Glioma is the most common malignant brain tumor and classification of low grade glioma (LGG) and high grade glioma (HGG) is an important reference of making decisions on patient treatment options and prognosis. This work is largely done manually by pathologist based on an examination of whole slide image (WSI), which is arduous and heavily dependent on doctors’ experience. In the World Health Organization (WHO) criteria, grade of glioma is closely related to hypercellularity, nuclear atypia and necrosis. Inspired by this, this paper designed and extracted cell density and atypia features to classify LGG and HGG. First, regions of interest (ROI) were located by analyzing cell density and global density features were extracted as well. Second, local density and atypia features were extracted in ROI. Third, balanced support vector machine (SVM) classifier was trained and tested using 10 selected features. The area under the curve (AUC) and accuracy (ACC) of 5-fold cross validation were 0.92 ± 0.01 and 0.82 ± 0.01 respectively. The results demonstrate that the proposed method of locating ROI is effective and the designed features of density and atypia can be used to predict glioma grade accurately, which can provide reliable basis for clinical diagnosis.
ObjectiveTo explore the relationship between glycated hemoglobin (HbA1c) level and blood glucose fluctuations after coronary artery bypass grafting (CABG) and adverse events in non-diabetic patients, thus providing theoretical support for intensive preoperative blood glucose management in patients undergoing CABG surgery.MethodsA total of 304 patients undergoing CABG with or without valvular surgery from October 2013 to December 2017 were enrolled in this prospective, single-center, observational cohort study. We classified them into two different groups which were a low-level group and a high-level group according to the HbA1c level. There were 102 males and 37 females, aged 36–85 (61.5±9.5) years in the low-level group, and 118 males and 47 females aged 34–85 (63.1±9.4) years in the high-level group. The main results were different in hospital mortality and perioperative complications including in-hospital death, myocardial infarction, sternal incision infection, new stroke, new-onset renal failure and multiple organ failure. To assess the effects of confounding factors, multivariate logistic regression analysis was used.Results Postoperative blood glucose fluctuation was more pronounced in the high-level group than that in the low-level group before admission [0.8 (0.6, 1.2) mmol/L vs. 1.0 (0.8, 1.8) mmol/L, P<0.01]. This study also suggested that the incidence of major adverse events was significantly lower in the low-level group compared with the high-level group (P=0.001). Multivariate logistic regression analyses to correct the influence of other confounding factors showed that HbA1c (OR=2.773, P=0.002) and postoperative blood glucose fluctuations (OR=3.091, P<0.001) could still predict the occurrence of postoperative adverse events.ConclusionHbA1c on admission can effectively predict blood glucose fluctuations in 24 hours after surgery. Secondly, HbA1c on admission and postoperative blood glucose fluctuations can further predict postoperative adverse events. It is suggested that we control the patient's preoperative HbA1c at a low level, which is beneficial to control postoperative blood glucose fluctuation and postoperative adverse events.