The ultrasound-based radiomics-clinical machine learning model to predict papillary thyroid microcarcinoma in TI-RADS 3 nodules.

Background: Conventional ultrasound (CUS) technology has proven to be successful in the identification of thyroid nodules. Moreover, the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) was developed for the purpose of evaluating the risk of thyroid nodules based on ultrasound imaging. Nevertheless, identifying papillary thyroid microcarcinoma (PTMC) from TI-RADS 3 nodules using this system can be difficult due to overlapping morphological features. The main objective of this study was to investigate the efficacy of a machine learning model that utilizes ultrasound-based radiomics features and clinical information in accurately predicting the presence of PTMC in TI-RADS 3 nodules. Methods: A total of 221 patients with TI-RADS 3 nodules were included, consisting of 91 cases of PTMC and 130 benign thyroid nodules. They were randomly divided into training and test cohort in an 8:2 ratio. Radiomics features were extracted from CUS images by manually outlining the targets, while clinical parameters were obtained from electronic medical records. The radiomics model, clinical model, and combined model were constructed and validated to distinguish between PTMC and benign thyroid nodules. Radiomics variables were extracted via the Pyradiomics package (V1.3.0). Moreover, least absolute shrinkage and selection operator (LASSO) regression was used for feature selection. Light Gradient Boosting Machine (LightGBM) was employed to build both radiomics and clinical models. Ultimately, a radiomics-clinical model, which fused radiomics features with clinical information, was developed. Results: Among a total of 1,477 radiomics features, fifteen features that were found to be associated with PTMC through univariate analysis and LASSO regression were selected for the development of the radiomics model. The combined "radiomics-clinical" model demonstrated superior diagnostic accuracy compared to the clinical model for distinguishing PTMC in both the training dataset [area under receiver operating curve (AUC): 0.975 vs. 0.845] and the validation dataset (AUC: 0.898 vs. 0.811). We constructed a radiomics-clinical nomogram, and the clinical applicability was confirmed through decision curve analysis. Conclusions: Utilizing an ultrasound-based radiomics approach has proven to be effective in predicting PTMC in patients with TI-RADS 3 nodules.

Comparing endoscopic ultrasonography and double contrast-enhanced ultrasonography in the preoperative diagnosis of gastric stromal tumor.

BACKGROUND: This study was designed to perform a comparative analysis between endoscopic ultrasonography (EUS) and double contrast-enhanced ultrasonography (DCEUS) for the preoperative diagnosis of gastric stromal tumors (GSTs). METHODS: A retrospective study was conducted involving 139 patients with histologically confirmed GSTs. All patients preoperatively underwent DCEUS and EUS. The pathology reports were treated as the baseline and were retrospectively compared with the findings of EUS and DCEUS. RESULTS: Of the 139 lesions, 120 and 113 were correctly identified by DCEUS and EUS, respectively, with an accuracy of 86.3% and 81.3%. The results revealed an insignificant difference between these two methods (p = 0.189). CONCLUSIONS: DCEUS can display not only the locations, sizes, shapes, borders, internal echoes, but also show the blood perfusion patterns of GSTs. It is a highly accurate, noninvasive, and convenient method to be used at the pre-treatment stage.

Application of Transperineal Pelvic Floor Ultrasound in Changes of Pelvic Floor Structure and Function Between Pregnant and Non-Pregnant Women.

Objective: To evaluate the changes of pelvic floor tissue structure and function between pregnant and non-pregnant women from the view of transperineal pelvic floor ultrasound. Methods: Thirty-eight cases of women with a second singleton pregnancy and thirty-two cases of women with a first singleton pregnancy underwent transperineal pelvic floor ultrasound, and their results were compared with forty-two cases of healthy non-pregnant women. Results: The differences of bladder neck descent (BND), rectal ampulla distance and levator hiatus area (LHA) among the three groups were statistically significant (P<0.05), and the differences of BND, rectal ampulla distance, LHA between the women with a second singleton pregnancy group and non-pragnent group were statistically significant (P<0.05). The BND, retrovesical angle at rest (RVA-R) and retrovesical angle underwent Valsalva maneuver (RVA-V) in the group of stress urinary incontinence (SUI) during pregnancy were larger than those in non-SUI group, with significant difference (P<0.05), especially BND and RVA-V (P = 0.00). Conclusion: Transperineal pelvic floor ultrasound has a high resolution of pelvic floor structure and function changes during pregnancy, and can dynamically evaluate pelvic floor function, providing a theoretical basis for early diagnosis and prevention of female pelvic floor dysfunction (FPFD) in subsequent pregnancies.

Differential Efficacy of B-Ultrasound Combined with Molybdenum Target Detection Mode for Breast Cancer Staging and Correlation of Blood Flow Parameters with IGF-1 and IGF-2 Expression Level and Prognosis.

The study investigates the diagnostic efficacy of ultrasound combined with the molybdenum target mode in breast cancer staging and the relationship between blood flow parameters and the expression of insulin-like growth factor 1 (IGF-1) and factor 2 (IGF-2) and prognosis. A total of 96 patients admitted to hospital from January 2020 to January 2021 are included in the breast cancer group, and 58 patients admitted to our hospital during the same period are included in the control group, who are diagnosed with benign breast lesions. All patients receive clinicopathological diagnosis, ultrasound detection, and X-ray molybdenum detection. Ultrasound detection, molybdenum target detection, ultrasound combined with the molybdenum target detection mode, and clinicopathological diagnosis results are compared. B-ultrasound combined with the molybdenum target detection mode has high efficiency in diagnosing breast cancer and differentiating pathological stages. Besides, blood flow parameters of patients are closely related to IGF-1 and IGF-2, and IGF-1 and IGF-2 expressions are closely related to the prognosis of patients. Subsequent diagnosis of the disease degree of breast cancer patients can be carried out by ultrasound combined with the molybdenum target detection mode. In addition, the expression of IGF-1 and IGF-2 in patients can be monitored to improve the clinical diagnosis and treatment plan to improve the prognosis of patients, which has a high clinical application value and is worth promoting.

B-Ultrasound Image Analysis of Intrauterine Pregnancy Residues after Mid-Term Pregnancy Based on Smart Medical Big Data.

Abdominal B-ultrasound images of intrauterine pregnancy tissue residues were analyzed to discuss their diagnostic value. With the rapid development of computer technology and medical imaging technology, doctors are also faced with more and more medical image diagnosis tasks, and computer-aided diagnosis systems are especially important in order to reduce the work pressure of doctors. In recent years, deep learning has made rapid development and achieved great breakthroughs in various fields. In medical-aided diagnostic systems, deep learning has greatly improved the diagnostic efficiency, but there are no mature research results for abdominal B-ultrasound image recognition of intrauterine pregnancy tissue residues. Therefore, the study of liver ultrasound image classification based on deep learning has important practical application value. In this paper, we propose to give a CNN model optimization method based on grid search. Compared with the conventional CNN model design, this method saves time and effort by eliminating the need to manually adjust parameters based on experience and has an accuracy of more than 92% in classifying abdominal B-ultrasound images of intrauterine pregnancy tissue residues. The diagnosis of intrauterine pregnancy tissue residues by abdominal B-ultrasound can effectively improve the diagnosis and provide important reference for patients to receive treatment, which has high diagnostic value.

Difference in Perfusion Parameters Between Gastric Cancer and Gastric Stromal Tumors: Evaluation With Oral Contrast Plus Contrast-Enhanced Ultrasonography.

Objective: To explore the difference of perfusion parameters between gastric cancer (GC) and gastric stromal tumors (GSTs) by using oral contrast plus contrast-enhanced ultrasonography (OC+CEUS). Methods: We retrospectively reviewed 149 patients with histologically confirmed gastric lesions (80 patients with GC and 69 patients with GST). OC+CEUS was performed in all patients in the GC group and the GST group before surgery. The cine loops of OC+CEUS of all cases were analyzed. The perfusion parameters including arrival time (AT), time to peak (TTP), basal intensity (BI), and peak intensity (PI) were obtained via a program designed for autotracking contrast quantification (ACQ). The between-group differences in these parameters were compared. Results: According to time-intensity curve (TIC) analysis, high-risk GST had higher PI than low-risk GST (P < 0.05). GC had faster AT and higher PI than normal gastric wall (P < 0.05); GST had higher PI than normal gastric wall (P < 0.05). Furthermore, the GC group had faster AT and higher PI than the GST group (P < 0.05). In contrast, the difference in BI and peak time (TTP) between the groups was not significant (P > 0.05). Conclusion: AT and PI differ significantly between the GC group and the GST group. As a new method, OC+CEUS has value for the differential diagnosis of GC and GST.

Double Contrast-Enhanced Ultrasonography in Preoperative T Staging of Gastric Cancer: A Comparison With Endoscopic Ultrasonography.

Objective: To compare the precision of double contrast-enhanced ultrasonography (DCEUS) to endoscopic ultrasonography (EUS) in preoperative T staging of gastric cancers. Methods: This retrospective study consisted of 158 pathologically confirmed gastric cancer patients. All patients underwent DCEUS (intravenous contrast-enhanced ultrasonography combined with oral contrast-enhanced ultrasonography) and endoscopic ultrasonography (EUS) preoperatively. The histopathological findings of resected specimens were compared with the results of DCEUS and EUS retrospectively. Results: The accuracy of DCEUS and EUS in evaluating the T staging of gastric cancer were 82.3% (T1 62.5%,T2 84.4%,T3 87.9%,T4 91.3%) and 76.6% (T1 84.4%,T2 82.2%,T3 72.4%,T4 65.2%), respectively. There were no significant differences between the methods for the overall T staging accuracy (χ2 = 1.569, P = 0.210). But EUS was superior to DCEUS for T1 stage (χ2 = 3.925, P = 0.048) and DCEUS was superior to EUS for T3 stage (χ2 = 4.393, P = 0.036) and T4 stage (χ2 = 4.600, P = 0.032). Conclusion: DCEUS is a convenient and noninvasive method with high precision, which can be used as the primary imaging technique for advanced gastric cancer T staging. In early gastric cancer, we should prefer EUS. Two methods are complementary for assessing tumor invasion depth of gastric cancer.

Comparing single oral contrast-enhanced ultrasonography and double contrast-enhanced ultrasonography in the preoperative Borrmann classification of advanced gastric cancer.

OBJECTIVES: To evaluate the accuracy of double contrast-enhanced ultrasonography (DCEUS) in preoperative Borrmann classification of advanced gastric cancer (AGC). MATERIALS AND METHODS: A total of 162 patients histologically confirmed AGC were enrolled into this study. Single oral contrast-enhanced ultrasonography (SOCEUS) were performed in 80 patients and DCEUS (intravenous microbubbles combined with oral contrast-enhanced ultrasound) were performed in 82 patients preoperatively. The findings of the histopathologic examination of resected specimens after surgery were considered as gold standard. The accuracy of SOCEUS was compared with the accuracy of DCEUS in determining Borrmann classification. Interobserver agreement between two sonographyers of SOCEUS and DCEUS had also been assessed. RESULTS: The accuracy of SOCEUS and DCEUS in Borrmann classification of advanced gastric cancer were 78.75% and 91.46% respectively. There was a significant difference between two methods (χ2 = 5.186, P < 0.05). The interobserver agreement of two methods was both excellent for assessing the Borrmann classification with a Kappa value of 0.777 by SOCEUS and 0.844 by DCEUS. CONCLUSIONS: DCEUS is a valuable method for Borrmann classification with its high accuracy preoperatively. It should be used widely.

The therapeuatic effect of Endostar on soft carotid plaque neovascularization in patients with non-small cell lung cancer.

The purpose of this study was to investigate the effect of the angiogenesis inhibitor Endostar on carotid plaque neovascularization in patients with non-small cell lung cancer (NSCLC) using contrast-enhanced ultrasound (CEUS). Ninety-one patients who had NSCLC with soft carotid plaques were selected for treatment either with the NP regimen (vinorelbine + cisplatin) (43 patients) or with the ENP regimen (Endostar + NP) (48 patients). Plaque thickness and neovascularization of the plaque were assessed before and at 1 month after treatment using CEUS. Enhanced intensity (EI) of CEUS was used for quantification of plaque neovascularization. There was no significant changes in any group in thickness of plaque between recruitment and 1 month after treatment (P > 0.05 for all). There was no significant change in the EI of plaque in the controls or NP groups at 1 month after treatment (P > 0.05), while EI in the ENP group was significantly reduced at 1 month after treatment (P < 0.01) and significantly lower than that in the controls or NP group at 1 month after treatment (P < 0.001 both). This study indicates that carotid soft plaque neovascularization in patients with NSCLC can be reduced by anti-angiogenesis treatment.

Experiment on the factors for enhancing the susceptibility of cancer cells to chemotherapeutic drug by ultrasound microbubbles.

The objective of this study was to investigate the factors for enhancing the susceptibility of cancer cells to chemotherapeutic drug by ultrasound microbubbles. Ultrasound (US) combined with phospholipid-based microbubbles (MB) was used to enhance the susceptibility of colon cancer cell line SWD-620 to anticancer drugs Topotecan hydrochloride (TOP). Experiments were designed to investigate the influence of main factors on cell viability and cell inhibition, such as US intensity, MB concentration, drug combination with MB, asynchronous action between US triggered cavitation and drug entering cell, MB particle size. US exposure for 10 sec with US probe power at 0.6 W/cm(2) had satisfied cell viability. Treated with US combined with 15% MB, cell viability maintained more than 85% and cell inhibition 86.16%. Under optimal US combined with MB, TOP showed much higher cell inhibition than that of only TOP group. Cell inhibition under short delayed time (<2 h) for TOP addition did not show obvious difference. In terms of MB particle size, the order of cell inhibition was: Mixture > Micron bubble part > Nanometer bubble part. US combined with MB can enhance the susceptibility of cancer cells to chemotherapeutic drug, which may provide a potential method for US-mediated tumor chemotherapy.