Search

To compare the safety, effectiveness, and feasibility of contrast-enhanced ultrasound (CEUS) versus conventional ultrasound-guided percutaneous nephrolithotomy (PCNL) in patients with nondilated collecting system.Between July 2018 and July 2020, 160 kidney stone patients with nondilated collecting system planned for PCNL were randomly assigned into two groups, CEUS with retrograde ureteral contrast injection and conventional ultrasound with retrograde ureteral normal saline injection. Patient's demographics, the success rate of puncture, success rate of a single-needle puncture, number of punctures, puncture time, perioperative outcomes, stone-free rate, and incidence of complications were compared.The success rate of a single-needle puncture for CEUS-guided PCNL was higher than that in the conventional ultrasound group (88.5% vs. 73.7%, p = 0.02). Patients performed with CEUS-guided PCNL required less needle passes (p = 0.02), shorter needle puncture time (p = 0.031), and shorter channel establishment time (p = 0.04) than those guided with conventional ultrasound. The postoperative hemoglobin decrease in the CEUS-guided PCNL group was less than that of the control group (p = 0.02). There was no significant difference in operating time, length of hospital stays, kidney function change, and complications between the two groups (p0.05). The 1-month stone-free rate was 94.9% in the CEUS group and 90.8% in the control group (p0.05).Compared with conventional ultrasound, CEUS-guided PCNL may facilitate ultrasound-guided PCNL for patients without hydronephrosis, and benefited with a higher success rate of a single-needle puncture, less needle passes, shorter puncture time, and lower postoperative Hb drop.Chinese Clinical Trial Registry: ChiCTR1800016981 KEY POINTS: • Compared with conventional ultrasound, CEUS-guided PCNL is a safe and efficacious procedure for kidney stone patients with nondilated collecting system. • Compared with conventional ultrasound, CEUS-guided PCNL benefited with a higher success rate of a single-needle puncture, less needle passes, shorter puncture time, and lower postoperative Hb drop. • CEUS-guided PCNL associated with the more accurate needle puncture and acceptable complications.

Background: This study aimed to develop a machine learning (ML)-assisted model capable of accurately predicting the probability of biopsy Gleason grade group upgrading before making treatment decisions.Methods: We retrospectively collected data from prostate cancer (PCa) patients who underwent systematic biopsy and radical prostatectomy from January 2015 to December 2019 at Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology. The study cohort was divided into training and testing datasets in a 70:30 ratio for further analysis. Four ML-assisted models were developed from 16 clinical features using logistic regression (LR), logistic regression optimized by least absolute shrinkage and selection operator (Lasso) regularization (Lasso-LR), random forest (RF) and support vector machine (SVM). The area under the curve (AUC) was applied to determine the model with the highest discrimination. Calibration plots were used to investigate the extent of over- or underestimation of predicted probabilities relative to the observed probabilities in models. Results: In total, 530 PCa patients were included, with 371 patients in the training dataset and 159 patients in the testing dataset. The Lasso-LR model showed good discrimination with an AUC, accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.776, 0.712, 0.679, 0.745, 0.730 and 0.695, respectively, followed by SVM (AUC 0.740, 95% confidence interval [CI]: 0.690–0.790), LR (AUC 0.725, 95% CI: 0.674–0.776) and RF (AUC 0.666, 95% CI: 0.618–0.714). Validation of the model showed that the Lasso-LR model had the best discriminative power (AUC 0.735, 95% CI: 0.656–0.813), followed by SVM (AUC 0.723, 95% CI: 0.644–0.802), LR (AUC 0.697, 95% CI: 0.615–0.778) and RF (AUC 0.607, 95% CI: 0.531–0.684) in the testing dataset. Both the Lasso-LR and SVM models were well-calibrated. Conclusion: The Lasso-LR model had good discrimination in the prediction of patients at high risk of harboring incorrect Gleason grade group assignment, and the use of this model may be greatly beneficial to urologists in treatment planning, patient selection, and the decision-making process for PCa patients.

Cyclic wetting and drying processes have been considered as important factors that accelerate the weathering process and have deteriorative effects on rock properties. In the present study, a fully nondestructive and noninvasive testing approach utilizing micro-CT and ultrasonic wave velocity tests was employed to investigate the microstructure of slate under wetting and drying cycles. We studied variations in the physical properties, including the dry weight and the velocities of P- and S-waves versus the number of wetting and drying cycles. The internal microstructural distributions were visualized and quantified by the 3D reconstruction and hybrid image segmentation of CT images. The degree of deterioration caused by wetting and drying cycles was reflected by exponential decreases of physical properties, including dry weight and velocities of the P- and S-waves. Parameters relating to the microfracture diameter, volume, etc. were quantified. The nondestructive and noninvasive testing approach utilizing micro-CT and ultrasonic wave velocity tests has potential for the detection and visualization of the internal microstructure of rock under wetting and drying cycles.

Hailang Liu,1 Kun Tang,1 Ejun Peng,1 Liang Wang,2 Ding Xia,1 Zhiqiang Chen1 1Department of Urology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, Hubei, People’s Republic of China; 2Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, Hubei, People’s Republic of ChinaCorrespondence: Ding Xia; Zhiqiang ChenTongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1095 Jiefang Avenue, Wuhan 430030, Hubei, People’s Republic of ChinaEmail 3012904661@qq.com; lhl20180129@163.comObjective: This study aimed to develop a machine learning (ML)-assisted model capable of accurately predicting the probability of biopsy Gleason grade group upgrading before making treatment decisions.Methods: We retrospectively collected data from prostate cancer (PCa) patients. Four ML-assisted models were developed from 16 clinical features using logistic regression (LR), logistic regression optimized by least absolute shrinkage and selection operator (Lasso) regularization (Lasso-LR), random forest (RF), and support vector machine (SVM). The area under the curve (AUC) was applied to determine the model with the highest discrimination. Calibration plots and decision curve analysis (DCA) were performed to evaluate the calibration and clinical usefulness of each model.Results: A total of 530 PCa patients were included in this study. The Lasso-LR model showed good discrimination with an AUC, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.776, 0.712, 0.679, 0.745, 0.730, and 0.695, respectively, followed by SVM (AUC=0.740, 95% confidence interval [CI]=0.690– 0.790), LR (AUC=0.725, 95% CI=0.674– 0.776) and RF (AUC=0.666, 95% CI=0.618– 0.714). Validation of the model showed that the Lasso-LR model had the best discriminative power (AUC=0.735, 95% CI=0.656– 0.813), followed by SVM (AUC=0.723, 95% CI=0.644– 0.802), LR (AUC=0.697, 95% CI=0.615– 0.778) and RF (AUC=0.607, 95% CI=0.531– 0.684) in the testing dataset. Both the Lasso-LR and SVM models were well-calibrated. DCA plots demonstrated that the predictive models except RF were clinically useful.Conclusion: The Lasso-LR model had good discrimination in the prediction of patients at high risk of harboring incorrect Gleason grade group assignment, and the use of this model may be greatly beneficial to urologists in treatment planning, patient selection, and the decision-making process for PCa patients.Keywords: prostate cancer, biopsy cores, Gleason grade group, upgrading, machine learning

Accurately predicting the surface displacement of the landslide is important and necessary. However, most of the existing research has ignored the frequency component of inducing factors and how it affects the landslide deformation. Therefore, a hybrid displacement prediction model based on time series theory and various intelligent algorithms was proposed in this paper to study the effect of frequency components. Firstly, the monitoring displacement of landslide from the Three Gorges Reservoir area (TGRA) was decomposed into the trend and periodic components by complete ensemble empirical mode decomposition (CEEMD). The trend component can be predicted by the least square method. Then, time series of inducing factors like rainfall and reservoir level was reconstructed into high frequency components and low frequency components with CEEMD and t-test, respectively. The dominant factors were selected by the method of dynamic time warping (DTW) from the frequency components and other common factors (e.g., current monthly rainfall). Finally, the ant colony optimization-based support vector machine regression (ACO-SVR) is utilized for prediction purposes in the TGRA. The results demonstrate that after considering the frequency components of landslide-induced factors, the accuracy of the displacement prediction model based on ACO-SVR is better than that of other models based on SVR and GA-SVR.

The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning. While voxel-based deep learning frameworks have been proposed for this segmentation task, their performance remains limited. In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly higher performance. Our proposed model takes a surface model of entire principal brain arteries containing aneurysms as input and returns aneurysms surfaces as output. A user first generates a surface model by manually specifying multiple thresholds for time-of-flight magnetic resonance angiography images. The system then samples small surface fragments from the entire brain arteries and classifies the surface fragments according to whether aneurysms are present using a point-based deep learning network (PointNet++). Finally, the system applies surface segmentation (SO-Net) to surface fragments containing aneurysms. We conduct a direct comparison of segmentation performance by counting voxels between the proposed surface-based framework and the existing voxel-based method, in which our framework achieves a much higher dice similarity coefficient score (72%) than the prior approach (46%)., It is a pre-released version

Objective To develop novel models for predicting extracapsular extension (EPE), seminal vesicle invasion (SVI), or upgrading in prostate cancer (PCa) patients using clinical parameters, biparametric magnetic resonance imaging (bp-MRI), and transrectal ultrasonography (TRUS)-guided systematic biopsies. Patients and Methods We retrospectively collected data from PCa patients who underwent standard (12-core) systematic biopsy and radical prostatectomy. To develop predictive models, the following variables were included in multivariable logistic regression analyses: total prostate-specific antigen (TPSA), central transition zone volume (CTZV), prostate-specific antigen (PSAD), maximum diameter of the index lesion at bp-MRI, EPE at bp-MRI, SVI at bp-MRI, biopsy Gleason grade group, and number of positive biopsy cores. Three risk calculators were built based on the coefficients of the logit function. The area under the curve (AUC) was applied to determine the models with the highest discrimination. Decision curve analyses (DCAs) were performed to evaluate the net benefit of each risk calculator. Results A total of 222 patients were included in this study. Overall, 83 (37.4%), 75 (33.8%), and 107 (48.2%) patients had EPE, SVI, and upgrading at final pathology, respectively. The addition of bp-MRI data improved the discrimination of models for predicting SVI (0.807 vs 0.816) and upgrading (0.548 vs 0.625) but not EPE (0.766 vs 0.763). Similarly, models including clinical parameters, bp-MRI data, and information on systematic biopsies achieved the highest AUC in the prediction of EPE (0.842), SVI (0.913), and upgrading (0.794), and the three corresponding risk calculators yielded the highest net benefit. Conclusion We developed three easy-to-use risk calculators for the prediction of adverse pathological features based on patient clinical parameters, bp-MRI data, and information on systematic biopsies. This may be greatly beneficial to urologists in the decision-making process for PCa patients.

Background We aim to determine the prevalence of hypervirulent Klebsiella pneumoniae (hvKp), which causes surgical site infections (SSIs), and describe the microbiological and molecular characteristics of hvKp isolates. Methods Non-duplicate K. pneumoniae strains were isolated from wound drainage specimens of postoperative patients at the Chinese PLA General Hospital between September 2008 and July 2017. Antimicrobial susceptibility, string test, pulsed-field gel electrophoresis (PFGE), and genome sequencing analyses were performed. Results Fifty-one K. pneumoniae strains were isolated from wound drainage specimens collected from postoperative patients. Twenty-six hvKp strains, including 17 (17/37, 46.0%) and 9 (9/14, 64.3%) hvKp strains, were isolated from 37 and 14 patients with SSIs and community-acquired infections (CAIs), respectively. Notably, 4 extended-spectrum beta-lactamase (ESBL)-producing hvKp strains (4/26, 15.4%) and 2 carbapenem-resistant hvKp strains (2/26, 7.7%) were found. Thirteen K1 serotype (13/26, 50.0%) and 7 K2 serotype (7/26, 26.9%) strains were identified. Phylogenetic analysis results showed that 13 K1 serotype isolates exhibited a high degree of clonality, while 7 K2 serotype strains were genetically unrelated. MLST analysis indicated that there was a strong correlation between ST23 and the K1 serotype. ST65, ST86, and ST375 were prevalent in K2 serotype strains. Almost all hvKp strains (24/26, 92.3%) harbored large virulence plasmids with a high degree of homology to pNTUH-K2044 and sizes ranging from 140 to 220 kbp. Conclusions HvKp strains were prevalent in SSIs. Effective surveillance and control measures should be implemented to prevent the dissemination of such organisms, including the ESBL-producing and carbapenem-resistant hvKp strains.

Objective. Hyperperfusion syndrome (HPS) after bypass surgery for moyamoya disease (MMD) mainly results from redistribution of blood flow, which leads to poor outcomes, while effective methods to predict HPS are still lacking. Indocyanine green (ICG) videoangiography can assess regional cerebral blood flow changes semiquantitatively with the application of FLOW 800 software. The purpose of this study was to investigate whether the intraoperative evaluation of local hemodynamic changes around anastomotic sites using FLOW 800 videoangiography mapping can predict the incidence of HPS and clinical outcomes. Methods. Of the patients who were diagnosed with MMD in our hospital between August 2018 and December 2019, who underwent superficial temporal artery-middle cerebral artery bypass surgeries, we investigated 65 hemispheres (in 62 patients) in which intraoperative ICG analysis was performed using FLOW 800 (Zeiss Meditec, Oberkochen, Germany) to evaluate the local cerebral hemodynamics before and after anastomosis. Regions of interest were set at more than 2 points on the brain surface according to the location and situation of recipient arteries in the surgical area. Peak cerebral blood volume (CBV), regional cerebral blood flow (CBF), and time to peak (TTP) were calculated from the selected points. As the data were available intraoperatively, anastomoses were performed in a suitable area. According to the occurrence of HPS, patients were divided into the asymptomatic and symptomatic groups, from which hemodynamic parameters were compared. Furthermore, ROC analysis was performed to determine the diagnostic accuracy of change rates in CBV, CBF, and TTP (i.e., ΔCBV, ΔCBF, and ΔTTP) for predicting HPS. Results. Data from the 62 patients were analyzed, and all patients were closely assessed during hospitalization after the procedures. The values of ΔCBV and ΔCBF were significantly higher in the symptomatic group (p<0.01), while ΔTTP is slightly lower in the symptomatic group with no statistical differences (p=0.72). Hemodynamic parameters including ΔCBV and ΔCBF, calculated by FLOW 800, had high sensitivity and specificity according to the ROC curve (ΔCBV: AUC=0.743, 95% CI, 0.605–0.881, p=0.002; ΔCBF: AUC=0.852, 95% CI, 0.750–0.954, p<0.01), which could be used as predictors for HPS. Conclusions. Intraoperative ICG-FLOW 800 videoangiography mapping is a safe method which can reflect hemodynamic characteristics in the surgical area for MMD, the findings of which correlate with the occurrence of HPS. Parameters including ΔCBV and ΔCBF are proven to be efficient in the prediction of HPS.

Medicine is an important application area for deep learning models. Research in this field is a combination of medical expertise and data science knowledge. In this paper, instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available. Our dataset can be used to diagnose intracranial aneurysms and to extract the neck for a clipping operation in medicine and other areas of deep learning, such as normal estimation and surface reconstruction. We provide a large-scale benchmark of classification and part segmentation by testing state-of-the-art networks. We also discuss the performance of each method and demonstrate the challenges of our dataset. The published dataset can be accessed here: https://github.com/intra3d2019/IntrA., Comment: Accepted by cvpr2020, camera-ready version will be uploaded later

Additional file 1: Supplementary Table 1: MLST profiles and genotype of 8 C. gattii strains. Supplementary Table 2: MLST profiles of 16 gene loci for 2 C. gattii strains with genotype VGII. Notes: R265 and R272 were Vancouver Island reference strains for C. gattii genotype VGIIa and VGIIb respectively; / represented that data was not available; GenBank accession numbers for multilocus sequence typing alleles were: CAP59–1, DQ096432; CAP59–2, DQ096433; GPD1–1, DQ096377; GPD1–6, DQ096382; IGS-4, DQ096314; IGS-10, DQ096319; PLB1–1, DQ096343; PLB1–2, DQ096344; SXI1α-18, DQ096308; SXI1α-19, AY973646; TEF1–7, DQ096364; TEF1–5, DQ096362; FTR1–1, DQ096448; FTR1–2, DQ096449; CBP1–1, DQ096435; CBP1–2, DQ096436; ICL1–1, DQ096458; ICL1–2, DQ096459; HOG1–1, DQ096456; TOR1–1, DQ096470; STE7–1, DQ096467; STE7–2, DQ096468;TRR1–1, DQ096472; TRR1–2, DQ096473; RAS1–1, DQ096464; RAS1–2, DQ096465; PAK1–1, DQ096461; PAK1–2, DQ096462.

An approach was proposed to automatically measure the discontinuity geometric properties from a point cloud acquired using Light Detection and Ranging (LiDAR). The procedure primarily includes the following features: (Assali et al., 2016) Grid data from the point cloud was created to enhance computational efficiency for data processing and retrieval; (Barton & Choubey, 1977) A modified region growing (MRG) algorithm, which is characterized by more efficient grow criterion, was used to recognize discontinuities from the point cloud; (Cao et al., 2017) Four geometric properties from identified discontinuities were calculated based on analytic geometry; (Chen et al., 2016) Influence of threshold T on the identified results was investigated through sensitivity analysis, and threshold T was suggested to be less than the minimum normal difference among all joints and larger than 0°. Two cases (regular polyhedrons and a tunnel in the Rumei hydropower station) were taken as case studies to validate the developed approach, and calculation results have good agreement with real situations.

PURPOSE To demonstrate the feasibility of the so-called quadrupolar jump-and-return (QJR) pulse sequence by assessing its performance on the contrast modification to knee cartilage and quality of fluid suppression in the knee joint in vivo at 7T. METHODS The right knee joints of five healthy volunteers (3 males: mean age = 32.4 ± 1.3 years; 2 females: mean age = 27.9 ± 1.0 years; mean age = 30.6 ± 2.7 years) were scanned on a 7T scanner with variation of the delay in the QJR sequence from 1 ms to 5 ms. For one healthy volunteer, the QJR scan with the delay of 3 ms and the inversion-recovery (IR) scan were performed. Numerical simulations were conducted to evaluate the effects of B0 - and B1 -field inhomogeneities and residual quadrupolar couplings on fluid suppression and tissue contrast, respectively. RESULTS The QJR sequence suppressed the fluid signal from the artery and produced the contrast of knee cartilage in vivo. Its performance was comparable to that of the conventional IR sequence. Numerical simulations suggested that the fluid suppression may not be affected much by field inhomogeneities but that a distribution of residual quadrupolar couplings and weak RF pulses may interfere with the clear interpretation of cartilage contrast. CONCLUSION This preliminary work demonstrated that the QJR pulse sequence produces contrast for knee cartilage while suppressing the fluid signal from the artery. The knee cartilage contrast and quality of fluid suppression obtained from the QJR sequence were comparable to those of the IR sequence. Magn Reson Med 80:641-647, 2018. © 2017 International Society for Magnetic Resonance in Medicine.