Comparison of the value of the GI-RADS and ADNEX models in the diagnosis of adnexal tumors by junior physicians.

Objective: To compare the diagnostic effectiveness of the Gynecologic Imaging Reporting and Data System (GI-RADS) and Neoplasias in the Adnexa (ADNEX) model for the diagnosis of benign and malignant ovarian tumors by junior physicians. Methods: The sonographic data of 634 patients with ovarian tumors confirmed by pathology in our hospital over 4 years were analyzed retrospectively by junior doctors. The diagnostic efficacy of the GI-RADS and ADNEX models was compared based on pathology. Results: (1) Regarding the diagnostic efficacy of the GI-RADS and ADNEX models, the sensitivity was 90.15% and 84.85%, the specificity was 87.65% and 85.86%, the accuracy rates were 88.17% and 85.65%, and the Youden Indices were 0.778 and 0.707, respectively. The areas under the receiver operating characteristic (ROC) curves were 0.924 (95% CI: 0.900-0.943) and 0.933 (95% CI: 0.911-0.951), respectively. The GI-RADS classification was equivalent to that of the ADNEX model in the diagnosis of adnexal tumors (P>0.05). These findings were highly consistent with the pathological results (Kappa values were 0.684 and 0.691, respectively). (2) When differentiating between different pathological types of adnexal tumors, the ADNEX model had the best diagnostic value for distinguishing between benign tumors and stage II-IV ovarian cancer (AUC=0.990, 95% CI: 0.978-0.997). Conclusions: (1) The diagnostic efficacy of the GI-RADS and ADNEX models in the diagnosis of benign and malignant ovarian tumors by junior physicians is excellent and comparable. (2) The ADNEX model shows good value for differentiating ovarian tumors of different pathological types by junior physicians.

Fetal echogenic bowel may be related to intestinal microbiota: A prospective cohort study.

OBJECTIVE: The purpose of the current study was to determine the difference in intestinal microbiota after delivery between healthy fetuses and fetuses with hyperechogenic bowel during the second trimester and the relationship between fetal echogenic bowel and microbiota. METHODS: Fourteen healthy fetuses (control group), 13 fetuses with echogenic bowel (EB group), and seven fetuses with echogenic bowel and other abnormalities (C-EB group) were selected. The first meconium after delivery was collected for 16S rRNA sequencing. RESULTS: A total of 1 222 131 high-quality sequences were generated after sequencing optimization of all samples. Each sample contained an average of 35 945 high-quality sequences and 2036 operational taxonomic units (OTUs). There was no significant difference in the Shannon, Simpson index among the three groups. At the genus level, the abundance of Escherichia coli/Shigella in the EB and C-EB groups was significantly lower than the control group, while the abundance of Staphylococcus, Methylobactrium, and Curvibacter in the EB group was significantly higher than the other groups. There was a difference in abundance of Gammaproteobacteria, Fusobacteria, Enterobacteriaceae, and E. coli in the EB and C-EB groups. CONCLUSIONS: The formation of echogenic bowel may be related to the microbiota.

Evaluating fetal lung development at various gestational weeks using two-dimensional shear wave elastography.

Background: Noninvasive evaluation of fetal lung development is a critical area of study. Two-dimensional shear-wave elastography (2D-SWE) provides valuable insights into tissue stiffness, potentially correlating with different stages of lung development. This study aims to explore the potential of the 2D-SWE technique for assessing the maturity of fetal lung development. Methods: This prospective cohort study included pregnant women undergoing routine antenatal ultrasound examinations at the Second Affiliated Hospital of Fujian Medical University and Quanzhou Women's and Children's Hospital from September 2022 to September 2023. The study consecutively recruited 300 pregnant women with normal pregnancies and 15 who opted for induced labor. Among those with normal pregnancies, the study assessed the differences in fetal pulmonary and hepatic elasticity measurements across different gestational weeks (GW) using one-way analysis of variance (ANOVA). Furthermore, regression analyses using linear, quadratic, and cubic equations were conducted to investigate the relationship between fetal parameters and GW. For those who opted for induced labor, elasticity measurements were taken before induction, and fetal lung tissue specimens were collected for post-induction observation. Results: Fetal lung and liver elasticity values, along with the lung-to-liver elasticity ratio (LLE ratio), showed significant variations across different GW (P<0.05). Specifically, fetal lung elasticity values initially increased and then decreased as GW advanced (R2=0.41). Liver elasticity values continuously increased throughout GW, though the rate of increase diminished during the prenatal period (R2=0.37). The LLE ratio values increased and then decreased over GW, fluctuating overall between 0.8 and 0.9 (R2=0.14). A 71.4% concordance was observed between the predicted stage of lung development, based on lung elasticity values, and the histological stage of lung development in the induced fetuses. Conclusions: 2D-SWE can depict the maturation of fetal lung development at various stages.

The establishment and severity assessment of ultrasound-guided prenatal bronchopulmonary dysplasia model in rat.

To study a new method for establishing animal models of prenatal bronchopulmonary dysplasia (BPD), we used lung ultrasound score (LUS) to semi-quantitatively assess the severity of lung lesions in model rats. Lipopolysaccharide (LPS) was injected into the right lung of the fetus of the rat under ultrasound-guided, and the right lung of the neonates were scanning for LUS. Specimens were collected for pathological scoring and detection of pulmonary surfactant-associated glycoprotein (SP)-C and vascular endothelial growth factor (VEGF) expression quantity. The correlation between LUS and pathological scores was analyzed. (1) The animal models were consistent with the pathological manifestations of BPD. (2) It showed a strong positive correlation between LUS and pathological scores in animal models (r = 0.84, P < 0.005), and the expression quantity of SP-C and VEGF in lung tissue were decreased (both P < 0.05). Animal models established by ultrasound-guided puncture of the lung of rats and injection of LPS were consistent with the manifestation of BPD. This method could be used to establish animal models of BPD before birth, and the severity of BPD could be assessed by using LUS.

Distinguishing types and severity of pediatric pneumonia using modified lung ultrasound score.

Objective: This study aimed to investigate the diagnostic utility of the modified lung ultrasound score (MLUS) in distinguishing between Mycoplasma pneumonia and viral pneumonia in children and evaluate their severity. Methods: A prospective collection of 137 suspected cases of community-acquired pneumonia in children admitted to the Quanzhou Maternity and Children's Hospital in Quanzhou City, Fujian Province, from January 2023 to December 2023 constituted the study cohort. All patients underwent lung ultrasound examinations, and MLUS scores were assigned based on ultrasound findings, including pleural lines, A-lines, B-lines, and lung consolidations. Based on the pathogenic results, the patients were categorized into the Mycoplasma pneumonia (74 cases) and viral pneumonia (63 cases) groups. The severity was classified as mild (110 cases) or severe (27 cases). The diagnostic value of MLUS for Mycoplasma pneumonia and viral pneumonia in children was analyzed. Results: (1) MLUS scores were significantly different between the Mycoplasma pneumonia (15, 10-21) and viral pneumonia (8, 5-16) groups (P = 0.002). ROC curve analysis indicated that using a cut-off value of 11, MLUS exhibited a sensitivity of 70.3%, specificity of 58.7%, and an area under curve (AUC) of 0.653 for diagnosing Mycoplasma pneumonia. Furthermore, large-area lung consolidation on ultrasound images demonstrated good diagnostic performance for predicting Mycoplasma pneumonia, with an AUC of 0.763, a sensitivity of 71.6%, and a specificity of 81.0%. (2) MLUS scores were significantly different between the mild pneumonia (10.5, 5-17) and severe pneumonia (21, 16-29) groups (P < 0.001). ROC curve analysis using a cut-off value of 16 showed a sensitivity of 77.8%, specificity of 73.6%, and AUC of 0.818 for diagnosing severe pneumonia. Multivariate regression analysis revealed that both MLUS and white blood cell count were independent factors influencing the severity. The constructed nomogram model demonstrated robust stability with a sensitivity of 85.2%, a specificity of 74.5%, and an AUC of 0.858 for predicting severe childhood pneumonia. Conclusion: MLUS, coupled with ultrasound signs of large-area lung consolidation, had reference significance for the differential diagnosis of Mycoplasma pneumonia and viral pneumonia in children and can be a preliminary assessment of the severity of viral pneumonia or mycoplasma pneumonia in children.

Developing a deep learning model for predicting ovarian cancer in Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US) Category 4 lesions: A multicenter study.

PURPOSE: To develop a deep learning (DL) model for differentiating between benign and malignant ovarian tumors of Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US) Category 4 lesions, and validate its diagnostic performance. METHODS: A retrospective analysis of 1619 US images obtained from three centers from December 2014 to March 2023. DeepLabV3 and YOLOv8 were jointly used to segment, classify, and detect ovarian tumors. Precision and recall and area under the receiver operating characteristic curve (AUC) were employed to assess the model performance. RESULTS: A total of 519 patients (including 269 benign and 250 malignant masses) were enrolled in the study. The number of women included in the training, validation, and test cohorts was 426, 46, and 47, respectively. The detection models exhibited an average precision of 98.68% (95% CI: 0.95-0.99) for benign masses and 96.23% (95% CI: 0.92-0.98) for malignant masses. Moreover, in the training set, the AUC was 0.96 (95% CI: 0.94-0.97), whereas in the validation set, the AUC was 0.93(95% CI: 0.89-0.94) and 0.95 (95% CI: 0.91-0.96) in the test set. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive values for the training set were 0.943,0.957,0.951,0.966, and 0.936, respectively, whereas those for the validation set were 0.905,0.935, 0.935,0.919, and 0.931, respectively. In addition, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the test set were 0.925, 0.955, 0.941, 0.956, and 0.927, respectively. CONCLUSION: The constructed DL model exhibited high diagnostic performance in distinguishing benign and malignant ovarian tumors in O-RADS US category 4 lesions.

Establishment and Validation of a Predictive Model for Sarcopenia Based on 2-D Ultrasound and Shear Wave Elastography in the Medial Gastrocnemius Muscle.

OBJECTIVE: To develop and validate a predictive model for sarcopenia. METHODS: A total of 240 subjects who visited our hospital between August 2021 and May 2023 were randomly divided by time of entry into a training set containing 2/3 of patients and a validation set containing 1/3 of patients. The muscle thickness (MT), echo intensity (EI), and shear wave velocity (SWV) of the medial gastrocnemius muscle were measured. Indicators that were meaningful in the univariate analysis in the training set were included in a binary logistic regression to derive a regression model, and the model was evaluated using a consistency index, calibration plot, and clinical validity curve. Diagnostic efficacy and clinical applicability were compared between the model and unifactorial indicators. RESULTS: Four meaningful variables, age, body mass index (BMI), MT, and SWV, were screened into the predictive model. The model was Logit Y = 21.292 + 0.065 × Age - 0.411 × BMI - 0.524 × MT - 3.072 × SWV. The model was well differentiated with an internally validated C-index of 0.924 and an external validation C-index of 0.914. The calibration plot predicted probabilities against actual probabilities showed excellent agreement. The specificity, sensitivity, and Youden's index of the model were 73.80%, 97.40%, and 71.20%, respectively, when using the diagnostic cut-off value of >0.279 for sarcopenia. The logistic model had higher diagnostic efficacy (p < 0.001) and higher net clinical benefit (p < 0.001) over the same threshold range compared to indicators. CONCLUSION: The logistic model of sarcopenia has been justified to have good discriminatory, calibrated, and clinical validity, and has higher diagnostic value than indicators.

Porta hepatis lymph nodes on US: not only identify biliary atresia but also predict outcomes after Kasai portoenterostomy surgery.

OBJECTIVES: To evaluate the usefulness of porta hepatis lymph nodes (PHLNs) on ultrasonography (US) scans in diagnosing biliary atresia (BA) and predicting the outcomes after Kasai portoenterostomy (KPE) surgery. METHODS: A total of 668 patients from one hospital were enrolled in the study (542 non-BA and 126 BA). The independent and combined diagnostic efficacy of PHLNs, triangular cord (TC) thickness, and gallbladder morphology were assessed by drawing the receiver operating characteristic (ROC) curves and counting the area under the ROC curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The US features, histopathological findings of PHLNs, and serum total bilirubin (TBIL) levels 3 months post-KPE were correlated. RESULTS: The AUC, sensitivity, specificity, PPV, and NPV of PHLNs with hyperechogenicity and a maximum length larger than 8.4 mm were 0.898, 81.8%, 97.8%, 89.6%, and 95.8%, respectively. The combination of PHLNs, TC thickness, and gallbladder morphology achieved the best overall diagnostic efficacy among all indicators with an AUC of 0.927 and a sensitivity of 99.2%. The germinal center number and bile particle number of PHLNs were positively correlated with pathological size and US echogenicity intensity of PHLNs, respectively (r = 0.591, 0.377, p = 0.001, 0.004). The pathological size of PHLNs in BA patients was negatively correlated with jaundice clearance status 3 months after KPE surgery (r = -0.385, p = 0.047). CONCLUSION: PHLNs with hyperechogenicity and a maximum length > 8.4 mm are useful US indicators for BA diagnosis. Additionally, the enlargement of PHLNs might play a role in predicting outcomes of KPE surgery. CRITICAL RELEVANCE STATEMENT: The article proposed for the first time that PHLNs with hyperechogenicity and a maximum length > 8.4 mm are a useful US indicator for diagnosing BA. KEY POINTS: PHLNs may be helpful in diagnosing BA and predicting outcomes after surgery. Enlarged hyperechoic PHLNs are a useful diagnostic indicator for BA, and play a role in predicting surgical outcomes. These findings can assist clinicians in more accurately diagnosing BA, enabling more timely treatments.

A novel simplified transperineal prostate biopsy guided by perineal ultrasound.

BACKGROUND: Prostate biopsies are mainly performed through transrectal or perineal approaches, while ultrasound probes are located in the rectum for guidance. However, reports on the use of perineal ultrasound-guided transperineal prostate biopsy (PG-TPPB) are few. METHODS: A retrospective case-control study was designed. A total of 111 patients who underwent PG-TPPB from February 2019 to December 2020 were investigated retrospectively. Simultaneously, 188 patients who underwent transrectal prostate biopsy (TRPB) were included as control. The prostate cancer detection rates (PCDR), complication rates, and application values were compared between the 2 groups. RESULTS: The overall PCDR in the PG-TPPB and TRPB groups were 33.3% (37/111) and 39.9% (75/188), respectively (P = .258). There was no significant difference in the PCDR between the 2 groups under each prostate-specific antigen level (all P > .05). The single-needle PCDR in the PG-TPPB and TRPB groups were 21.5% (277/1 287) and 24.0% (513/2 134), respectively (P = .091). The incidence of complications in the PG-TPPB group was significantly lower than that in the TRPB group (8.1% vs 21.3%, P = .003). CONCLUSIONS: The PCDRs of PG-TPPB and TRPB were the same. However, the postoperative complication rate of PG-TPPB was significantly lower than that of TRPB. Moreover, PG-TPPB required simpler equipment and did not require enema administration, which is suitable for patients with rectal contraindications. ADVANCES IN KNOWLEDGE: The reports on PG-TPPB are few. Our study indicated that PG-TPPB reduced the postoperative complication rate. Moreover, PG-TPPB required simpler equipment. Importantly, PG-TPPB is suitable for patients with rectal contraindications.

Uric Acid Inhibits Mice Pancreatic Steatosis via the Glycerophospholipid Pathway.

Background: despite evidence for mutually reinforcing effects of serum uric acid (SUA) and lipids, the effects of uric levels on pancreatic steatosis are not well-established. In this study, the relationship between low concentrations of uric acid and pancreatic steatosis was evaluated. Methods: forty C57BL/6J mice were fed a diet of high uric acid (HU), high fat (HF), high uric acid and high fat (HUHF), and normal control (NC) (10 mice in each group). Weight was measured weekly. Ultrasonography was performed to observe the pancreatic echo intensity of all mice before the end of feeding. Subsequently, peripheral blood was taken for biochemical examination. Intact pancreatic tissues were taken, part of which was used for pathological examination, part of which was used for PCR experiments and Western Blot experiments to obtain glycerophospholipid-associated mRNA data and protein levels. Results: body weight was significantly higher in the HF group than in the other three groups. Higher uric acid matched lower total cholesterol and triglyceride, matched higher low-density lipoprotein, and matched equal high-density lipoprotein. Ultrasound images and HE staining of pancreatic tissues of mice showed that higher uric acid matched lower fat content. The mRNA levels of phospholipase A2 group IB were highest in high uric acid group, while relative protein expression levels were lowest in high uric acid and control groups. Phospholipase A2 group IIA showed the opposite patterns. Conclusions: elevated serum uric acid at low concentrations can inhibit pancreatic steatosis, which is modulated via the glycerophospholipid metabolic pathway.

Multimodal ultrasound imaging: a method to improve the accuracy of sentinel lymph node diagnosis in breast cancer.

Aim: This study assessed the utility of multimodal ultrasound in enhancing the accuracy of breast cancer sentinel lymph node (SLN) assessment and compared it with single-modality ultrasound. Methods: Preoperative examinations, including two-dimensional ultrasound (2D US), intradermal contrast-enhanced ultrasound (CEUS), intravenous CEUS, shear-wave elastography (SWE), and surface localization, were conducted on 86 SLNs from breast cancer patients. The diagnostic performance of single and multimodal approaches for detecting metastatic SLNs was compared to postoperative pathological results. Results: Among the 86 SLNs, 29 were pathologically diagnosed as metastatic, and 57 as non-metastatic. Single-modality ultrasounds had AUC values of 0.826 (intradermal CEUS), 0.705 (intravenous CEUS), 0.678 (2D US), and 0.677 (SWE), respectively. Intradermal CEUS significantly outperformed the other methods (p<0.05), while the remaining three methods had no statistically significant differences (p>0.05). Multimodal ultrasound, combining intradermal CEUS, intravenous CEUS, 2D US, and SWE, achieved an AUC of 0.893, with 86.21% sensitivity and 84.21% specificity. The DeLong test confirmed that multimodal ultrasound was significantly better than the four single-modal ultrasound methods (p<0.05). Decision curve analysis and clinical impact curves demonstrated the superior performance of multimodal ultrasound in identifying high-risk SLN patients. Conclusion: Multimodal ultrasound improves breast cancer SLN identification and diagnostic accuracy.

Predictive value of anthropometric and biochemical indices in non-alcoholic fatty pancreas disease: a cross-sectional study.

OBJECTIVES: Triglyceride (TG), triglyceride-glucose index (TyG), body mass index (BMI), TyG-BMI and triglyceride to high-density lipoprotein ratio (TG/HDL) have been reported to be reliable predictors of non-alcoholic fatty liver disease. However, there are few studies on potential predictors of non-alcoholic fatty pancreas disease (NAFPD). Our aim was to evaluate these and other parameters for predicting NAFPD. DESIGN: Cross-sectional study design. SETTING: Physical examination centre of a tertiary hospital in China. PARTICIPANTS: This study involved 1774 subjects who underwent physical examinations from January 2016 to September 2016. PRIMARY AND SECONDARY OUTCOME MEASURES: From each subject, data were collected for 13 basic physical examination and blood biochemical parameters: age, weight, height, BMI, TyG, TyG-BMI, high-density lipoprotein (HDL), low-density lipoprotein, total cholesterol, TG, fasting plasma glucose, TG/HDL and uric acid. NAFPD was diagnosed by abdominal ultrasonography. A logistic regression model with a restricted cubic spline was used to evaluate the relationship between each parameter and NAFPD. The receiver operating characteristic (ROC) curve was used to calculate the area under the curve for each parameter. RESULTS: HDL was negatively correlated with NAFPD, height was almost uncorrelated with NAFPD and the remaining 11 parameters were positively correlated with NAFPD. ROC curve showed that weight-related parameters (weight, BMI and TyG-BMI) and TG-related parameters (TyG, TG and TG/HDL) had high predictive values for the identification of NAFPD. The combinations of multiple parameters had a better prediction effect than a single parameter. All the predictive effects did not differ by sex. CONCLUSIONS: Weight-related and TG-related parameters are good predictors of NAFPD in all populations. BMI showed the greatest predictive potential. Multiparameter combinations appear to be a good way to predict NAFPD.

Benchmarking Supervised and Self-Supervised Learning Methods in A Large Ultrasound Muti-task Images Dataset.

Deep learning in ultrasound(US) imaging aims to construct foundational models that accurately reflect the modality's unique characteristics. Nevertheless, the limited datasets and narrow task types have restricted this field in recent years. To address these challenges, we introduce US-MTD120K, a multi-task ultrasound dataset with 120,354 real-world two-dimensional images. This dataset covers three standard plane recognition and two diagnostic tasks in ultrasound imaging, providing a rich basis for model training and evaluation. We detail the data collection, distribution, and labelling processes, ensuring a thorough understanding of the dataset's structure. Furthermore, we conduct extensive benchmark tests on 27 state-of-the-art methods from both supervised and self-supervised learning(SSL) perspectives. In the realm of supervised learning, we analyze the sensitivity of two main feature computation methods to ultrasound images at the representational level, highlighting that models which judiciously constrain global feature computation could potentially serve as a viable analytical approach for US image analysis. In the context of self-supervised learning, we delved into the modelling process of self-supervised learning models for medical images and proposed an improvement strategy, named MoCo-US, a solution that addresses the excessive reliance on pretext task design from the input side. It achieves competitive performance with minimal pretext task design and enhances other SSL methods simply. The dataset and the code will be available at https://github.com/JsongZhang/CDOA-for-UMTD.

Exploring the diagnostic value of ultrasound radiomics for neonatal respiratory distress syndrome.

BACKGROUND: Neonatal respiratory distress syndrome (NRDS) is a prevalent cause of respiratory failure and death among newborns, and prompt diagnosis is imperative. Historically, diagnosis of NRDS relied mostly on typical clinical manifestations, chest X-rays, and CT scans. However, recently, ultrasound has emerged as a valuable and preferred tool for aiding NRDS diagnosis. Nevertheless, evaluating lung ultrasound imagery necessitates rigorous training and may be subject to operator-dependent bias, limiting its widespread use. As a result, it is essential to investigate a new, reliable, and operator-independent diagnostic approach that does not require subjective factors or operator expertise. This article aims to explore the diagnostic potential of ultrasound-based radiomics in differentiating NRDS from other non-NRDS lung disease. METHODS: A total of 150 neonatal lung disease cases were consecutively collected from the department of neonatal intensive care unit of the Quanzhou Maternity and Children's Hospital, Fujian Province, from September 2021 to October 2022. Of these patients, 60 were diagnosed with NRDS, whereas 30 were diagnosed with neonatal pneumonia, meconium aspiration syndrome (MAS), and transient tachypnea (TTN). Two ultrasound images with characteristic manifestations of each lung disease were acquired and divided into training (n = 120) and validation cohorts (n = 30) based on the examination date using an 8:2 ratio. The imaging texture features were extracted using PyRadiomics and, after the screening, machine learning models such as random forest (RF), logistic regression (LR), K-nearest neighbors (KNN), support vector machine (SVM), and multilayer perceptron (MLP) were developed to construct an imaging-based diagnostic model. The diagnostic efficacy of each model was analyzed. Lastly, we randomly selected 282 lung ultrasound images and evaluated the diagnostic efficacy disparities between the optimal model and doctors across differing levels of expertise. RESULTS: Twenty-two imaging-based features with the highest weights were selected to construct a predictive model for neonatal respiratory distress syndrome. All models exhibited favorable diagnostic performances. Analysis of the Youden index demonstrated that the RF model had the highest score in both the training (0.99) and validation (0.90) cohorts. Additionally, the calibration curve indicated that the RF model had the best calibration (P = 0.98). When compared to the diagnostic performance of experienced and junior physicians, the RF model had an area under the curve (AUC) of 0.99; however, the values for experienced and junior physicians were 0.98 and 0.85, respectively. The difference in diagnostic efficacy between the RF model and experienced physicians was not statistically significant (P = 0.24), whereas that between the RF model and junior physicians was statistically significant (P < 0.0001). CONCLUSION: The RF model exhibited excellent diagnostic performance in the analysis of texture features based on ultrasound radiomics for diagnosing NRDS.

Hydrochloric Acid-Induced Acute Lung Injury Models: Dynamic Change and Quantitative Analysis of Modified Lung Ultrasound Scoring System and High-Resolution Computed Tomography.

OBJECTIVE: Acute lung injury (ALI) has become a research hotspot due to its significant public health impact. To explore the value of the use of modified lung ultrasound (MLUS) scoring system for evaluating ALI using a rabbit model of ALI induced by hydrochloric acid (HCl) and investigate its correlation with high-resolution computed tomography (HRCT) and histopathological scores. METHODS: Twenty New Zealand laboratory rabbits were randomly assigned to control group (N = 5) and 3 experimental groups (N = 5 each). The control group received instillation of physiological saline, while the 3 experimental groups received 2 mL/kg of different doses of HCl instillation (mild group: pH 1.5, moderate group: pH 1.2, and severe group: pH 1.0) through the trachea under ultrasound guidance. Pulmonary ultrasound (using Mindray Reason9 linear array probes with frequency of 6-15 mHz) and HRCT examinations were performed before modeling (0H) and at 1H, 2H, 4H, 8H, 12H after modeling. The experimental rabbits were sacrificed at 12H for examination of gross lung morphology and hematoxylin-eosin-stained histopathological sections. The correlation of MLUS scores with HRCT/histopathological scores was assessed. RESULTS: All rabbits in the experimental groups showed oxygenation index PaO2/FiO2<300. Successful establishment of ALI model was proven by autopsy (successful modeling rate: 100%). The pathological damage increased with increase in HCl dosage. MLUS scores showed a positive correlation with HRCT scores/pathological severity. There was a strong positive correlation between MLUS scores and histopathological scores (r = 0.963, p < 0.05) as well as between HRCT scores and histopathological scores (r = 0.932, p < 0.05). CONCLUSION: Transtracheal injection of different dosages of HCl under ultrasound guidance induced different degrees of ALI. The MLUS scoring system can be used for semiquantitative evaluation of ALI, and is suitable as a screening tool.

Lung Ultrasound Assessment of Lung Hyperinflation in Patients with Stable COPD: An Effective Diagnostic Tool.

Purpose: To evaluate the degree of lung hyperinflation (LH) in patients with stable chronic obstructive pulmonary disease (COPD) by lung ultrasound score (LUS) and assess its value. Patients and Methods: We conducted a study of 149 patients with stable COPD and 100 healthy controls recruited by the Second Affiliated Hospital of Fujian Medical University. The pleural sliding displacement (PSD) was measured, the sliding of the pleura in different areas was observed, and LUS was calculated from both of them. The diaphragm excursion (DE), residual capacity (RV), total lung capacity (TLC), inspiratory capacity (IC) and functional residual capacity (FRC) were measured. We described the correlation between ultrasound indicators and pulmonary function indicators reflecting LH. Multiple linear regression analysis was used. The ROC curves of LUS and DE were drawn to evaluate their diagnostic efficacy, and De Long method was used for comparison. Results: (1) The LUS of patients with stable COPD were positively correlated with RV, TLC, RV/TLC and FRC and negatively correlated with IC and IC/TLC (r1=0.72, r2=0.41, r3=0.72, r4=0.70, r5=-0.56, r6=-0.65, P < 0.001). The correlation was stronger than that between DE at maximal deep inspiration and the corresponding pulmonary function indices (r1=-0.41, r2=-0.26, r3=-0.40, r4=-0.43, r5=0.30, r6=0.37, P < 0.001). (2) Multiple linear regression analysis showed that LUS were significantly correlated with IC/TLC and RV/TLC. (3) With IC/TLC<25% and RV/TLC>60% as the diagnostic criterion of severe LH, the areas under the ROC curves of LUS and DE at maximal deep inspiration for diagnosing severe LH were 0.914 and 0.385, 0.845 and 0.543, respectively (P < 0.001). Conclusion: The lung ultrasound score is an important parameter for evaluating LH. LUS is better than DE at maximal deep inspiration for diagnosing severe LH and is expected to become an effective auxiliary tool for evaluating LH.

Evaluation of extravascular lung water and cardiac function in normal vaginal delivery by intrapartum bedside ultrasound.

BACKGROUND: Healthy parturients may experience pulmonary edema and disturbed cardiac function during labor. We aimed to evaluate the extravascular lung water (EVLW), intravascular volume, and cardiac function of normal parturients during spontaneous vaginal delivery by bedside ultrasound. And to explore the correlation between EVLW and intravascular volume, cardiac function. METHODS: This was a prospective observational study including 30 singleton-term pregnant women undergoing spontaneous vaginal delivery. Bedside ultrasound was performed at the early labor, the end of the second stage of labor, 2 and 24 h postpartum, and 120 scanning results were recorded. EVLW was evaluated by the echo comet score (ECS) obtained by the 28-rib interspaces technique. Inferior vena cava collapsibility index (IVC-CI), left ventricle ejection fraction, right ventricle fractional area change, left and right ventricular E/A ratio, and left and right ventricular index of myocardial performance (LIMP and RIMP) were measured. Measurements among different time points were compared, and the correlations between ECS and other measurements were analyzed. RESULTS: During the spontaneous vaginal delivery of healthy pregnant women, 2 had a mild EVLW increase at the early labor, 8 at the end of the second stage of labor, 13 at 2 h postpartum, and 4 at 24 h postpartum (P < 0.001). From the early labor to 24 h postpartum, ECS first increased and then decreased, reaching its peak at 2 h postpartum (P < 0.001). IVC-CI first decreased and then increased, reaching its minimum at the end of the second stage of labor (P < 0.001). RIMP exceeded the cut-off value of 0.43 at the end of the second stage of labor. ECS was weakly correlated with IVC-CI (r=-0.373, P < 0.001), LIMP (r = 0.298, P = 0.022) and RIMP (r = 0.211, P = 0.021). CONCLUSIONS: During spontaneous vaginal delivery, the most vital period of perinatal care is between the end of the second stage of labor and 2 h postpartum, because the risk of pulmonary edema is higher and the right ventricle function may decline. IVC-CI can be used to evaluate maternal intravascular volume. The increase in EVLW may be related to the increase in intravascular volume and the decrease in ventricular function.

Advances in artificial intelligence for the diagnosis and treatment of ovarian cancer (Review).

Artificial intelligence (AI) has emerged as a crucial technique for extracting high­throughput information from various sources, including medical images, pathological images, and genomics, transcriptomics, proteomics and metabolomics data. AI has been widely used in the field of diagnosis, for the differentiation of benign and malignant ovarian cancer (OC), and for prognostic assessment, with favorable results. Notably, AI­based radiomics has proven to be a non­invasive, convenient and economical approach, making it an essential asset in a gynecological setting. The present study reviews the application of AI in the diagnosis, differentiation and prognostic assessment of OC. It is suggested that AI­based multi­omics studies have the potential to improve the diagnostic and prognostic predictive ability in patients with OC, thereby facilitating the realization of precision medicine.

Nomogram model for predicting invasive placenta in patients with placenta previa: integrating MRI findings and clinical characteristics.

This study aims to validate a nomogram model that predicts invasive placenta in patients with placenta previa, utilizing MRI findings and clinical characteristics. A retrospective analysis was conducted on a training cohort of 269 patients from the Second Affiliated Hospital of Fujian Medical University and a validation cohort of 41 patients from Quanzhou Children's Hospital. Patients were classified into noninvasive and invasive placenta groups based on pathological reports and intraoperative findings. Three clinical characteristics and eight MRI signs were collected and analyzed to identify risk factors and develop the nomogram model. The mode's performance was evaluated in terms of its discrimination, calibration, and clinical utility. Independent risk factors incorporated into the nomogram included the number of previous cesarean sections ≥ 2 (odds ratio [OR] 3.32; 95% confidence interval [CI] 1.28-8.59), type-II placental bulge (OR 17.54; 95% CI 3.53-87.17), placenta covering the scar (OR 2.92; CI 1.23-6.96), and placental protrusion sign (OR 4.01; CI 1.06-15.18). The area under the curve (AUC) was 0.908 for the training cohort and 0.803 for external validation. The study successfully developed a highly accurate nomogram model for predicting invasive placenta in placenta previa cases, based on MRI signs and clinical characteristics.

SEG-LUS: A novel ultrasound segmentation method for liver and its accessory structures based on muti-head self-attention.

Although liver ultrasound (US) is quick and convenient, it presents challenges due to patient variations. Previous research has predominantly focused on computer-aided diagnosis (CAD), particularly for disease analysis. However, characterizing liver US images is complex due to structural diversity and a limited number of samples. Normal liver US images are crucial, especially for standard section diagnosis. This study explicitly addresses Liver US standard sections (LUSS) and involves detailed labeling of eight anatomical structures. We propose SEG-LUS, a US image segmentation model for the liver and its accessory structures. In SEG-LUS, we have adopted the shifted windows feature encoder combined with the cross-attention mechanism to adapt to capturing image information at different scales and resolutions and address context mismatch and sample imbalance in the segmentation task. By introducing the UUF module, we achieve the perfect fusion of shallow and deep information, making the information retained by the network in the feature extraction process more comprehensive. We have improved the Focal Loss to tackle the imbalance of pixel-level distribution. The results show that the SEG-LUS model exhibits significant performance improvement, with mPA, mDice, mIOU, and mASD reaching 85.05%, 82.60%, 74.92%, and 0.31, respectively. Compared with seven state-of-the-art semantic segmentation methods, the mPA improves by 5.32%. SEG-LUS is positioned to serve as a crucial reference for research in computer-aided modeling using liver US images, thereby advancing the field of US medicine research.