Ultrasound-Based Deep Learning Radiomics Nomogram for the Assessment of Lymphovascular Invasion in Invasive Breast Cancer: A Multicenter Study.

RATIONALE AND OBJECTIVES: The aim of this study was to develop a deep learning radiomics nomogram (DLRN) based on B-mode ultrasound (BMUS) and color doppler flow imaging (CDFI) images for preoperative assessment of lymphovascular invasion (LVI) status in invasive breast cancer (IBC). MATERIALS AND METHODS: In this multicenter, retrospective study, 832 pathologically confirmed IBC patients were recruited from eight hospitals. The samples were divided into training, internal test, and external test sets. Deep learning and handcrafted radiomics features reflecting tumor phenotypes on BMUS and CDFI images were extracted. The BMUS score and CDFI score were calculated after radiomics feature selection. Subsequently, a DLRN was developed based on the scores and independent clinic-ultrasonic risk variables. The performance of the DLRN was evaluated for calibration, discrimination, and clinical usefulness. RESULTS: The DLRN predicted the LVI with accuracy, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI 0.90-0.95), 0.91 (95% CI 0.87-0.95), and 0.91 (95% CI 0.86-0.94) in the training, internal test, and external test sets, respectively, with good calibration. The DLRN demonstrated superior performance compared to the clinical model and single scores across all three sets (p < 0.05). Decision curve analysis and clinical impact curve confirmed the clinical utility of the model. Furthermore, significant enhancements in net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indicated that the two scores could serve as highly valuable biomarkers for assessing LVI. CONCLUSION: The DLRN exhibited strong predictive value for LVI in IBC, providing valuable information for individualized treatment decisions.

An intelligent quantification system for fetal heart rhythm assessment: A multicenter prospective study.

BACKGROUND: The motion relationship and time intervals of the pulsed-wave Doppler (PWD) spectrum are essential for diagnosing fetal arrhythmia. However, few technologies currently are available to automatically calculate fetal cardiac time intervals (CTIs). OBJECTIVE: The purpose of this study was to develop a fetal heart rhythm intelligent quantification system (HR-IQS) for the automatic extraction of CTIs and establish the normal reference range for fetal CTIs. METHODS: A total of 6498 PWD spectrums of 2630 fetuses over the junction between the left ventricular inflow and outflow tracts were recorded across 14 centers. E, A, and V waves were manually labeled by 3 experienced fetal cardiologists, with 17 CTIs extracted. Five-fold cross-validation was performed for training and testing of the deep learning model. Agreement between the manual and HR-IQS-based values was evaluated using the intraclass correlation coefficient and Spearman's rank correlation coefficient. The Jarque-Bera test was applied to evaluate the normality of CTIs' distributions, and the normal reference range of 17 CTIs was established with quantile regression. Arrhythmia subset was compared with the non-arrhythmia subset using the Mann-Whitney U test. RESULTS: Significant positive correlation (P <.001) and moderate-to-excellent consistency (P <.001) between the manual and HR-IQS automated measurements of CTIs was found. The distribution of CTIs was non-normal (P <.001). The normal range (2.5th to 97.5th percentiles) was successfully established for the 17 CTIs. CONCLUSIONS: Using our HR-IQS is feasible for the automated calculation of CTIs in practice and thus could provide a promising tool for the assessment of fetal rhythm and function.

CFAP70 is a solid and valuable target for the genetic diagnosis of oligo-astheno-teratozoospermia in infertile men.

BACKGROUND: Male infertility is a worldwide population health concern, but its aetiology remains largely understood. Although CFAP70 variants have already been reported in two oligo-astheno-teratozoospermia (OAT) individuals by sequencing, animal evidence to support CFAP70 as a credible OAT-pathogenic gene is lacking. METHOD: Cfap70-KO mice were generated to explore the physiological role of CFAP70. CFAP70 variants were detected in infertile men with OAT by whole exome sequencing and Sanger sequencing confirmation. Cfap70-truncated mice were further generated to explore the pathogenicity of the nonsense variant of CFAP70 identified in the proband. FINDINGS: Here, we demonstrate that Cfap70-KO mice are sterile mainly due to OAT and further identify a Chinese infertile man carrying a homozygous nonsense variant (c.2962C > T/p.R988X) of CFAP70. Cfap70-truncated mice lacking 5-8 tetratricopeptide repeats (TPRs) mimic the patient's symptoms. CFAP70 is required for the biogenesis of spermatid flagella partially by regulating the expression of OAT-associated proteins (e.g., QRICH2), assisting the cytoplasmic preassembly of the calmodulin- and radial spoke-associated complex (CSC), and controlling the manchette localization of axoneme-related proteins. Moreover, we suggest that CFAP70-associated male infertility could be overcome by intracytoplasmic sperm injection (ICSI) treatment. INTERPRETATION: Overall, we demonstrate that CFAP70 is necessary to assemble spermatid flagella and that CFAP70 gene could be used as a diagnostic target for male infertility with OAT in the clinic. FUNDING: This study was supported by the National Key Research and Development Project (2019YFA0802101 to S.C), Open Fund of Key Laboratory of Cell Proliferation and Regulation Biology, Ministry of Education (to S.C), Central Government to Guide Local Scientific and Technological Development (ZY21195023 to B.W), and Basic Research Projects of Central Scientific Research Institutes (to B.W).

Three-dimensional ultrasound assessment of risk factors for cystocele and Green classification in primipara.

Background and aims: The present study aimed to analyze the effects of factors on cystocele and the Green classification. Materials and methods: We conducted a cross-sectional study on 357 primiparous women examined at our hospital from January 2019 to May 2021. The following data were recorded: maternal characteristics, neonatal characteristics, and factors of childbirth. It was added to the multivariate logistic regression model to determine the independent predictors of the cystocele and the Green classification. Results: A total of 242 women had cystocele, including 71 women with Green type I cystocele, 134 women with Green type II cystocele, and 37 women with Green type III cystocele. In multivariate logistic regression analysis, body mass index (BMI) at delivery was associated with cystocele, while BMI at delivery and the second stage of labor (SSL) > 1 h were independently with the distance from the symphysis pubis to the bladder neck (SPBN) abnormal (P < 0.05). BMI at examination was associated with the large retrovesical angle (RVA) (P < 0.05). BMI at delivery and the fetal right occiput anterior position (ROA) were independently associated with the distance from the symphysis pubis to the posterior wall of the bladder (SPBP) abnormal (P < 0.05), while epidural anesthesia (EDA) was the protective factor (P < 0.05). Conclusion: Primipara women should strive to avoid exposure to modifiable risk factors such as controlling weight during pregnancy, reducing weight after delivery, and shortening SSL to reduce the occurrence of cystocele.

Byzantine-robust federated learning via credibility assessment on non-IID data.

Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands. However, standard federated learning is vulnerable to Byzantine attacks, which will cause the global model to be manipulated by the attacker or fail to converge. On non-iid data, the current methods are not effective in defensing against Byzantine attacks. In this paper, we propose a Byzantine-robust framework for federated learning via credibility assessment on non-iid data (BRCA). Credibility assessment is designed to detect Byzantine attacks by combing adaptive anomaly detection model and data verification. Specially, an adaptive mechanism is incorporated into the anomaly detection model for the training and prediction of the model. Simultaneously, a unified update algorithm is given to guarantee that the global model has a consistent direction. On non-iid data, our experiments demonstrate that the BRCA is more robust to Byzantine attacks compared with conventional methods.

Associations between Self-Determined Motivation, Accelerometer-Determined Physical Activity, and Quality of Life in Chinese College Students.

Purpose: To better promote college students' physical activity (PA) and quality of life (QoL), it is imperative to understand this population's PA correlates, such as self-determined motivation and perceived competence. However, few studies existed in this area of inquiry among Chinese college students. Thus, the purpose of this study was to examine the relationships among Chinese college students' self-determined motivation, PA, and QoL. Method: A total of 220 college students (115 females; Mage = 20.29 years, SD = 2.37; MBMI = 20.67) were recruited from one university in south-central China. Participants were instructed to wear the ActiGraph GT9X Link (ActiGraph, Pensacola, FL, USA) accelerometers for 7 days. A minute-by-minute stepping rate methodology was used to determine participants sedentary behaviors, light physical activity (LPA) and moderate-to-vigorous physical activity (MVPA). Participants' self-determined motivation (autonomous, controlled, and amotivation), perceived competence, and QoL (physical function, stress, depression, fatigue, sleep, and social issues) were assessed by a battery of validated surveys in June 2017. Results: Participants reported moderate-high levels of PA correlates and QoL as the means ranged from 5.5 to 6 (out of 7) for PA correlates and 2.75 to 4 (out of 4) for QoL. The minute-by-minute stepping rate revealed participants had average 580.51 min/day in sedentary, 134.77 min/day in LPA, and 1.57 min/day in MVPA. Regression analyses for physical function, stress, depression, and social issues suggested that the models explained 4%-8% of the variances. Specifically, perceived competence was the negative predictor of the problems with physical function (ß = -0.17, p < 0.05) and depression (ß = -0.18, p < 0.01), amotivation was positively associated with depression and stress (p < 0.05). Additionally, controlled motivation predicted the ability to participate in social roles and activities (ß = 0.22, p < 0.05). No significant predictors emerged for fatigue or for sleep. Conclusions: Findings suggest Chinese college students' perceived competence and social support are critical for improving PA and QoL. In addition, strategies are needed to motivate Chinese college students to engage in PA participation and improve overall well-being.

Assessment of eutrophication and water quality in the estuarine area of Lake Wuli, Lake Taihu, China.

Our study assessed the actual water situation in the estuarine area of Lake Wuli, Meiliang Bay, Lake Taihu, China, based on eutrophication levels and status of water quality using the trophic level index (TLI) and water quality index (WQI) methods. In the wet (August 2017) and dry (March 2018) seasons, 22 estuarine areas were tested at 69 sampling sites, which included lake and rivers. Five parameters-chlorophyll a (Chl-a), total phosphorus (TP), total nitrogen (TN), Secchi disk (SD) and permanganate index (CODMn)-were measured to calculate the TLI, and 15 parameters-temperature (T), pH, electrical conductivity (EC), dissolved oxygen (DO), total dissolved solids (TDS), TN, TP, ammonium (NH4-N), nitrate (NO3-N), nitrite (NO2-N), CODMn, calcium (Ca2+), magnesium (Mg2+), chloride (Cl-) and phosphate (PO4-P)-were measured to calculate the WQI. The average TLI and WQI values in the wet season were 61.69 and 60.70, respectively, and the eutrophication level and water quality status were worse than that in the dry season (TLI: 57.40, WQI: 65.74). Significant differences were observed between three parts of Lake Wuli (West, Middle and East). Regardless of wet or dry season, East Wuli had worse eutrophication levels and water quality status than the other parts, whereas West Wuli showed less severe levels. DO, TN and CODMn used in the minimum WQI (WQImin) were the most effective parameters in our study. WQImin had stricter standards than WQI when analyzing water quality in the estuarine area of Wulihu. Factor analysis from principal component analysis (PCA) indicated that N might be the main factor affecting water quality of the most eastern sites in the wet season, and P may be the main factor in the dry season. Our results provide a valuable contribution to inform decision-making for the management of water environments by providing the actual water situation of the estuarine area of Lake Wuli.