Background Intraplaque neovascularization is a biomarker of vulnerable plaque. However, no data are available whether the increase in neovascularization within carotid plaques is a result of ischemia or an increase in adventitial vasa vasorum (VV).

Objective To evaluate the VV signal in carotid vulnerable plaques.

Methods Contrast-enhanced ultrasound (CEUS) examination was performed to examine changes in VV density in 47 patients with carotid plaque, and 21 patients received CT angiography (CTA) examination to assess the VV signal. In addition, a single-channel flow tissue model was fabricated for use in vitro studies to exclude pseudo-enhancement interferences in the distal wall of arteries by CEUS.

Results The intensities of adventitial VV behind carotid plaque were lower than that of adventitial VV at the same level adjacent to the plaque in both CEUS and CTA examinations (P < 0.05). In vitro study, the intensities of far wall increased as the microbubble concentration increased (P < 0.05). However, no significant differences of intensities of far wall were found between different thicknesses tubes at the concentration of microbubble concentrations of 0.3% and 0.5% (P ≥ 0.05).

Conclusion The formation of intraplaque neovascularization in carotid arteries is associated with the adventitial VV, and ischemia of VV may be a potential mechanism for intraplaque neovascularization.

Stroke is a critical condition marked by the death of brain cells due to inadequate blood flow, necessitating improved predictive models for stroke lesions. The accuracy and flexibility required to forecast and classify stroke lesions is lacking in current approaches, which compromise patient outcomes. To solve these issues, Bille-Viper-Segmentation with the Tandem-MU-Net Model is suggested as a solution for tissue damage detection problems. This study improves blood flow detection in stroke images by introducing the Bille-Viper-Segmentation method to overcome difficulties in recognizing tissue injury. This novel method effectively samples pixel data and analyzes fogging phases related to stroke lesions by utilizing a Deep Luxe Gauging Tree. Existing methods struggle with flexibility in varying conditions; thus, the Trans-Lucent-Rich Reprise Pattern recognition algorithm for precise identification of infected areas is introduced. Furthermore, the Focus View Algorithm is suggested, which incorporates features from infarcted regions to improve early detection of emerging lesions. Furthermore, the Tandem-MU-Net model is used to extract essential morphological features and categorize stroke types, including Hemorrhagic and Acute strokes, through an investigation of their neutral and ionic forms. The results show that the suggested model performs substantially better than existing methods, achieving an amazing accuracy rate of 75%, recall rate of 83%, F1 score of 98%, Dice score of 98%, and precision of 73%, all while operating effectively in a time frame of 250 seconds.

Objective Antenatal vaginal bleeding, particularly during the first trimester, is worrisome for obstetricians. The common causes are all types of abortions, including molar and ectopic pregnancies. The aim is to evaluate the obstetric causes of vaginal bleeding during the first trimester.

Methods The study population comprises 100 pregnant women with complaints of vaginal bleeding during their first trimester period. These patients were subjected to ultrasound examination to diagnose the causes of bleeding. Patients with 12 completed weeks of gestation and non-obstetrical causes of vaginal bleeding were excluded.

Results The study population of 18-34 years had complained of vaginal bleeding during their first trimester of pregnancy. Most 57% were in the age group of 20-24 years. Forty-two percent of the study population presented at ten weeks of amenorrhea. Out of 100 cases, the majority (58%) were diagnosed as threatened abortion, 31% cases were diagnosed as incomplete abortion, 4% cases were diagnosed as complete abortion, 2 (2%) cases each were diagnosed as ectopic gestation, inevitable and missed abortions, and 1 (1%) case diagnosed as Hydatidiform mole. Out of 100 patients, the gestational sac was seen in 75 (75%).

Conclusion Antenatal ultrasonography is helpful in accurate and early diagnosis of the causes of vaginal bleeding during the first trimester. This aids the obstetrician in selecting the best treatment planning and helps with prognosis prediction, establishing an accurate diagnosis in a few clinically misdiagnosed cases.

Objective Biliary atresia is a significant cause of neonatal pathological jaundice, demanding effective interventions such as the Kasai procedure to impede its advancement. Previous research highlights the potential of shear wave elastography for assessing liver fibrosis and the subsequent necessity for liver transplantation following Kasai procedure. This underlines the significance of our study in investigating shear wave elastography as a predictive tool for the success of Kasai procedure in biliary atresia patients.

Methods This retrospective case-control comparative study analyzed data from biliary atresia patients who underwent shear wave elastography ultrasound and the Kasai procedure at our center from 2020 to 2022. Successful Kasai outcomes formed the case group; unsuccessful, the control. We calculated the mean shear wave elastography values for each group and established a predictive Kasai success cut-off using SPSS for statistical analysis.

Results Twenty-one subjects, with 8 males and 13 females (median age: 82 days), were evaluated. Of the 21 subjects, 9 (42.9%) had successful Kasai outcomes, while 12 (57.1%) were unsuccessful. There are statistically different values between two groups, such as the shear wave elastography value (P = 0.001). The optimal cut-off point of shear wave elastography value to predict the success of Kasai procedure is 2.21 m/s or 14.4 kPa (sensitivity 88.9%, specificity 83.3%, accuracy 85.7%, PPV 87.65%, NPV 84.91%), with an AUC of 0.889 (95%CI = 0.75-1.00), OR = 10.50 (1.360-81.053).

Conclusion This study demonstrates shear wave elastography’s potential utility in predicting Kasai procedure success for biliary atresia patients, suggesting its role as a valuable prognostic tool.

Objective: This study aims to assess the performance of the Chat Generative Pre-Trained Transformer (ChatGPT), specifically versions GPT-3.5 and GPT-4, on ultrasonography board-style questions, and subsequently compare it with the performance of third-year radiology residents on the identical set of questions.
Methods: The study, conducted from May 19 to May 30, 2023, utilized a selection of 134 multiple-choice questions sourced from a commercial question bank for American Registry for Diagnostic Medical Sonography (ARDMS) examinations and imported into the ChatGPT model (encompassing GPT-3.5 and GPT-4 versions). ChatGPT’s responses were evaluated overall, by topic, and by GPT version. An identical question set was assigned to three third-year radiology residents, enabling a direct comparison of performances with ChatGPT.
Results: GPT-4 correctly responded to 82.1% of questions (110 of 134), significantly surpassing the performance of GPT-3.5 (P = 0.003), which correctly answered 66.4% of questions (89 of 134). Although GPT-3.5’s performance was statistically indistinguishable from the average performance of the radiology residents (66.7%, 89.3 of 134) (P = 0.969), there was a notable difference in the accuracy in question-answering accuracy between GPT-4 and the residents (P = 0.004).
Conclusions: ChatGPT demonstrated significant competency in responding to ultrasonography board-style questions, with the GPT-4 version markedly surpassing both its predecessor GPT-3.5 and the radiology residents.

Objectives: The incidence of chronic liver diseases in children is increasing worldwide due to congenital, metabolic, autoimmune and viral diseases. Currently, liver biopsy for fibrosis assessment is considered the gold standard. However, this procedure is invasive, may result in unavoidable complications and is prone to sampling errors. These limitations have led to an increasing demand for noninvasive methods for fibrosis screening. Artificial intelligence integration in ultrasound diagnosis of liver fibrosis has gained interest in clinical research. In the current study we used a cloud-based artificial intelligence platform utilizing transfer learning to evaluate the accuracy of B-mode ultrasound based AI model compared to pediatric radiologists in detection of liver fibrosis in a pediatric population.
Methods: For this IRB approved study, charts of 190 pediatric patients who were referred for liver biopsy and ultrasound were reviewed. On average 14 images of different liver areas were selected and a single image per decision was used for both radiologist and AI reads. A supervised machine learning model for image classification was developed using Google Vision AutoML (Google Inc., Mountain View, CA, USA). Data was divided for model development (80% of cases (154 cases) = 2324 images) and a model validation cohort for external testing (20% (36 cases) = 360 images). As a comparator, three blinded radiologists read the ultrasound images of the validation cohort and provided a binary diagnosis of fibrosis versus non fibrotic liver appearance. Tissue sampling was used as the reference standard for all cases.
Results: There were 99 and 91 patients in the biopsy proven fibrosis and non-fibrosis group, respectively. The model’s internal evaluation resulted in precision of 78.2%, recall of 78.5% and average precision of 87.7%. In the external validation cohort, three radiologists (Mean ± Standard Deviation) and Google AutoML (confidence interval (CI)) achieved a sensitivity of 42.04% ± 0.04 and 70.56% (63.32% to 77.10% CI), specificity of 50.18% ± 0.04 and 45.00% (37.59% to 52.58% CI), positive predictive value of 45.76% ± 0.01 and 56.19% (52.17% to 60.14% CI), negative predictive value of 46.39% ± 0.01 and 60.45% (53.65% to 66.86% CI) and accuracy of 46.11% ± 0.01 and 57.78% (52.49% to 62.94% CI). When evaluating agreement across multiple images from the same patient, intra-reader agreement was 77.2% for AutoML and 90.8%-92.5% for the 3 radiologists. The models' F1 scores for the development and validation cohort were 0.78 and 0.62, respectively.
Conclusions: Liver fibrosis assessment in children is challenging without biopsy. An ultrasound-based AI model showed high sensitivity compared to radiologists, albeit still without suitable diagnostic performance for clinical use.

Objective: Drug-induced liver injury (DILI) is one of the most challenging forms of liver disorder. We aimed to use ultrasound dual elastography, by combining strain and shear wave imaging, to noninvasively assess liver inflammation and injury severity of DILI.

Methods: 291 DILI patients were included in the prospective multicenter study and divided into training and validation cohorts. All patients received liver biopsy and dual elastography examination. Liver inflammation grading (G0-4) and fibrosis staging (F0-4) were considered as the gold standard of liver injury and G+F ≥ 5 was defined as severe liver injury. Indexes of dual elastography and serological indicators (DESI) were selected and analyzed with multivariable logistic regression to build DESI models for evaluating liver inflammation, and the C score model was built with the same method for diagnosing severe liver injury.

Results: Areas under the receiver operating characteristic curve (AUCs) of the DESI model to assess liver inflammation ≥ G2 were 0.887 and 0.868 in training and validation cohorts, respectively. AUCs of the DESI model in diagnosing ≥ G3 were 0.893 and 0.896 in the two cohorts, respectively. The C score accurately assessed severe liver injury with AUCs of 0.909 and 0.885 in two cohorts. Of the 87 patients with mild clinical severity, 10 (11.49%) had severe pathological injury, which could be identified by C score.

Conclusion: Dual elastography demonstrated high performance in diagnosing liver inflammation and identifying severe pathological liver injury of DILI, making up for the deficiency of serological indicators alone for evaluating DILI severity.

Objective: To evaluate accuracy and feasibility of a handheld ultrasound machine for measuring carotid artery intima-media thicknesses (CIMT) and hemodynamic parameters by different expertise levels of ultrasound operators.

Methods: The operators were divided into three groups based on the level of their medical expertise: ultrasound technician, sonographer, and nursing staff. Operators from each group measured the CIMT and hemodynamic parameters of 25 volunteers using both handheld ultrasound and a conventional ultrasound machine. The reliability and reproducibility of handheld ultrasound measurements of CIMT and hemodynamic parameters (peak systolic velocity (PSV), end-diastolic velocity (EDV)) in operators were analyzed.

Results: After a period of training, there was no statistically significant difference between the mean CIMT measured using handheld ultrasound among the three operators (0.45 ± 0.09 mm, 0.50 ± 0.07 mm, 0.46 ± 0.08 mm, P> 0.05, respectively), as well as PSV (83.30 ± 15.42 cm/s, 76.28 ± 13.26 cm/s, 81.12 ± 21.21 cm/s, P> 0.05, respectively) and EDV (21.04 ± 4.12 cm/s, 21.87 ± 5.05 cm/s, 20.17 ± 5.90 cm/s, respectively, P> 0.05). Furthermore, there was a good repeatability and consistent of handheld ultrasound device in measuring mean CIMT in the ultrasound technician and sonographer groups (r = 0.662, 0.691, respectively, P < 0.01).

Conclusions: Under the premise of proper training, handheld ultrasound systems are feasible for rapid and primary assessment of carotid artery by operators with different levels of expertise.

Objective: To explore the diagnostic value of real-time shear wave elastography (SWE) in hepatic hemangioma (ANGI) and hepatocellular carcinoma (HCC).

Methods: A total of 88 patients diagnosed with angiosarcoma (ANGI) or hepatocellular carcinoma (HCC) in our department from February 2019 to February 2020 were included in this study. These patients were assigned to two groups based on pathological diagnosis: the ANGI group (n = 42) and the HCC group (n = 46). All patients underwent SWE examination, and the clinical efficacy was analyzed by comparing the average value of Young's modulus of the two groups and plotting the receiver operator characteristic (ROC) curve.

Results: There was no significant difference in lesion diameter between ANGI and HCC patients (P > 0.05). The ANGI group exhibited a significantly higher average Young's modulus for both the lesions and the adjacent liver tissues compared to the HCC group (P < 0.001); The area under the curve (AUC) of the average value of Young’s modulus of the lesion to ANGI and HCC was 0.875 (95% CI = 0.795-0.955).

Conclusion: SWE demonstrates high diagnostic accuracy in distinguishing ANGI from HCC, providing valuable clinical evidence for differentiating between the two diseases.

Objective: To determine whether COVID-19 causes an increase in spleen dimensions in individuals with a recent history of COVID-19 infection.

Methods: This case-control study was conducted at the Radiology Department of the University of Lahore Teaching Hospital and Sehat Medical Complex, both in Lahore. The study sample comprised 384 individuals, selected using a convenience sampling technique. Participants included individuals of all age groups and both genders; however, those under 18 were excluded due to the potential for incomplete spleen maturation. Other exclusion criteria included a history of splenectomy, the presence of traumatic or non-traumatic splenic lesions, or any other splenic abnormalities. Data collection commenced after obtaining approval from the Research Ethics Committee at the University of Lahore. The Siemens Sonovista c3000 Grey Scale Ultrasound Machine was used, and the data were analyzed using SPSS version 24.

Results: In a study involving 384 participants, the mean age was 35.7 ± 6.14, ranging from 22 to 50 years. Of these, 296 (71.1%) were female, and 88 (22.9%) were male. Echogenicity varied, with 29 participants (7.6%) exhibiting heterogeneous echogenicity and 355 (92.4%) showing homogeneous echogenicity. Spleen margins were irregular in 67 participants (17.4%) and smooth in 317 participants (82.6%). Regarding the history of Covid-19, 188 participants (49%) tested negative, while 196 participants (51%) tested positive.

Conclusion: Patients with a history of COVID-19 exhibited a significant increase in spleen length, volume, and thickness.

Objective This study aimed to evaluate the development of atherosclerosis in ApoE-deficient dogs fed with a high-fat diet (HFD) using vascular duplex ultrasonography (VDU).

Methods Thirty beagle dogs were enrolled, including 10 wild-type, 16 heterozygous (ApoE^-/+), and four homozygous (ApoE^-/-) mutant dogs. The dogs were categorized into either the normal diet (ND) or HFD group. Plasma lipids levles were tested at baseline and then after feeding the dog a different diet for 6 months. The carotid arteries, abdominal aorta (AO) and iliac arteries were examined using VDU. Artery sections of the ApoE^-/- dogs were analyzed.

Results After HFD, lipids especially triglycerides, total cholesterol and low-density lipoprotein (LDL) in the wild type and ApoE^-/+ dogs were significantly increased. Both the intima-media thickness (IMT) of the common carotid artery (CCA) and AO in the wild type and ApoE^-/+ dogs significantly increased. In the ApoE^-/+ dogs, the mean percentages increases in CCA-IMT and AO-IMT after HFD were higher than those in the ND dogs. The mean values of CCA-IMT and AO-IMT in the ApoE^-/-dogs increased to 2-2.5 folds after HFD. Histological analysis confirmed that the carotid and iliac arteries had advanced atherosclerotic lesions in the ApoE^-/- dogs.

Conclusions HFD may accelerate the development of atherosclerosis in ApoE-deficient dogs, which is an optimal large-animal model of atherosclerosis.

ObjectiveThe objective of this study was to develop a sonographic technique using two-dimensional (2D) markers for detecting isolated fetal cleft palate (no cleft lip) and to evaluate the ability of 2D and three-dimensional (3D) sonography to image the normal and abnormal palate.

Methods Seventy-three fetuses with a high risk of cleft palate at 12-39 weeks of gestation were referred for specialist ultrasound. A detailed evaluation of the palate was performed through 2D ultrasound, which revealed the appearance of the palatine line in the sagittal plane; the palate and alveolar ridge in the coronal plane of the fetal face; the horizontal plate of the palatine bone in the axial maxillary plane; and the soft palate in the transverse plane of the cavum pharyngis. Subsequently, 3D ultrasound imaging of the palate was performed in all fetuses. Antenatal diagnoses were compared with postnatal findings or autopsy findings.

Results Visualization of 2D markers was accomplished in all fetuses, and 3D assessment was achieved in 97% of fetuses. Cleft palate was suspected in 16 cases (21.9%), among which 14 were suspected on the basis of both 2D and 3D evaluation, and two were suspected only on the basis of 3D evaluation. A normal palate was observed in 57 fetuses (78.1%). The mean gestational age was 27 weeks (range of 12 weeks to 39 weeks). All 16 fetuses with suspected cleft palate were confirmed by postnatal or autopsy findings, no false-positives were observed, and one case with a bifid uvula was missed among 57 fetuses with a presumed normal palate.

Conclusions The fetal palate can be evaluated with 2D markers and 3D sonography. The detection of isolated cleft palate is more sensitive when 2D markers are present in all four planes.

Objective Aimed to evaluate patients with essential hypertension (EH) using four-dimensional automatic left atrial quantification (4DLAQ) To assess the occurrence of EH.

Methods This study selected 80 patients with EH for the EH group and 36 healthy individuals for the control group. Various cardiac parameters, including left atrial diameter (LAD), interventricular septal thickness (IVST), left ventricular end-diastolic diameter (LVDD), left ventricular posterior wall thickness (LVPWT), early E-wave velocity of mitral valve diastole/mitral valve ring myocardial displacement velocity (E/e'), biplanar left ventricular ejection fraction (biplanLVEF), left atrial minimum volume (LAVmin), lateral left atrial maximum volume (LAVmax), left atrial presystolic volume (LAVpreA), left atrial ejection fraction obtained by two-dimensional echocardiography (LAEF), left atrial passive ejection fraction (LAPEF), left atrial active ejection fraction (LAAEF), left atrial reservoir longitudinal strain (LASr), left atrial catheter longitudinal strain (LAScd), left atrial systolic longitudinal strain (LASct), left atrial reservoir circular strain (LASr_c), left atrial catheter circular strain (LAScd_c), and left atrial systolic circular strain (LASct_c) were measured using 4DLAQ. Binary logistic regression was employed to analyze the effect of 4DLAQ strain parameters on EH. Receiver operating characteristic (ROC) curves were used to assess the predictive value of 4DLAQ strain parameters for EH.

Results Systolic blood pressure and diastolic blood pressure in the EH group were higher than those in the control group (P = 0.000 and 0.000, respectively). In the EH group, LAD, IVST, LVDD, LVPWT, E/e', LAVmin, LAVmax, and LAVpreA were significantly increased (P = 0.000, 0.000, 0.072, 0.000, 0.000, 0.001, 0.052, and 0.004, respectively), whereas biplanLVEF, LAEF, LAPEF, LAAEF, LASr, LAScd, LASct, LASr_c, LAScd_c, and LASct_c significantly decreased (P = 0.090, 0.000, 0.009, 0.064, 0.000, 0.000, 0.000, 0.000, 0.000, and 0.689, respectively). Bland-Altman plots were used to illustrate the relationship between variables and audience consensus. LASr and LAScd were identified as independent risk factors for EH. The area under the ROC curve (AUC) for LASr was 0.925, (95% confidence interval [CI] = 0.879-0.971) with a sensitivity of 80.00%, specificity of 94.44%, using a cut-off value of 20%. For LAScd, the AUC-ROC was 0.878 (95% CI = 0.818-0.939 with a sensitivity of 76.25%, specificity 86.11%, and using a critical value of -11%.

Conclusion LASr and LAScd exhibited superior predictive capabilities for EH, with LASr performing the best. This study fills a critical gap in left atrial research and holds significant clinical implications.

Objective To evaluate the feasibility and capability of UT in detecting musculoskeletal system lesions in the limbs and to explore its image quality.

Materials and Methods The Institutional Review Board has approved this prospective single-center study. This study included participants with various musculoskeletal and neurologic disorders in the limbs who provided written consent from October 2022 to April 2023. In addition to other radiological examinations (X-rays, CT, or MRI) and conventional handheld ultrasound scans requested by clinicians based on the conditions, each participant also underwent UT scanning using our developed limb ultrasound imaging system during the same period. Four radiologists and ultrasound physicians with more than five years of experience in musculoskeletal diagnostics analyzed the two-dimensional and three-dimensional images of the examination area.

Results Overall, 50 participants were evaluated (mean age, 36 years ± 18 [SD]; 26 males). The conditions included musculoskeletal tumors (n = 10), postoperative follow-up of musculoskeletal tumors (n = 20), peripheral nerve disorders in the limbs (n = 10) and postoperative pain in orthopedic surgery (n = 10). In all UT images, the region of interest was completely displayed, and internal structures such as muscles and nerves were clearly visible. Compared to conventional ultrasound images, the reconstructed three-dimensional images intuitively displayed the relationship between the lesions and surrounding tissues. Furthermore, UT did not exhibit metal artifacts when observing soft tissues around metallic implants, providing more comprehensive soft tissue information and more intuitive stereoscopic images.

Conclusion Clinical results of the UT system have demonstrated its feasibility as an automated and standardized imaging technique for musculoskeletal imaging, providing a new imaging modality for the diagnosis of musculoskeletal diseases in the human body.

Objective To investigate the effectiveness of SMI in evaluating hepatic IRI and detecting its therapy response.

Methods Thirty rats were randomly divided into sham (n = 12), IRI (n = 12), and andrographolide pretreatment (n = 6) groups. SMI, pathological, and biochemical examinations were conducted for the sham and IRI groups at 4 (n = 6) and 24 h (n = 6) after reperfusion, respectively. Two ultrasonologists measured the vascular index (VI). The interobserver agreement was evaluated using the intraclass correlation coefficient (ICC). The rat liver parameters, including Suzuki's score, alanine aminotransferase (ALT), and aspartate aminotransferase (AST), were obtained at different time steps in each group. For the andrographolide pretreatment group, data were obtained at 24 h after reperfusion to further verify the advantage of VI. Parameters were analyzed for correlations and compared between each group at 4 and 24 h.

Results The ICC between two ultrasonologists who measured the VI was 0.912 (95%CI: 0.889-0.940). Suzuki's score and VI were negatively correlated (r = -0.504, P = 0.012). Compared with the sham group, the IRI group showed a significant decrease in the VI at 4 and 24 h after reperfusion [(24.78 ± 3.23) versus (20.22 ± 2.55); (22.67 ± 1.36) versus (19.27 ± 2.23), P < 0.05)]. The VI in the andrographolide pretreatment group was higher than that in the IRI group [(21.90 ± 1.47) versus (19.27 ± 2.23), P <0.05].

Conclusions The VI on SMI can be used as a noninvasive and sensitive index to evaluate hepatic IRI and detect its therapeutic response.

Objective MicroRNAs (miRNAs) play important roles in various diseases’ development and progression. The aim of this study is to identify the differently expressed miRNAs (DEmiRNAs) and differently expressed genes (DEGs) between BPH and PCa.

Methods Selecting BPH and PCa tissues from GEO database (GSE118038 as test dataset; GSE30994 as validation dataset), we identified DEmiRNAs and DEGs between BPH and PCa using GEO2R online tool and “Deseq2” R package. We applied random forest method to select hub DEmiRNAs, combining age and BMI, to establish a nomogram model for BPH detection. Finally, GO and KEGG enrichment analyses were conducted to explore the underlying mechanisms and pathways of DEmiRNAs in BPH.

Results We found 26 DEmiRNAs between BPH and PCa, of which 21 DEmiRNAs were up-regulated and 5 DEmiRNAs were down-regulated. Via forest random method, we selected miR-636, miR-324-3p, miR-210-3p and miR-3615 as hub DEmiRNAs in BPH. Combing these four hub DEmiRNAs, age and BMI, we established a nomogram model to distinguish BPH from PCa. Through “miRWalk” online tool, we targeted 499 hub DEGs between BPH and PCa, and found most of genes enriched in muscle system process, muscle contraction, contractile fiber, myofibril, actin binding, passive transmembrane transporter activity, focal adhesion, axon guidance.

Conclusion Our results suggested that miR-636, miR-324-3p, miR-210-3p and miR-3615 might the hub DEmiRNAs between BPH and PCa, which may play a crucial role to distinguish BPH from PCa.

Objective A non-invasive assessment of the risk of benign and malignant follicular thyroid cancer is invaluable in the choice of treatment options. The extraction and fusion of multidimensional features from ultrasound images of follicular thyroid cancer is decisive in improving the accuracy of identifying benign and malignant thyroid cancer. This paper presents a non-invasive preoperative benign and malignant risk assessment system for follicular thyroid cancer, based on the proposed deep feature extraction and fusion of ultrasound images of follicular thyroid cancer.

Methods First, this study uses a convolution neural network (CNN) to obtain a global feature map of the image, and the fusion of global features cropped to local features to identify tumor images. Secondly, this tumour image is also extracted by googleNet and ResNet respectively to extract features and recognize the image. Finally, we employ an averaging algorithm to obtain the final recognition results.

Results The experimental results show that the method proposed in this study achieved 89.95% accuracy, 88.46% sensitivity, 91.30% specificity and an AUC value of 96.69% in the local dataset obtained from Peking University Shenzhen Hospital, all of which are far superior to other models.

Conclusion In this study, a non-invasive risk prediction system is proposed for ultrasound images of thyroid follicular tumours. We solve the problem of unbalanced sample distribution by means of an image enhancement algorithm. In order to obtain enough features to differentiate ultrasound images, a three-branched feature extraction network was designed in this study, and a balance of sensitivity and specificity is ensured by an averaging algorithm.

Objectives To measure the CSA of the HST musculature measured with ultrasonography in soccer players undergoing ACLR and compare limb differences with healthy controls.

Methods A case-control study was performed with patients after anterior cruciate ligament repair (ACLR) and healthy controls in which cross-sectional areas (CSA) obtained using a model TE7 ultrasound machine (MINDRAY ®, USA) in B mode (4.2 to 13 MHz) with a multifrequency linear array transducer (L12-4S). Three CSA images were taken of the semitendinosus muscle (ST) and the long head of the biceps femoris (BFlh), at a distance of 30% and 70% of the ischial tuberosity insertion. Mean differences between groups were analyzed using SPSS v.20 (IBM®, USA), and statistical analyses were performed using non-parametric techniques to determine differences between groups (Student's t-test) and Cohen's correlation coefficient to quantify effect size.

Results 14 ACLR operated 17 ± 5.4 months ago and 12 healthy controls (W = 6; M = 20M; 24.5 ± 3.92 years; BMI = 25.1 ± 2.32 kg/m²) were recruited. There were differences between groups in CSA-ST70 (Post-ACLR = 1.43 ± 1.029 cm² vs Control 2.65 ± 0.664 cm², T Student = -3.68, 95% CI [-Inf, -0.648], P < 0. 001, ES = -1.418), but not in CSA-ST30 (Post-ACLR = 8.42 ± 1.596 cm² vs Control 9.16 ± 0.945 cm², T Student = -1.535; 95% CI [-Inf, -0.0793], P = 0. 068, ES = -0.5607), CSA-BFlh30 (Post-ACLR = 8.79 ± 1.47 cm² vs Control 8.87 ± 2.312 cm², T Student = -0.123; 95% CI [-Inf, 1.1049], P = 0.452, ES = -0. 049) or CSA-BFlh70 (Post-ACLR = 6.91 ± 1.011 cm² vs Control 7.01 ± 1.453 cm², T Student = -0.214; 95% CI [-Inf, 0.6795], P = 0.416, ES = -0.0783).

Conclusion Ultrasound measurement of the CSA can be an image marker to identify muscle weakness or atrophy that predicts functional loss early.

Objective This cross-sectional study was designed considering disagreements on the normal range of Median Nerve Cross-Sectional Area (MNCSA) and its association with age.

Methods In this cross-sectional descriptive study, the upper limbs of 98 healthy subjects (46 men and 52 women) were assessed bilaterally by sonography, and MNCSA was measured at the distal wrist crease.

Results Mean MNCSA values for subjects older and younger than 40 were 11.25 mm² and 10.21 mm², respectively. The results showed that the MNCSA significantly increased after 40 years of age.

Conclusion According to the present study's findings, advances in age can increase the MNCSA and affect the diagnostic accuracy of MNCSA measurement in CTS diagnosis.

Objective The purpose of this study was to compare the diagnostic performance of virtual touch tissue quantification (VTTQ) combined with B-mode ultrasonograpgy (US), strain elastography (SE) combined with B-mode US and B-mode US alone in differentiating the properties of breast lesions.

Methods A retrospective database was queried for 283 healthy subjects and 100 consecutive patients with 130 breast lesions. All the cases were examined by B-mode US, VTTQ and SE. Histological diagnosis was used as the reference standard. The area under the receiver operating curve (AUC) values of each data set was compared.

Results Twenty-two lesions were determined as malignant and 108 as benign. The best cutoff point of VTTQ was 7.82 m/s. The AUC of B-mode US combined with VTTQ or SE was greater than that of B-mode US alone (0.913 or 0.918 vs. 0.797) (P = 0.007 and 0.012).

Conclusion Both VTTQ and SE could give help to B-mode US in distinguishing benign from malignant breast lesions about elastography values. There was no difference between them.

Objective VaveHealth is a company that developed an app-based POCUS (Point of Care Ultrasound) education platform. Our objective is to provide educators with insights into novel approaches to medical education by comparing the platform to PowerPoint-based education, the standard and current technique used to instruct medical students in the United States.

Methods We used a non-inferiority study to assess if the app-based platform was not less efficacious than the current standard of PowerPoint-based education. Thirty-three military medical students were provided with app-based or PowerPoint-based education for instructions on performing a focused assessment with sonography for trauma (FAST exam). Physicians evaluated each image and assigned a score from 1-5. The final scores were the average of all views. In addition, a two-sample t-test of the final scores and each view of the FAST was used to measure whether the VaveHealth platform was non-inferior to a PowerPoint-based model.

Results Overall, the VaveHealth group had lower average scores on each view and a lower average total score. There was no statistically significant difference in overall scores (VaveHealth = 7.65, PowerPoint = 9.04, P = 0.07). Subgroup analysis showed no statistically significant difference in student performance in the views of the splenorenal recess (VaveHealth score = 1.60, PowerPoint score = 1.65, P = 0.42), hepatorenal recess (VaveHealth score = 2.45, PowerPoint score = 3.00, P = 0.11), and suprapubic (VaveHealth score = 2.10, PowerPoint score = 2.46, P = 0.23) regions. In the subxiphoid region, students in the VaveHealth had a statistically significantly lower average score (VaveHealth score = 1.70, PowerPoint score = 2.08, P = 0.04).

Conclusion VaveHealth education is not a viable alternative to traditional PowerPoint education for POCUS training based on the lower raw scores and statistically significantly lower scores on one of the views of the FAST exam.

Objective: To compare the diagnostic sensitivity and consistency of ultrasound-guided attenuation parameter (UGAP) with B-mode ultrasound in nonalcoholic fatty liver disease (NAFLD) patients, and explored their correlation with clinical indicators.
Methods: Patients suspected of NAFLD from July to November 2021 were enrolled in this prospective study. After performing the B-mode ultrasound and UGAP examination, all patients were divided into four groups according to the grade of NAFLD obtained by two modalities, respectively. The diagnostic agreement of the two modalities were evaluated, and the diagnostic sensitivity was compared by the McNemar test. The correlation between clinical indicators and the attenuation coefficient (AC) of UGAP was analyzed by linear regression.
Results: The intraclass correlation coefficient of UGAP was 0.958 (95%CI: 0.943,0.970), while the kappa value of B-mode ultrasound grading was 0.799 (95%CI: 0.686, 0.912). The diagnostic sensitivity of UGAP was higher than that of B-mode ultrasound (99.0% vs. 32%, P < 0.001). BMI and TG can be distinguished in different grades of NAFLD diagnosed by B-mode ultrasound, while BMI, ALT, HDL, and Apo A can be distinguished in different grades of NAFLD diagnosed by UGAP. BMI (r = 0.502, P < 0.001), ALT (r = 0. 396, P < 0.001), TG (r = 0.418, P < 0.001), HDL (r = -0. 359, P < 0.001) and Apo A (r = -0.228, P = 0.020) were linearly correlated with the AC value of UGAP.
Conclusions: Compared with the B-mode ultrasound, UGAP had a higher sensitivity and consistency in diagnosing NAFLD, and correlated well with some laboratory indicators, which may be more valuable in screening and diagnosis of NAFLD.

Background and Purpose: Surgery of ultrasound-detected non-palpable breast lesions should be guided by ultrasound. Commonly radiologists localize the lesion under ultrasound preoperatively, which necessitates the availability of a localization device and may involve a substantial cost. We performed a study to prospectively assess the feasibility of ultrasound-guided localization without any special device.
Methods: Women with non-palpable benign breast masses were assigned to the “guide wire insertion” (GWI) or the “local coordinates and skin inking” (LOCSI) groups. In both groups, the tumor was marked as a shadow on the skin by the radiologist under ultrasound. In the GWI group, a guidewire was inserted, and in the LOCSI group, the local coordinates of the lesion relative to the skin and the nipple as well as its clockwise placement were reported.
Results: Overall, 29 cases were included in the study, 11 in the GWI and 18 in the LOCSI groups. In all cases, the specimen was correctly excised. The weights of the resected specimens were significantly higher with GWI; LOCSI prevented excessive tissue extraction. Clinicians reported LOCSI as “very easy” more frequently, and surgery took less time.
Conclusions: Overall, our study showed that LOCSI was feasible and can be a suitable method in areas with limited resources. We propose similar studies with a larger sample size, inclusion of malignant cases for margin assessment, and estimation of the cost-effectiveness of the technique.

Objective: Computed tomography (CT) imaging of the chest is an effective diagnostic tool assisting physicians in making a diagnosis. This study aimed to propose a new convolutional neural network for classifying the lung nodules of the patient through chest CT scan data to determine whether the patient has related disease genes.
Methods: We proposed a DenseNet-based neural network structure that uses multi-scale convolutional kernels to obtain features of different receptive fields, which are fed into a DenseNet containing four improved DenseBlocks, followed by a classification module to obtain the model output, i.e., whether a lung nodule contains a cancer gene. We conducted classification experiments on a CT scan dataset containing 465 training samples and 117 test samples.
Results: The results showed that DenseNet was better than ResNet in terms of classification, whereas ResNet was better than VGG, which was consistent with the findings of previous studies. However, because these models were more complex, they suffered from overfitting problems. Among all of the models used in this paper, our proposed network achieved the best results in terms of accuracy, F1 score, and sensitivity without an over fitting. The accuracy was 72.0%, sensitivity was 78%, and F1 score was 68%.
Conclusion: The proposed DenseNet neural network can improve and assist medical imaging diagnostic physicians in the initial diagnosis of lung nodules.

Objective: An observational cross-sectional study to assess sonographic splenomegaly quantitatively in thalassemia patients grouped with respect to transfusion given whole blood vs packed red cells.
Methods: A study was conducted among 330 patients equally divided into two groups, undergoing an abdominal ultrasound examination with a transducer frequency ranging from 3-5 MHz during the period December 2021 to August 2022. An independent t-test was applied to compare the splenic volume in thalassemia patients given whole blood transfusions versus packed red cells transfusions, and Cohen's d was used to indicate the standardized difference between two ultrasound splenic volume means.
Results: The mean splenic volume of the patients who received whole blood cells was 320.62 ± 219.05 cm³, which is greater than the patients who received packed red cells, whose mean was 60.72 ± 58.72 cm³, The splenomegaly was quantitatively assessed in six age groups ranging from 1 to 3 years, 4 to 6 years, 7 to 9 years, 10 to 12 years, 13 to 15 years, and 16-18 years and mean splenic volume in each age group was compared to those receiving whole blood or packed red cells transfusion. there is a statistically significant difference between both transfusion receiving groups, having a larger Cohen’s d size effect of 1.62.
Conclusion: Ultrasound is a reliable imaging modality for assessing splenic volume and linear parameters of the spleen with greater splenomegaly in thalassemia patients with whole blood transfusions than those with packed red cells when quantitatively assessed according to relevant age groups. Thalassemia patients should be transfused packed red cells to delay splenomegaly, that should be assessed sonographically.

Objective: To evaluate the real-time accuracy of cloud handheld ultrasound system using AI technology in screening carotid plaque.

Methods: 2627 ultrasound images of the carotid artery are collected using the cloud handheld system. Bounding boxes of carotid plaques are labeled by qualified sonographers, and the dataset is trained using a lightweight YOLOv3 model. An additional and separate 390 images are collected and tested using the evaluation metrics average recall (AR), average precision (AP), and frames per second (FPS) for quantifying classification performance and time consumption.

Results: We use a plaque grading definition with a thickness of 1.2-1.5 mm defined as small plaque, 1.5-3 mm as medium plaque, and more than 3 mm thick as large plaque. Our model achieves AP^IoU=0.50 with 96.5%, with AP^large is 79.9%, AP^medium is 90.7%, AP^small is 93.5%; AR^IoU=0.50 is 64.5%, where AR^large is 60.6%, AR^medium is 58.3%, AR^small is 70.8%, and FPS is 33.3.

Conclusion: We establish a framework for data set construction, model selection, training, and testing of carotid ultrasound images and verify the effectiveness of real-time AI technology in the automatic detection of carotid artery plaque.