HSA-net with a novel CAD pipeline boosts both clinical brain tumor MR image classification and segmentation.

Brain tumors are among the most prevalent neoplasms in current medical studies. Accurately distinguishing and classifying brain tumor types accurately is crucial for patient treatment and survival in clinical practice. However, existing computer-aided diagnostic pipelines are inadequate for practical medical use due to tumor complexity. In this study, we curated a multi-centre brain tumor dataset that includes various clinical brain tumor data types, including segmentation and classification annotations, surpassing previous efforts. To enhance brain tumor segmentation accuracy, we propose a new segmentation method: HSA-Net. This method utilizes the Shared Weight Dilated Convolution module (SWDC) and Hybrid Dense Dilated Convolution module (HDense) to capture multi-scale information while minimizing parameter count. The Effective Multi-Dimensional Attention (EMA) and Important Feature Attention (IFA) modules effectively aggregate task-related information. We introduce a novel clinical brain tumor computer-aided diagnosis pipeline (CAD) that combines HSA-Net with pipeline modification. This approach not only improves segmentation accuracy but also utilizes the segmentation mask as an additional channel feature to enhance brain tumor classification results. Our experimental evaluation of 3327 real clinical data demonstrates the effectiveness of the proposed method, achieving an average Dice coefficient of 86.85 % for segmentation and a classification accuracy of 95.35 %. We also validated the effectiveness of our proposed method using the publicly available BraTS dataset.

Privacy-Preserving Federated Learning with Domain Adaptation for Multi-Disease Ocular Disease Recognition.

As one of the effective ways of ocular disease recognition, early fundus screening can help patients avoid unrecoverable blindness. Although deep learning is powerful for image-based ocular disease recognition, the performance mainly benefits from a large number of labeled data. For ocular disease, data collection and annotation in a single site usually take a lot of time. If multi-site data are obtained, there are two main issues: 1) the data privacy is easy to be leaked; 2) the domain gap among sites will influence the recognition performance. Inspired by the above, first, a Gaussian randomized mechanism is adopted in local sites, which are then engaged in a global model to preserve the data privacy of local sites and models. Second, to bridge the domain gap among different sites, a two-step domain adaptation method is introduced, which consists of a domain confusion module and a multi-expert learning strategy. Based on the above, a privacy-preserving federated learning framework with domain adaptation is constructed. In the experimental part, a multi-disease early fundus screening dataset, including a detailed ablation study and four experimental settings, is used to show the stepwise performance, which verifies the efficiency of our proposed framework.

DCAM-NET:A novel domain generalization optic cup and optic disc segmentation pipeline with multi-region and multi-scale convolution attention mechanism.

Fundus images are an essential basis for diagnosing ocular diseases, and using convolutional neural networks has shown promising results in achieving accurate fundus image segmentation. However, the difference between the training data (source domain) and the testing data (target domain) will significantly affect the final segmentation performance. This paper proposes a novel framework named DCAM-NET for fundus domain generalization segmentation, which substantially improves the generalization ability of the segmentation model to the target domain data and enhances the extraction of detailed information on the source domain data. This model can effectively overcome the problem of poor model performance due to cross-domain segmentation. To enhance the adaptability of the segmentation model to target domain data, this paper proposes a multi-scale attention mechanism module (MSA) that functions at the feature extraction level. Extracting different attribute features to enter the corresponding scale attention module further captures the critical features in channel, position, and spatial regions. The MSA attention mechanism module also integrates the characteristics of the self-attention mechanism, it can capture dense context information, and the aggregation of multi-feature information effectively enhances the generalization of the model when dealing with unknown domain data. In addition, this paper proposes the multi-region weight fusion convolution module (MWFC), which is essential for the segmentation model to extract feature information from the source domain data accurately. Fusing multiple region weights and convolutional kernel weights on the image to enhance the model adaptability to information at different locations on the image, the fusion of weights deepens the capacity and depth of the model. It enhances the learning ability of the model for multiple regions on the source domain. Our experiments on fundus data for cup/disc segmentation show that the introduction of MSA and MWFC modules in this paper effectively improves the segmentation ability of the segmentation model on the unknown domain. And the performance of the proposed method is significantly better than other methods in the current domain generalization segmentation of the optic cup/disc.

Weakly supervised real-time instance segmentation for ultrasound images of median nerves.

Medical ultrasound technology has garnered significant attention in recent years, with Ultrasound-guided regional anesthesia (UGRA) and carpal tunnel diagnosis (CTS) being two notable examples. Instance segmentation, based on deep learning approaches, is a promising choice to support the analysis of ultrasound data. However, many instance segmentation models cannot achieve the requirement of ultrasound technology e.g. real-time. Moreover, fully supervised instance segmentation models require large numbers of images and corresponding mask annotations for training, which can be time-consuming and labor-intensive in the case of medical ultrasound data. This paper proposes a novel weakly supervised framework, CoarseInst, to achieve real-time instance segmentation of ultrasound images with only box annotations. CoarseInst not only improves the network structure, but also proposes a two-stage "coarse-to-fine" training strategy. Specifically, median nerves are used as the target application for UGRA and CTS. CoarseInst consists of two stages, with pseudo mask labels generated in the coarse mask generation stage for self-training. An object enhancement block is incorporated to mitigate the performance loss caused by parameter reduction in this stage. Additionally, we introduce a pair of loss functions, the amplification loss, and the deflation loss, that work together to generate the masks. A center area mask searching algorithm is also proposed to generate labels for the deflation loss. In the self-training stage, a novel self-feature similarity loss is designed to generate more precise masks. Experimental results on a practical ultrasound dataset demonstrate that CoarseInst could achieve better performance than some state-of-the-art fully supervised works.

A clinical prediction model for lung metastasis risk in osteosarcoma: A multicenter retrospective study.

Background: Lung metastases (LM) have a poor prognosis of osteosarcoma. This study aimed to predict the risk of LM using the nomogram in patients with osteosarcoma. Methods: A total of 1100 patients who were diagnosed as osteosarcoma between 2010 and 2019 in the Surveillance, Epidemiology and End Results (SEER) database were selected as the training cohort. Univariate and multivariate logistic regression analyses were used to identify independent prognostic factors of osteosarcoma lung metastases. 108 osteosarcoma patients from a multicentre dataset was as valiation data. The predictive power of the nomogram model was assessed by receiver operating characteristic curves (ROC) and calibration plots, and decision curve analysis (DCA) was utilized to interpret the accurate validity in clinical practice. Results: A total of 1208 patients with osteosarcoma from both the SEER database(n=1100) and the multicentre database (n=108) were analyzed. Univariate and multivariate logistic regression analyses showed that Survival time, Sex, T-stage, N-stage, Surgery, Radiation, and Bone metastases were independent risk factors for lung metastasis. We combined these factors to construct a nomogram for estimating the risk of lung metastasis. Internal and external validation showed significant predictive differences (AUC 0.779, 0.792 respectively). Calibration plots showed good performance of the nomogram model. Conclusions: In this study, a nomogram model for predicting the risk of lung metastases in osteosarcoma patients was constructed and turned out to be accurate and reliable through internal and external validation. Moreover we built a webpage calculator (https://drliwenle.shinyapps.io/OSLM/) taken into account nomogram model to help clinicians make more accurate and personalized predictions.

MRCG: A MRI Retrieval Framework With Convolutional and Graph Neural Networks for Secure and Private IoMT.

In the context of Industry 4.0, the medical industry is horizontally integrating the medical resources of the entire industry through the Internet of Things (IoT) and digital interconnection technologies. Speeding up the establishment of the public retrieval database of diagnosis-related historical data is a common call for the entire industry. Among them, the Magnetic Resonance Imaging (MRI) retrieval system, which is one of the key tools for secure and private the Internet of Medical Things (IoMT), is significant for patients to check their conditions and doctors to make clinical diagnoses securely and privately. Hence, this paper proposes a framework named MRCG that integrates Convolutional Neural Network (CNN) and Graph Neural Network (GNN) by incorporating the relationship between multiple gallery images in the graph structure. First, we adopt a Vgg16-based triplet network jointly trained for similarity learning and classification task. Next, a graph is constructed from the extracted features of triplet CNN where each node feature encodes a query-gallery image pair. The edge weight between nodes represents the similarity between two gallery images. Finally, a GNN with skip connections is adopted to learn on the constructed graph and predict the similarity score of each query-gallery image pair. Besides, Focal loss is also adopted while training GNN to tackle the class imbalance of the nodes. Experimental results on some benchmark datasets, including the CE-MRI dataset and a public MRI dataset from the Kaggle platform, show that the proposed MRCG can achieve 88.64% mAP and 86.59% mAP, respectively. Compared with some other state-of-the-art models, the MRCG can also outperform all the baseline models.

A deep belief network-based clinical decision system for patients with osteosarcoma.

Osteosarcoma was the most frequent type of malignant primary bone tumor with a poor survival rate mainly occurring in children and adolescents. For precision treatment, an accurate individualized prognosis for Osteosarcoma patients is highly desired. In recent years, many machine learning-based approaches have been used to predict distant metastasis and overall survival based on available individual information. In this study, we compared the performance of the deep belief networks (DBN) algorithm with six other machine learning algorithms, including Random Forest, XGBoost, Decision Tree, Gradient Boosting Machine, Logistic Regression, and Naive Bayes Classifier, to predict lung metastasis for Osteosarcoma patients. Therefore the DBN-based lung metastasis prediction model was integrated as a parameter into the Cox proportional hazards model to predict the overall survival of Osteosarcoma patients. The accuracy, precision, recall, and F1 score of the DBN algorithm were 0.917/0.888, 0.896/0.643, 0.956/0.900, and 0.925/0.750 in the training/validation sets, respectively, which were better than the other six machine-learning algorithms. For the performance of the DBN survival Cox model, the areas under the curve (AUCs) for the 1-, 3- and 5-year survival in the training set were 0.851, 0.806 and 0.793, respectively, indicating good discrimination, and the calibration curves showed good agreement between the prediction and actual observations. The DBN survival Cox model also demonstrated promising performance in the validation set. In addition, a nomogram integrating the DBN output was designed as a tool to aid clinical decision-making.

A tool for predicting overall survival in patients with Ewing sarcoma: a multicenter retrospective study.

OBJECTIVE: The aim of this study was to establish and validate a clinical prediction model for assessing the risk of metastasis and patient survival in Ewing's sarcoma (ES). METHODS: Patients diagnosed with ES from the Surveillance, Epidemiology and End Results (SEER) database for the period 2010-2016 were extracted, and the data after exclusion of vacant terms was used as the training set (n=767). Prediction models predicting patients' overall survival (OS) at 1 and 3 years were created by cox regression analysis and visualized using Nomogram and web calculator. Multicenter data from four medical institutions were used as the validation set (n=51), and the model consistency was verified using calibration plots, and receiver operating characteristic (ROC) verified the predictive ability of the model. Finally, a clinical decision curve was used to demonstrate the clinical utility of the model. RESULTS: The results of multivariate cox regression showed that age, , bone metastasis, tumor size, and chemotherapy were independent prognostic factors of ES patients. Internal and external validation results: calibration plots showed that the model had a good agreement for patient survival at 1 and 3 years; ROC showed that it possessed a good predictive ability and clinical decision curve proved that it possessed good clinical utility. CONCLUSIONS: The tool built in this paper to predict 1- and 3-year survival in ES patients ( https://drwenleli0910.shinyapps.io/EwingApp/ ) has a good identification and predictive power.

Interpretable clinical visualization model for prediction of prognosis in osteosarcoma: a large cohort data study.

Background: Currently, the clinical prediction model for patients with osteosarcoma was almost developed from single-center data, lacking external validation. Due to their low reliability and low predictive power, there were few clinical applications. Our study aimed to set up a clinical prediction model with stronger predictive ability, credibility, and clinical application value for osteosarcoma. Methods: Clinical information related to osteosarcoma patients from 2010 to 2016 was collected in the SEER database and four different Chinese medical centers. Factors were screened using three models (full subset regression, univariate Cox, and LASSO) via minimum AIC and maximum AUC values in the SEER database. The model was selected by the strongest predictive power and visualized by three statistical methods: nomogram, web calculator, and decision tree. The model was further externally validated and evaluated for its clinical utility in data from four medical centers. Results: Eight predicting factors, namely, age, grade, laterality, stage M, surgery, bone metastases, lung metastases, and tumor size, were selected from the model based on the minimum AIC and maximum AUC value. The internal and external validation results showed that the model possessed good consistency. ROC curves revealed good predictive ability (AUC > 0.8 in both internal and external validation). The DCA results demonstrated that the model had an excellent clinical predicted utility in 3 years and 5 years for North American and Chinese patients. Conclusions: The clinical prediction model was built and visualized in this study, including a nomogram and a web calculator (https://dr-lee.shinyapps.io/osteosarcoma/), which indicated very good consistency, predictive power, and clinical application value.

Deep Learning-Based Prediction of Hematoma Expansion Using a Single Brain Computed Tomographic Slice in Patients With Spontaneous Intracerebral Hemorrhages.

OBJECTIVES: We aimed to predict hematoma expansion in intracerebral hemorrhage (ICH) patients by using the deep learning technique. METHODS: We retrospectively collected data from ICH patients treated between May 2015 and May 2019. Head computed tomography (CT) scans were performed at admission, and 6 hours, 24 hours, and 72 hours after admission. CT scans were mandatory when neurologic deficits occurred. Univariate and multivariate analyses were conducted to illustrate the association between clinical variables and hematoma expansion. Convolutional neural network (CNN) was adopted to predict hematoma expansion based on brain CT slices. In addition, 5 machine learning methods, including support vector machine, multi-layer perceptron, naive Bayes, decision tree, and random forest, were also performed to predict hematoma expansion based on clinical variables for comparisons. RESULTS: A total of 223 patients were included. It was revealed that patients' older age (odds ratio [95% confidence interval]: 1.783 [1.417-1.924]), cerebral hemorrhage and breaking into the ventricle (2.524 [1.291-1.778]), coagulopathy (2.341 [1.677-3.454]), and baseline National Institutes of Health Stroke Scale (1.545 [1.132-3.203]) and Glasgow Coma Scale scores (0.782 [0.432-0.918]) independently associated with hematoma expanding. After 4-5 epochs, the CNN framework was well trained. The average sensitivity, specificity, and accuracy of CNN prediction are 0.9197, 0.8837, and 0.9058, respectively. Compared with 5 machine learning methods based on clinical variables, CNN can also achieve better performance. CONCLUSIONS: More than 90% of hematomas with or without expansion can be precisely classified by deep learning technology within this study, which is better than other methods based on clinical variables only. Deep learning technology could favorably predict hematoma expansion from non-contrast CT scan images.

A Visualized Dynamic Prediction Model for Lymphatic Metastasis in Ewing's Sarcoma for Smart Medical Services.

Background: This study aims to predict the lymphatic metastasis in Ewing's sarcoma (ES) patients by nomogram. The risk of lymphatic metastasis in patients with ES was predicted by the built model, which provided guidance for the clinical diagnosis and treatment planning. Methods: A total of 929 patients diagnosed with ES were enrolled from the year of 2010 to 2016 in the Surveillance, Epidemiology, and End Results (SEER) database. The nomogram was established to determine predictive factors of lymphatic metastasis according to univariate and multivariate logistic regression analysis. The validation of the model performed using multicenter data (n = 51). Receiver operating characteristics (ROC) curves and calibration plots were used to evaluate the prediction accuracy of the nomogram. Decision curve analysis (DCA) was implemented to illustrate the practicability of the nomogram clinical application. Based on the nomogram, we established a web calculator to visualize the risk of lymphatic metastases. We further plotted Kaplan-Meier overall survival (OS) curves to compare the survival time of patients with and without lymphatic metastasis. Results: In this study, the nomogram was established based on six significant factors (survival time, race, T stage, M stage, surgery, and lung metastasis), which were identified for lymphatic metastasis in ES patients. The model showed significant diagnostic accuracy with the value of the area under the curve (AUC) was 0.743 (95%CI: 0.714-0.771) for SEER internal validation and 0.763 (95%CI: 0.623-0.871) for multicenter data external validation. The calibration plot and DCA indicated that the model had vital clinical application value. Conclusion: In this study, we constructed and developed a nomogram with risk factors to predict lymphatic metastasis in ES patients and validated accuracy of itself. We found T stage (Tx OR = 2.540, 95%CI = 1.433-4.503, P < 0.01), M stage (M1, OR = 2.061, 95%CI = 1.189-3.573, P < 0.05) and survival time (OR = 0.982, 95%CI = 0.972-0.992, P < 0.001) were important independent factors for lymphatic metastasis in ES patients. Furthermore, survival time in patients with lymphatic metastasis or unclear situation (P < 0.0001) was significantly lower. It can help clinicians make better decisions to provide more accurate prognosis and treatment for ES patients.

Machine Learning-Based Prediction of Lymph Node Metastasis Among Osteosarcoma Patients.

Background: Regional lymph node metastasis is a contributor for poor prognosis in osteosarcoma. However, studies on risk factors for predicting regional lymph node metastasis in osteosarcoma are scarce. This study aimed to develop and validate a model based on machine learning (ML) algorithms. Methods: A total of 1201 patients, with 1094 cases from the surveillance epidemiology and end results (SEER) (the training set) and 107 cases (the external validation set) admitted from four medical centers in China, was included in this study. Independent risk factors for the risk of lymph node metastasis were screened by the multifactorial logistic regression models. Six ML algorithms, including the logistic regression (LR), the gradient boosting machine (GBM), the extreme gradient boosting (XGBoost), the random forest (RF), the decision tree (DT), and the multilayer perceptron (MLP), were used to evaluate the risk of lymph node metastasis. The prediction model was developed based on the bestpredictive performance of ML algorithm and the performance of the model was evaluatedby the area under curve (AUC), prediction accuracy, sensitivity and specificity. A homemade online calculator was capable of estimating the probability of lymph node metastasis in individuals. Results: Of all included patients, 9.41% (113/1201) patients developed regional lymph node metastasis. ML prediction models were developed based on nine variables: age, tumor (T) stage, metastasis (M) stage, laterality, surgery, radiation, chemotherapy, bone metastases, and lung metastases. In multivariate logistic regression analysis, T and M stage, surgery, and chemotherapy were significantly associated with lymph node metastasis. In the six ML algorithms, XGB had the highest AUC (0.882) and was utilized to develop as prediction model. A homemade online calculator was capable of estimating the probability of CLNM in individuals. Conclusions: T and M stage, surgery and Chemotherapy are independent risk factors for predicting lymph node metastasis among osteosarcoma patients. XGB algorithm has the best predictive performance, and the online risk calculator can help clinicians to identify the risk probability of lymph node metastasis among osteosarcoma patients.

Development of a Machine Learning-Based Predictive Model for Lung Metastasis in Patients With Ewing Sarcoma.

Background: This study aimed to develop and validate machine learning (ML)-based prediction models for lung metastasis (LM) in patients with Ewing sarcoma (ES), and to deploy the best model as an open access web tool. Methods: We retrospectively analyzed data from the Surveillance Epidemiology and End Results (SEER) Database from 2010 to 2016 and from four medical institutions to develop and validate predictive models for LM in patients with ES. Patient data from the SEER database was used as the training group (n = 929). Using demographic and clinicopathologic variables six ML-based models for predicting LM were developed, and internally validated using 10-fold cross validation. All ML-based models were subsequently externally validated using multiple data from four medical institutions (the validation group, n = 51). The predictive power of the models was evaluated by the area under receiver operating characteristic curve (AUC). The best-performing model was used to produce an online tool for use by clinicians to identify ES patients at risk from lung metastasis, to improve decision making and optimize individual treatment. Results: The study cohort consisted of 929 patients from the SEER database and 51 patients from multiple medical centers, a total of 980 ES patients. Of these, 175 (18.8%) had lung metastasis. Multivariate logistic regression analysis was performed with survival time, T-stage, N-stage, surgery, and bone metastasis providing the independent predictive factors of LM. The AUC value of six predictive models ranged from 0.585 to 0.705. The Random Forest (RF) model (AUC = 0.705) using 4 variables was identified as the best predictive model of LM in ES patients and was employed to construct an online tool to assist clinicians in optimizing patient treatment. (https://share.streamlit.io/liuwencai123/es_lm/main/es_lm.py). Conclusions: Machine learning were found to have utility for predicting LM in patients with Ewing sarcoma, and the RF model gave the best performance. The accessibility of the predictive model as a web-based tool offers clear opportunities for improving the personalized treatment of patients with ES.

A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing's Sarcoma.

Objective: In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing's sarcoma (ES) based on machine learning (ML) algorithms. Methods: Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application. Results: LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed (https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py). Conclusion: With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.

Predictors of adverse events after percutaneous pedicle screws fixation in patients with single-segment thoracolumbar burst fractures.

BACKGROUND: Percutaneous pedicle screw fixation (PPSF) is the primary approach for single-segment thoracolumbar burst fractures (TLBF). The healing angle at the thoracolumbar junction is one of the most significant criteria for evaluating the efficacy of PPSF. Therefore, the purpose of this study was to analyze the predictors associated with the poor postoperative alignment of the thoracolumbar region from routine variables using a support vector machine (SVM) model. METHODS: We retrospectively analyzed patients with TLBF operated at our academic institute between March 1, 2014 and December 31, 2019. Stepwise logistic regression analysis was performed to assess potential statistical differences between all clinical and radiological variables and the adverse events. Based on multivariate logistic results, a series of independent risk factors were fed into the SVM model. Meanwhile, the feature importance of radiologic outcome for each parameter was explored. The predictive performance of the SVM classifier was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy (ACC) and confusion matrices with 10-fold cross-validation, respectively. RESULTS: In the recruited 150 TLBFs, unfavorable radiological outcomes were observed in 53 patients (35.33%). The relationship between osteoporosis (p = 0.036), preoperative Cobb angle (p = 0.001), immediate postoperative Cobb angle (p = 0.029), surgically corrected Cobb angle (p = 0.001), intervertebral disc injury (Score 2 p = 0.001, Score 3 p = 0.001), interpedicular distance (IPD) (p = 0.001), vertebral body compression rate (VBCR) (p = 0.010) and adverse events was confirmed by univariate regression. Thereafter, independent risk factors including preoperative Cobb angle, the disc status and IPD and independent protective factors surgical correction angle were identified by multivariable logistic regression. The established SVM classifier demonstrated favorable predictive performance with the best AUC = 0.93, average AUC = 0.88, and average ACC = 0.87. The variables associated with radiological outcomes, in order of correlation strength, were intervertebral disc injury (42%), surgically corrected Cobb angle (25%), preoperative Cobb angle (18%), and IPD (15%). The confusion matrix reveals the classification results of the discriminant analysis. CONCLUSIONS: Critical radiographic indicators and surgical purposes were confirmed to be associated with an unfavorable radiographic outcome of TLBF. This SVM model demonstrated good predictive ability for endpoints in terms of adverse events in patients after PPSF surgery.

Self-Paced Dynamic Infinite Mixture Model for Fatigue Evaluation of Pilots' Brains.

Current brain cognitive models are insufficient in handling outliers and dynamics of electroencephalogram (EEG) signals. This article presents a novel self-paced dynamic infinite mixture model to infer the dynamics of EEG fatigue signals. The instantaneous spectrum features provided by ensemble wavelet transform and Hilbert transform are extracted to form four fatigue indicators. The covariance of log likelihood of the complete data is proposed to accurately identify similar components and dynamics of the developed mixture model. Compared with its seven peers, the proposed model shows better performance in automatically identifying a pilot's brain workload.

Scalable Gamma-Driven Multilayer Network for Brain Workload Detection Through Functional Near-Infrared Spectroscopy.

This work proposes a scalable gamma non-negative matrix network (SGNMN), which uses a Poisson randomized Gamma factor analysis to obtain the neurons of the first layer of a network. These neurons obey Gamma distribution whose shape parameter infers the neurons of the next layer of the network and their related weights. Upsampling the connection weights follows a Dirichlet distribution. Downsampling hidden units obey Gamma distribution. This work performs up-down sampling on each layer to learn the parameters of SGNMN. Experimental results indicate that the width and depth of SGNMN are closely related, and a reasonable network structure for accurately detecting brain fatigue through functional near-infrared spectroscopy can be obtained by considering network width, depth, and parameters.

Establishment and validation of a nomogram and web calculator for the risk of new vertebral compression fractures and cement leakage after percutaneous vertebroplasty in patients with osteoporotic vertebral compression fractures.

PURPOSE: The aim of this work was to investigate the risk factors for cement leakage and new-onset OVCF after Percutaneous vertebroplasty (PVP) and to develop and validate a clinical prediction model (Nomogram). METHODS: Patients with Osteoporotic VCF (OVCF) treated with PVP at Liuzhou People's Hospital from June 2016 to June 2018 were reviewed and met the inclusion criteria. Relevant data affecting bone cement leakage and new onset of OVCF were collected. Predictors were screened using univariate and multi-factor logistic analysis to construct Nomogram and web calculators. The consistency of the prediction models was assessed using calibration plots, and their predictive power was assessed by tenfold cross-validation. Clinical value was assessed using Decision curve analysis (DCA) and clinical impact plots. RESULTS: Higher BMI was associated with lower bone mineral density (BMD). Higher BMI, lower BMD, multiple vertebral fractures, no previous anti-osteoporosis treatment, and steroid use were independent risk factors for new vertebral fractures. Cement injection volume, time to surgery, and multiple vertebral fractures were risk factors for cement leakage after PVP. The development and validation of the Nomogram also demonstrated the predictive ability and clinical value of the model. CONCLUSIONS: The established Nomogram and web calculator (https://dr-lee.shinyapps.io/RefractureApp/) (https://dr-lee.shinyapps.io/LeakageApp/) can effectively predict the occurrence of cement leakage and new OVCF after PVP.

Development and Validation of a Predictive Model to Evaluate the Risk of Bone Metastasis in Kidney Cancer.

BACKGROUND: Bone is a common target of metastasis in kidney cancer, and accurately predicting the risk of bone metastases (BMs) facilitates risk stratification and precision medicine in kidney cancer. METHODS: Patients diagnosed with kidney cancer were extracted from the Surveillance, Epidemiology, and End Results (SEER) database to comprise the training group from 2010 to 2017, and the validation group was drawn from our academic medical center. Univariate and multivariate logistic regression analyses explored the statistical relationships between the included variables and BM. Statistically significant risk factors were applied to develop a nomogram. Calibration plots, receiver operating characteristic (ROC) curves, probability density functions (PDF), and clinical utility curves (CUC) were used to verify the predictive performance. Kaplan-Meier (KM) curves demonstrated survival differences between two subgroups of kidney cancer with and without BMs. A convenient web calculator was provided for users via "shiny" package. RESULTS: A total of 43,503 patients were recruited in this study, of which 42,650 were training group cases and 853 validation group cases. The variables included in the nomogram were sex, pathological grade, T-stage, N-stage, sequence number, brain metastases, liver metastasis, pulmonary metastasis, histological type, primary site, and laterality. The calibration plots confirmed good agreement between the prediction model and the actual results. The area under the curve (AUC) values in the training and validation groups were 0.952 (95% CI, 0.950-0.954) and 0.836 (95% CI, 0.809-0.860), respectively. Based on CUC, we recommend a threshold probability of 5% to guide the diagnosis of BMs. CONCLUSIONS: The comprehensive predictive tool consisting of nomogram and web calculator contributes to risk stratification which helped clinicians identify high-risk cases and provide personalized treatment options.