Ultrasonic Characteristics Research Articles

Automatic classification of weld defects from ultrasonic signals using WPEE-KPCA feature extraction and an ABC-SVM approach

The classification of weld defects is very important for the safety assessment of welded structures and feature extraction of ultrasonic defect signals is vital for defect classification. A novel approach based on wavelet packet energy entropy (WPEE) and kernel principal component analysis (KPCA) feature extraction and an artificial bee colony optimisation support vector machine (ABC-SVM) classifier is proposed in this paper. Firstly, the WPEE method is adopted to extract ultrasonic signal features of weld defects and KPCA is used for feature selection. Secondly, an ABC-SVM classifier is employed to perform defect classification. Finally, experiments involving defect feature extraction, selection and classification are carried out using four types of weld defect. The results demonstrate that the performance of the proposed feature extraction method based on WPEE is superior to that of wavelet packet energy (WPE). In addition, the WPEE-KPCA method achieved a higher accuracy rate of defect classification than WPEE.

High speed water droplet impact erosive behavior on dry and wet pulsed waterjet treated surfaces

During water droplet impact onto a dry or wet rough solid surface, several phenomena affect the surface erosion process, such as splashing, crown formation, and small droplet emission to name a few. These phenomena have been extensively studied for various simple target surface geometries. However, droplet impact studies on complex irregular and asymmetric target surface topographies resulting from a waterjet treatment have never been conducted. Furthermore, very limited reports are found on the role of target surface topography and water droplet deformation development on the resulting target stress state. In the present study, high speed droplet impingements on surfaces exhibiting coarse topographical features associated with ultrasonic pulsed waterjet treatment are modeled to understand the underlying mechanisms causing erosion. Impacts on surfaces with various roughness values and water film thicknesses are modeled using a three-dimensional coupled Eulerian–Lagrangian approach. A detailed comparative analysis of the model with experimental ultrasonic pulsed waterjet erosion features and material loss is provided. It was found that the synclastic curvature of the modeled coarse surface features increases the shock wave's strength as many compression wavelets are simultaneously emitted at each water droplet contact location with the surface, resulting in concentrated high-pressure zones. The ultrasonic pulsed waterjet treated surface features and water film thickness also greatly influence the onset of water droplet splashing, subsequent finger, secondary droplet characteristics, and crown stability. According to the numerical results, strong splashing patterns and droplet breakup are generated and create high stress zones capable of accelerating surface erosion, explaining the enhanced performance of ultrasonic pulsed waterjet process.

Ultrasonic Transducer-based Rebar Damage Monitoring Technology

In order to improve the accuracy of mechanical damage monitoring of steel bars, this paper proposes a method of mechanical damage monitoring of steel bars based on ultrasonic nondestructive testing technology. The influence of damage depth on ultrasonic was studied and analyzed, and the corresponding relationship between mechanical damage and ultrasonic characteristics was established. The test results show that the mechanical damage monitoring of steel bars based on ultrasonic nondestructive testing technology has higher accuracy and lower energy consumption and flexible installation.

Ultrasound-based prediction of preoperative core biopsy categories in solid breast tumor using machine learning.

The American College of Radiology Breast Imaging Reporting and Data System (ACR BI-RADS) used with ultrasonography cannot guide the individual management of solid breast tumors, but preoperative core biopsy categories (CBCs) can. We aimed to use machine learning to analyze clinical and ultrasonic features for predicting CBCs and to aid in the development of a new ultrasound (US) imaging reporting system for solid tumors of the breast. This retrospective study included women with solid breast tumors who underwent US-guided core needle biopsy from March 1, 2019, to December 31, 2019. All patients were randomly assigned to a training or validation cohort (7:3 ratio). CBC was predicted using 5 machine learning models: random forest (RF), support vector machine (SVM), k-nearest-neighbor (KNN), multilayer perceptron (MLP), and ridge regression (RR). In the validation cohort, the area under the curve (AUC) and accuracy were ascertained for every algorithm. Based on AUC values, the optimal algorithm was determined, and the features' importance was depicted. A total of 1,082 female patients were included (age range, 12-96 years; mean age ± standard deviation, 42.22±13.37 years). The proportion of the 4 CBCs was 4% (44/1,185) for the B1 group, 60% (714/1,185) for the B2 group, 5% (57/1,185) for the B3 group, and 31% (370/1,185) for the B5 group. In the validation cohort, AUCs of the optimal algorithm constructed RF were 0.78, 0.88, 0.64, and 0.92 for B1, B2, B3, and B5, respectively, with an accuracy of 0.82. Machine learning could strongly predict CBC, particularly in B2 and B5 categories of solid breast tumors, with RF being the optimal machine learning model.

Evaluation of nail psoriasis with ultrasound enhanced blood flow imaging (eflow) and Power Doppler (PD).

The aim of this study was to assess the discriminative utility of nail features detected by B-mode (BM), enhanced flow (eflow) and power Doppler (PD) in patients with psoriasis or nail psoriasis (NP) and healthy controls. Ultrasound appearance of nails was investigated in 5 patients with NP, 8 patients with psoriasis and 7 healthy controls. In total, 195 nails were examined. The thickness of the nail bed (TNB), the thickness of the nail plate (TNP) and the thickness of the nail matrix (TNM) did not differentiate between NP and psoriasis in longitudinal and cross-section of nails. Resistance index (RI) in nails was higher in patients with NP than in patients with psoriasis, and significantly higher in patients with psoriasis than in healthy controls. TNP between patients with psoriasis and healthy controls was statistically insignificant in longitudinal section of nails, but higher than that in the cross-section of nails. TNM was higher in patients with psoriasis than in healthy controls. The ultrasound features of NP in longitudinal and cross-section of nails, nail bed (NB) eflow and PD signal were statistically significant among patients with NP or psoriasis and healthy controls. In patients with NP, there was a correlation between the ultrasound features of NP in longitudinal and cross-section of nails and nail psoriasis severity index (NAPSI). Our study displayed the usefulness of ultrasound nail examinations in psoriatic nails, not only assessing ultrasonic features of nails and proving correlation between ultrasonic features of nails and NAPSI, but also comparing the accuracy of new technology of blood flow signal in nails.

Delamination of rotator cuff tears: Real-time dynamic ultrasound findings.

The purpose of this study was to evaluate the value of diagnosing delaminated tears and ultrasonic characteristics on real-time dynamic ultrasound. We enrolled 143 consecutive patients who underwent arthroscopic rotator cuff repair between April 2020 and January 2021. All patients were examined using real-time dynamic ultrasound of the shoulder within 2 weeks before arthroscopy. In our study, delaminated tears were defined as intratendinous horizontal splitting with or without the retraction of the articular or bursal layer of tendon. Delaminated tears were classified into three types on the basis of their shape: greater retraction of the articular layer (type I), greater retraction of the bursal layer (type II), and equal retraction of both layers (type III). The sensitivity and specificity of real-time dynamic ultrasound for evaluation of delaminated tears were calculated using arthroscopy findings as the gold standard. Ultrasonic imaging appearances of delaminated rotator cuff tears were further described. Of the 143 patients, 47 (32.9%) had delaminated tears as confirmed by arthroscopy; 35 of these tears involved the supraspinatus tendon and 12 involved both supraspinatus and infraspinatus tendons. Real-time dynamic ultrasound correctly diagnosed 36 of 47 delaminated tears with sensitivity 72.0% (57.2%-83.3%) and specificity 96.7% (90.2%-99.2%). Moreover, type I tear (n = 32) was more common than type II (n = 11) and type III tears (n = 4). Real-time dynamic ultrasound evaluated shape of type I, type II, and type III with a sensitivity and specificity of 56% and 80%, 72% and 83%, and 100% and 98%, respectively. Anechoic horizontal linear splitting of tendon, unequal retraction of the bursal and articular layers, and thinning of the suffering tendon were the three signs observed during real-time dynamic ultrasound examination. These three signs were indicative of a diagnosis of delaminated rotator cuff tears with high specificities (100.0%, 100.0%, and 97.9%, respectively) but relatively low sensitivities (25.5%, 25.5%, and 36.2%, respectively). Real-time dynamic ultrasound can be practically used for diagnosing delamination of rotator cuff tears with medium sensitivity and high specificity. Anechoic horizontal linear splitting of tendon, unequal retraction of the bursal and articular layers, and thinning of the involved tendon are the three important ultrasonic signs for diagnosis of delaminated rotator cuff tears.

A Multivariable Model Based on Ultrasound Imaging Features of Gastrocnemius Muscle to Identify Patients With Sarcopenia.

Low skeletal muscle mass, strength, or somatic function are used to diagnose sarcopenia; however, effective assessment methods are still lacking. Therefore, we evaluated the effectiveness of ultrasound in identifying patients with sarcopenia. This study included 167 patients, 78 with sarcopenia and 89 healthy participants, from two hospitals. We evaluated clinical factors and five ultrasound imaging features, of which three ultrasound imaging features were used to create the model. In both the training and validation datasets, the sarcopenia detection performances of chosen ultrasonic characteristics and the constructed model were evaluated using receiver operating characteristic (ROC) curves. The predictive performance was evaluated by area under the ROC (AUROC), calibration, and decision curves. There were statistically significant differences in muscle thickness (MT) of gastrocnemius medialis muscle (GM), flaky myosteatosis echo (FE), pennation angle (PA), average shear wave velocity (SWV) in the relaxed state (RASWV), and average SWV in the passive stretched state (PASWV) between sarcopenic and normal subjects. PA, RASWV, and PASWV were effective predictors of sarcopenia. The AUROC (95% confidence interval) for these three parameters were 0.930 (0.882-0.978), 0.865 (0.791-0.940), and 0.849 (0.770-0.928), respectively, in the training set, and 0.873 (0.777-0.969), 0.936 (0.878-0.993), and 0.826 (0.716-0.935), respectively, in the validation set. The combined model had better detection power. Finally, the calibration curve showed that the combined model had good prediction accuracy. Our model can be used to identify sarcopenia in primary medical institutions, which is valuable for the early recognition and management of sarcopenia patients.

An ultrasound-based radiomics model to distinguish between sclerosing adenosis and invasive ductal carcinoma.

We aimed to develop an ultrasound-based radiomics model to distinguish between sclerosing adenosis (SA) and invasive ductal carcinoma (IDC) to avoid misdiagnosis and unnecessary biopsies. From January 2020 to March 2022, 345 cases of SA or IDC that were pathologically confirmed were included in the study. All participants underwent pre-surgical ultrasound (US), from which clinical information and ultrasound images were collected. The patients from the study population were randomly divided into a training cohort (n = 208) and a validation cohort (n = 137). The US images were imported into MaZda software (Version 4.2.6.0) to delineate the region of interest (ROI) and extract features. Intragroup correlation coefficient (ICC) was used to evaluate the consistency of the extracted features. The least absolute shrinkage and selection operator (LASSO) logistic regression and cross-validation were performed to obtain the radiomics score of the features. Based on univariate and multivariate logistic regression analyses, a model was developed. 56 cases from April 2022 to December 2022 were included for independent validation of the model. The diagnostic performance of the model and the radiomics scores were evaluated by performing the receiver operating characteristic (ROC) analysis. The calibration curve and decision curve analysis (DCA) were used for calibration and evaluation. Leave-One-Out Cross-Validation (LOOCV) was used for the stability of the model. Three predictors were selected to develop the model, including radiomics score, palpable mass and BI-RADS. In the training cohort, validation cohort and independent validation cohort, AUC of the model and radiomics score were 0.978 and 0.907, 0.946 and 0.886, 0.951 and 0.779, respectively. The model showed a statistically significant difference compared with the radiomics score (p<0.05). The Kappa value of the model was 0.79 based on LOOCV. The Brier score, calibration curve, and DCA showed the model had a good calibration and clinical usefulness. The model based on radiomics, ultrasonic features, and clinical manifestations can be used to distinguish SA from IDC, which showed good stability and diagnostic performance. The model can be considered a potential candidate diagnostic tool for breast lesions and can contribute to effective clinical diagnosis.

A Pseudo-Siamese Feature Fusion Generative Adversarial Network for Synthesizing High-Quality Fetal Four-Chamber Views.

Four-chamber (FC) views are the primary ultrasound(US) images that cardiologists diagnose whether the fetus has congenital heart disease (CHD) in prenatal diagnosis and screening. FC views intuitively depict the developmental morphology of the fetal heart. Early diagnosis of fetal CHD has always been the focus and difficulty of prenatal screening. Furthermore, deep learning technology has achieved great success in medical image analysis. Hence, applying deep learning technology in the early screening of fetal CHD helps improve diagnostic accuracy. However, the lack of large-scale and high-quality fetal FC views brings incredible difficulties to deep learning models or cardiologists. Hence, we propose a Pseudo-Siamese Feature Fusion Generative Adversarial Network (PSFFGAN), synthesizing high-quality fetal FC views using FC sketch images. In addition, we propose a novel Triplet Generative Adversarial Loss Function (TGALF), which optimizes PSFFGAN to fully extract the cardiac anatomical structure information provided by FC sketch images to synthesize the corresponding fetal FC views with speckle noises, artifacts, and other ultrasonic characteristics. The experimental results show that the fetal FC views synthesized by our proposed PSFFGAN have the best objective evaluation values: SSIM of 0.4627, MS-SSIM of 0.6224, and FID of 83.92, respectively. More importantly, two professional cardiologists evaluate healthy FC views and CHD FC views synthesized by our PSFFGAN, giving a subjective score that the average qualified rate is 82% and 79%, respectively, which further proves the effectiveness of the PSFFGAN.

Values of new ultrasonic imaging methods for the diagnosis of apical Takotsubo syndrome.

Takotsubo syndrome (TTS) is a multifactorial disease contributed to by several pathological factors. It is characterized by transient left ventricular dysfunction, and patients with TTS can spontaneously recover within days or weeks. This study's objective was to investigate the ultrasonic characteristics of TTS during different periods and assess the clinical application value of real-time 3-dimensional echocardiography (RT-3DE) and speckle tracking imaging (STI) in TTS. In this prospective cohort study, the patients with apical TTS were evaluated by echocardiography on admission (within 1-3 days) and after 4 and 8 weeks. RT-3DE was performed to observe the structure and function of the left ventricle (LV). LV end-diastolic volume (LVEDV), end-systolic volume (LVESV), stroke volume (LVSV), and ejection fraction (LVEF) were calculated. The longitudinal peak systolic strain (LPSS) of all LV myocardial segments was acquired by 2D STI. For comparison, 20 healthy individuals were included as normal controls. A total of 16 patients with TTS were included. Their LV was characterized as an "octopus pot" in morphology with obvious hypokinesis on admission. The LVEDV, LVESV, LVSV, and LVEF were 84.23±10.67, 55.94±8.51, 28.31±8.06 mL, and 33.59%±4.12%, respectively, in patients with TTS on admission with a significant difference from those of the controls (P=0.005, P<0.001, P<0.001, and P<0.001, respectively). A definite improvement was found upon follow-up, with these parameters even returning to normal morphology after 8 weeks. The LVEDV, LVESV, LVSV, and LVEF were 75.79±6.86, 28.05±4.33, 47.81±3.57 mL, and 63.02%±3.92%, respectively, in TTS patients after 8 weeks with no significant difference from those of the controls (P=0.907, P=0.235, P=0.162, and P=0.052, respectively). A significant decrease in LPSS was also found in patients with TTS on admission. In the eighth week of follow-up, the LPSS of the apical and middle segments in TTS patients remained significantly decreased compared with that of the normal controls (-18.54%±4.69% vs. -24.29%±3.46%, P<0.001; -19.38%±2.88% vs. -22.36%±3.23%, P<0.001), but that of the basal segments in TTS patients returned to normal and there was no significant differences from the normal controls (-20.75%±2.91% vs. -21.51%±2.85%; P=0.055). RT-3DE and STI played an indispensable role in visually and quantitatively inspecting the abnormalities of patients with TTS, including in diagnosis and follow-up.

The Clinical Characteristics of Psoriatic Arthritis: A Cross-Sectional Study Based on the Psoriatic Arthritis Cohort of West China Hospital.

This study aims to describe the demographic, clinical, laboratory, and ultrasonic characteristics of patients with psoriatic arthritis (PsA) in the Psoriatic Arthritis cohort of West China Hospital. In this cross-sectional study, we included patients diagnosed with PsA according to the Classification Criteria for Psoriatic Arthritis, collected their demographic information, medical histories, and treatments, evaluated all domains (skin and nail lesions, tenderness, swelling, enthesitis, dactylitis, and axial arthritis) related to PsA, and then performed descriptive statistical analyses of all data. A total of 275 patients with PsA were included in this study. The ratio of male to female patients was 2.16:1. Skin lesions preceded arthritis in 86.5% of these patients with PsA with a mean interval of 10.1years. The metacarpophalangeal (MCP) joints, proximal interphalangeal (PIP) joints of fingers, and sacroiliac joints are the most commonly involved sites of tenderness, swelling, and the spine, respectively. Among all comorbidities, fatty liver has the highest incidence with 33.1%. Finally, we noted that the mean disease duration of PsA was 4.2years, suggesting a delay in the diagnosis of PsA. Our study proposes that the prevalent population of PsA are male patients with psoriasis over 40years of age who have a long disease course. For patients with PsA, MCP, PIP joints of fingers, and sacroiliac joints are the most frequently affected anatomical sites. With respect to comorbidities, the association between PsA and fatty liver and the underlying molecular mechanisms are worthy of further exploration.

Diagnostic performance of artificial intelligence-based computer-aided diagnosis system in longitudinal and transverse ultrasonic views for differentiating thyroid nodules.

To evaluate the diagnostic performance of different ultrasound sections of thyroid nodule (TN) using computer-aided diagnosis system based on artificial intelligence (AI-CADS) in predicting thyroid malignancy. This is a retrospective study. From January 2019 to July 2019, patients with preoperative thyroid ultrasound data and postoperative pathological results were enrolled, which were divided into two groups: lower risk group (ACR TI-RADS 1, 2 and 3) and higher risk group (ACR TI-RADS 4 and 5). The malignant risk scores (MRS) of TNs were obtained from longitudinal and transverse sections using AI-CADS. The diagnostic performance of AI-CADS and the consistency of each US characteristic were evaluated between these sections. The receiver operating characteristic (ROC) curve and the Cohen κ-statistic were performed. A total of 203 patients (45.61 ± 11.59 years, 163 female) with 221 TNs were enrolled. The area under the ROC curve (AUC) of criterion 3 [0.86 (95%CI: 0.80~0.91)] was lower than criterion 1 [0.94 (95%CI: 0.90~ 0.99)], 2 [0.93 (95%CI: 0.89~0.97)] and 4 [0.94 (95%CI: 0.90, 0.99)] significantly (P<0.001, P=0.01, P<0.001, respectively). In the higher risk group, the MRS of transverse section was higher than longitudinal section (P<0.001), and the agreement of extrathyroidal extension and shape was moderate and fair (κ =0.48, 0.31 respectively). The diagnostic agreement of other ultrasonic features was substantial or almost perfect (κ >0.60). The diagnostic performance of computer-aided diagnosis system based on artificial intelligence (AI-CADS) in longitudinal and transverse ultrasonic views for differentiating thyroid nodules (TN) was different, which was higher in the transverse section. It was more dependent on the section for the AI-CADS diagnosis of suspected malignant TNs.

An omics-to-omics joint knowledge association subtensor model for radiogenomics cross-modal modules from genomics and ultrasonic images of breast cancers

The radiogenomics analysis can provide the connections between genomics and radiomics, which can infer the genomic features of tumors from their radiogenomic associations through the low-cost and non-invasiveness screening ultrasonic images. Although there are a number of pioneer approaches exploring the connections between genomic aberrations and ultrasonic features, these studies mainly focus on the relationship between ultrasonic features and only the most popular cancer genes, confronting two difficulties: missing many-to-many relationships as omics-to-omics view, and confounding group-specific associations with whole sample associations. To overcome the difficulty of omics-to-omics view and the issue of tumor heterogeneity, we propose an omics-to-omics joint knowledge association subtensor model. Specifically, the subtensor factorization framework can successfully discover the joint cross-modal module via an omics-to-omics view, while the sparse weight sample indication strategy can mine sample subgroups from the multi-omic data with tumor heterogeneity. The experimental evaluation result shows the jointness of the discovered modules across omics, their association with tumorigenesis contribution, and their relation for cancer related functions. In summary, our proposed omics-to-omics joint knowledge association subtensor model can serve as an efficient tool for radiogenomic knowledge associations, promoting the cross-modal knowledge graph construction of in explainable artificial intelligence cancer diagnosis.

Exploring the link between ultrasonic and strength behavior of cementitious mine backfill by considering pore structure

Understanding the porosity/pore linkage and strength properties of cementitious mine backfill (CMB) is essential for the design of underground mining filling. Adoption of new production techniques in parallel with the development of technology in the mining sector has also increased the orientation to easier and less costly applications for evaluating CMB performance. This study aimed to evaluate the strength development of CMB and the change in its pore structure by using ultrasonic pulse velocity (UPV) technique. The influence of two types of pyritic tailings (low pH and high pH) obtained because of diverse production techniques on the quality of filling specimens was also investigated. The link between the microstructure formation (e.g., MIP), mechanical (e.g., UCS) and ultrasonic (e.g., UPV) characteristics of backfilling was explored by using a fixed ratio of fly ash-slag as a cement substitute (cement/slag-fly ash: 70/30). Filling samples were prepared at constant solid content (74 wt%), different curing times (3–90 days), and binder ratios (3–5-7 wt%). The results revealed that the total porosity of CMBs decreased with increasing age and binder ratio. One could also observe that the total porosity of the fill samples containing high pH tailings was lower (up to 56 %) compared to those containing low pH tailings. The acidic nature of low pH tailings negatively affected the aged strength of CMBs, destructing its microstructure. However, it was observed that the negative effects of low pH added backfills decreased in slag substitution and high binder dosages. Excellent correlation curves (power fitting) were found between UPV and UCS according to the variables used (e.g., different types of processing tailings and mineral additives). The measured and calculated UCS values were largely (R2 = 94.8 %) consistent. Finally, this study provides a complete report to support operationally low cost, easy and feasible fill design for underground metallic mines.

Deep learn-based computer-assisted transthoracic echocardiography: approach to the diagnosis of cardiac amyloidosis

Myocardial amyloidosis (CA) differs from other etiological pathologies of left ventricular hypertrophy in that transthoracic echocardiography is challenging to assess the texture features based on human visual observation. There are few studies on myocardial texture based on echocardiography. Therefore, this paper proposes an adaptive machine learning method based on ultrasonic image texture features to identify CA. In this retrospective study, a total of 289 participants (50 cases of myocardial amyloidosis; Hypertrophic cardiomyopathy: 70 cases; Uremic cardiomyopathy: 92 cases; Hypertensive heart disease: 77 cases). We extracted the myocardial ultrasonic imaging features of these patients and screened the features, and four models of random forest (RF), support vector machine (SVM), logistic regression (LR) and gradient decision-making lifting tree (GBDT) were established to distinguish myocardial amyloidosis from other diseases. Finally, the diagnostic efficiency of the model was evaluated and compared with the traditional ultrasonic diagnostic methods. In the overall population, the four machine learning models we established could effectively distinguish CA from nonCA diseases, AUC (RF 0.77, SVM 0.81, LR 0.81, GBDT 0.71). The LR model had the best diagnostic efficiency with recall, F1-score, sensitivity and specificity of 0.21, 0.34, 0.21 and 1.0, respectively. Slightly better than the traditional ultrasonic diagnosis model. In further subgroup analysis, the myocardial amyloidosis group was compared one-by-one with the patients with hypertrophic cardiomyopathy, uremic cardiomyopathy, and hypertensive heart disease groups, and the same method was used for feature extraction and data modeling. The diagnostic efficiency of the model was further improved. Notably, in identifying of the CA group and HHD group, AUC values reached more than 0.92, accuracy reached more than 0.87, sensitivity equal to or greater than 0.81, specificity 0.91, and F1 score higher than 0.84. This novel method based on echocardiography combined with machine learning may have the potential to be used in the diagnosis of CA.

Experimental investigation on pores and permeability variation characteristics of coal treated by chemical solvents

Enhancing coal permeability by adopting chemical solvents treatment is one of the most effective methods to improve coalbed methane production efficiency in deep coal reservoirs with low permeability. However, coal pores and permeability variation characteristics affected by chemical solvents is not quantitatively determined. In this study, after being treated with carbon disulfide (CS2), acetone (C3H6O) and N-methyl pyrrolidone (NMP), changes in coal ultrasonic characteristics were investigated. Relationship between ultrasonic parameter variations and coal fracture development was revealed. Meanwhile, through adopting nuclear magnetic resonance (NMR) and permeability testing equipment, coal pore structure, porosity and permeability changes were studied. Results show that after treated by three chemical solvents, ultrasonic velocity in coal reduces by 7.7%–51.2%, while ultrasonic attenuation coefficient increases by 4.22dB/m-123.8 dB/m, indicating that coal fractures experience good development. Moreover, NMR signal quantity of treated coal under saturated state rises significantly, with big growth in mesopore and macropore peaks. Compared with NMP and acetone, CS2-treated coal porosity experiences the maximum increase of 7.71%, while the corresponding permeability growth is also the largest of 69.565 × 10−15m2. Permeability changes obtained from NMP calculation model is basically consistent with that acquired by lab measurement. Furthermore, changes in extraction rate, ultrasonic parameters, pore fracture characteristics and permeability results of solvent-treated coal are mutually consistent. This verifies that chemical solvents could dissolve molecular substances in coal, effectively increase primary fractures and change small pores to mesopores and macropores, as well as improving pore connectivity. As a result, coalbed methane extraction performance is expected to be enhanced due to increased coal permeability.

Noninvasive Evaluation of Lupus Nephritis Activity Using a Radiomics Machine Learning Model Based on Ultrasound.

To explore whether ultrasonic radiomics extracted by machine learning method can noninvasively evaluate lupus nephritis (LN) activity. This retrospective study included 149 patients with LN diagnosed by renal biopsy. They were divided into a training cohort (n=104) and a test cohort (n=45). Ultrasonic radiomics features were extracted from the ultrasound images, and the radiomics features were constructed. Furthermore, five machine learning algorithms were compared to evaluate LN activity. The performance of the binary classification model was evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The average AUC of the five machine learning models was 79.4, of which the MLP model was the best. The AUC of the training group was 89.1, with an accuracy of 81.7%, a sensitivity of 83%, a specificity of 80.7%, a negative predictive value of 85.2%, and a positive predictive value of 78%. The AUC of the test group was 82.2, the accuracy was 73.3%, the sensitivity was 78.9%, the specificity was 69.2%, the negative predictive value was 81.8%, and the positive predictive value was 65.2%. Machine learning classifier based on ultrasonic radiomics has high accuracy for LN activity. The model can be used to noninvasively detect the activity of LN and can be an effective tool to assist the clinical decision-making process.

Models of ultrasonic radiomics and clinical characters for lymph node metastasis assessment in thyroid cancer: a retrospective study.

Preoperative prediction of cervical lymph node metastasis in papillary thyroid carcinoma provided a basis for tumor staging and treatment decision. This study aimed to investigate the utility of machine learning and develop different models to preoperatively predict cervical lymph node metastasis based on ultrasonic radiomic features and clinical characteristics in papillary thyroid carcinoma nodules. Data from 400 papillary thyroid carcinoma nodules were included and divided into training and validation group. With the help of machine learning, clinical characteristics and ultrasonic radiomic features were extracted and selected using randomforest and least absolute shrinkage and selection operator regression before classified by five classifiers. Finally, 10 models were built and their area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, positive predictive value and negative predictive value were measured. Among the 10 models, RF-RF model revealed the highest area under curve (0.812) and accuracy (0.7542) in validation group. The top 10 variables of it included age, seven textural features, one shape feature and one first-order feature, in which eight were high-dimensional features. RF-RF model showed the best predictive performance for cervical lymph node metastasis. And the importance features selected by it highlighted the unique role of higher-dimensional statistical methods for radiomics analysis.

Development and validation of a simple-to-use nomogram for predicting minimal change disease based on quantification of color Doppler sonography data from a region of interest.

To establish a simple-to-use nomogram based on quantification of color Doppler sonography data from a region of interest (ROI) to diagnose minimal change disease (MCD) promptly and non-invasively, and to evaluate the prediction capability of the nomogram. We recruited 564 patients with pathology-proven renal disease who were admitted to our hospital from July 2020 to July 2021 (388 patients in the training dataset and 176 patients in the validation dataset), and their color Doppler sonography data were acquired from a ROI and underwent ipsilateral renal biopsy. The collected clinical features and ultrasonic features were imported into Rstuido and statistically significant features were selected by stepwise regression using the forward-backward method. Multivariate Logistic regression analysis was combined with clinical analysis to obtain the final modeling features. General and dynamic nomogram models were constructed with the selected features, depending on whether they were MCD or not. Bootstrapping and internal validation were used for internal and external validation of the nomogram, respectively. The performance of the nomogram was assessed by C-index, calibration curve, and receiver operating characteristic (ROC) curve. Age and VI were independent factors in predicting MCD. The value of Age (Best cut-off value: 33.5years) combined with VI (Best cut-off value: 40.50 points) in the diagnosis of MCD was significantly higher than that of single diagnosis (AUC 0.901, 95% CI 0.863-0.938). The C-index of the nomogram constructed with age and VI in the training and validation datasets was 0.915 [95% confidence interval (CI) 0.874-0.956 and 0.875 95% CI 0.783-0.967], respectively. Calibration curves were fitted well. The sensitivity, specificity, and accuracy were 76.1%, 95.6%, and 78.3%, respectively, in the training dataset, and 74.1%, 94.4%, and 76.1% in the validation dataset, respectively. The nomogram constructed with age and VI showed a satisfactory degree of differentiation and accuracy, which is of great significance for early, non-invasively, and individually analysis of the risk of MCD.

Clinical and ultrasonic characteristics of male gout patients with normal serum uric acid

The clinical data and joint ultrasound characteristics of 140 male patients aged from 18 to 70 years who were diagnosed with acute gout from June 2017 to June 2021 in Department of Rheumatology and Immunology of the Third Hospital of Hebei Medical University were selected for the retrospective analysis. According to the serum uric acid levels, the patients were divided into normal uric acid group (sUA≤420 μmol/L, 38 cases) and hyperuric acid group (sUA>420 μmol/L, 102 cases).The results suggested that the lower limb joints were the most affected in gout patients. The deposition of MSU crystal were still found in male gout patients with normal serum uric acid, and the standard urate-lowering therapy should also be carried out. Ultrasound can be used as an important supplementary tool for the diagnosis of gout. Group with high level serum uric acid may be more serious.