ABSTRACT
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.
ABSTRACT
BACKGROUND: This study aimed at predicting the survival status on non-small cell lung cancer patients with the phenotypic radiomics features obtained from the CT images. METHODS: A 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. RESULTS: From 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. CONCLUSION: A 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.
