Background: Accurate glioma grading before surgery is of the utmost importance in treatment planning and prognosis prediction. But previous studies on magnetic resonance imaging (MRI) images were not effective enough. According to the remarkable performance of convolutional neural network (CNN) in medical domain, we hypothesized that a deep learning algorithm can achieve high accuracy in distinguishing the World Health Organization (WHO) low grade and high grade gliomas.Methods: One hundred and thirteen glioma patients were retrospectively included. Tumor images were segmented with a rectangular region of interest (ROI), which contained about 80% of the tumor. Then, 20% data were randomly selected and leaved out at patient-level as test dataset. AlexNet and GoogLeNet were both trained from scratch and fine-tuned from models that pre-trained on the large scale natural image database, ImageNet, to magnetic resonance images. The classification task was evaluated with five-fold cross-validation (CV) on patient-level split.Results: The performance measures, including validation accuracy, test accuracy and test area under curve (AUC), averaged from five-fold CV of GoogLeNet which trained from scratch were 0.867, 0.909, and 0.939, respectively. With transfer learning and fine-tuning, better performances were obtained for both AlexNet and GoogLeNet, especially for AlexNet. Meanwhile, GoogLeNet performed better than AlexNet no matter trained from scratch or learned from pre-trained model.Conclusion: In conclusion, we demonstrated that the application of CNN, especially trained with transfer learning and fine-tuning, to preoperative glioma grading improves the performance, compared with either the performance of traditional machine learning method based on hand-crafted features, or even the CNNs trained from scratch.
Super-resolution three-dimensional (3D) optical microscopy has incomparable advantages over other high-resolution microscopic technologies, such as electron microscopy and atomic force microscopy, in the study of biological molecules, pathways and events in live cells and tissues. We present a novel approach of structured illumination microscopy (SIM) by using a digital micromirror device (DMD) for fringe projection and a low-coherence LED light for illumination. The lateral resolution of 90 nm and the optical sectioning depth of 120 μm were achieved. The maximum acquisition speed for 3D imaging in the optical sectioning mode was 1.6×107 pixels/second, which was mainly limited by the sensitivity and speed of the CCD camera. In contrast to other SIM techniques, the DMD-based LED-illumination SIM is cost-effective, ease of multi-wavelength switchable and speckle-noise-free. The 2D super-resolution and 3D optical sectioning modalities can be easily switched and applied to either fluorescent or non-fluorescent specimens.
Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.
Exposure of Lead (Pb), a known neurotoxicant, can impair spatial learning and memory probably via impairing the hippocampal long-term potentiation (LTP) as well as hippocampal neuronal injury. Activation of hippocampal microglia also impairs spatial learning and memory. Thus, we raised the hypothesis that activation of microglia is involved in the Pb exposure induced hippocampal LTP impairment and neuronal injury. To test this hypothesis and clarify its underlying mechanisms, we investigated the Pb-exposure on the microglia activation, cytokine release, hippocampal LTP level as well as neuronal injury in in vivo or in vitro model. The changes of these parameters were also observed after pretreatment with minocycline, a microglia activation inhibitor. Long-term low dose Pb exposure (100 ppm for 8 weeks) caused significant reduction of LTP in acute slice preparations, meanwhile, such treatment also significantly increased hippocampal microglia activation as well as neuronal injury. In vitro Pb-exposure also induced significantly increase of microglia activation, up-regulate the release of cytokines including tumor necrosis factor-alpha (TNF-α), interleukin-1β (IL-1β) and inducible nitric oxide synthase (iNOS) in microglia culture alone as well as neuronal injury in the co-culture with hippocampal neurons. Inhibiting the microglia activation with minocycline significantly reversed the above-mentioned Pb-exposure induced changes. Our results showed that Pb can cause microglia activation, which can up-regulate the level of IL-1β, TNF-α and iNOS, these proinflammatory factors may cause hippocampal neuronal injury as well as LTP deficits.
Neuropathic pain (NP) is an intractable clinical problem without satisfactory treatments. However, certain natural products have been revealed as effective therapeutic agents for the management of pain states. In this study, we used the spinal nerve ligation (SNL) pain model to investigate the antinociceptive effect of triptolide (T10), a major active component of the traditional Chinese herb Tripterygium wilfordii Hook F. Intrathecal T10 inhibited the mechanical nociceptive response induced by SNL without interfering with motor performance. Additionally, the anti-nociceptive effect of T10 was associated with the inhibition of the activation of spinal astrocytes. Furthermore, intrathecal administration of T10 attenuated SNL-induced janus kinase (JAK) signal transducers and activators of transcription 3 (STAT3) signalling pathway activation and inhibited the upregulation of proinflammatory cytokines, such as interleukin-6, interleukin-1 beta, and tumour necrosis factor-α, in dorsal horn astrocytes. Moreover, NR2B-containing spinal N-methyl D-aspartate receptor (NMDAR) was subsequently inhibited. Above all, T10 can alleviate SNL-induced NP via inhibiting the neuroinflammation in the spinal dorsal horn. The anti-inflammation effect of T10 may be related with the suppression of spinal astrocytic JAK-STAT3 activation. Our results suggest that T10 may be a promising drug for the treatment of NP.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.