosis of TNs.

Ultrasound elastography of the thyroid: principles and current status

Ultrasound (US) elastography has been introduced as a non-invasive technique for evaluating thyroid diseases. This paper presents a detailed description of the technical principles, peculiarities, and limitations of US elastography techniques, including strain elastography and shear-wave elastography. This review was conducted from a clinical perspective, and aimed to assess the usefulness of US elastography for thyroid diseases in specific clinical scenarios. Although its main focus is on thyroid nodules, the applications of US elastography for other thyroid diseases, such as diffuse thyroid diseases and thyroiditis, are also presented. Furthermore, unresolved questions and directions for future research are also discussed.

Conventional Ultrasound, Immunohistochemical Factors and BRAFV600E Mutation in Predicting Central Cervical Lymph Node Metastasis of Papillary Thyroid Carcinoma

The study was aimed at evaluating the correlation between central cervical lymph node metastasis (CLNM) in papillary thyroid carcinoma (PTC) patients and ultrasound (US) features, immunohistochemical factors and BRAF^V600E mutation. A total of 225 consecutive patients (225 PTCs) who had undergone surgery were included. All PTCs were pre-operatively analysed by US with respect to size, components, echogenicity, shape, margins, microcalcification, multiple cancers or not, internal vascularity and capsule contact or involvement. The presence of four immunohistochemical factors, including cytokeratin 19, human bone marrow endothelial cell 1, galectin-3 and thyroid peroxidase, and BRAF^V600E mutation was also evaluated. Univariate and multivariate analyses were performed to identify the risk factors for central CLNM, and a risk model was established. Pathologically, 44% (99/225) of the PTCs had central CLNMs. Multivariate analysis revealed that size ≤10mm, microcalcification, internal vascularity, capsule contact or involvement and BRAF^V600E mutation were independent risk factors for central CLNM. The risk score for central CLNM was calculated as follows: risk score = 1.5 × (if lesion size ≤10 mm) + 1.9 × (if microcalcification) + 0.8 × (if internal flow) + 3.0 × (if capsule contact or involvement) + 1.5 × (if BRAF^V600E mutation). The rating result was divided into six stages, and the relevant risk rates of central CLNM were 0% (0/1), 0% (0/22), 7.4% (4/54), 48.6% (34/70), 71.2% (42/59) and 100% (19/19), respectively. In conclusion, PTC ≤10mm, microcalcification, internal vascularity, capsule contact or involvement and BRAF^V600E mutation are risk factors for central CLNM. The risk model may be useful in treatment planning and management of patients with PTCs.

A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images

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.

Complex cystic and solid breast lesions: Diagnostic performance of conventional ultrasound, strain imaging and point shear wave speed measurement

OBJECTIVE

To assess the performance of conventional high frequency ultrasound (US) and US elastography in diagnosis of complex cystic and solid breast lesions.

METHODS

Ninety three lesions in 93 patients underwent conventional US and US elastography, including strain elastography, acoustic radiation force impulse (ARFI) imaging, and point shear wave speed (SWS) measurement.

RESULTS

Pathological examination revealed 31 (33.3%) of the 93 lesions were malignant and the remaining 62 (66.7%) were benign. Multivariate analysis showed that elder patient (OR: 25.301), internal vascularity (OR: 4.518), and not circumscribed margin (OR: 3.813) were independent predictors for malignancy, while predominately cystic lesions (OR: 0.178) was a predictor for benign lesions (all p < 0.05). Invalid SWS measurement was occurred in 19 of 31 (61.3%) malignant lesions and 16 of 62 (25.8%) benign lesions, respectively (p < 0.05). The mean SWS value for malignant lesions was significantly lower than that for benign ones, being 1.60±0.63 m/s (range, 0.68-2.70 m/s) versus 2.33±0.77 m/s (range, 0.67-3.97 m/s) (p < 0.05). Areas under the ROC curve (Azs) for Breast Imaging Reporting and Data System (BI-RADS) assessment, strain elasticity score, ARFI imaging and valid point SWS measurement were 0.844, 0.734, 0.763 and 0.778,respectively.

CONCLUSIONS

US BI-RADS category, strain elastography score, ARFI imaging patterns and point SWS measurement are useful for malignancy prediction of complex cystic and solid breast lesions. The result that SWS for malignant lesions is lower than benign one should be carefully interpreted since invalid SWS measurement is excluded for analysis. The true stiffness of malignant cystic and solid lesions should be further evaluated with a new generation of two-dimensional SWS imaging.

Three-Dimensional Shear Wave Elastography for Differentiating Benign From Malignant Thyroid Nodules

OBJECTIVES

To prospectively evaluate the diagnostic performance of 3-dimensional (3D) shear wave elastography (SWE) for assessing thyroid nodules.

METHODS

A total of 176 surgically or cytologically confirmed thyroid nodules (63 malignant and 113 benign) in 176 patients who had undergone conventional ultrasound (US), 2-dimensional (2D) SWE, and 3D SWE examinations were included in this study. Quantitative elasticity values (mean elasticity, maximum elasticity, and standard deviation of elasticity of a large region of interest and mean elasticity of a 2-mm region of interest) were measured on 2D and 3D SWE. Diagnostic performances of conventional US, 2D SWE, and 3D SWE were assessed. The role of 2D and 3D SWE in reducing unnecessary fine-needle aspiration (FNA) for nodules with low suspicion was also evaluated.

RESULTS

The diagnostic performances in terms of the area under the receiver operating characteristic curve were 0.612 for conventional US, 0.836 for 2D SWE (P < .001 in comparison with conventional US), and 0.839 for 3D SWE (P < .001 in comparison with conventional US). The mean elasticity achieved the highest diagnostic performance in 2D SWE, whereas the standard deviation of elasticity achieved the highest performance in 3D SWE, although no significant difference was found between them (P > .05). Three-dimensional SWE increased the specificity in comparison with 2D SWE (88.5% versus 82.3%; P = .039). For the 37 nodules with low suspicion on conventional US imaging, 2D SWE was able to avoid unnecessary FNA in 77.1% (27 of 35) of benign nodules, and 3D SWE further increased the number to 88.6% (31 of 35).

CONCLUSIONS

Three-dimensional SWE is a useful tool for predicting thyroid nodule malignancy and reducing unnecessary FNA procedures in thyroid nodules with low suspicion of malignancy.

Risk stratification of thyroid nodules with Bethesda category III results on fine-needle aspiration cytology: The additional value of acoustic radiation force impulse elastography

To assess the value of conventional ultrasound, conventional strain elastography (CSE) and acoustic radiation force impulse (ARFI) elastography in differentiating likelihood of malignancy for Bethesda category III thyroid nodules. 103 thyroid nodules with Bethesda category III results on fine-needle aspiration cytology (FNAC) in 103 patients were included and all were pathologically confirmed after surgery. Conventional ultrasound, CSE and ARFI elastography including ARFI imaging and point shear wave speed (SWS) measurement were performed. Univariate and multivariate analyses were performed to identify the independent factors associated with malignancy. Area under the receiver operating characteristic curve (Az) was calculated to assess the diagnostic performance. Pathologically, 65 nodules were benign and 38 were malignant. Significant differences were found between benign and malignant nodules in ARFI. The cut-off points were ARFI imaging grade ≥ 4, SWS > 2.94 m/s and SWS ratio > 1.09, respectively. ARFI imaging (Az: 0.861) had the highest diagnostic performance to differentiate malignant from benign nodules, following by conventional ultrasound (Az: 0.606 - 0.744), CSE (Az: 0.660) and point SWS measurement (Az: 0.725 - 0.735). Multivariate logistic regression analysis showed that ARFI imaging grade ≥ 4 was the most significant independent predictor. The combination of ARFI imaging with point SWS measurement significantly improved the specificity (100% vs. 80.0%) and positive predictive value (100 % vs. 72.9%) in comparison with ARFI imaging alone. ARFI elastography is a useful tool in differentiating malignant from benign thyroid nodules with Bethesda category III results on FNAC.

Two-dimensional shear wave elastography of breast lesions: Comparison of two different systems

OBJECTIVE

To evaluate the diagnostic performance of two different shear wave elastography (SWE) techniques in distinguishing malignant breast lesions from benign ones.

MATERIALS AND METHODS

From March 2016 to May 2016, a total of 153 breast lesions (mean diameter, 16.8 mm±10.5; range 4.1-90.0 mm) in 153 patients (mean age, 46.4 years±15.1; age range 20-86 years) were separately performed by two different SWE techniques (i.e. T-SWE, Aplio500, Toshiba Medical System, Tochigi, Japan; and S-SWE, the Aixplorer US system, SuperSonic Imagine, Provence, France). The maximum (Emax), mean (Emean) and standard deviation (ESD) of elasticity modulus values in T-SWE and S-SWE were analyzed. All the lesions were confirmed by ultrasound (US)-guided core needle biopsy (n = 26), surgery (n = 122), or both (n = 5), with pathological results as the gold standard. The areas under the receiver operating characteristic curves (AUROCs) were calculated. Sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV) were calculated to assess the diagnostic performance between T-SWE and S-SWE. Operator consistency was also evaluated.

RESULTS

Among the 153 lesions, 41 (26.8%) were malignant and 112 (73.2%) were benign. Emax (T-SWE: 40.10±37.14 kPa vs. 118.78±34.41 kPa; S-SWE: 41.22±22.54 kPa vs. 134.77±60.51 kPa), Emean (T-SWE: 19.75±16.31 kPa vs. 52.93±25.75 kPa; S-SWE: 20.95±10.98 kPa vs. 55.95±22.42 kPa) and ESD (T-SWE: 9.00±8.55 kPa vs. 38.44±12.30 kPa; S-SWE: 8.17±6.14 kPa vs. 29.34±13.88 kPa) showed statistical differences in distinguishing malignant lesions from benign ones both in T-SWE and S-SWE (all p < 0.05). In T-SWE, the diagnostic performance of ESD was the highest (AUROC = 0.958), followed by Emax (AUROC = 0.909; p = 0.001 in comparison with ESD) and Emean (AUROC = 0.892; p < 0.001 in comparison with ESD), while in S-SWE, the diagnostic performance of Emax was the highest (AUROC = 0.967), followed by ESD (AUROC = 0.962, p > 0.05 in comparison with Emax) and Emean (AUROC = 0.930, p = 0.034 in comparison with Emax). AUROC-max (T-SWE: 0.909 vs.

S-SWE

0.967), AUROC-mean (T-SWE: 0.892 vs.

S-SWE

0.930) and AUROC-SD (T-SWE: 0.958 vs.

S-SWE

0.962) showed no significant difference between T-SWE and S-SWE (all p > 0.05). The intra-class correlation coefficients (ICC) of the intra-operator consistency and inter-operator consistency respectively were 0.961 and 0.898 in T-SWE, while 0.954 and 0.897 in S-SWE.

CONCLUSION

T-SWE and S-SWE are equivalent for distinguishing the breast lesions. In T-SWE, ESD had the best diagnostic performance, while in S-SWE, Emax had the best diagnostic performance.

Malignancy risk stratification of thyroid nodules: comparisons of four ultrasound Thyroid Imaging Reporting and Data Systems in surgically resected nodules

To compare the efficiency of four different ultrasound (US) Thyroid Imaging Reporting and Data Systems (TI-RADS) in malignancy risk stratification in surgically resected thyroid nodules (TNs). The study included 547 benign TNs and 464 malignant TNs. US images of the TNs were retrospectively reviewed and categorized according to the TI-RADSs published by Horvath E et al. (TI-RADS H), Park et al. (TI-RADS P), Kwak et al. (TI-RADS K) and Russ et al. (TI-RADS R). The diagnostic performances for the four TI-RADSs were then compared. At multivariate analysis, among the suspicious US features, marked hypoechogenicity was the most significant independent predictor for malignancy (OR: 15.344, 95% CI: 5.313-44.313) (P < 0.05). Higher sensitivity was seen in TI-RADS H, TI-RADS K, TI-RADS R comparing with TI-RADS P (P < 0.05 for all), whereas the specificity, accuracy and area under the ROC curve (Az) of TI-RADS P were the highest (all P < 0.05). Higher specificity, accuracy and Az were seen in TI-RADS K compared with TI-RADS R (P = 0.003). With its higher sensitivity, TI-RADS K, a simple predictive model, is practical and convenient for the management of TNs in clinical practice. The study indicates that there is a good concordance between TI-RADS categories and histopathology.

The diagnostic performance of shear wave speed (SWS) imaging for thyroid nodules with elasticity modulus and SWS measurement

To evaluate the diagnostic performance of a new technique of shear wave speed (SWS) imaging for the diagnosis of thyroid nodule with elasticity modulus and SWS measurement. 322 thyroid nodules in 322 patients (216 benign nodules, 106 malignant nodules) were included in this study. All the nodules received conventional ultrasound (US) and SWS imaging (Aplio500, Toshiba Medical Systems, Japan) before fine-needle aspiration (FNA) and/or surgery. The values of E-max and E-mean with elastic modulus (61.27 ± 36.31 kPa and 31.89 ± 19.11 kPa) or SWS (4.45 ± 1.49 m/s and 3.26 ± 2.71 m/s) in malignant nodules were significantly higher than those in benign lesions (29.18 ± 18.62 kPa and 15.85 ± 6.96 kPa, or 2.98 ± 0.85 m/s and 2.19 ± 0.42 m/s, all P < 0.001). No significant differences in area under the curve (AUC) between the SWS imaging parameters were found (all P > 0.05). In multivariate logistic regression analysis, E-max (m/s) with SWS was identified to be the strongest independent predictor for malignant nodules (odds ratio [OR] = 16.760), followed by poorly-defined margin (OR = 7.792), taller-than-wide shape (OR = 3.160), micro-calcification (OR = 2.422), and E-max (kPa) with elastic modulus (OR = 0.914). The AUC was 0.813 for E-max with SWS (m/s) and 0.796 for E-max with elastic modulus (kPa). With cut-off SWS value of 3.52 m/s in E-max, sensitivity of 69.8%, specificity of 81.5%, and accuracy of 77.6% were achieved. SWS imaging is a valuable tool in predicting thyroid malignancy. E-max with SWS measurement is the strongest independent predictor for thyroid malignancy.

Virtual touch tissue imaging and quantification: value in malignancy prediction for complex cystic and solid breast lesions

This study was aimed to evaluatethe usefulness of conventional ultrasound (US) and US elastography, including the latest virtual touch tissue imaging and quantification (VTIQ), in malignancy prediction for complex cystic and solid breast lesions. Eighty-nine complex cystic and solid breast lesions were subject to conventional US and US elastography, including strain elastography (SE), virtual touch tissue imaging (VTI) and VTIQ. Among the 89 lesions, thirty-four (38.2%) lesions were malignant and 55 (61.8%) lesions were benign. Sixteen variables were subject to multivariate logistic regression analysis. Pattern 4b in VTI (odds ratio, OR:15.278), not circumscribed margin of lesion (OR:12.346), SWS mean >4.6 m/s in VTIQ (OR:11.896), and age elder than 50 years (OR:6.303) were identified to be independent predictors for malignancy. In receiver operating characteristic (ROC) curve analyses, associated areas under the ROC curve (Az) for conventional US could be significantly elevated, from 0.649 to 0.918, by combining with US elastography (p < 0.0001). The combined diagnostic method was able to improve the specificity (32.7% vs. 87.3%, p < 0.0001) without sacrificing the sensitivity (97.1% vs. 85.3%, p = 0.075). Both conventional US and US elastography contribute substantially to malignancy prediction in complex cystic and solid lesions. The diagnostic efficacy of conventional US in terms of Az and specificity could be significantly improved by combining with US elastography.

Cytologically indeterminate thyroid nodules: increased diagnostic performance with combination of US TI-RADS and a new scoring system

To investigate the diagnostic performance of combination of ultrasound (US) thyroid imaging reporting and data system (TI-RADS) and a new US scoring system for diagnosing thyroid nodules (TNs) with indeterminate results (Bethesda categories III, IV and V) on fine-needle aspiration (FNA) cytology. 453 patients with 453 cytologically indeterminate TNs were included in this study. Multivariate analyses were performed to construct the scoring system. The diagnostic performances of TI-RADS and the combined method were evaluated and compared. Multivariate analyses revealed that marked hypoechogenicity, taller than wide shape and absence of halo sign were independent predictors for malignancy in cytologically indeterminate TNs. Scoring system was thereafter defined as follows: risk score (RS) = 3.2 x (if marked hypoechogenicity) + 2.8 x (if taller than wide shape) + 1.3 x (if absence of halo sign). Compared with TI-RADS alone, the areas under the receiver operating characteristic curves (AUC), specificity, accuracy and positive predictive value (PPV) of the combined method increased significantly with 0.731 versus 0.569, 48.5% versus 14.1%, 76.2% versus 62.3%, and 70.9% versus 59.9%, respectively (all P < 0.05). The combination of TI-RADS and new US scoring system showed superior diagnostic performances in predicting malignant TNs with indeterminate FNA cytology results in comparison with TI-RADS alone.

Ablative safety margin depicted by fusion imaging with post-treatment contrast-enhanced ultrasound and pre-treatment CECT/CEMRI after radiofrequency ablation for liver cancers

OBJECTIVE

To evaluate the value of fusion imaging with post-treatment contrast-enhanced ultrasound (CEUS) and pre-treatment contrast-enhanced CT/MRI (CECT/CEMRI) in evaluating ablative safety margin after percutaneous ultrasound (US)-guided radiofrequency ablation (RFA) for liver cancers.

METHODS

34 consecutive patients with 47 liver lesions who had undergone RFA were included. Fusion imaging with post-treatment CEUS and pre-treatment CECT/CEMRI was carried out to evaluate local treatment response and ablative safety margin within 1-3 days after RFA. The minimal ablative safety margins of the ablation zones were recorded. The complete response (CR) rate was calculated with reference to CECT/CEMRI results 1 month after RFA. The local tumour progression (LTP) was also recorded.

RESULTS

Of the 47 ablation zones, 47 (100%) were clearly depicted with CEUS-CECT/CEMRI fusion imaging, 36 (76.6%) with US-CECT/CEMRI fusion imaging and 21 (44.7%) with conventional US (both p < 0.001). The minimal ablative safety margins were great than or equal to 5 mm in 28 ablation zones, between 0 and 5 mm in 15, and less than 0 mm in 4. For the four lesions without enough ablative safety margin, three were referred to follow-up because CEUS showed larger ablation zones than pre-treatment lesions and the remaining lesion was subject to additional RFA 5 days after the first RFA. The CR rate was 95.7% (45/47) with reference to CECT/CEMRI results 1 month after RFA. During 2 to 34 months follow-up, LTP was found in two (4.4%) of 45 lesions with CR. Insufficient ablative safety margin was more commonly found in those lesions with LTP than those without LTP (1/4 vs 1/43, p < 0.001).

CONCLUSION

Fusion imaging with post-treatment CEUS and pre-treatment CECT/CEMRI can depict the ablative safety margin accurately after RFA. Inadequate ablative safety margin is associated with LTP. Depiction of ablative safety margin by fusion imaging after ablation might be considered as a routine procedure to assess the treatment response of RFA. Advances in knowledge: Fusion imaging with post-treatment CEUS and pre-treatment CECT/CEMRI is an effective method to evaluate the ablative safety margin early after RFA. Therefore, it should be recommended to be used as a routine procedure after RFA for liver cancers.

Association between BRAF V600E Mutation and Ultrasound Features in Papillary Thyroid Carcinoma Patients with and without Hashimoto's Thyroiditis

To assess the association between BRAF V600E mutation and ultrasound (US) features in papillary thyroid carcinoma (PTC) patients with and without Hashimoto’s thyroiditis (HT). We retrospectively reviewed the US features and status of BRAF V600E mutation in 438 consecutive patients with surgically confirmed PTCs. The association between BRAF mutation and US features were analyzed. In addition, we conducted subgroup analyses in terms of coexistent HT. The BRAF mutation was found in 86.5% of patients (379 of 438). Patient age (OR: 1.028, P = 0.010), age ≥ 50 y (OR: 1.904, P = 0.030), and microcalcification (OR: 2.262, P = 0.015) on US were significantly associated with BRAF mutation in PTC patients. Solid component (OR: 5.739, P = 0.019) on US was the significant predictor for BRAF mutation in patients with HT, while age (OR: 1.036, P = 0.017) and microcalcification (OR: 3.093, P = 0.017) were significantly associated with BRAF mutation in patients without HT. In conclusion, older age and microcalcification are risk factors for BRAF mutation in PTC patients, especially in those without HT. For those with HT, however, PTCs with BRAF mutation tend to be solid on ultrasound. These factors might be considered when making treatment planning or prognosis evaluation.

The diagnostic performances of conventional strain elastography (SE), acoustic radiation force impulse (ARFI) imaging and point shear-wave speed (pSWS) measurement for non-calcified thyroid nodules

BACKGROUND

Non-calcified thyroid nodules are relatively difficult to diagnose only relying on features of at conventional US images.

OBJECTIVE

To investigate the diagnostic performances of conventional strain elastography (SE), acoustic radiation force impulse (ARFI) SE and point shear-wave speed (pSWS) measurement for non-calcified thyroid nodules.

METHODS

A total of 201 non-calcified thyroid nodules in 195 patients were studied. They were examined with conventional ultrasound (US), conventional SE, ARFI SE and pSWS measurement. Their diagnostic performances and multivariable models were assessed with receiver operating characteristic (ROC) curve and logistic regression analyses respectively.

RESULTS

There were 156 benign and 45 malignant non-calcified nodules proven by histopathology or cystology. The mean diameters of the nodules were 21.2±10.8 mm. Areas under receiver operating characteristic curve (AUCs) of elastography features (ranged, 0.488-0.745) were all greater than that of US (ranged, 0.111-0.332). At multivariate analysis, there were three predictors of malignancy for non-calcified nodules, including pSWS of nodule (odds ratio [OR], 34.960; 95% CI, 11.582-105.529), marked hypoechogenicity (OR, 16.223; 95% CI, 1.761-149.454) and ARFI SE grade (OR, 10.900; 95% CI, 3.567-33.310). US+SE+pSWS owned the largest AUC (0.936; 95% CI, 0.887-0.985; P < 0.05), followed by US+pSWS (0.889; 95% CI, 0.823-0.955), and the poorest was US (0.727; 95% CI, 0.635-0.819).

CONCLUSIONS

ARFI SE and pSWS measurement had better diagnostic performances than conventional SE and US. When US combined with SE and pSWS measurement, it could achieve an excellent diagnostic performance and might contribute a better decision-making of FNA for non-calcified thyroid nodules.

Virtual touch tissue imaging and quantification (VTIQ) in the evaluation of thyroid nodules: the associated factors leading to misdiagnosis

To evaluate the associated factors leading to misdiagnosis with VTIQ for differentiation between benign from malignant thyroid nodules (TNs). The study included 238 benign TNs and 150 malignant TNs. Conventional ultrasound (US) features and VTIQ parameters were obtained and compared with the reference standard of histopathological and/or cytological results. Binary logistic regression analysis was performed to select independent variables leading to misdiagnosis. The maximum shear wave speed (SWS) (SWS-max), mean SWS (SWS-mean), SWS-ratio and standard deviation of SWS (SWS-_SD) were significantly higher for malignant TNs compared with benign TNs (all P < 0.001). SWS-mean achieved the highest diagnostic performance with a cut-off value of 3.15 m/s. False positive rate was 13.4% (32/238) while false negative rate was 35.3% (53/150). Intranodular calcification (OR: 1.715) was significantly associated with false positive VTIQ findings, while nodule size (OR: 0.936) and echotexture of the thyroid gland (OR: 0.033) were negatively associated with them. Nodule depth (OR: 0.881) and TI-RADS category (OR: 0.563) were negatively associated with false negative VTIQ findings. These US characteristic of TNs should be taken into consideration when interpreting the results of VTIQ examinations.

Comparison of fine needle aspiration and non-aspiration cytology for diagnosis of thyroid nodules: A prospective, randomized, and controlled trial

OBJECTIVES

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.

MATERIALS AND METHODS

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.

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).

CONCLUSIONS

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.

Quality measurement on shear wave speed imaging: diagnostic value in differentiation of thyroid malignancy and the associated factors

To evaluate the associated factors for quality measurement (QM) on shear wave speed (SWS) imaging and the additional value of QM for differentiation of thyroid nodules. A consecutive series of 238 patients with 254 thyroid nodules were enrolled. They were all evaluated by conventional ultrasound and SWS imaging and were finally proven pathologically. QM was used to assess whether SWS propagation was authentic and was classified as high QM and Low QM. Twelve variables were analyzed to evaluate the associated factors for QM using binary logistic regression. Receiver operating characteristic (ROC) curve was plotted on SWS and SWS+QM. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy and area under ROC curve (AUC) were calculated. The study included 170 benign thyroid nodules (160 high QM and 10 low QM) and 84 malignant thyroid nodules (56 high QM and 28 low QM) (P < 0.001). The mean SWS of benign and malignant nodules were 2.51 ± 0.47 m/s and 3.43 ± 1.21 m/s respectively (P < 0.001). The sensitivities, specificities, PPVs, NPVs, accuracies and AUCs were 77.4%, 80.0%, 65.7%, 87.7%, 79.1%, 0.82 for SWS alone with SWS ≥ 2.78 m/s; 33.3-34.5%, 91.2-94.1%, 65.9-73.7%, 73.8-74.1%, 72.4-74.0%, 0.63-0.64 for QM alone and 84.5-85.7%, 72.4-75.9%, 60.5-63.4%, 90.8-91.0%, 76.8-78.7%, 0.79-0.80 for SWS+QM. Nodule depth was identified to be the strongest associated factor for QM of SWS, followed by malignancy and SWS. In conclusion, QM for thyroid nodule is associated with nodule depth, malignancy, and SWS. QM improves the specificity in comparison with SWS alone, whereas SWS+QM does not improve the overall diagnostic performance.