Gray-scale Ultrasonography Research Articles

Do as Sonographers Think: Contrast-Enhanced Ultrasound for Thyroid Nodules Diagnosis via Microvascular Infiltrative Awareness.

Dynamic contrast-enhanced ultrasound (CEUS) imaging can reflect the microvascular distribution and blood flow perfusion, thereby holding clinical significance in distinguishing between malignant and benign thyroid nodules. Notably, CEUS offers a meticulous visualization of the microvascular distribution surrounding the nodule, leading to an apparent increase in tumor size compared to gray-scale ultrasound (US). In the dual-image obtained, the lesion size enlarged from gray-scale US to CEUS, as the microvascular appeared to be continuously infiltrating the surrounding tissue. Although the infiltrative dilatation of microvasculature remains ambiguous, sonographers believe it may promote the diagnosis of thyroid nodules. We propose a deep learning model designed to emulate the diagnostic reasoning process employed by sonographers. This model integrates the observation of microvascular infiltration on dynamic CEUS, leveraging the additional insights provided by gray-scale US for enhanced diagnostic support. Specifically, temporal projection attention is implemented on time dimension of dynamic CEUS to represent the microvascular perfusion. Additionally, we employ a group of confidence maps with flexible Sigmoid Alpha Functions to aware and describe the infiltrative dilatation process. Moreover, a self-adaptive integration mechanism is introduced to dynamically integrate the assisted gray-scale US and the confidence maps of CEUS for individual patients, ensuring a trustworthy diagnosis of thyroid nodules. In this retrospective study, we collected a thyroid nodule dataset of 282 CEUS videos. The method achieves a superior diagnostic accuracy and sensitivity of 89.52% and 94.75%, respectively. These results suggest that imitating the diagnostic thinking of sonographers, encompassing dynamic microvascular perfusion and infiltrative expansion, proves beneficial for CEUS-based thyroid nodule diagnosis.

The value of renal color Doppler ultrasound as an objective tool in the diagnosis of renal affection in SLE patients

BackgroundSystemic lupus erythematosus (SLE) is an autoimmune disease with diverse manifestations, which resembles a clinical challenge to be managed. Lupus nephritis is a life-threatening condition as about 10% of patients develop chronic kidney disease.Aim of the workTo assess the role of resistive index (RI) as a noninvasive parameter in detecting renal affection in SLE patients.ResultsA case–control study included 3 matched groups: 30 patients, 15 SLE with no renal affection, and 15 SLE lupus nephritis patients, who were selected, diagnosed according to ACR criteria 2019 for SLE, beside 15 age- and gender-matched healthy controls without any risk factors of chronic diseases. Written informed consent was obtained from all the three groups, and the study was approved by ethical committee. There was a statistically significant increase in both SLEDAI and renal SLEDAI scores, serum BUN, creatinine, urinary pus cells, RBCs, casts and proteins, 24-h urinary proteins, and protein/creatinine ratio beside a statistically significant increase in both right and left resistive indices in the group of lupus nephritis than the other group. There was highly statistically significant difference between SLE without nephritis and SLE with nephritis regarding renal echogenicity. There was statistically significant positive correlation between average RI and SLEDAI, rSLEDAI, serum creatinine, BUN, 24-h urinary proteins, protein/creatinine ratio, and renal echogenicity. Relation between renal echogenicity and demographic, laboratory, and clinical data was highly statistically significant with rSLEDAI, serum creatinine, BUN, 24-h urinary proteins, and P/C ratio. Our study highlighted that the best cutoff point of Rt average RI to detect SLE with nephritis group was found > 0.68 with sensitivity of 86.7% and specificity of 100.0%, while the best cutoff point of left average RI to detect SLE with nephritis group was found > 0.7 with sensitivity of 80.0% and specificity of 100.0%.ConclusionRenal RI is a noninvasive technique that can be used for detection renal disease activity in SLE patients, together with renal parenchymal echogenicity by grayscale US.

Resistive index of central retinal artery, aortic arterial stiffness and OCTA correlated parameters in the early stage of fabry disease

This study aimed to evaluate the impact of Fabry disease (FD) on retinal microvasculature using optical coherence tomography angiography (OCTA), arterial stiffness, and the resistive index (RI) of the central retinal artery (CRA) in early disease stages. Twenty-nine genetically confirmed FD patients and twenty-six healthy controls were enrolled. Vessel density (VD) values of the superficial, deep, and choriocapillaris plexuses (SCP, DCP, and CC) were measured via OCTA. CRA RI was studied using color Doppler and grayscale sonography, and aortic pulse wave velocity (PWV) was assessed with the Complior method. CRA RI was significantly lower in the control group compared to the Fabry group (p < 0.001). Central VD was found to be significantly higher in the control group compared to the Fabry group in all the retinal layers (SCP (p < 0.001), DCP (p < 0.005), CC (p < 0.001)). PWV was significantly higher in the Fabry group than in the control group (p = 0.03). Fabry disease patients demonstrate elevated arterial stiffness, increased CRA RI, and diminished retinal microvascular density compared to healthy controls, indicating early ocular damage. Continuous monitoring and targeted screening for organ impairment are crucial in FD management. Identifying biomarkers for assessing ocular vascular involvement and treatment response is imperative. Further research is needed.

Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound.

Testicular histology based on testicular biopsy is an important factor for determining appropriate testicular sperm extraction surgery and predicting sperm retrieval outcomes in patients with azoospermia. Therefore, we developed a deep learning (DL) model to establish the associations between testicular grayscale ultrasound images and testicular histology. We retrospectively included two-dimensional testicular grayscale ultrasound from patients with azoospermia (353 men with 4357 images between July 2017 and December 2021 in The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China) to develop a DL model. We obtained testicular histology during conventional testicular sperm extraction. Our DL model was trained based on ultrasound images or fusion data (ultrasound images fused with the corresponding testicular volume) to distinguish spermatozoa presence in pathology (SPP) and spermatozoa absence in pathology (SAP) and to classify maturation arrest (MA) and Sertoli cell-only syndrome (SCOS) in patients with SAP. Areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were used to analyze model performance. DL based on images achieved an AUC of 0.922 (95% confidence interval [CI]: 0.908-0.935), a sensitivity of 80.9%, a specificity of 84.6%, and an accuracy of 83.5% in predicting SPP (including normal spermatogenesis and hypospermatogenesis) and SAP (including MA and SCOS). In the identification of SCOS and MA, DL on fusion data yielded better diagnostic performance with an AUC of 0.979 (95% CI: 0.969-0.989), a sensitivity of 89.7%, a specificity of 97.1%, and an accuracy of 92.1%. Our study provides a noninvasive method to predict testicular histology for patients with azoospermia, which would avoid unnecessary testicular biopsy.

Randomized trial of low intensity shockwave therapy for erectile dysfunction utilizing grayscale ultrasound for analysis of erectile tissue homogeneity/inhomogeneity.

Electrohydraulic shockwave devices have been Food and Drug Administration-cleared for improved blood flow and connective tissue activation and have been used to treat erectile dysfunction (ED). In this study, the main focus was to evaluate improvement in erectile tissue quality after low intensity shockwave therapy (LiSWT). A single-blind, sham-controlled, randomized, prospective study, was performed in men with ED naïve to shockwave or radial ballistic pressure wave therapy. Participants were randomized 1:2 to simulated (sham) or active LiSWT treatment. After simulated treatments, participants in the Sham Arm were converted to active LiSWT, while participants initially in the Active Treatment Arm received no further treatment. Assessments were performed at baseline and two follow-up visits. Subjective parameters of erectile function (EF) were assessed by total and EF domain scores of the International Index of Erectile Function (IIEF) and sexual encounter profile (SEP). Objective parameters of penile erection were measurements of hypoechoic areas in images obtained by grayscale ultrasound (GUS) with high resolution 15.4 MHz probe and cavernosal artery peak systolic velocity (PSV) and end diastolic velocity (EDV) by color duplex Doppler ultrasound (DUS). Outcome measures for erectile and urinary function were also obtained. Simulated LiSWT did not significantly change any assessment parameter. Sham Arm participants who converted to active LiSWT had significantly increased mean IIEF total (P=0.02) and IIEF-EF scores that approached statistical significance (P=0.06), relative to baseline. Similarly, at the end of the study, Active Treatment Arm participants had significantly increased mean IIEF total (P=0.02) and IIEF-EF scores that approached statistical significance (P=0.07), relative to baseline. Additionally, at the end of the study, SEP3 success rates (erection lasting long enough for successful intercourse) approached statistical significance when Sham Arm participants were converted to active LiSWT (P=0.08) and reached statistical significance in the Active Treatment Arm (P=0.049). GUS assessments by visual grading were significantly correlated to IIEF-EF score (P=0.002) and were significantly increased relative to baseline in the Active Treatment Arm at follow-up Assessment 1 (P=0.03) and Assessment 2 (P=0.04). The greatest reduction in hypoechoic area after LiSWT occurred in the proximal penile shaft. EDV was also significantly reduced in the Active Treatment Arm at follow-up Assessment 1 (P=0.04) and Assessment 2 (P=0.04). LiSWT also resulted in improved prostate symptom scores, approaching significance in the Active Treatment Arm (P=0.055) with no changes in prostate-specific antigen. Treatment-related adverse events were limited and transient. In this prospective trial, LiSWT was safe and efficacious for erectile symptoms using GUS imaging as a novel, non-invasive method to assess improvements in corporal veno-occlusive function. Improved veno-occlusion and reduced hypoechoic area demonstrated by GUS imaging suggest that LiSWT decreases connective tissue content in penile erectile tissue. Lower urinary tract symptoms also improved with LiSWT. NCT06600893 on clinicaltrials.gov.

9176 Deep Learning Analysis with Gray Scale and Doppler Ultrasonography Images to Differentiate Graves’ Disease

9176 Deep Learning Analysis with Gray Scale and Doppler Ultrasonography Images to Differentiate Graves’ Disease

Ultrasound 7 score and serum chemerin in rheumatoid arthritis: Relation to disease activity

Background and objectives. Chemerin is an adipokine associated with inflammation. Musculoskeletal ultrasonography is now widely used for detecting and monitoring RA due to its availability, practicality, and cost-effectiveness. The aim of the study is to determine how accurate serum chemerin levels are as a biomarker of active rheumatoid arthritis (RA) disease and to find a link between these levels and ultrasonographic findings. Materials and methods. This case-control study included 44 RA cases and 44 matched-age and sex-healthy controls. Seven joints in the hand and foot were assessed by the German-ultrasound 7 (GUS 7) score through greyscale (GSUS) and power Doppler US (PDUS) in all cases. Disease activity score 28 (DAS28) evaluated RA activity, and serum chemerin levels were measured in cases and controls. Both DAS28-CRP and DAS28-ESR were used in the assessment of the disease. Outcomes. The mean age of patients was 43.48 years versus 39.18 years of controls. 86.4% of patients were females; versus 75% of the control group. 47.7% of the studied patients had moderate disease activity, 31.8% had high disease activity, and 20.5% had low disease activity. There was a statistically significant higher median chemerin serum level among RA cases compared to the control group (898.94 versus 247.81 ng/ml, p &lt;0.001). There was a significant difference in median chemerin between inactive and active patients (352.1 versus 1032.6 ng/ml (p &lt;0.001). The serum chemerin can differentiate between RA patients and controls with a higher sensitivity of 81.8%, a specificity of 88.6%, and an accuracy of 85.2%. There was a statistically significant positive association between chemerin and RA activity (p &lt;0.001). The combination of serum chemerin level and tenosynovitis GSUS score and DAS2-ESR to differentiate between active and inactive RA patients was highly significant with the highest sensitivity of 100%. Conclusions. Chemerin can serve as an advantageous marker for assessing RA activity. The US-7 score is a complementary method used in standard assessment to determine synovial inflammation in RA. The combined use of serum chemerin and the US 7 score could be of high value for detecting disease activity in RA.

Study on microwave ablation temperature prediction model based on grayscale ultrasound texture and machine learning.

Temperature prediction is crucial in the clinical ablation treatment of liver cancer, as it can be used to estimate the coagulation zone of microwave ablation. Experiments were conducted on 83 fresh ex vivo porcine liver tissues at two ablation powers of 15 W and 20 W. Ultrasound grayscale images and temperature data from multiple sampling points were collected. The machine learning method of random forests was used to train the selected texture features, obtaining temperature prediction models for sampling points and the entire ultrasound imaging area. The accuracy of the algorithm was assessed by measuring the area of the hyperechoic area in the porcine liver tissue cross-section and ultrasound grayscale images. The model exhibited a high degree of accuracy in temperature prediction and the identification of coagulation zone. Within the test sets for the 15 W and 20 W power groups, the average absolute error for temperature prediction was 1.14°C and 4.73°C, respectively. Notably, the model's accuracy in measuring the area of coagulation was higher than that of traditional ultrasonic grey-scale imaging, with error ratios of 0.402 and 0.182 for the respective power groups. Additionally, the model can filter out texture features with a high correlation to temperature, providing a certain degree of interpretability. The temperature prediction model proposed in this study can be applied to temperature monitoring and coagulation zone range assessment in microwave ablation.

2D Shear Wave Elastography of Normal Thyroid Gland in Nepalese Population

Ultrasonography (USG) is modality of choice for normal, diffuse or nodular thyroid diseases. Two dimensional shear wave elastography (2D-SWE) is the latest innovation in USG techniques that allows real-time quantitative assessment of tissue stiffness using acoustic radiation force impulse (ARFI) induced by ultrafast focused US beam sequence (up to 20,000Hz) to record the propagation of the shear waves in real time and displays a map that represents the local elasticity values of tissues in real-time and in a quantitative manner without any compression of the organ. At times, there are difficulties in differentiating normal thyroid gland from diffuse thyroid disease based solely on gray scale USG for which 2D-SWE can be an adjunct. This study aims to establish 2D-SWE parameters for normal thyroid gland in Nepalese population. A cross sectional descriptive study was carried out with 2D SWE on all euthyroid patients with normal thyroid gland on B-mode USG at Department of Radiology, Nepal Medical College Teaching Hospital between December 2021 and November 2022. Tissue stiffness of normal thyroid gland was recorded and tabulated in terms of SMV units (m/s) according age and gender. Out of 100 subjects ( 52 females and 48 males) the youngest was 16 year female and oldest was 68 year female with mean age of 37.07 year (S.D = 11.58). Minimum mean velocity of 1.78 m/s was seen in 36 year old male and maximum of 3.40 m/s in 26 year old female. Mean of mean velocity was 2.36 m/s with (S.D= 0.34). Linear positive correlation was seen between shear wave velocities and age with no statistically significant difference between genders. This study had the most number of normal subjects (100) with almost equal gender distribution (52 females and 48 males) compared to previous studies in known literature. This study also analyzed correlation of shear wave velocity with age unlike other studies. Statistically significant correlation was seen between age and velocities in males only and also in mean velocities between age group 21-40 and 41-60 years (p-value= 0.037).

Ultrasound Multimodality Examination Improves the Diagnostic Efficiency of Non-Mass-Like Breast Lesions

This study is focused on ultrasound multimodality examination, which refers to the combined use of three ultrasound examination modalities, ultrasound (US), acoustic radiation force impulse (ARFI) imaging, and contrast-enhanced ultrasound (CEUS). The purpose of this study is to analyze the value of applying ultrasound multimodality examination in the differential diagnosis of benign and malignant breast non-mass-like lesions (NMLs). Cases of breast NMLs were analyzed retrospectively, and the nature of all the lesions was verified by pathological examination. Based on the gray-scale ultrasound image characteristics, the cases were classified into types Ⅰ to Ⅴ, and type Ⅰ and type Ⅱ were further classified into 4 subtypes, Ⅰa, Ⅰb, Ⅱa, and Ⅱb, according to whether there was also calcification, and the proportion of malignant cases in each subtype was statistically analyzed. Logistic regression models of US, US+ARFI, US+CEUS, and US+ARFI+CEUS for the diagnosis of malignant cases were established, ROC curves were drawn, the area under the curve (AUC) was calculated, and comparisons were made accordingly. The detection rate of malignant NMLs without calcification (atypical malignant NMLs) by the combination examination of US, ARFI, and CEUS was analyzed. A total of 407 cases were included in the study. All subjects were female, aged 22 to 81 years, with the average age being (47.0±11.0) years. There were 220 benign cases and 187 malignant cases. Ranked from the highest to the lowest, the malignancy proportion of the different types was Ⅰb>Ⅱb>Ⅲ>Ⅴ>Ⅰa>Ⅱa>Ⅳ. The malignant proportion of the low echo area with calcification was significantly higher than that of the lesions without calcification. The AUC (95% confidence interval [CI]) for diagnosing malignant cases with the logistic regression models of US, US+ARFI, US+CEUS, and US+ARFI+CEUS were 0.895 (0.862-0.927), 0.908 (0.878-0.937), 0.921 (0.893-0.948), and 0.927 (0.902-0.952), respectively. Comparison of the AUC of the 4 regression models showed significant differences (P<0.001). The detection rate of US for NMLs without calcification was 80.7%. When US was used in combination with ARFI and CEUS, 86.4% of the malignant NMLs lesions without calcification could be detected if the lesion CEUS score was 4 or 5 points or if shear-wave velocity (SWV)≥4.28 m/s. Breast NMLs with calcification show high risks of malignancy, and a pathological examination is always recommended for a conclusive diagnosis. Ultrasound multimodality examination can improve the diagnostic accuracy of breast NML without calcification.

Cold reducing acupuncture as adjunctive therapy for wrist joint disorder of active rheumatoid arthritis with dampness-heat obstruction：a randomized controlled trial

To compare the clinical efficacy between cold reducing acupuncture combined with western medication and western medication alone for wrist joint disorder of active rheumatoid arthritis (RA) with dampness-heat obstruction. A total of 80 patients with wrist joint disorder of active RA with dampness-heat obstruction were randomly divided into a combination group (40 cases, 3 cases dropped out) and a western medication group (40 cases, 3 cases dropped out). The western medication group was treated with methotrexate tablets, 15 mg each time, once a week. The combination group was treated with cold reducing acupuncture at bilateral Hegu (LI 4), Houxi (SI 3), Waiguan (TE 5), etc. on the basis of the western medication group, once a day, 5 times a week. Both groups were treated for 8 weeks. The pain visual analogue scale (VAS) score, swelling score, morning stiffness score, Cooney wrist joint function score, ultrasound of wrist joint and serum level of C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR) before and after treatment were compared in the two groups. After treatment, the pain VAS scores, swelling scores, morning stiffness scores, grey scale ultrasound (GSUS) grade of synovitis, power doppler ultrasound (PDUS) grade of synovitis of wrist joint and serum levels of CRP and ESR in the two groups were reduced compared with those before treatment (P<0.05), the Cooney wrist joint function scores were increased compared with those before treatment (P<0.05); the pain VAS score, swelling score, PDUS grade of synovitis of wrist joint and serum level of CRP and ESR in the combination group were lower than those in the western medication group (P<0.05), the Cooney wrist joint function score was higher than that in the western medication group (P<0.05). Cold reducing acupuncture combined with western medication could improve clinical symptoms and joint function, reduce inflammatory response in patients with wrist joint disorder of active RA with dampness-heat obstruction, and the efficacy is better than that of western medication alone.

Role of Combining Grayscale Findings With Superb Microvascular Imaging and Shear Wave Elastography in Standardization and Management of NON-MASS Breast Lesions.

The non-mass breast lesions on ultrasound (US) are a group of challenging pathology. We aimed to standardize these grayscale findings and investigate the effectiveness of superb microvascular imaging (SMI) and shear wave elastography (SWE). A total of 195 lesions were evaluated by B-mode US, SWE, and SMI in the same session. A "NON-MASS model" was built on grayscale US to group the lesions only as areas and those with associated features: microcalcifications, architectural distortion, ductal changes, and microcysts. The mean stiffness parameters Emean, Eratio, and mean vascular index (VI) were recorded following consecutive measurements. Besides, the microvascularity was graded based on Adler's classification (grades 0 to 3). Lesions were divided into 3 groups: benign, category B3, and malignant. One hundred twelve (57.4%) lesions were benign, 23 (11.8%) were B3, and 60 were (30.8%) in the malignant category. Thirty-eight (19.5%) lesions were observed only as an area, whereas associated features were present in 157 lesions (80.5%). Distortion was the only associated feature predicting malignancy among the grayscale findings (P < 0.001). There was a significant difference between malignant and nonmalignant (benign and B3) groups in terms of Adler's grade, Emean, Eratio, and VI values (P < 0.001). Sensitivity, specificity, and accuracy increased when advanced imaging parameters were added to grayscale findings (P < 0.001). In the presence of microcalcifications, architectural distortion, high elasticity, and hypervascularity in the "NON-MASS" imaging model, the suspicion of malignancy increases. The non-mass findings and advanced imaging techniques have the potential to find greater coverage in the following versions of BI-RADS atlas.

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography.

The objective of the study was to use a deep learning model to differentiate between benign and malignant sentinel lymph nodes (SLNs) in patients with breast cancer compared to radiologists' assessments.Seventy-nine women with breast cancer were enrolled and underwent lymphosonography and contrast-enhanced ultrasound (CEUS) examination after subcutaneous injection of ultrasound contrast agent around their tumor to identify SLNs. Google AutoML was used to develop image classification model. Grayscale and CEUS images acquired during the ultrasound examination were uploaded with a data distribution of 80% for training/20% for testing. The performance metric used was area under precision/recall curve (AuPRC). In addition, 3 radiologists assessed SLNs as normal or abnormal based on a clinical established classification. Two-hundred seventeen SLNs were divided in 2 for model development; model 1 included all SLNs and model 2 had an equal number of benign and malignant SLNs. Validation results model 1 AuPRC 0.84 (grayscale)/0.91 (CEUS) and model 2 AuPRC 0.91 (grayscale)/0.87 (CEUS). The comparison between artificial intelligence (AI) and readers' showed statistical significant differences between all models and ultrasound modes; model 1 grayscale AI versus readers, P = 0.047, and model 1 CEUS AI versus readers, P < 0.001. Model 2 r grayscale AI versus readers, P = 0.032, and model 2 CEUS AI versus readers, P = 0.041.The interreader agreement overall result showed κ values of 0.20 for grayscale and 0.17 for CEUS.In conclusion, AutoML showed improved diagnostic performance in balance volume datasets. Radiologist performance was not influenced by the dataset's distribution.

Diagnostic Performance of Grayscale Ultrasonography in the Evaluation of Mass-forming Breast Lesions.

In our study, we evaluated the diagnostic performance of grayscale ultrasonography (USG) in risk stratification of mass-forming breast lesions. Our study included 90 cases, in which 88 were females and 2 cases were male with age ranging from 16 to 73 years. Out of 90 lesions, 51 (58%) lesions were benign and 39 (39%) lesions were malignant. High-resolution USG done in all 90 lesions revealed sensitivity (90.2%), specificity (74.36%), positive predictive value (PPV) (82.14%), negative predictive value (NPV) (85.29%), and accuracy (83.33%). Calculated weighted kappa value 0.665, indicating better level of agreement in predicting malignant lesions compared to gold standard. Our study revealed that USG is sensitive and specific test in detecting malignant lesions with high PPV and NPV; the calculated weighted kappa value was 0.665, indicating better level of agreement in predicting malignant lesions compared to gold standard.

Deep learning radiomics based on ultrasound images for the assisted diagnosis of chronic kidney disease.

This study aimed to explore the value of ultrasound (US) images in chronic kidney disease (CKD) screening by constructing a CKD screening model based on grey-scale US images. According to the CKD diagnostic criteria, 1049 patients from Tongde Hospital of Zhejiang Province were retrospectively enrolled in the study. A total of 4365 renal US images were collected from these patients. Convolutional neural networks were used for feature extractions and a screening model was constructed by fusing ResNet34 and texture features to identify CKD and its stage. A comparative analysis was performed to compare the diagnosis results of the model with physicians. When diagnosing CKD or non-CKD, the receiver operating characteristic curve (AUC) of our model was 0.918 and that of the senior physician group was 0.869 (p < .05). For the diagnosis of CKD stage, the AUC of our model for CKD G1-G3 was 0.781, 0.880, and 0.905, respectively, while the AUC of the senior physician group for CKD G1-G3 was 0.506, 0.586, and 0.796, respectively; all differences were statistically significant (p < .05). The diagnostic efficiency of our model for CKD G4 and G5 reached the level of the senior physicians group. Specifically, the AUC of our model for CKD G4-G5 was 0.867 and 0.931, respectively, while the AUC of the senior physician group for CKD G4-G5 was 0.838 and 0.963, respectively (all p > .05). Our deep learning radiomics model is more effective than senior physicians in the diagnosis of early CKD.

Clinical applications of superb microvascular imaging and virtual touch imaging quantification in pediatric mesenteric lymphadenitis diagnosis: A promising pathway to enhanced precision.

Mesenteric lymphadenitis (ML) demonstrates a distinctive inclination for the pediatric and adolescent demographic and the diagnosis of ML in young children poses a substantial challenge. This prospective study aimed to assess the diagnostic efficacy of Superb Microvascular Imaging (SMI) and Virtual Touch Tissue Imaging quantification (VTIQ) in distinguishing pediatric mesenteric lymphadentitis. We examined 82 mesentric lymph node (MLN) in pediatric patients with mesenteric lymphadentitis and 50 MLN in a healthy group. SMI was utilized to evaluate vascularity within the MLN, while MLN stiffness, quantified as shear wave velocity (SWV) in meters per second (m/s), was assessed using VTIQ. We compared the diagnostic performance of greyscale Ultrasound, US combined with SMI, US combined with VTIQ, and US combined with both SMI and VTIQ. SMI revealed a significant distinction between mesenteric lymphadentitis and normal MLN (p < 0.001). MLN affected by mesenteric lymphadentis exhibited increased vascularity (marked vascularity: 13/82, 15.85%) compared to normal MLN (marked vascularity: 1/50, 2.00%). Statistically significant differences were observed in SWV values beween mesenteric lymphadentitis and normal MLN (all p-values <0.001). The mean and minimum SWV values for MLN with mesenteric lymphadentitis were 1.66±0.77 m/s and 1.51±0.53 m/s, respectively. Control group SWV values were approximately three times higher than those in the mesenteric lymphadenitis group. The highest area under the curve values were achieved with the combination of all three modalities (0.837, 95% confidence interval: 0.763- 0.896), followed by US + VTIQ (0.795, 0.716- 0.860), US + SMI (0.753, 0.670- 0.824) and US alone (0.642, 0.554- 0.724). SMI and VTIQ offer a promising noninvasive adjunct to grayscale ultrasound for identifying mesenteric lymphadentitis in pediatric patients.

Usefulness of Picture Archiving and Communication System-Based Quantitative Ultrasound Measurements in Evaluation of Allograft Dysfunction in Patients With Liver Transplantation.

The aim of this study was to assess the usefulness of picture archiving and communication system (PACS)-based quantitative grayscale ultrasonography (US) measurements in detecting allograft dysfunction in posttransplant patients. In this retrospective study, 116 patients with liver transplantation who underwent biopsy for allograft evaluation were recruited from the database. All participants had US images prior to procedure. Normal, acute cellular rejection (ACR), recurrent hepatitis (Hep), or combined (ACR/Hep) groups were generated based on pathology results. Region of interests were drawn for liver and rectus abdominus muscle to perform quantitative US analysis. The liver/muscle mean ratio (L/M) and heterogeneity index (HI; liver standard deviation/liver mean) were obtained. The ratios of groups were compared, and receiver-operating-characteristic analysis was performed. There was a significant difference between normal (n = 16) and each of other groups (ACR, 39; Hep, 36; combined, 25) for L/M and HI (P < 0.05). No significant difference was detected between ACR, Hep, and combined groups. The areas under the curve for L/M and HI were 0.755 (moderate) and 0.817 (good), respectively. To differentiate abnormal (ACR, Hep, and combined) from normal allografts sensitivity, specificity, PPV, and NPV were 50.0%, 87.5%, 96.2%, and 21.9% for cut point of L/M ≥1 and 84.0%, 68.8%, 94.4%, and 40.7% for cut point of HI ≥0.2 with odds ratios of 7.52 (for L/M ≥1) and 13.10 (for HI ≥0.2), respectively (P < 0.01). L/M has moderate and HI has good discrimination of normal from abnormal allograft in liver transplant patients. PACS-based quantitative US measurements is an objective, easy to use, noninvasive auxiliary tool to discriminate hepatic allograft dysfunction.

US-based radiomics analysis of different machine learning models for differentiating benign and malignant BI-RADS 4A breast lesions

To investigate and authenticate the effectiveness of various radiomics models in distinguishing between benign and malignant BI-RADS 4A lesions. A total of 936 patients with pathologically confirmed 4A lesions were included in the study (training cohort: n=655; test cohort: n=281). Radiomic features were derived from greyscale US images. Following dimensionality reduction and feature selection, radiomics models were developed using logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. Univariate and multivariable logistic regression analyses were employed to investigate clinical-radiological characteristics and determine variables for creating a clinical model. Five combined models integrating radiomic and clinical parameters were constructed by using each algorithm, and comparison with radiologists' performance was performed. SHapley Additive exPlanations (SHAP) approach was used to elucidate the radiomic model by ranking the significance of features based on their contribution to the evaluation. A total of 1561 radiomic features were extracted. Thirty-six features were deemed significant by dimensionality reduction and selection. The radiomic models showed good performance with AUCs of 0.829-0.945 in training cohort; and 0.805-0.857 in test cohort. The combined model developed by using LR showed the best performance (AUC, training cohort: 0.909; test cohort: 0.905), which is superior to radiologists' performance. Decision curve analysis (DCA) of this combined model indicated better clinical efficacy than clinical and radiomic models. The combined model integrating radiomic and clinical features demonstrated excellent performance in differentiating between benign and malignant 4A lesions. It may offer a non-invasive and efficient approach to aid in clinical decision-making.

Thyroid Nodule Characterization: Overview and State of the Art of Diagnosis with Recent Developments, from Imaging to Molecular Diagnosis and Artificial Intelligence.

Ultrasound (US) is the primary tool for evaluating patients with thyroid nodules, and the risk of malignancy assessed is based on US features. These features help determine which patients require fine-needle aspiration (FNA) biopsy. Classification systems for US features have been developed to facilitate efficient interpretation, reporting, and communication of thyroid US findings. These systems have been validated by numerous studies and are reviewed in this article. Additionally, this overview provides a comprehensive description of the clinical and laboratory evaluation of patients with thyroid nodules, various imaging modalities, grayscale US features, color Doppler US, contrast-enhanced US (CEUS), US elastography, FNA biopsy assessment, and the recent introduction of molecular testing. The potential of artificial intelligence in thyroid US is also discussed.

Correlation of Grayscale Ultrasound and Doppler Evaluation with Histopathological Diagnosis in Cases of Tubercular Cervical Lymphadenitis

ABSTRACT Introduction: Cervical lymphadenopathy is a relatively common clinical presentation that can have varied causes including reactive, inflammatory, tubercular, or neoplastic etiologies. Sonography is most often the first line of investigation used in clinical practice to characterize the enlarged nodes with respect to their location, number, size, and morphological imaging characteristics and determine the differential etiological possibilities. Materials and Methods: The present study was conducted involving 434 patients who presented over a period of 3 years to radiology departments of three multispecialty hospitals for the evaluation of cervical swellings. The study aimed to establish the correlation between the ultrasound and Doppler parameters used in clinical practice and the final histological diagnosis in cases of tubercular cervical lymphadenitis. Results: Overall, a female predisposition was observed in the proportion of patients who presented with cervical lymphadenopathy. A similar increased female percentage was also observed in cases finally detected to have tubercular pathology. The highest diagnostic indices were obtained for two ultrasound parameters of “matted nodes” and “caseous necrosis with posterior acoustic enhancement.” Although other features such as hypoechoic nodes, Doppler findings of peripheral vascularity, and high resistive index (RI)/pulsatility index (PI) values demonstrated high sensitivity, they showed poor specificity, positive predictive values, and low accuracy. Conclusion: In ultrasound scans for suspected cases of tubercular cervical lymphadenitis, the maximum weightage should be given to “matted nodes” and “caseous necrosis with posterior acoustic enhancement” parameters to differentiate the tubercular etiology from other potential causes. These parameters demonstrate high sensitivity, specificity, positive predictive value, and accuracy. Hence, they can be relied upon to start timely anti-tubercular treatment and follow-up with patients on a clinical-radiological basis. This can supplement waiting for suboptimal cytology reports that are difficult to arrive at, specifically in tubercular cervical lymphadenitis cases. The same applies as well to biopsy specimens that are hard to obtain from cervical nodes with associated potential grave complications.