Single-cell type annotation with deep learning in 265 cell types for humans.

Motivation: Annotating cell types is a challenging yet essential task in analyzing single-cell RNA sequencing data. However, due to the lack of a gold standard, it is difficult to evaluate the algorithms fairly and an overfitting algorithm may be favored in benchmarks. To address this challenge, we developed a deep learning-based single-cell type prediction tool that assigns the cell type to 265 different cell types for humans, based on data from approximately five million cells. Results: We achieved a median area under the ROC curve (AUC) of 0.93 when evaluated across datasets. We found that inconsistent labeling in the existing database generated by different labs contributed to the mistakes of the model. Therefore, we used cell ontology to correct the annotations and retrained the model, which resulted in 0.971 median AUC. Our study reveals a limiting factor of the accuracy one may achieve with the current database annotation and points to the solutions towards an algorithm-based correction of the gold standard for future automated cell annotation approaches. Availability and implementation: The code is available at: https://github.com/SherrySDong/Hierarchical-Correction-Improves-Automated-Single-cell-Type-Annotation. Data used in this study are listed in Supplementary Table S1 and are retrievable at the CZI database.

Tracing the origin of alveolar stem cells in lung repair and regeneration.

Alveolar type 2 (AT2) cells are stem cells of the alveolar epithelia. Previous genetic lineage tracing studies reported multiple cellular origins for AT2 cells after injury. However, conventional lineage tracing based on Cre-loxP has the limitation of non-specific labeling. Here, we introduced a dual recombinase-mediated intersectional genetic lineage tracing approach, enabling precise investigation of AT2 cellular origins during lung homeostasis, injury, and repair. We found AT1 cells, being terminally differentiated, did not contribute to AT2 cells after lung injury and repair. Distinctive yet simultaneous labeling of club cells, bronchioalveolar stem cells (BASCs), and existing AT2 cells revealed the exact contribution of each to AT2 cells post-injury. Mechanistically, Notch signaling inhibition promotes BASCs but impairs club cells' ability to generate AT2 cells during lung repair. This intersectional genetic lineage tracing strategy with enhanced precision allowed us to elucidate the physiological role of various epithelial cell types in alveolar regeneration following injury.

AI-luminating Artificial Intelligence in Inflammatory Bowel Diseases: A Narrative Review on the Role of AI in Endoscopy, Histology, and Imaging for IBD.

Endoscopy, histology, and cross-sectional imaging serve as fundamental pillars in the detection, monitoring, and prognostication of inflammatory bowel disease (IBD). However, interpretation of these studies often relies on subjective human judgment, which can lead to delays, intra- and interobserver variability, and potential diagnostic discrepancies. With the rising incidence of IBD globally coupled with the exponential digitization of these data, there is a growing demand for innovative approaches to streamline diagnosis and elevate clinical decision-making. In this context, artificial intelligence (AI) technologies emerge as a timely solution to address the evolving challenges in IBD. Early studies using deep learning and radiomics approaches for endoscopy, histology, and imaging in IBD have demonstrated promising results for using AI to detect, diagnose, characterize, phenotype, and prognosticate IBD. Nonetheless, the available literature has inherent limitations and knowledge gaps that need to be addressed before AI can transition into a mainstream clinical tool for IBD. To better understand the potential value of integrating AI in IBD, we review the available literature to summarize our current understanding and identify gaps in knowledge to inform future investigations.

The Effect of Paternal Co-Parenting on Preschool Children's Problem Behaviors: The Chain-Mediating Role of Maternal Parenting Burnout and Psychological Aggression.

Objective: With the social changes, a growing number of women have joined the workforce, leading to a shift in the traditional roles of child-rearing. There has been a growing focus on the significance of fathers' roles in child development, particularly the influence of fathers on children's problematic behaviors, making it an increasingly prominent issue. However, there is limited understanding regarding the potential mechanisms through which fathers may exert influence on children's problem behaviors. To address this gap, this study sought to investigate the link between paternal co-parenting and preschool children's problem behaviors, and the mediating effects of maternal parenting burnout and psychological aggression. Methods: This study used the Personal Information Form and four scales to administer questionnaires to 1164 mothers of preschool children (Mage = 4.26 ± 0.85) in Guangdong Province, China. The collected data underwent processing and analysis using SPSS 22.0. Results: Paternal co-parenting demonstrated a significantly positive correlation with problem behaviors among preschool children. The impact of paternal co-parenting on children's problem behaviors was mediated by maternal parenting burnout, maternal psychological aggression, and the combined effect of maternal parenting burnout and psychological aggression. Conclusion: Maternal parenting burnout and maternal psychological aggression play a sequential mediating role between paternal co-parenting and problem behaviors among preschool children. This study revealed the internal mechanism through which paternal co-parenting influenced problem behaviors exhibited by children. It provides some evidence to support the important role of fathers in child development, and provides a reference for policymakers and educators to develop interventions for children's problem behaviors.

Dynamics of Endothelial Cell Generation and Turnover in Arteries During Homeostasis and Diseases.

BACKGROUND: Endothelial cell (EC) generation and turnover by self-proliferation contributes to vascular repair and regeneration. The ability to accurately measure the dynamics of EC generation would advance our understanding of cellular mechanisms of vascular homeostasis and diseases. However, it is currently challenging to evaluate the dynamics of EC generation in large vessels such as arteries because of their infrequent proliferation. METHODS: By using dual recombination systems based on Cre-loxP and Dre-rox, we developed a genetic system for temporally seamless recording of EC proliferation in vivo. We combined genetic recording of EC proliferation with single-cell RNA sequencing and gene knockout to uncover cellular and molecular mechanisms underlying EC generation in arteries during homeostasis and disease. RESULTS: Genetic proliferation tracing reveals that ≈3% of aortic ECs undergo proliferation per month in adult mice during homeostasis. The orientation of aortic EC division is generally parallel to blood flow in the aorta, which is regulated by the mechanosensing protein Piezo1. Single-cell RNA sequencing analysis reveals 4 heterogeneous aortic EC subpopulations with distinct proliferative activity. EC cluster 1 exhibits transit-amplifying cell features with preferential proliferative capacity and enriched expression of stem cell markers such as Sca1 and Sox18. EC proliferation increases in hypertension but decreases in type 2 diabetes, coinciding with changes in the extent of EC cluster 1 proliferation. Combined gene knockout and proliferation tracing reveals that Hippo/vascular endothelial growth factor receptor 2 signaling pathways regulate EC proliferation in large vessels. CONCLUSIONS: Genetic proliferation tracing quantitatively delineates the dynamics of EC generation and turnover, as well as EC division orientation, in large vessels during homeostasis and disease. An EC subpopulation in the aorta exhibits more robust cell proliferation during homeostasis and type 2 diabetes, identifying it as a potential therapeutic target for vascular repair and regeneration.

Artificial Intelligence-Based Video Feedback to Improve Novice Performance on Robotic Suturing Skills: A Pilot Study.

Introduction: Automated skills assessment can provide surgical trainees with objective, personalized feedback during training. Here, we measure the efficacy of artificial intelligence (AI)-based feedback on a robotic suturing task. Materials and Methods: Forty-two participants with no robotic surgical experience were randomized to a control or feedback group and video-recorded while completing two rounds (R1 and R2) of suturing tasks on a da Vinci surgical robot. Participants were assessed on needle handling and needle driving, and feedback was provided via a visual interface after R1. For feedback group, participants were informed of their AI-based skill assessment and presented with specific video clips from R1. For control group, participants were presented with randomly selected video clips from R1 as a placebo. Participants from each group were further labeled as underperformers or innate-performers based on a median split of their technical skill scores from R1. Results: Demographic features were similar between the control (n = 20) and feedback group (n = 22) (p > 0.05). Observing the improvement from R1 to R2, the feedback group had a significantly larger improvement in needle handling score (0.30 vs -0.02, p = 0.018) when compared with the control group, although the improvement of needle driving score was not significant when compared with the control group (0.17 vs -0.40, p = 0.074). All innate-performers exhibited similar improvements across rounds, regardless of feedback (p > 0.05). In contrast, underperformers in the feedback group improved more than the control group in needle handling (p = 0.02). Conclusion: AI-based feedback facilitates surgical trainees' acquisition of robotic technical skills, especially underperformers. Future research will extend AI-based feedback to additional suturing skills, surgical tasks, and experience groups.

Single protein encapsulated SN38 for tumor-targeting treatment.

BACKGROUND: The alkaloid camptothecin analog SN38 is a potent antineoplastic agent, but cannot be used directly for clinical application due to its poor water solubility. Currently, the prodrug approach on SN38 has resulted in 3 FDA-approved cancer therapeutics, irinotecan, ONIVYDE, and Trodelvy. However, only 2-8% of irinotecan can be transformed enzymatically in vivo into the active metabolite SN38, which severely limits the drug's efficacy. While numerous drug delivery systems have been attempted to achieve effective SN38 delivery, none have produced drug products with antitumor efficacy better than irinotecan in clinical trials. Therefore, novel approaches are urgently needed for effectively delivering SN38 to cancer cells with better efficacy and lower toxicity. METHODS: Based on the unique properties of human serum albumin (HSA), we have developed a novel single protein encapsulation (SPE) technology to formulate cancer therapeutics for improving their pharmacokinetics (PK) and antitumor efficacy and reducing their side effects. Previous application of SPE technology to doxorubicin (DOX) formulation has led to a promising drug candidate SPEDOX-6 (FDA IND #, 152154), which will undergo a human phase I clinical trial. Using the same SPE platform on SN38, we have now produced two SPESN38 complexes, SPESN38-5 and SPESN38-8. We conducted their pharmacological evaluations with respect to maximum tolerated dose, PK, and in vivo efficacy against colorectal cancer (CRC) and soft tissue sarcoma (STS) in mouse models. RESULTS: The lyophilized SPESN38 complexes can dissolve in aqueous media to form clear and stable solutions. Maximum tolerated dose (MTD) of SPESN38-5 is 250 mg/kg by oral route (PO) and 55 mg/kg by intravenous route (IV) in CD-1 mice. SPESN38-8 has the MTD of 45 mg/kg by IV in the same mouse model. PK of SPESN38-5 by PO at 250 mg/kg gave mouse plasma AUC0-∞ of 0.05 and 4.5 nmol × h/mL for SN38 and SN38 glucuronidate (SN38G), respectively, with a surprisingly high molar ratio of SN38G:SN38 = 90:1. However, PK of SPESN38-5 by IV at 55 mg/kg yielded much higher mouse plasma AUC0-∞ of 19 and 28 nmol × h/mL for SN38 and SN38G, producing a much lower molar ratio of SN38G:SN38 = 1.5:1. Antitumor efficacy of SPESN38-5 and irinotecan (control) was evaluated against HCT-116 CRC xenograft tumors. The data indicates that SPESN38-5 by IV at 55 mg/kg is more effective in suppressing HCT-116 tumor growth with lower systemic toxicity compared to irinotecan at 50 mg/kg. Additionally, SPESN38-8 and DOX (control) by IV were evaluated in the SK-LMS-1 STS mouse model. The results show that SPESN38-8 at 33 mg/kg is highly effective for inhibiting SK-LMS-1 tumor growth with low toxicity, in contrast to DOX's insensitivity to SK-LMS-1 with high toxicity. CONCLUSION: SPESN38 complexes provide a water soluble SN38 formulation. SPESN38-5 and SPESN38-8 demonstrate better PK values, lower toxicity, and superior antitumor efficacy in mouse models, compared with irinotecan and DOX.

Single Protein Encapsulated SN38 for Tumor-Targeting Treatment.

Background: The alkaloid camptothecin analog SN38 is a potent antineoplastic agent, but cannot be used directly for clinical application due to its poor water solubility. Currently, the prodrug approach on SN38 has resulted in 3 FDA-approved cancer therapeutics, irinotecan, ONIVYDE, and Trodelvy. However, only 2-8% of irinotecan can be transformed enzymatically in vivo into the active metabolite SN38, which severely limits the drug's efficacy. While numerous drug delivery systems have been attempted to achieve effective SN38 delivery, none have produced drug products with antitumor efficacy better than irinotecan in clinical trials. Therefore, novel approaches are urgently needed for effectively delivering SN38 to cancer cells with better efficacy and lower toxicity. Methods: Based on the unique properties of human serum albumin (HSA), we have developed a novel single protein encapsulation (SPE) technology to formulate cancer therapeutics for improving their pharmacokinetics (PK) and antitumor efficacy and reducing their side effects. Previous application of SPE technology to doxorubicin (DOX) formulation has led to a promising drug candidate SPEDOX-6 (FDA IND #, 152154), which will undergo a human phase I clinical trial. Using the same SPE platform on SN38, we have now produced two SPESN38 complexes, SPESN38-5 and SPESN38-8. We conducted their pharmacological evaluations with respect to maximum tolerated dose, PK, and in vivo efficacy against colorectal cancer (CRC) and soft tissue sarcoma (STS) in mouse models. Results: The lyophilized SPESN38 complexes can dissolve in aqueous media to form clear and stable solutions. Maximum tolerated dose (MTD) of SPESN38-5 is 250 mg/kg by oral route (PO) and 55 mg/kg by intravenous route (IV) in CD-1 mice. SPESN38-8 has the MTD of 45 mg/kg by IV in the same mouse model. PK of SPESN38-5 by PO at 250 mg/kg gave mouse plasma AUC0-∞ of 0.0548 and 4.5007 (nmol × h/mL) for SN38 and SN38 glucuronidate (SN38G), respectively, with a surprisingly high molar ratio of SN38G:SN38 = 82:1. However, PK of SPESN38-5 by IV at 55 mg/kg yielded much higher mouse plasma AUC0-∞ of 18.80 and 27.78 nmol × h/mL for SN38 and SN38G, producing a much lower molar ratio of SN38G:SN38 = 1.48:1. Antitumor efficacy of SPESN38-5 and irinotecan (control) was evaluated against HCT-116 CRC xenograft tumors. The data indicates that SPESN38-5 by IV at 55 mg/kg is more effective in suppressing HCT-116 tumor growth with lower systemic toxicity compared to irinotecan at 50 mg/kg. Additionally, SPESN38-8 and DOX (control) by IV were evaluated in the SK-LMS-1 STS mouse model. The results show that SPESN38-8 at 33 mg/kg is highly effective for inhibiting SK-LMS-1 tumor growth with low toxicity, in contrast to DOX's insensitivity to SK-LMS-1 with high toxicity. Conclusion: SPESN38 complexes provide a water soluble SN38 formulation. SPESN38-5 and SPESN38-8 demonstrate better PK values, lower toxicity, and superior antitumor efficacy in mouse models, compared with irinotecan and DOX.

Bipotent transitional liver progenitor cells contribute to liver regeneration.

Following severe liver injury, when hepatocyte-mediated regeneration is impaired, biliary epithelial cells (BECs) can transdifferentiate into functional hepatocytes. However, the subset of BECs with such facultative tissue stem cell potential, as well as the mechanisms enabling transdifferentiation, remains elusive. Here we identify a transitional liver progenitor cell (TLPC), which originates from BECs and differentiates into hepatocytes during regeneration from severe liver injury. By applying a dual genetic lineage tracing approach, we specifically labeled TLPCs and found that they are bipotent, as they either differentiate into hepatocytes or re-adopt BEC fate. Mechanistically, Notch and Wnt/ß-catenin signaling orchestrate BEC-to-TLPC and TLPC-to-hepatocyte conversions, respectively. Together, our study provides functional and mechanistic insights into transdifferentiation-assisted liver regeneration.

Dual genetic tracing reveals a unique fibroblast subpopulation modulating cardiac fibrosis.

After severe heart injury, fibroblasts are activated and proliferate excessively to form scarring, leading to decreased cardiac function and eventually heart failure. It is unknown, however, whether cardiac fibroblasts are heterogeneous with respect to their degree of activation, proliferation and function during cardiac fibrosis. Here, using dual recombinase-mediated genetic lineage tracing, we find that endocardium-derived fibroblasts preferentially proliferate and expand in response to pressure overload. Fibroblast-specific proliferation tracing revealed highly regional expansion of activated fibroblasts after injury, whose pattern mirrors that of endocardium-derived fibroblast distribution in the heart. Specific ablation of endocardium-derived fibroblasts alleviates cardiac fibrosis and reduces the decline of heart function after pressure overload injury. Mechanistically, Wnt signaling promotes activation and expansion of endocardium-derived fibroblasts during cardiac remodeling. Our study identifies endocardium-derived fibroblasts as a key fibroblast subpopulation accounting for severe cardiac fibrosis after pressure overload injury and as a potential therapeutic target against cardiac fibrosis.

Use of a dual genetic system to decipher exocrine cell fate conversions in the adult pancreas.

Unraveling cell fate plasticity during tissue homeostasis and repair can reveal actionable insights for stem cell biology and regenerative medicine. In the pancreas, it remains controversial whether lineage transdifferentiation among the exocrine cells occur under pathophysiological conditions. Here, to address this question, we used a dual recombinase-mediated genetic system that enables simultaneous tracing of pancreatic acinar and ductal cells using two distinct genetic reporters, avoiding the "ectopic" labeling by Cre-loxP recombination system. We found that acinar-to-ductal transdifferentiation occurs after pancreatic duct ligation or during caerulein-induced pancreatitis, but not during homeostasis or after partial pancreatectomy. On the other hand, pancreatic ductal cells contribute to new acinar cells after significant acinar cell loss. By genetic tracing of cell proliferation, we also quantify the cell proliferation dynamics and deduce the turnover rate of pancreatic exocrine lineages during homeostasis. Together, these results suggest that the lineage transdifferentiation happens between acinar cells and ductal cells in the pancreatic exocrine glands under specific conditions.

COVID19 Diagnosis Using Chest X-rays and Transfer Learning.

A pandemic of respiratory illnesses from a novel coronavirus known as Sars-CoV-2 has swept across the globe since December of 2019. This is calling upon the research community including medical imaging to provide effective tools for use in combating this virus. Research in biomedical imaging of viral patients is already very active with machine learning models being created for diagnosing Sars-CoV-2 infections in patients using CT scans and chest x-rays. We aim to build upon this research. Here we used a transfer-learning approach to develop models capable of diagnosing COVID19 from chest x-ray. For this work we compiled a dataset of 112120 negative images from the Chest X-Ray 14 and 2725 positive images from public repositories. We tested multiple models, including logistic regression and random forest and XGBoost with and without principal components analysis, using five-fold cross-validation to evaluate recall, precision, and f1-score. These models were compared to a pre-trained deep-learning model for evaluating chest x-rays called COVID-Net. Our best model was XGBoost with principal components with a recall, precision, and f1-score of 0.692, 0.960, 0.804 respectively. This model greatly outperformed COVID-Net which scored 0.987, 0.025, 0.048. This model, with its high precision and reasonable sensitivity, would be most useful as "rule-in" test for COVID19. Though it outperforms some chemical assays in sensitivity, this model should be studied in patients who would not ordinarily receive a chest x-ray before being used for screening.

Genetic Lineage Tracing of Pericardial Cavity Macrophages in the Injured Heart.

BACKGROUND: Macrophages play an important role in cardiac repair after myocardial infarction (MI). In addition to the resident macrophages and blood-derived monocytes, Gata6+ cavity macrophages located in the pericardial space were recently reported to relocate to the injured myocardium and prevent cardiac fibrosis. However, there is no direct genetic evidence to support it. METHODS: We used dual recombinases (Cre and Dre) to specifically label Gata6+ pericardial macrophages (GPCMs) in vivo. For functional study, we generated genetic systems to specifically ablate GPCMs by induced expression of DTR (diphtheria toxin receptor) or knockout of Gata6 (GATA binding protein 6) gene in GPCMs. We used these genetic systems to study GPCMs in pericardium intact MI model. RESULTS: Dual recombinases-mediated genetic system targeted GPCMs specifically and efficiently. Lineage tracing study revealed accumulation of GPCMs on the surface of MI heart without deep penetration into the myocardium. We did not detect significant change of cardiac fibrosis or function of MI hearts after cell ablation or Gata6 knockout in GPCMs. CONCLUSIONS: GPCMs minimally invade the injured heart after MI. Nor do they prevent cardiac fibrosis and exhibit reparative function on injured heart. This study also underlines the importance of using specific genetic tool for studying in vivo cell fates and functions.

Detecting Intra-Field Variation in Rice Yield With Unmanned Aerial Vehicle Imagery and Deep Learning.

Unmanned aerial vehicles (UAVs) equipped with multispectral sensors offer high spatial and temporal resolution imagery for monitoring crop stress at early stages of development. Analysis of UAV-derived data with advanced machine learning models could improve real-time management in agricultural systems, but guidance for this integration is currently limited. Here we compare two deep learning-based strategies for early warning detection of crop stress, using multitemporal imagery throughout the growing season to predict field-scale yield in irrigated rice in eastern Arkansas. Both deep learning strategies showed improvements upon traditional statistical learning approaches including linear regression and gradient boosted decision trees. First, we explicitly accounted for variation across developmental stages using a 3D convolutional neural network (CNN) architecture that captures both spatial and temporal dimensions of UAV images from multiple time points throughout one growing season. 3D-CNNs achieved low prediction error on the test set, with a Root Mean Squared Error (RMSE) of 8.8% of the mean yield. For the second strategy, a 2D-CNN, we considered only spatial relationships among pixels for image features acquired during a single flyover. 2D-CNNs trained on images from a single day were most accurate when images were taken during booting stage or later, with RMSE ranging from 7.4 to 8.2% of the mean yield. A primary benefit of convolutional autoencoder-like models (based on analyses of prediction maps and feature importance) is the spatial denoising effect that corrects yield predictions for individual pixels based on the values of vegetation index and thermal features for nearby pixels. Our results highlight the promise of convolutional autoencoders for UAV-based yield prediction in rice.

Extension of Endocardium-Derived Vessels Generate Coronary Arteries in Neonates.

BACKGROUND: Unraveling how new coronary arteries develop may provide critical information for establishing novel therapeutic approaches to treating ischemic cardiac diseases. There are 2 distinct coronary vascular populations derived from different origins in the developing heart. Understanding the formation of coronary arteries may provide insights into new ways of promoting coronary artery formation after myocardial infarction. METHODS: To understand how intramyocardial coronary arteries are generated to connect these 2 coronary vascular populations, we combined genetic lineage tracing, light sheet microscopy, fluorescence micro-optical sectioning tomography, and tissue-specific gene knockout approaches to understand their cellular and molecular mechanisms. RESULTS: We show that a subset of intramyocardial coronary arteries form by angiogenic extension of endocardium-derived vascular tunnels in the neonatal heart. Three-dimensional whole-mount fluorescence imaging showed that these endocardium-derived vascular tunnels or tubes adopt an arterial fate in neonates. Mechanistically, we implicate Mettl3 (methyltransferase-like protein 3) and Notch signaling in regulating endocardium-derived intramyocardial coronary artery formation. Functionally, these intramyocardial arteries persist into adulthood and play a protective role after myocardial infarction. CONCLUSIONS: A subset of intramyocardial coronary arteries form by extension of endocardium-derived vascular tunnels in the neonatal heart.

Spatial Pyramid Pooling With 3D Convolution Improves Lung Cancer Detection.

Lung cancer is the leading cause of cancer deaths. Low-dose computed tomography (CT)screening has been shown to significantly reduce lung cancer mortality but suffers from a high false positive rate that leads to unnecessary diagnostic procedures. The development of deep learning techniques has the potential to help improve lung cancer screening technology. Here we present the algorithm, DeepScreener, which can predict a patient's cancer status from a volumetric lung CT scan. DeepScreener is based on our model of Spatial Pyramid Pooling, which ranked 16th of 1972 teams (top 1 percent)in the Data Science Bowl 2017 competition (DSB2017), evaluated with the challenge datasets. Here we test the algorithm with an independent set of 1449 low-dose CT scans of the National Lung Screening Trial (NLST)cohort, and we find that DeepScreener has consistent performance of high accuracy. Furthermore, by combining Spatial Pyramid Pooling and 3D Convolution, it achieves an AUC of 0.892, surpassing the previous state-of-the-art algorithms using only 3D convolution. The advancement of deep learning algorithms can potentially help improve lung cancer detection with low-dose CT scans.

Study COVID-19 Severity of Patients Admitted to Emergency Room (ER) with Chest X-ray Images.

We have conducted a study of the COVID-19 severity with the chest x-ray images, a private dataset collected from our collaborator St Bernards Medical Center. The dataset is comprised of chest x-ray images from 1,550 patients who were admitted to emergency room (ER) and were all tested positive for COVID-19. Our study is focused on the following two questions: (1) To predict patients hospital staying duration, based on the chest x-ray image which was taken when the patient was admitted to the ER. The length of stay ranged from zero hours to 95 days in the hospital and followed a power law distribution. Based on our testing results, it is hard for the prediction models to detect strong signal from the chest x-ray images. No model was able to perform better than a trivial most-frequent classifier. However, each model was able to outperform the most-frequent classifier when the data was split evenly into four categories. This would suggest that there is signal in the images, and the performance may be further improved by the addition of clinical features as well as increasing the training set. (2) To predict if a patient is COVID-19 positive or not with the chest x-ray image. We also tested the generalizability of training a prediction model on chest x-ray images from one hospital and then testing the model on images captures from other sites. With our private dataset and the COVIDx dataset, the prediction model can achieve a high accuracy of 95.9%. However, for our hold-one-out study of the generalizability of the models trained on chest x-rays, we found that the model performance suffers due to a significant reduction in training samples of any class.

An Ensemble of U-Net Models for Kidney Tumor Segmentation With CT Images.

We present here the Arkansas AI-Campus solution method for the 2019 Kidney Tumor Segmentation Challenge (KiTS19). Our Arkansas AI-Campus team participated the KiTS19 Challenge for four months, from March to July of 2019. This paper provides a summary of our methods, training, testing and validation results for this grand challenge in biomedical imaging analysis. Our deep learning model is an ensemble of U-Net models developed after testing many model variations. Our model has consistent performance on the local test dataset and the final competition independent test dataset. The model achieved local test Dice scores of 0.949 for kidney and tumor segmentation, and 0.601 for tumor segmentation, and the final competition test earned Dice scores 0.9470 and 0.6099 respectively. The Arkansas AI-Campus team solution with a composite DICE score of 0.7784 has achieved a final ranking of top fifty worldwide, and top five among the United States teams in the KiTS19 Competition.