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.

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.

[Intravenous contrast-enhanced ultrasound of metastatic lymph nodes in rabbit VX2 tongue carcinoma model].

OBJECTIVE: To investigate the sonographic features of the cervical lymph nodes in rabbit VX2 tongue carcinoma model and hyperplasia cervical lymph nodes model using gray scale contrast-enhanced ultrasonography (CEUS) after intravenous administration of SonoVue (a sonographic contrast agent) and to evaluate the potential utility of CEUS in detecting early metastatic cervical lymph nodes in the rabbit VX2 tongue carcinoma model. METHODS: Twenty New Zealand rabbits were placed into 2 groups, 12 for node metastasis and 18 for node hyperplasia. Cervical CEUS was performed in the rabbits of both groups before and after intravenous administration of SonoVue(0.6 ml). The phase, pattern, beginning area and echogenicity of enhancement of the lymph nodes on the right neck were observed and recorded. Dissection of the lymph nodes were guided by the marks made during CEUS and examined histopathologically. RESULTS: On the right side of each rabbit only one lymph node were detected in both groups. All 8 cases in the hyperplasia group showed homogeneous enhancement starting from central, while in the metastasis group one case showed homogeneous enhancement starting from the central, 3 cases showed inhomogeneous enhancement starting from periphery, and 8 cases showed inhomogeneous enhancement starting both from central and periphery. One lymph node was dissected on the right side of the neck in each rabbit in both groups. Pathological examination showed all 12 lymph nodes in the metastatic group were metastatic lymph nodes, and all 8 lymph nodes in the hyperplasia group were hyperplastic lymph nodes. CONCLUSIONS: After intravenous CEUS, metastatic lymph nodes show inhomogeneous enhancement starting from periphery/central or periphery area, while hyperplastic lymph nodes show homogeneous enhancement starting from central area. Metastatic lymph nodes can be characterized as being neoplastic or benign on the basis of the enhancement patterns evaluated by CEUS.