BackgroundThis study aimed at predicting the survival status on non-small cell lung cancer patients with the phenotypic radiomics features obtained from the CT images.MethodsA total of 186 patients’ CT images were used for feature extraction via Pyradiomics. The minority group was balanced via SMOTE method. The final dataset was randomized into training set (n = 223) and validation set (n = 75) with the ratio of 3:1. Multiple random forest models were trained applying hyperparameters grid search with 10-fold cross-validation using precision or recall as evaluation standard. Then a decision threshold was searched on the selected model. The final model was evaluated through ROC curve and prediction accuracy.ResultsFrom those segmented images of 186 patients, 1218 features were obtained via feature extraction. The preferred model was selected with recall as evaluation standard and the optimal decision threshold was set 0.56. The model had a prediction accuracy of 89.33% and the AUC score was 0.9296.ConclusionA hyperparameters tuning random forest classifier had greater performance in predicting the survival status of non-small cell lung cancer patients, which could be taken for an automated classifier promising to stratify patients.Electronic supplementary materialThe online version of this article (10.1186/s12931-018-0887-8) contains supplementary material, which is available to authorized users.

Background In this COVID-19 pandemic, the differential diagnosis of viral pneumonia is still challenging. We aimed to assess the classification performance of computed tomography (CT)-based CT signs and radiomics features for discriminating COVID-19 and influenza pneumonia. Methods A total of 154 patients with confirmed viral pneumonia (COVID-19: 89 cases, influenza pneumonia: 65 cases) were collected retrospectively in this study. Pneumonia signs and radiomics features were extracted from the initial unenhanced chest CT images to build independent and combined models. The predictive performance of the radiomics model, CT sign model, the combined model was constructed based on the whole dataset and internally invalidated by using 1000-times bootstrap. Diagnostic performance of the models was assessed via receiver operating characteristic (ROC) analysis. Results The combined models consisted of 4 significant CT signs and 7 selected features and demonstrated better discrimination performance between COVID-19 and influenza pneumonia than the single radiomics model. For the radiomics model, the area under the ROC curve (AUC) was 0.888 (sensitivity, 86.5%; specificity, 78.4%; accuracy, 83.1%), and the AUC was 0.906 (sensitivity, 86.5%; specificity, 81.5%; accuracy, 84.4%) in the CT signs model. After combining CT signs and radiomics features, AUC of the combined model was 0.959 (sensitivity, 89.9%; specificity, 90.7%; accuracy, 90.3%). Conclusions CT-based radiomics combined with signs might be a potential method for distinguishing COVID-19 and influenza pneumonia with satisfactory performance.

Background: Our study aimed to investigate the feasibility of functional magnetic resonance imaging [blood oxygen level-dependent (BOLD) imaging and T2 mapping] in monitoring the activation of lumbar paraspinal muscles before and after exercise. Methods:The ethics committee of the First Affiliated Hospital of Kunming Medical University approved our study. Both BOLD and T2 mapping of paraspinal muscles were performed in 50 healthy, young volunteers before and after upper-body extension exercises. The movement tasks included upper body flexion and extension using a simple Roman chair. Cross-sectional area (CSA), R2*, and T2 values were measured in various lower-back anatomical regions. The SPSS22.0 statistical software was used to analyze all the data.Results: Post-exercise CSA and T2 values were higher than those recorded in the pre-exercise session for the three lower-back muscles that were evaluated (iliocostalis, longissimus, and multifidus) (P<0.01).However, R2* values of these muscles were significantly lower after exercise (P<0.01). A significant difference in the R2*, CSA, and T2 values of the iliocostalis occurred between males and females (P<0.05). No statistically significant differences were evident for R2*, CSA, and T2 of the lower-back muscles between L3 and L4 levels, or between the left and right sides. The total CSA of the iliocostalis was higher than that of the multifidus and longissimus (P<0.05).Conclusions: BOLD and T2 mapping are feasible non-invasive indirect assessments of lumbar paraspinal muscle activation before and after exercise.

Background. Circular RNAs (circRNAs) have been reported to play important roles in the development and progression of papillary thyroid carcinoma (PTC). However, the function and molecular mechanism of circRNA low-density lipoprotein receptor (circLDLR) in the tumorigenesis of PTC remain unknown. Results. In this study, circLDLR was found to be markedly upregulated in PTC tissues and cell lines, and knockdown of circLDLR inhibited PTC cell proliferation, migration, and invasion but induced apoptosis in vitro. Moreover, circLDLR acted as a sponge for miR-637, and miR-637 interference reversed the anticancer effects of circLDLR knockdown on PTC cells. LMO4 was verified to be a target of miR-637; LMO4 upregulation abolished miR-637 mediated inhibition of cell growth and metastasis in PTC. Additionally, circLDLR could indirectly modulate LMO4 via acting as a sponge of miR-637 in PTC cells. Besides that, xenograft analysis showed that circLDLR knockdown suppressed tumor growth in vivo via regulating LMO4 and miR-637. Conclusion. Taken together, these results demonstrated that circLDLR promoted PTC tumorigenesis through miR-637/LMO4 axis, which may provide a novel insight into the understanding of PTC tumorigenesis and be useful in developing potential targets for PTC treatment.

Background: To investigate the dynamic changes in high-resolution computed tomography (HRCT) findings of coronavirus disease 2019 (COVID-19) patients with different severities in different disease stages. Methods: We retrospectively collected the clinical and imaging data of 96 patients in Yunnan Province, China, who were diagnosed with COVID-19 between January 22 and March 15, 2020. Based on disease severity, the COVID-19 patients were classified into four types: mild (n=15), moderate (n=59), severe (n=19), and critical (n=3). Based on hospital stay and number of computed tomography (CT) scans, the clinical/ disease course was divided into four stages, including stage 1 (days 0-4), stage 2 (days 5-9), stage 3 (days 10-14), and stage 4 (days 15-19). The HRCT findings, CT value, and lesion volume were analyzed for each stage and compared among the four stages of COVID-19 patients. Results: CT findings were negative over the four stages for all mild COVID-19 patients. More lesions were found in the peripheral lung fields than in peripheral + central fields (P<0.05), and the number of negative patients in stage 4 were more than those in stages 1-3 (P<0.05). The left and right lower lobe were the most frequently affected lobes (P<0.05). In moderate patients, round ground glass opacities (GGOs) decreased from stage 1 to stage 4; partial consolidation peaked in stage 2 and then decreased in stages 3-4; Huang et al. Dynamic changes in chest CT of COVID-19 patients