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.

Value of contrast-enhanced ultrasonography in microwave ablation treatment of symptomatic focal uterine adenomyosis.

PURPOSE: This study evaluated the value of contrast-enhanced ultrasonography (CEUS) in the ultrasound-guided microwave ablation (MWA) treatment of symptomatic focal uterine adenomyosis. METHODS: This retrospective study was conducted between March 2020 and January 2023, enrolling 52 patients with symptomatic focal uterine adenomyosis who had undergone MWA. All patients were examined with CEUS before and after MWA. The non-perfused volume (NPV) was compared between CEUS and dynamic contrast-enhanced magnetic resonance imaging (DCEMRI) following ablation. Therapeutic efficacy and safety were evaluated at 3-, 6-, and 12-month follow-ups. Additionally, this study explored the correlations between pre-treatment CEUS features and a volume reduction ratio indicating sufficient ablation, defined as 50% or more at the 3-month follow-up. RESULTS: No significant differences in NPV were noted between CEUS and DCE-MRI immediately after MWA and during follow-up (all P>0.05). At the 3-month follow-up, the median VRRs for the uterus and adenomyosis were 33.2% and 63.9%, respectively. Sufficient ablation was achieved in 69.2% (36/52) of adenomyosis cases, while partial ablation was observed in the remaining 30.8% (16/52). The identification of non-enhancing areas on pre-treatment CEUS was associated with sufficient ablation (P=0.016). At the 12-month follow-up, significant decreases were observed in both the uterine and adenomyosis volumes (all P<0.001). Dysmenorrhea and menorrhagia were significantly alleviated at 12 months, and no major complications were encountered. CONCLUSION: CEUS can be used to evaluate the ablation zone of focal adenomyosis that has been treated with MWA, similarly to DCE-MRI. The identification of non-enhancing areas on pretreatment CEUS indicates satisfactory treatment outcomes.

Baseline and contrast-enhanced ultrasound features of hepatic epithelioid angiomyolipoma.

BACKGROUND: Recurrence or metastasis after surgery had been reported in hepatic epithelioid angiomylipoma (epi-AML). Most hepatic epi-AMLs were misdiagnosed with hepatocellular carcinoma or other hepatic tumors before surgery. OBJECTIVE: To describe the baseline and contrast-enhanced ultrasound (CEUS) features of hepatic epi-AMLs and to explore the potential ultrasonic features for prognosis. METHODS: The retrospective study enrolled 67 patients (56 females, 11 males) with 67 pathologically confirmed hepatic epi-AML lesions. All the lesions were examined by baseline ultrasound and 42 lesions were examined using CEUS with SonoVue (Bracco, Milan, Italy) before surgery. RESULTS: Baseline ultrasound features of hepatic epi-AMLs included heterogeneous echo (86.6%), well-defined border (68.7%), hypoecho (64.2%), regular morphology (62.7%), peripheral-tumor arc-shaped or ring-like vessels (53.7%), and low value of resistive index (0.51±0.08). CEUS features of hepatic epi-AMLs included arterial phase hyper-enhancement with smooth and well-defined margin (100%), peripheral-tumor ring-like vessels (57.1%), and intra-tumor vessels (52.4%). Some CEUS features, including arterial phase heterogeneously tortuous filling, intra-tumor vessels and peripheral-tumor ring-like vessels were more commonly found in hepatic epi-AMLs of uncertain malignant potential/malignant than in benign hepatic epi-AMLs (p < 0.05). CONCLUSIONS: Baseline ultrasound and CEUS features may be useful in diagnosis of hepatic epi-AML, and some CEUS features may be indicative of its malignant potential.

Contrast-Enhanced Ultrasound Features of Hepatic Reactive Lymphoid Hyperplasia: Correlation With Histopathologic Findings.

OBJECTIVES: To find certain specifics of hepatic reactive lymphoid hyperplasia (HRLH) on contrast-enhanced ultrasound (CEUS) imaging as diagnostic imaging clues by retrospectively analyzing its enhancement features. METHODS: From June 2010 to June 2017, 18 histopathologically confirmed HRLH lesions in 18 patients were included in this retrospective study. The lesion's location, maximum diameter, shape, margin, echogenicity, and color flow signal on conventional ultrasound (US) imaging and enhancement pattern, presence of a feeding artery, and donutlike enhancement on CEUS imaging were observed and recorded. The lesion size on CEUS imaging at peak enhancement and that on conventional US imaging were compared and recorded. RESULTS: All of the lesions showed homogeneous hypoechogenicity with a regular well-defined margin on conventional US imaging, with a mean diameter ± SD of 14.3 ± 4.6 mm (range, 8-24 mm). On CEUS imaging, all of the lesions showed "quick-wash-in and quick-wash-out," which showed complete homogeneous hyperenhancement in the arterial phase and wash-out in the second half of the arterial phase or first half of the portal phase. In 83.3% (15 of 18) of the lesions, the lesion size that was enhanced at peak was enlarged compared with the hypoechoic area on conventional US imaging, and transient donutlike enhancement appeared when the lesion showed wash-out. In 55.6% (10 of 18) of cases, the feeding artery was detected. CONCLUSIONS: Enlarged complete homogeneous hyperenhancement in the arterial phase, consequently followed by quick wash-out of the lesion and the appearance of donutlike enhancement, may be the CEUS features of HRLH.

Xanthogranulomatous cholecystitis: contrast-enhanced ultrasound features and differential diagnosis from wall-thickening gallbladder carcinoma.

OBJECTIVE: The purpose of this study is to evaluate the value of contrast-enhanced ultrasound (CEUS) in differential diagnosis of Xanthogranulomatous cholecystitis (XGC). MATERIAL AND METHODS: Patients of 17 XGCs and 43 wall-thickening gallbladder carcinomas (GBCs) were enrolled in this study. Firstly, we compared the ability of conventional ultrasound (CUS) and CEUS in detecting gallbladder (GB) features. Secondly, XGCs and GBCs features were compared on CEUS. Finally, all valuable indicators were ranked by Odds ratio. RESULTS: Significant differences were found in detecting GB wall thickness, GB stones, and hypoechoic nodules frequencies by CEUS and CUS. The mean GB wall thickness was 8.53 mm on CEUS, whereas the thickness measured 9.47 mm on CUS (p=0.011). GB stones and hypoechoic nodules were detected in 43 cases (71.7%) and 21 cases (30.0%) on CEUS, respectively, compared to 29 cases (48.3%) and 8 cases (13.3%) on CUS (p=0.009, p=0.027), respectively. Secondly, hypoenhancement time was longer in XGC (mean 78.9 s) than in GBC (mean 56.0 s) (p=0.002). Diffuse GB wall thickening, continuous inner wall, and hypoechoic nodules in the GB wall were observed in 12 patients (70.6%), 12 patients (70.6%) and 10 patients (58.8%) with XGC, respectively, compared to detection in 10 patients (23.3%), 4 patients (9.3%) and 11 patients (25.6%) by GBC (p=0.001, p=0.000 and p=0.015), respectively. Thirdly, the continuous inner wall was the most valuable indicator, with ORs of 23.4. The second valuable indicator was hypoenhancement time >80.5 s, with ORs of 11.9. CONCLUSIONS: CEUS demonstrated superior detection of GB wall thickness, GB stone and hypoechoic nodules compared to CUS. A continuous inner wall, hypoenhancement times greater than 80.5 s, diffuse thickening, and hypoechoic nodules were valuable indicators in XGCs.

Ultrasound features of hepatocellular adenoma and the additional value of contrast-enhanced ultrasound.

BACKGROUND: Hepatocellular adenoma (HCA) is a rare benign tumor of the liver. It is of clinical importance to differentiate HCA from other liver tumors, especially hepatocellular carcinoma (HCC). This study aimed to evaluate the characteristic features of HCA by conventional ultrasound and contrast-enhanced ultrasound (CEUS) findings. METHODS: Twenty-six patients (10 males and 16 females; mean age 36.2+/-5.0 years) with 26 histopathologically proven HCAs were retrospectively identified. According to the maximum diameter of HCAs, they were divided into three groups: <30 mm, 30-50 mm, and >50 mm. Ultrasound examinations were performed with C5-2 broadband curved transducer of Philips iU22 unit (Philips Bothell, WA, USA). For each lesion, a dose of 2.4 mL SonoVue® (Bracco Imaging Spa, Milan, Italy) was injected as a quick bolus into the cubital vein. Lesions' echogenicity, color-Doppler flow imaging and contrast enhancement patterns were recorded. RESULTS: Grayscale ultrasound revealed that most of HCAs were hypoechoic (73.1%, 19/26). Spotty calcifications were detected in 26.9% (7/26) of the lesions. Color-Doppler flow imaging detected centripetal bulky color flow in 46.2% (12/26) of the HCAs. CEUS showed that 73.1% (19/26) of the HCAs displayed as rapid, complete and homogenous enhancement, and 53.8% (14/26) showed decreased contrast enhancement in the late phase. There was no significant difference in enhancement patterns among different sizes of HCAs (P>0.05). Centripetal enhancement with subcapsular tortuous arteries was common in larger HCAs. CONCLUSIONS: CEUS combined with grayscale and color-Doppler flow imaging helped to improve preoperative diagnosis of HCAs. The characteristic imaging features of HCAs included: rapid homogeneous enhancement and slow wash-out pattern on CEUS; heterogeneous echogenicity on grayscale ultrasound; and centripetal enhancement with subcapsular tortuous arteries in large HCAs.

Evaluation of Liver Metastases Using Contrast-Enhanced Ultrasound: Enhancement Patterns and Influencing Factors.

BACKGROUND/AIMS: To evaluate the enhancement patterns of liver metastases and their influencing factors using dynamic contrast-enhanced ultrasound (CEUS). METHODS: A total of 240 patients (139 male and 101 female; 58.5 ± 11.2 years of age) diagnosed with liver metastases in our hospital were enrolled in this study to evaluate tumor characteristics using CEUS. A comparison of enhancement patterns with tumor size and primary tumor type was performed using the chi-square test. The differences between quantitative variables were evaluated with the independent-sample t-test and one-way analysis of variance. RESULTS: The enhancement patterns of liver metastases on CEUS were categorized as diffuse homogeneous hyperenhancement (133/240, 55.4%), rim-like hyperenhancement (80/240, 33.3%), heterogeneous hyperenhancement (10/240, 4.2%), and isoenhancement (17/240, 7.1%). There were significant differences in the enhancement patterns during the arterial phase based on the nodule size (p=0.001). A total of 231 of the nodules showed complete washout during the portal phase, and 237 nodules were hypoenhanced during the delayed phase. The washout time was correlated with tumor vascularity, with a longer washout time observed in hypervascular metastases compared to hypovascular metastases (p=0.033). CONCLUSIONS: Diffuse homogeneous hyperenhancement followed by rapid washout was the most common enhancement pattern of liver metastases on CEUS and was affected by the nodule size and tumor vascularity. Small metastases were prone to show diffuse homogeneous hyperenhancement. Hypervascular metastases showed a significantly longer washout time compared to hypovascular metastases.

Application of imaging fusion combining contrast-enhanced ultrasound and magnetic resonance imaging in detection of hepatic cellular carcinomas undetectable by conventional ultrasound.

BACKGROUND AND AIM: The aim of this study is to explore the value of volume navigation image fusion-assisted contrast-enhanced ultrasound (CEUS) in detection for radiofrequency ablation guidance of hepatocellular carcinomas (HCCs), which were undetectable on conventional ultrasound. METHODS: From May 2012 to May 2014, 41 patients with 49 HCCs were included in this study. All lesions were detected by dynamic magnetic resonance imaging (MRI) and planned for radiofrequency ablation but were undetectable on conventional ultrasound. After a bolus injection of 2.4 ml SonoVue® (Bracco, Italy), LOGIQ E9 ultrasound system with volume navigation system (version R1.0.5, GE Healthcare, Milwaukee, WI, USA) was used to fuse CEUS and MRI images. The fusion time, fusion success rate, lesion enhancement pattern, and detection rate were analyzed. RESULTS: Image fusions were conducted successfully in 49 HCCs, the technical success rate was 100%. The average fusion time was (9.2 ± 2.1) min (6-12 min). The mean diameter of HCCs was 25.2 ± 5.3 mm (mean ± SD), and mean depth was 41.8 ± 17.2 mm. The detection rate of HCCs using CEUS/MRI imaging fusion (95.9%, 47/49) was significantly higher than CEUS (42.9%, 21/49) (P < 0.05). For small HCCs (diameter, 1-2 cm), the detection rate using imaging fusion (96.9%, 32/33) was also significantly higher than CEUS (18.2%, 6/33) (P < 0.01). All HCCs displayed a rapid wash-in pattern in the arterial phase of CEUS. CONCLUSIONS: Imaging fusion combining CEUS and MRI is a promising technique to improve the detection, precise localization, and accurate diagnosis of undetectable HCCs on conventional ultrasound, especially small and atypical HCCs.

Primary non-Hodgkin's lymphoma of the liver: sonographic and CT findings.

BACKGROUND: A preoperative diagnosis of primary hepatic lymphoma (PHL) can have profound therapeutic and prognostic implications. Because of the rarity of PHL, however, there are few reports on diagnostic imaging. We reviewed the clinical and radiologic findings of 29 patients with PHL, the largest series to date, to evaluate the diagnostic features of this disease. METHODS: Clinical data and radiologic findings at presentation were retrospectively reviewed for 29 patients with pathologically confirmed PHL from January 2005 to June 2013. Imaging studies, including ultrasound (US) (n=29) and contrast-enhanced computed tomography (CECT) (n=24), were performed within 2 weeks before biopsy or surgery. RESULTS: Among the 29 patients, 23 (79%) were positive for hepatitis B virus (HBV) and 26 (90%) had a significantly elevated level of serum lactate dehydrogenase (LDH). There were two distinct types of PHL on imaging: diffuse (n=5) and nodular (n=24). Homogeneous or heterogeneous hepatomegaly was the only sign for diffuse PHL on both US and CECT, without any definite hepatic mass. For the nodular type, 63% (15/24) of patients had solitary lesions and 38% (9/24) had multiple lesions. On US, seven patients displayed patchy distribution with an indistinct tumor margin and a rich color flow signal. CECT showed rim-like enhancement (n=3) and slightly homogeneous or heterogeneous enhancement (n=14) in the arterial phase and isoenhancement (n=5) and hypoenhancement (n=12) in the portal venous and late phases. Furthermore, in five patients, CT revealed that hepatic vessels passed through the lesions and were not displaced from the abnormal area or appreciably compressed. CONCLUSIONS: The infiltration type of PHL was associated with the histologic subtype. Considered together with HBV positivity and elevated LDH, homogeneous or heterogeneous hepatomegaly may indicate diffuse PHL, whereas patchy distribution with a rich color flow signal on US or normal vessels extending through the lesion on CECT may be the diagnostic indicators of nodular PHL.

Tissue elasticity quantification by acoustic radiation force impulse for the assessment of renal allograft function.

Acoustic radiation force impulse (ARFI) quantification, a novel ultrasound-based elastography method, has been used to measure liver fibrosis. However, few studies have been performed on the use of ARFI quantification in kidney examinations. We evaluated renal allograft stiffness using ARFI quantification in patients with stable renal function (n = 52) and those with biopsy-proven allograft dysfunction (n = 50). ARFI quantification, given as shear wave velocity (SWV), was performed. The resistance index (RI) was calculated by pulsed-wave Doppler ultrasound, and clinical and laboratory data were collected. Morphologic changes in transplanted kidneys were diagnosed by an independent pathologist. Mean SWV was more significantly negatively correlated with estimated glomerular filtration rate (eGFR) (r = -0.657, p < 0.0001) than was RI (r = -0.429, p = 0.0004) in transplanted kidneys. Receiver operating characteristic curve analysis revealed that the sensitivity and specificity of quantitative ultrasound in the diagnosis of renal allograft dysfunction were 72.0% and 86.5% (cutoff value = 2.625), respectively. The latter values were better than those of RI, which were 62.0% and 69.2% (cutoff value = 0.625), respectively. The coefficient of variation for repeat SWV measurements of the middle part of transplanted kidney was 8.64%, and inter-observer agreement on SWV was good (Bland-Altman method, ICC = 0.890). In conclusion, tissue elasticity quantification by ARFI is more accurate than the RI in diagnosing renal allograft function.

[Diagnosis of atypical liver abscesses with real-time contrast-enhanced ultrasound].

OBJECTIVE: To investigate the value of real-time harmonic contrast-enhanced ultrasound (CEUS) in the diagnosis of atypical liver abscesses. METHODS: We used Technos DU8 system with CEUS technique to examine 32 patients with suspected liver masses. Mechanical index was set at 0.08- 0.11. The contrast agent SonoVue was injected as a bolus (2.4 ml, < 5s) in the antecubital vein. RESULTS: A total of 36 lesions were studied in 32 patients, including 30 patients with single nodule and 2 patients with multiple nodules. All lesions with liver abscess were confirmed by biopsy. The whole-enhanced pattern in all lesions was clearly displayed in the arterial phase after the administration of SonoVue. The mean time of the beginning enhancement was (14.48 +/- 3.62) s, the mean peak enhancement time was (22.92 +/- 4.35) s, and the mean time of hypoechoic appearance of lesion was (80.30 +/- 35.30) s. The lesions with hypoechoic pattern (37.5%, 12/32) and isoechoic pattern (62.5%, 20/32) in the portal phase were detected by CEUS. The characteristic sign with honeycomb pattern on CEUS was shown in 30 (93.8%) liver abscess lesions. CONCLUSION: CEUS is valuable in the diagnosis of atypical liver abscesses.