GNAQ R183Q somatic mutation contributes to aberrant arteriovenous specification in Sturge-Weber syndrome through Notch signaling.

Episcleral vasculature malformation is a significant feature of Sturge-Weber syndrome (SWS) secondary glaucoma, the density and diameter of which are correlated with increased intraocular pressure. We previously reported that the GNAQ R183Q somatic mutation was located in the SWS episclera. However, the mechanism by which GNAQ R183Q leads to episcleral vascular malformation remains poorly understood. In this study, we investigated the correlation between GNAQ R183Q and episcleral vascular malformation via surgical specimens, human umbilical vein endothelial cells (HUVECs), and the HUVEC cell line EA.hy926. Our findings demonstrated a positive correlation between episcleral vessel diameter and the frequency of the GNAQ R183Q variant. Furthermore, the upregulation of genes from the Notch signaling pathway and abnormal coexpression of the arterial marker EphrinB2 and venous marker EphB4 were demonstrated in the scleral vasculature of SWS. Analysis of HUVECs overexpressing GNAQ R183Q in vitro confirmed the upregulation of Notch signaling and arterial markers. In addition, knocking down of Notch1 diminished the upregulation of arterial markers induced by GNAQ R183Q. Our findings strongly suggest that GNAQ R183Q leads to malformed episcleral vasculatures through Notch-induced aberrant arteriovenous specification. These insights into the molecular basis of episcleral vascular malformation will provide new pathways for the development of effective treatments for SWS secondary glaucoma.

Matrix decomposition for modeling lesion development processes in multiple sclerosis.

Our main goal is to study and quantify the evolution of multiple sclerosis lesions observed longitudinally over many years in multi-sequence structural magnetic resonance imaging (sMRI). To achieve that, we propose a class of functional models for capturing the temporal dynamics and spatial distribution of the voxel-specific intensity trajectories in all sMRI sequences. To accommodate the hierarchical data structure (observations nested within voxels, which are nested within lesions, which, in turn, are nested within study participants), we use structured functional principal component analysis. We propose and evaluate the finite sample properties of hypothesis tests of therapeutic intervention effects on lesion evolution while accounting for the multilevel structure of the data. Using this novel testing strategy, we found statistically significant differences in lesion evolution between treatment groups.

Diagnosis of cholangiocarcinoma from microscopic hyperspectral pathological dataset by deep convolution neural networks.

This paper focuses on automatic Cholangiocarcinoma (CC) diagnosis from microscopic hyperspectral (HSI) pathological dataset with deep learning method. The first benchmark based on the microscopic hyperspectral pathological images is set up. Particularly, 880 scenes of multidimensional hyperspectral Cholangiocarcinoma images are collected and manually labeled each pixel as either tumor or non-tumor for supervised learning. Moreover, each scene from the slide is given a binary label indicating whether it is from a patient or a normal person. Different from traditional RGB images, the HSI acquires pixels in multiple spectral intervals, which is added as an extension on the channel dimension of 3-channel RGB image. This work aims at fully exploiting the spatial-spectral HSI data through a deep Convolution Neural Network (CNN). The whole scene is first divided into several patches. Then they are fed into CNN for the tumor/non-tumor binary prediction and the tumor area regression. The further diagnosis on the scene is made by random forest based on the features from patch prediction. Experiments show that HSI provides a more accurate result than RGB image. Moreover, a spectral interval convolution and normalization scheme are proposed for further mining the spectral information in HSI, which demonstrates the effectiveness of the spatial-spectral data for CC diagnosis.

LightR-YOLOv5: A compact rotating detector for SARS-CoV-2 antigen-detection rapid diagnostic test results.

Nucleic acid testing is currently the golden reference for coronaviruses (SARS-CoV-2) detection, while the SARS-CoV-2 antigen-detection rapid diagnostic tests (RDT) is an important adjunct. RDT can be widely used in the community or regional screening management as self-test tools and may need to be verified by healthcare authorities. However, manual verification of RDT results is a time-consuming task, and existing object detection algorithms usually suffer from high model complexity and computational effort, making them difficult to deploy. We propose LightR-YOLOv5, a compact rotating SARS-CoV-2 antigen-detection RDT results detector. Firstly, we employ an extremely light-weight L-ShuffleNetV2 network as a feature extraction network with a slight reduction in recognition accuracy. Secondly, we combine semantic and texture features in different layers by judiciously combining and employing GSConv, depth-wise convolution, and other modules, and further employ the NAM attention to locate the RDT result detection region. Furthermore, we propose a new data augmentation approach, Single-Copy-Paste, for increasing data samples for the specific task of RDT result detection while achieving a small improvement in model accuracy. Compared with some mainstream rotating object detection networks, the model size of our LightR-YOLOv5 is only 2.03MB, and it is 12.6%, 6.4%, and 7.3% higher in mAP@.5:.95 metrics compared to RetianNet, FCOS, and R3Det, respectively.

Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone.

Coronavirus Disease 2019 (COVID-19) has spread all over the world since it broke out massively in December 2019, which has caused a large loss to the whole world. Both the confirmed cases and death cases have reached a relatively frightening number. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of COVID-19, can be transmitted by small respiratory droplets. To curb its spread at the source, wearing masks is a convenient and effective measure. In most cases, people use face masks in a high-frequent but short-time way. Aimed at solving the problem that we do not know which service stage of the mask belongs to, we propose a detection system based on the mobile phone. We first extract four features from the gray level co-occurrence matrixes (GLCMs) of the face mask's micro-photos. Next, a three-result detection system is accomplished by using K Nearest Neighbor (KNN) algorithm. The results of validation experiments show that our system can reach an accuracy of 82.87% (measured by macro-measures) on the testing dataset. The precision of Type I 'normal use' and the recall of type III 'not recommended' reach 92.00% and 92.59%. In future work, we plan to expand the detection objects to more mask types. This work demonstrates that the proposed mobile microscope system can be used as an assistant for face mask being used, which may play a positive role in fighting against COVID-19.

Detection of Respiratory Infections Using RGB-Infrared Sensors on Portable Device.

Coronavirus Disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronaviruses 2 (SARS-CoV-2) has become a serious global pandemic in the past few months and caused huge loss to human society worldwide. For such a large-scale pandemic, early detection and isolation of potential virus carriers is essential to curb the spread of the pandemic. Recent studies have shown that one important feature of COVID-19 is the abnormal respiratory status caused by viral infections. During the pandemic, many people tend to wear masks to reduce the risk of getting sick. Therefore, in this paper, we propose a portable non-contact method to screen the health conditions of people wearing masks through analysis of the respiratory characteristics from RGB-infrared sensors. We first accomplish a respiratory data capture technique for people wearing masks by using face recognition. Then, a bidirectional GRU neural network with an attention mechanism is applied to the respiratory data to obtain the health screening result. The results of validation experiments show that our model can identify the health status of respiratory with 83.69% accuracy, 90.23% sensitivity and 76.31% specificity on the real-world dataset. This work demonstrates that the proposed RGB-infrared sensors on portable device can be used as a pre-scan method for respiratory infections, which provides a theoretical basis to encourage controlled clinical trials and thus helps fight the current COVID-19 pandemic. The demo videos of the proposed system are available at: https://doi.org/10.6084/m9.figshare.12028032.

Estimating Departure Time Using Thermal Camera and Heat Traces Tracking Technique.

Advancement in science and technology is playing an increasingly important role in solving difficult cases at present. Thermal cameras can help the police crack difficult cases by capturing the heat trace on the ground left by perpetrators, which cannot be spotted by the naked eye. Therefore, the purpose of this study is to establish a thermalfoot model using thermal imaging system to estimate the departure time. To this end, in the current work, we use a thermal camera to acquire the thermal sequence left on the floor, and convert it into the heat signal via image processing algorithm. We establish the model of thermalfoot print as we observe that the residual temperature would exponentially decrease with the departure time according to Newton's Law of Cooling. The correlation coefficients of 107 thermalfoot models derived from the corresponding 107 heat signals are basically above 0.99. In a validation experiment, a residual analysis is conducted and the residuals between estimated departure time points and ground-truth times are almost within a certain range from -150 s to +150 s. The reverse accuracy of the thermalfoot model for estimating departure time at one-third, one-half, two-thirds, three-fourths, four-fifths, and five-sixths capture time points are 71.96%, 50.47%, 42.06%, 31.78%, 21.70%, and 11.21%, respectively. The results of comparison experiments with two subjective evaluation methods (subjective 1: we directly estimate the departure time according to obtained local curves; subjective 2: we utilize auxiliary means such as a ruler to estimate the departure time based on obtained local curves) further demonstrate the effectiveness of thermalfoot model for detecting the departure time inversely. Experimental results also demonstrated that the thermalfoot model has good performance on the departure time reversal within a short time window someone leaves, whereas it is probably only approximately 15% to accurately determine the departure time via thermalfoot model within a long time window someone leaves. The influence of outliers, ROI (Region of Interest) selection, ROI size, different capture time points and environment temperature on the performance of thermalfoot model on departure time reversal can be explored in the future work. Overall, the thermalfoot model can help the police solve crimes to some extent, which in turn brings more guarantees for people's health, social security, and stability.

Active Learning Plus Deep Learning Can Establish Cost-Effective and Robust Model for Multichannel Image: A Case on Hyperspectral Image Classification.

Relying on large scale labeled datasets, deep learning has achieved good performance in image classification tasks. In agricultural and biological engineering, image annotation is time-consuming and expensive. It also requires annotators to have technical skills in specific areas. Obtaining the ground truth is difficult because natural images are expensive. In addition, images in these areas are usually stored as multichannel images, such as computed tomography (CT) images, magnetic resonance images (MRI), and hyperspectral images (HSI). In this paper, we present a framework using active learning and deep learning for multichannel image classification. We use three active learning algorithms, including least confidence, margin sampling, and entropy, as the selection criteria. Based on this framework, we further introduce an "image pool" to make full advantage of images generated by data augmentation. To prove the availability of the proposed framework, we present a case study on agricultural hyperspectral image classification. The results show that the proposed framework achieves better performance compared with the deep learning model. Manual annotation of all the training sets achieves an encouraging accuracy. In comparison, using active learning algorithm of entropy and image pool achieves a similar accuracy with only part of the whole training set manually annotated. In practical application, the proposed framework can remarkably reduce labeling effort during the model development and upadting processes, and can be applied to multichannel image classification in agricultural and biological engineering.

Inpatient Outcomes for Gastrointestinal Bleeding Associated With Percutaneous Coronary Intervention.

GOALS: The goal of this study was to evaluate the impact of inpatient outcomes of gastrointestinal bleeding (GIB) related to percutaneous coronary intervention (PCI). BACKGROUND: With all-cause mortality increasing in patients undergoing PCIs, outcomes for GIB associated with PCI may be adversely impacted. STUDY: Using the National Inpatient Sample (2007 to 2012), we performed a nested case-control study assessing inpatient outcomes including incidence and mortality for PCI-related GIB hospitalizations. Multivariate logistic regression analyses were performed to determine significant predictors for GIB incidence and mortality. RESULTS: A total of 9332 (1.2%) of PCI hospitalizations were complicated by GIB with the age-adjusted incidence rate increasing 13% from 2007 (11.3 GIB per 1000 PCI) to 2012 (12.8). Patients ≥75 years of age experienced the steepest incline in GIB incidence, which increased 31% during the study period. Compared with non-GIB patients, mean length of stay (9.4 d vs. 3.3 d) and median cost of care ($29,236 vs. $17,913) was significantly higher. Significant demographic risk factors for GIB included older age and comorbid risk factors included gastritis or duodenitis, and Helicobacter pylori infection.In total, 1044 (11%) of GIB patients died during hospitalization with the GIB mortality rate increasing 30% from 2007 (95 deaths per 1000 GIB) to 2012 (123). Older age had the strongest association with inpatient mortality. CONCLUSIONS: Inpatient incidence and mortality for PCI-related GIB has been increasing particularly with a large increase in incidence among older patients. A multidisciplinary approach focused on risk-stratifying patients may improve preventable causes of GIB.

Paper-Based ZnS:Cu Alternating Current Electroluminescent Devices for Current Humidity Sensors with High-Linearity and Flexibility.

Humidity sensors are indispensable for various electronic systems and instrumentations. To develop a new humidity sensing mechanism is the key for the next generation of sensor technology. In this work, a novel flexible paper-based current humidity sensor is proposed. The developed alternating current electroluminescent devices (ACEL) consist of the electroless plating Ni on filter paper and silver nanowires (AgNWs) as the bottom and upper electrodes, and ZnS:Cu as the phosphor layer, respectively. The proposed humidity sensor is based on ACEL with the paper substrate and the ZnS:Cu phosphor layer as the humidity sensing element. The moisture effect on the optical properties of ACELs has been studied firstly. Then, the processing parameters of the paper-based ACELs such as electroless plated bottom electrode and spin-coated phosphor layer as a function of the humidity-sensitive characteristics are investigated. The sensing mechanism of the proposed sensor has been elucidated based on the Q ~ V analysis. The sensor exhibits an excellent linearity ( R 2 = 0.99965 ) within the humidity range from 20% to 90% relative humidity (RH) and shows excellent flexibility. We also demonstrate its potential application in postharvest preservation where the EL light is used for preservation and the humidity can be monitored simultaneously through the current.

Increased Waitlist Mortality and Lower Rate for Liver Transplantation in Hispanic Patients With Primary Biliary Cholangitis.

BACKGROUND & AIMS: Data on the differences in ethnicity and race among patients with primary biliary cholangitis (PBC) awaiting liver transplantation (LT) are limited. We evaluated liver transplant waitlist trends and outcomes based on ethnicity and race in patients with PBC in the United States. METHODS: Using the United Network for Organ Sharing (UNOS) registry, we collected data on patients with PBC on the liver transplant waitlist, and performed analysis with a focus on ethnicity and race-based variations clinical manifestations, waitlist mortality and LT rates from 2000 to 2014. Outcomes were adjusted for demographics, complications of portal hypertension, and Model for End-stage Liver Disease score at time of waitlist registration. RESULTS: Although the number of white PBC waitlist registrants and additions decreased from 2000 to 2014, there were no significant changes in the number of Hispanic PBC waitlist registrants and additions each year. The proportion of Hispanic patients with PBC on the liver transplant waitlist increased from 10.7% in 2000 to 19.3% in 2014. Hispanics had the highest percentage of waitlist deaths (20.8%) of any ethnicity or race evaluated. After adjusting for demographic and clinical characteristics, Hispanic patients with PBC had the lowest overall rate for undergoing LT (adjusted hazard ratio, 0.71; 95% CI, 0. 60-0.83; P < .001) and a significantly higher risk of death while on the waitlist, compared to whites (adjusted hazard ratio, 1.41; 95% CI, 1.15-1.74; P < .001). Furthermore, Hispanic patients with PBC had the highest proportion of waitlist removals due to clinical deterioration. CONCLUSIONS: In an analysis of data from UNOS registry focusing on outcomes, we observed differences in rates of LT and liver transplant waitlist mortality of Hispanic patients compared with white patients with PBC. Further studies are needed to improve our understanding of ethnicity and race-based differences in progression of PBC.

Waitlist Outcomes in Liver Transplant Candidates with High MELD and Severe Hepatic Encephalopathy.

BACKGROUND: Organ Procurement and Transplantation Network and United Network for Organ Sharing (OPTN/UNOS) implemented the Share 35 policy in June 2013 to prioritize the sickest patients awaiting liver transplantation (LT). However, Model for End-Stage Liver Disease (MELD) score does not incorporate hepatic encephalopathy (HE), an independent predictor of waitlist mortality. AIM: To evaluate the impact of severe HE (grade 3-4) on waitlist outcomes in MELD ≥ 30 patients. METHODS: Using the OPTN/UNOS database, we evaluated LT waitlist registrants from 2005-2014. Demographics, comorbidities, and waitlist survival were compared between four cohorts: MELD 30-34 with severe HE, MELD 30-34 without severe HE, MELD ≥ 35 with severe HE, and MELD ≥ 35 without severe HE. RESULTS: Among 10,003 waitlist registrants studied, 41.6% had MELD score 30-34 and 58.4% had MELD ≥ 35. Patients with severe HE had a higher 90-day waitlist mortality in both MELD 30-34 (severe HE 71.1% vs. no HE 56.6%; p < 0.001) and MELD ≥ 35 subgroups (severe HE 85% versus no HE 74.2%; p < 0.001). MELD 30-34 patients with severe HE had similar 90-day waitlist mortality as MELD ≥ 35 patients without severe HE (71.1 vs. 74.2%, respectively; p = 0.35). On multivariate Cox proportional hazards modeling, MELD ≥ 30 patients had 58% greater risk of 90-day waitlist mortality than those without severe HE (HR 1.58, 95% CI 1.53-1.62; p < 0.001). CONCLUSION: Patients awaiting LT with MELD score of 30-34 and severe HE should receive priority status for organ allocation with exception MELD ≥ 35.

Application of Deep Learning Architectures for Accurate and Rapid Detection of Internal Mechanical Damage of Blueberry Using Hyperspectral Transmittance Data.

Deep learning has become a widely used powerful tool in many research fields, although not much so yet in agriculture technologies. In this work, two deep convolutional neural networks (CNN), viz. Residual Network (ResNet) and its improved version named ResNeXt, are used to detect internal mechanical damage of blueberries using hyperspectral transmittance data. The original structure and size of hypercubes are adapted for the deep CNN training. To ensure that the models are applicable to hypercube, we adjust the number of filters in the convolutional layers. Moreover, a total of 5 traditional machine learning algorithms, viz. Sequential Minimal Optimization (SMO), Linear Regression (LR), Random Forest (RF), Bagging and Multilayer Perceptron (MLP), are performed as the comparison experiments. In terms of model assessment, k-fold cross validation is used to indicate that the model performance does not vary with the different combination of dataset. In real-world application, selling damaged berries will lead to greater interest loss than discarding the sound ones. Thus, precision, recall, and F1-score are also used as the evaluation indicators alongside accuracy to quantify the false positive rate. The first three indicators are seldom used by investigators in the agricultural engineering domain. Furthermore, ROC curves and Precision-Recall curves are plotted to visualize the performance of classifiers. The fine-tuned ResNet/ResNeXt achieve average accuracy and F1-score of 0.8844/0.8784 and 0.8952/0.8905, respectively. Classifiers SMO/ LR/RF/Bagging/MLP obtain average accuracy and F1-score of 0.8082/0.7606/0.7314/0.7113/0.7827 and 0.8268/0.7796/0.7529/0.7339/0.7971, respectively. Two deep learning models achieve better classification performance than the traditional machine learning methods. Classification for each testing sample only takes 5.2 ms and 6.5 ms respectively for ResNet and ResNeXt, indicating that the deep learning framework has great potential for online fruit sorting. The results of this study demonstrate the potential of deep CNN application on analyzing the internal mechanical damage of fruit.

Liver Transplantation for Nonalcoholic Steatohepatitis in the US: Temporal Trends and Outcomes.

BACKGROUND AND AIMS: Nonalcoholic steatohepatitis (NASH) is a rapidly growing etiology of end-stage liver disease in the US. Temporal trends and outcomes in NASH-related liver transplantation (LT) in the US were studied. METHODS: A retrospective cohort study utilizing the United Network for Organ Sharing and Organ Procurement and Transplantation (UNOS/OPTN) 2003-2014 database was conducted to evaluate the frequency of NASH-related LT. Etiology-specific post-transplant survival was evaluated with Kaplan-Meier methods and multivariate Cox proportional hazards models. RESULTS: Overall, 63,061 adult patients underwent LT from 2003 to 2014, including 20,782 HCV (32.96%), 9470 ALD (15.02%), and 8262 NASH (13.11%). NASH surpassed ALD and became the second leading indication for LT beginning in 2008, accounting for 17.38% of LT in 2014. From 2003 to 2014, the number of LT secondary to NASH increased by 162%, whereas LT secondary to HCV increased by 33% and ALD increased by 55%. Due to resurgence in ALD, the growth in NASH and ALD was comparable from 2008 to 2014 (NASH +50.15% vs. ALD +41.87%). The post-transplant survival in NASH was significantly higher compared to HCV (5-year survival: NASH -77.81%, 95% CI 76.37-79.25 vs. HCV -72.15%, 95% CI 71.37-72.93, P < .001). In the multivariate Cox proportional hazards model, NASH demonstrated significantly higher post-transplant survival compared to HCV (HR 0.75; 95% CI 0.71-0.79, P < .001). CONCLUSIONS: Currently, NASH is the most rapidly growing indication for LT in the US. Despite resurgence in ALD, NASH remains the second leading indication for LT.

Chronic Hepatitis B Is Associated with Higher Inpatient Resource Utilization and Mortality Versus Chronic Hepatitis C.

BACKGROUND: Chronic hepatitis B virus (HBV) and chronic hepatitis C virus (HCV) infections remain one of the leading causes of chronic liver disease and hepatocellular carcinoma. Healthcare initiatives for chronic viral hepatitis to facilitate early diagnosis and linkage to care in an effort to reduce inpatient resource utilization associated with late diagnosis and end-stage liver disease have been partially successful. AIMS: Our objective was to determine the impact of liver-related complications from chronic HBV and HCV infections on inpatient cost of care, length of stay, and mortality. METHODS: Using the Healthcare Cost and Utilization Project, National Inpatient Sample (HCUP-NIS), we studied the impact of chronic HBV and HCV infections on inpatient healthcare system following hospitalizations from 2003 to 2012. RESULTS: Of the 79,185,729 million hospitalizations among adult patients in the USA from 2003 to 2012, 143,896 (0.18 %) hospitalizations were HBV related and 1,073,269 (1.36 %) hospitalizations HCV related. HBV hospitalizations had a higher inpatient mortality (OR 1.34; 95 % CI 1.30, 1.38), median cost of care per hospitalization (+$2100.33; 95 % CI 1982.53, 2217.53), and increased length of hospitalization stay (+0.64 days; 95 % CI 0.60, 0.68; p < 0.01) compared to HCV. CONCLUSIONS: Despite higher per case resource utilization following hospitalization, HBV-infected patients demonstrate a lower inpatient survival in comparison with chronic HCV infection. These disparate observations underscore the need for early diagnosis of chronic HBV infection in at-risk population and prompt linkage to care.

Modelling postharvest quality of blueberry affected by biological variability using image and spectral data.

BACKGROUND: Hyperspectral reflectance and transmittance sensing as well as near-infrared (NIR) spectroscopy were investigated as non-destructive tools for estimating blueberry firmness, elastic modulus and soluble solid content (SSC). Least squares-support vector machine models were established from these three spectra based on samples from three cultivars viz. Bluecrop, Duke and M2 and two harvest years viz. 2014 and 2015 for predicting blueberry postharvest quality. RESULTS: One-cultivar reflectance models (establishing model using one cultivar) derived better results than the corresponding transmittance and NIR models for predicting blueberry firmness with few cultivar effects. Two-cultivar NIR models (establishing model using two cultivars) proved to be suitable for estimating blueberry SSC with correlations over 0.83. Rp (RMSEp ) values of the three-cultivar reflectance models (establishing model using 75% of three cultivars) were 0.73 (0.094) and 0.73 (0.186), respectively , for predicting blueberry firmness and elastic modulus. For SSC prediction, the three-cultivar NIR model was found to achieve an Rp (RMSEp ) value of 0.85 (0.090). Adding Bluecrop samples harvested in 2014 could enhance the three-cultivar model robustness for firmness and elastic modulus. CONCLUSION: The above results indicated the potential for using spatial and spectral techniques to develop robust models for predicting blueberry postharvest quality containing biological variability. © 2015 Society of Chemical Industry.

[Comparison of Predicting Blueberry Firmness and Elastic Modulus with Hyperspectral Reflectance, Transmittance and Interactance Imaging Modes].

In this study, a imaging system with hyperspectral reflectance, transmittance and interactance was constructed for estimate the firmness and elastic modulus of blueberry. The comparisons of these three imaging modes were carried out. This hyperspectral system could also be applied for scattering modewhile this mode was not suitable for small fruit such as blueberry. The reflectance hypercubes were segmented with the algorithm based on the Otsu method, and the transmittance and interactance hypercubes were processed with the algorithms based on region growing approach. Subsequently, the extracted spectra were pretreated with the Standard Normal Variate (SNV) and Savitzky-Golay of the first derivative (Der), and least squares-support vector machine was applied for the establishment of the corresponding prediction models. The obtained results demonstrated that -reflectance-SNV model could predict blueberry firmness with correlation coefficient of prediction sample set (Rp) of 0.80 and the ratio of percent deviation (RPD) of 1.76 among the models using full spectra. The elastic modulus of blueberry was better estimated by the full transmittance spectra subjected to SNV pretreatment with Rp (RPD) of 0.78 (1.74) than the other models. Furthermore, Random Frog selection approach could to some extent reduce the uninformative wavelengths while increasing the prediction accuracy of the established models. Random Frog-Interactance-Der model achieved Rp (RPD) of 0.80 (1.83) for blueberry firmness, but the number of wavelength was 140. In the case of blueberry elastic modulus, random frog-transmittance-SNV showed the relatively superior performance compared to the other models, with Rp (RPD) of 0.82 (1.83) and fewer wavelength number of 20.

Xiaoqing: A Q&A model for glaucoma based on LLMs.

Glaucoma is one of the leading cause of blindness worldwide. Individuals affected by glaucoma, including patients and their family members, frequently encounter a deficit in dependable support beyond the confines of clinical environments. Seeking advice via the internet can be a difficult task due to the vast amount of disorganized and unstructured material available on these sites, nevertheless. This research explores how Large Language Models (LLMs) can be leveraged to better serve medical research and benefit glaucoma patients. We introduce Xiaoqing, a Natural Language Processing (NLP) model specifically tailored for the glaucoma field, detailing its development and deployment. To evaluate its effectiveness, we conducted two forms of experiments: comparative and experiential. In the comparative analysis, we presented 22 glaucoma-related questions in simplified Chinese to three medical NLP models (Xiaoqing LLMs, HuaTuo, Ivy GPT) and two general models (ChatGPT-3.5 and ChatGPT-4), covering a range of topics from basic glaucoma knowledge to treatment, surgery, research, management standards, and patient lifestyle. Responses were assessed for informativeness and readability. The experiential experiment involved glaucoma patients and non-patients interacting with Xiaoqing, collecting and analyzing their questions and feedback on the same criteria. The findings demonstrated that Xiaoqing notably outperformed the other models in terms of informativeness and readability, suggesting that Xiaoqing is a significant advancement in the management and treatment of glaucoma in China. We also provide a Web-based version of Xiaoqing, allowing readers to directly experience its functionality. The Web-based Xiaoqing is available at https://qa.glaucoma-assistant.com//qa.

Prediction model of radiotherapy outcome for Ocular Adnexal Lymphoma using informative features selected by chemometric algorithms.

BACKGROUND: Ocular Adnexal Lymphoma (OAL) is a non-Hodgkin's lymphoma that most often appears in the tissues near the eye, and radiotherapy is the currently preferred treatment. There has been a controversy regarding the prognostic factors for systemic failure of OAL radiotherapy, the thorough evaluation prior to receiving radiotherapy is highly recommended to better the patient's prognosis and minimize the likelihood of any adverse effects. PURPOSE: To investigate the risk factors that contribute to incomplete remission in OAL radiotherapy and to establish a hybrid model for predicting the radiotherapy outcomes in OAL patients. METHODS: A retrospective chart review was performed for 87 consecutive patients with OAL who received radiotherapy between Feb 2011 and August 2022 in our center. Seven image features, derived from MRI sequences, were integrated with 122 clinical features to form comprehensive patient feature sets. Chemometric algorithms were then employed to distill highly informative features from these sets. Based on these refined features, SVM and XGBoost classifiers were performed to classify the effect of radiotherapy. RESULTS: The clinical records of from 87 OAL patients (median age: 60 months, IQR: 52-68 months; 62.1% male) treated with radiotherapy were reviewed. Analysis of Lasso (AUC = 0.75, 95% CI: 0.72-0.77) and Random Forest (AUC = 0.67, 95% CI: 0.62-0.70) algorithms revealed four potential features, resulting in an intersection AUC of 0.80 (95% CI: 0.75-0.82). Logistic Regression (AUC = 0.75, 95% CI: 0.72-0.77) identified two features. Furthermore, the integration of chemometric methods such as CARS (AUC = 0.66, 95% CI: 0.62-0.72), UVE (AUC = 0.71, 95% CI: 0.66-0.75), and GA (AUC = 0.65, 95% CI: 0.60-0.69) highlighted six features in total, with an intersection AUC of 0.82 (95% CI: 0.78-0.83). These features included enophthalmos, diplopia, tenderness, elevated ALT count, HBsAg positivity, and CD43 positivity in immunohistochemical tests. CONCLUSION: The findings suggest the effectiveness of chemometric algorithms in pinpointing OAL risk factors, and the prediction model we proposed shows promise in helping clinicians identify OAL patients likely to achieve complete remission via radiotherapy. Notably, patients with a history of exophthalmos, diplopia, tenderness, elevated ALT levels, HBsAg positivity, and CD43 positivity are less likely to attain complete remission after radiotherapy. These insights offer more targeted management strategies for OAL patients. The developed model is accessible online at: https://lzz.testop.top/.

Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning.

Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning method based on cardiac ultrasound video to assist in ASD diagnosis. We chose four standard views in pediatric cardiac ultrasound to identify atrial septal defects; the four standard views were as follows: subcostal sagittal view of the atrium septum (subSAS), apical four-chamber view (A4C), the low parasternal four-chamber view (LPS4C), and parasternal short-axis view of large artery (PSAX). We enlist data from 300 children patients as part of a double-blind experiment for five-fold cross-validation to verify the performance of our model. In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training). In our model, we present a block random selection, maximal agreement decision, and frame sampling strategy for training and testing respectively, resNet18 and r3D networks are used to extract the frame features and aggregate them to build a rich video-level representation. We validate our model using our private dataset by five cross-validation. For ASD detection, we achieve 89.33 ± 3.13 AUC, 84.95 ± 3.88 accuracy, 85.70 ± 4.91 sensitivity, 81.51 ± 8.15 specificity, and 81.99 ± 5.30 F1 score. The proposed model is a multiple instances learning-based deep learning model for video atrial septal defect detection which effectively improves ASD detection accuracy when compared to the performances of previous networks and clinical doctors.