4 January 2021 in BioMed Research International
Diabetic retinopathy is one of the main causes of blindness in human eyes, and lesion segmentation is an important basic work for the diagnosis of diabetic retinopathy. Due to the small lesion areas scattered in fundus images, it is laborious to segment the lesion of diabetic retinopathy effectively with the existing U‐Net model. In this paper, we proposed a new lesion segmentation model named FFU‐Net (Feature Fusion U‐Net) that enhances U‐Net from the following points. Firstly, the pooling layer in the network is replaced with a convolutional layer to reduce spatial loss of the fundus image. Then, we integrate multiscale feature fusion (MSFF) block into the encoders which helps the network to learn multiscale features efficiently and enrich the information carried with skip connection and lower‐resolution decoder by fusing contextual channel attention (CCA) models. Finally, in order to solve the problems of data imbalance and misclassification, we present a Balanced Focal Loss function. In the experiments on benchmark dataset IDRID, we make an ablation study to verify the effectiveness of each component and compare FFU‐Net against several state‐of‐the‐art models. In comparison with baseline U‐Net, FFU‐Net improves the segmentation performance by 11.97%, 10.68%, and 5.79% on metrics SEN, IOU, and DICE, respectively. The quantitative and qualitative results demonstrate the superiority of our FFU‐Net in the task of lesion segmentation of diabetic retinopathy.
5 January 2022 in Frontiers in Integrative Neuroscience
Glioblastoma multiforme (GBM) is the most malignant and multiple tumors of the central nervous system. The survival rate for GBM patients is less than 15 months. We aimed to uncover the potential mechanism of GBM in tumor microenvironment and provide several candidate biomarkers for GBM prognosis. In this study, ESTIMATE analysis was used to divide the GBM patients into high and low immune or stromal score groups. Microenvironment associated genes were filtered through differential analysis. Weighted gene co-expression network analysis (WGCNA) was performed to correlate the genes and clinical traits. The candidate genes’ functions were annotated by enrichment analyses. The potential prognostic biomarkers were assessed by survival analysis. We obtained 81 immune associated differentially expressed genes (DEGs) for subsequent WGCNA analysis. Ten out of these DEGs were significantly associated with targeted molecular therapy of GBM patients. Three genes (S100A4, FCGR2B, and BIRC3) out of these genes were associated with overall survival and the independent test set testified the result. Here, we obtained three crucial genes that had good prognostic efficacy of GBM and may help to improve the prognostic prediction of GBM.