An Effective Malignancy Prediction Model for Incidentally Detected Pulmonary Subsolid Nodules Based on Current and Prior CT Scans.

INTRODUCTION: It is challenging to diagnose and manage incidentally detected pulmonary subsolid nodules due to their indolent nature and heterogeneity. The objective of this study is to construct a decision tree-based model to predict malignancy of a subsolid nodule based on radiomics features and evolution over time. MATERIALS AND METHODS: We derived a training set (2947 subsolid nodules), a test set (280 subsolid nodules) from a cohort of outpatient CT scans, and a second test set (5171 subsolid nodules) from the National Lung Cancer Screening Trial (NLST). A Computer-Aided Diagnosis system (CADs) automatically extracted 28 preselected radiomics features, and we calculated the feature change rates as the change of the quantitative measure per time unit between the prior and current CT scans. We built classification models based on XGBoost and employed 5-fold cross validation to optimize the parameters. RESULTS: The model that combined radiomics features with their change rates performed the best. The Areas Under Curve (AUCs) on the outpatient test set and on the NLST test set were 0.977 (95% CI, 0.958-0.996) and 0.955 (95% CI, 0.930-0.980), respectively. The model performed consistently well on subgroups stratified by nodule diameters, solid components, and CT scan intervals. CONCLUSION: This decision tree-based model trained with the outpatient dataset gives promising predictive performance on the malignancy of pulmonary subsolid nodules. Additionally, it can assist clinicians to deliver more accurate diagnoses and formulate more in-depth follow-up strategies.

Accuracy and efficiency of an artificial intelligence-based pulmonary broncho-vascular three-dimensional reconstruction system supporting thoracic surgery: retrospective and prospective validation study.

BACKGROUND: Anthropomorphic phantoms are used in surgical planning and intervention. Ideal accuracy and high efficiency are prerequisites for its clinical application. We aimed to develop a fully automated artificial intelligence-based three-dimensional (3D) reconstruction system (AI system) to assist thoracic surgery and to determine its accuracy, efficiency, and safety for clinical use. METHODS: This AI system was developed based on a 3D convolutional neural network (CNN) and optimized by gradient descent after training with 500 cases, achieving a Dice coefficient of 89.2%. Accuracy was verified by comparing virtual structures predicted by the AI system with anatomical structures of patients in retrospective (n = 113) and prospective cohorts (n = 139) who underwent lobectomy or segmentectomy at the Peking University Cancer Hospital. Operation time and blood loss were compared between the retrospective cohort (without AI assistance) and prospective cohort (with AI assistance) for safety evaluation. The time consumption for reconstruction and the quality score were compared between the AI system and manual reconstruction software (Mimics®) for efficiency validation. This study was registered at https://www.chictr.org.cn as ChiCTR2100050985. FINDINGS: The AI system reconstructed 13,608 pulmonary segmental branches from retrospective and prospective cohorts, and 1573 branches of interest corresponding to phantoms were detectable during the operation for verification, achieving 100% and 97% accuracy for segmental bronchi, 97.2% and 99.1% for segmental arteries, and 93.2% and 98.8% for segmental veins, respectively. With the assistance of the AI system, the operation time was shortened by 24.5 min for lobectomy (p < 0.001) and 20 min for segmentectomy (p = 0.007). Compared to Mimics®, the AI system reduced the model reconstruction time by 14.2 min (p < 0.001), and it also outperformed Mimics® in model quality scores (p < 0.001). INTERPRETATION: The AI system can accurately predict thoracic anatomical structures with higher efficiency than manual reconstruction software. Constant optimization and larger population validation are required. FUNDING: This study was funded by the Beijing Natural Science Foundation (No. L222020) and other sources.

Identification of distinct clinical phenotypes of acute respiratory distress syndrome with differential responses to treatment.

BACKGROUND: Acute respiratory distress syndrome (ARDS) is a heterogeneous syndrome, and the identification of homogeneous subgroups and phenotypes is the first step toward precision critical care. We aimed to explore whether ARDS phenotypes can be identified using clinical data, are reproducible and are associated with clinical outcomes and treatment response. METHODS: This study is based on a retrospective analysis of data from the telehealth intensive care unit (eICU) collaborative research database and three ARDS randomized controlled trials (RCTs) (ALVEOLI, FACTT and SAILS trials). We derived phenotypes in the eICU by cluster analysis based on clinical data and compared the clinical characteristics and outcomes of each phenotype. The reproducibility of the derived phenotypes was tested using the data from three RCTs, and treatment effects were evaluated. RESULTS: Three clinical phenotypes were identified in the training cohort of 3875 ARDS patients. Of the three phenotypes identified, phenotype I (n = 1565; 40%) was associated with fewer laboratory abnormalities, less organ dysfunction and the lowest in-hospital mortality rate (8%). Phenotype II (n = 1232; 32%) was correlated with more inflammation and shock and had a higher mortality rate (18%). Phenotype III (n = 1078; 28%) was strongly correlated with renal dysfunction and acidosis and had the highest mortality rate (22%). These results were validated using the data from the validation cohort (n = 3670) and three RCTs (n = 2289) and had reproducibility. Patients with these ARDS phenotypes had different treatment responses to randomized interventions. Specifically, in the ALVEOLI cohort, the effects of ventilation strategy (high PEEP vs low PEEP) on ventilator-free days differed by phenotype (p = 0.001); in the FACTT cohort, there was a significant interaction between phenotype and fluid-management strategy for 60-day mortality (p = 0.01). The fluid-conservative strategy was associated with improved mortality in phenotype II but had the opposite effect in phenotype III. CONCLUSION: Three clinical phenotypes of ARDS were identified and had different clinical characteristics and outcomes. The analysis shows evidence of a phenotype-specific treatment benefit in the ALVEOLI and FACTT trials. These findings may improve the identification of distinct subsets of ARDS patients for exploration in future RCTs.

Emotion Correlation Mining Through Deep Learning Models on Natural Language Text.

Emotion analysis has been attracting researchers' attention. Most previous works in the artificial-intelligence field focus on recognizing emotion rather than mining the reason why emotions are not or wrongly recognized. The correlation among emotions contributes to the failure of emotion recognition. In this article, we try to fill the gap between emotion recognition and emotion correlation mining through natural language text from Web news. The correlation among emotions, expressed as the confusion and evolution of emotion, is primarily caused by human emotion cognitive bias. To mine emotion correlation from emotion recognition through text, three kinds of features and two deep neural-network models are presented. The emotion confusion law is extracted through an orthogonal basis. The emotion evolution law is evaluated from three perspectives: one-step shift, limited-step shifts, and shortest path transfer. The method is validated using three datasets: 1) the titles; 2) the bodies; and 3) the comments of news articles, covering both objective and subjective texts in varying lengths (long and short). The experimental results show that in subjective comments, emotions are easily mistaken as anger. Comments tend to arouse emotion circulations of love-anger and sadness-anger. In objective news, it is easy to recognize text emotion as love and cause fear-joy circulation. These findings could provide insights for applications regarding affective interaction, such as network public sentiment, social media communication, and human-computer interaction.

Artificial Intelligence-Aided Diagnosis Software to Identify Highly Suspicious Pulmonary Nodules.

INTRODUCTION: To evaluate the value of artificial intelligence (AI)-assisted software in the diagnosis of lung nodules using a combination of low-dose computed tomography (LDCT) and high-resolution computed tomography (HRCT). METHOD: A total of 113 patients with pulmonary nodules were screened using LDCT. For nodules with the largest diameters, an HRCT local-target scanning program (combined scanning scheme) and a conventional-dose CT scanning scheme were also performed. Lung nodules were subjectively assessed for image signs and compared by size and malignancy rate measured by AI-assisted software. The nodules were divided into improved visibility and identical visibility groups based on differences in the number of signs identified through the two schemes. RESULTS: The nodule volume and malignancy probability for subsolid nodules significantly differed between the improved and identical visibility groups. For the combined scanning protocol, we observed significant between-group differences in subsolid nodule malignancy rates. CONCLUSION: Under the operation and decision of AI, the combined scanning scheme may be beneficial for screening high-risk populations.

TeraVR empowers precise reconstruction of complete 3-D neuronal morphology in the whole brain.

Neuron morphology is recognized as a key determinant of cell type, yet the quantitative profiling of a mammalian neuron's complete three-dimensional (3-D) morphology remains arduous when the neuron has complex arborization and long projection. Whole-brain reconstruction of neuron morphology is even more challenging as it involves processing tens of teravoxels of imaging data. Validating such reconstructions is extremely laborious. We develop TeraVR, an open-source virtual reality annotation system, to address these challenges. TeraVR integrates immersive and collaborative 3-D visualization, interaction, and hierarchical streaming of teravoxel-scale images. Using TeraVR, we have produced precise 3-D full morphology of long-projecting neurons in whole mouse brains and developed a collaborative workflow for highly accurate neuronal reconstruction.

The relationship between inflammatory factors, oxidative stress and DIO-1 concentration in patients with chronic renal failure accompanied with or without euthyroid sick syndrome.

Objective To investigate the relationship between inflammatory factors, oxidative stress and type 1 deiodinase (DIO-1) concentration in patients with chronic renal failure (CRF) with or without euthyroid sick syndrome (ESS). Methods This study recruited patients with CRF and divided them into two groups: group 1 had low free triiodothyronine (FT3) levels; and group 2 had normal FT3 levels. Group 3 consisted of healthy volunteers. Serum levels of interleukin (IL)-6, IL-1ß, tumour necrosis factor (TNF)-α, 8-isoprostane and DIO-1 were measured using enzyme-linked immunosorbent assays. Multiple regression analysis was used to analyse correlations between parameters. Results Sixty patients were enrolled into each group and the groups were comparable in terms of vital signs, white blood cell count, free thyroxine and thyroid stimulating hormone concentrations. The serum DIO-1 concentration was significantly higher in group 2 than in groups 1 and 3. Multivariate regression analysis revealed that the DIO-1 concentration was inversely correlated with the TNF-α concentration. Conclusions Patients with CRF without ESS showed higher concentrations of DIO-1 than patients with ESS. The DIO-1 concentration was inversely correlated with the TNF-α concentration, which might indicate that the inflammatory response was milder in the patients with CRF without ESS than in those with ESS.

Doubly Nonparametric Sparse Nonnegative Matrix Factorization Based on Dependent Indian Buffet Processes.

Sparse nonnegative matrix factorization (SNMF) aims to factorize a data matrix into two optimized nonnegative sparse factor matrices, which could benefit many tasks, such as document-word co-clustering. However, the traditional SNMF typically assumes the number of latent factors (i.e., dimensionality of the factor matrices) to be fixed. This assumption makes it inflexible in practice. In this paper, we propose a doubly sparse nonparametric NMF framework to mitigate this issue by using dependent Indian buffet processes (dIBP). We apply a correlation function for the generation of two stick weights associated with each column pair of factor matrices while still maintaining their respective marginal distribution specified by IBP. As a consequence, the generation of two factor matrices will be columnwise correlated. Under this framework, two classes of correlation function are proposed: 1) using bivariate Beta distribution and 2) using Copula function. Compared with the single IBP-based NMF, this paper jointly makes two factor matrices nonparametric and sparse, which could be applied to broader scenarios, such as co-clustering. This paper is seen to be much more flexible than Gaussian process-based and hierarchial Beta process-based dIBPs in terms of allowing the two corresponding binary matrix columns to have greater variations in their nonzero entries. Our experiments on synthetic data show the merits of this paper compared with the state-of-the-art models in respect of factorization efficiency, sparsity, and flexibility. Experiments on real-world data sets demonstrate the efficiency of this paper in document-word co-clustering tasks.

Topic Model for Graph Mining.

Graph mining has been a popular research area because of its numerous application scenarios. Many unstructured and structured data can be represented as graphs, such as, documents, chemical molecular structures, and images. However, an issue in relation to current research on graphs is that they cannot adequately discover the topics hidden in graph-structured data which can be beneficial for both the unsupervised learning and supervised learning of the graphs. Although topic models have proved to be very successful in discovering latent topics, the standard topic models cannot be directly applied to graph-structured data due to the "bag-of-word" assumption. In this paper, an innovative graph topic model (GTM) is proposed to address this issue, which uses Bernoulli distributions to model the edges between nodes in a graph. It can, therefore, make the edges in a graph contribute to latent topic discovery and further improve the accuracy of the supervised and unsupervised learning of graphs. The experimental results on two different types of graph datasets show that the proposed GTM outperforms the latent Dirichlet allocation on classification by using the unveiled topics of these two models to represent graphs.

Measuring semantic relatedness between Flickr images: from a social tag based view.

Relatedness measurement between multimedia such as images and videos plays an important role in computer vision, which is a base for many multimedia related applications including clustering, searching, recommendation, and annotation. Recently, with the explosion of social media, users can upload media data and annotate content with descriptive tags. In this paper, we aim at measuring the semantic relatedness of Flickr images. Firstly, four information theory based functions are used to measure the semantic relatedness of tags. Secondly, the integration of tags pair based on bipartite graph is proposed to remove the noise and redundancy. Thirdly, the order information of tags is added to measure the semantic relatedness, which emphasizes the tags with high positions. The data sets including 1000 images from Flickr are used to evaluate the proposed method. Two data mining tasks including clustering and searching are performed by the proposed method, which shows the effectiveness and robustness of the proposed method. Moreover, some applications such as searching and faceted exploration are introduced using the proposed method, which shows that the proposed method has broad prospects on web based tasks.

Early gut barrier dysfunction in patients with severe acute pancreatitis: attenuated by continuous blood purification treatment.

OBJECTIVES: The aim of this study was to investigate the effect of continuous blood purification (CBP) on early gut mucosal dysfunction in patients with severe acute pancreatitis (SAP). METHODS: Patients with SAP were randomized to receive 24 hours of continuous veno-venous hemofiltration (CVVH; n = 33) or no CVVH (n = 30). Blood samples were taken from the patients at 0, 6, 12, and 24 hours during CVVH therapy. Serum diamine oxidase (DAO) and endotoxin, epithelial permeability, transepithelial electrical resistance (TER) and F-actin rearrangement of the epithelial monolayer were used as the markers for the assessment of gut barrier function and the effect of CBP therapy in patients with SAP. RESULTS: Patients with SAP had increased levels of serum DAO, endotoxin, and epithelial permeability when compared with normal controls, and the increase was more pronounced in patients with organ dysfunction (p<0.01). F-actin rearrangement, loose cell-cell junction, and iNOS mRNA upregulation were found in all patients. After CBP treatment, Acute Physiology and Chronic Health Evaluation II score and SOFA score improved significantly; levels of serum DAO, endotoxin, and epithelial permeability decreased(p<0.05). CBP also significantly attenuated reorganization of actin and downregulated iNOS mRNA expression and NO production (p<0.05). CONCLUSIONS: CBP can not only improve the general conditions but also effectively improve gut barrier dysfunction. The beneficial effect of CBP on gut barrier dysfunction is associated with the improvement of cytoskeletal instability, by downregulating iNOS through the removal of excess proinflammatory factors.