Search

Background Long noncoding RNAs play influential roles in the progression of many types of human malignancies. The present study aimed to explore the prognostic value of long noncoding RNA FTX (FTX) on patients with glioma. Methods FTX expression in glioma specimens and matched adjacent non‐neoplasm specimens was examined by a quantitative real‐time polymerase chain reaction assay. Furthermore, assays of the relationships between FTX expression and clinicopathologic characteristics of patients with glioma were also performed. Kaplan–Meier methods were applied for the assays of the overall survival (OS) and progression‐free survival (PFS) of patients and Cox regression assays were used to analyze the clinical value of FTX used as a possible biomarker. Results FTX levels were significantly up‐regulated in glioma specimens compared to the paired non‐neoplasm specimens (p < 0.01). Furthermore, high FTX expression in neoplasm tissues was dramatically associated with World Health Organization grade (p = 0.001) and Karnofsky Performance Score (p = 0.009). Kaplan–Meier assays with 187 patients revealed that patients with high level of FTX expression displayed poorer OS (p = 0.002) and PFS (p = 0.000). Subsequently, multivariable Cox regression analysis identified FTX expression as an independent prognostic factor of unfavorable survivals in glioma (OS: p = 0.001; PFS: p = 0.002). Conclusions These findings indicated that FTX may be a novel predictor for prognostic assessment of glioma patients. However, studies conducted with larger numbers of patients are essential to confirm our findings.

Classification of brain tumor is one of the most vital tasks within medical image processing. Classification of images greatly depends on the features extracted from the image, and thus, feature extraction plays a great role in the correct classification of images. In this paper, an enhanced method is presented for glioma MR images classification using hybrid statistical and wavelet features. In the proposed method, 52 features are extracted using the first-order and second-order statistical features (based on the four MRI modalities: Flair, T1, T1c, and T2) in addition to the discrete wavelet transform producing a total of 152 features. The extracted features are applied to the multilayer perceptron (MLP) classifier. The results using the MLP were compared with various known classifiers. The method was tested on the dataset MICCAI BraTS 2015 which is a standard dataset used for research purposes. The proposed hybrid statistical and wavelet features produced 96.72% accuracy for high-grade glioma and 96.04% accuracy for low-grade glioma, which are relatively better compared to the existing studies.