Narrow Results

China’s 2018 Future Science Prize winners announced.

China tops world in alcohol-related deaths.

Nanotech to inhibit wheat sprouting.

New antibacterial hydrogel for wound healing.

Genetically modified Zika virus vaccine to treat brain tumour.

Semi-elastic nanoparticles to deliver drugs.

Chinese stent for heart disease reported safe in European patients.

First China-developed drug for colorectal cancer approved in China.

More medicines added to the national list of essential medicines.

Recent revisions in Chinese regulations open new doors for contract research organisations.

The following topics are under this section:

• Repurposing of Waste
• Brain Tumours: Identifying Patients for Targeted Therapy
• Metabolic Imaging

Invasive grade III and IV malignant gliomas remain difficult to treat with a typical survival time post-diagnosis hovering around 16 months with only minor extension thereof seen in the past decade, whereas some improvements have been obtained towards five-year survival rates for which completeness of resection is a prerequisite. Optical techniques such as fluorescence guided resection (FGR) and photodynamic therapy (PDT) are promising adjuvant techniques to increase the tumor volume reduction fraction. PDT has been used in combination with surgical resection or alternatively as standalone treatment strategy with some success in extending the median survival time of patients compared to surgery alone and the current standard of care. This document reviews the outcome of past clinical trials and highlights the general shift in PDT therapeutic approaches. It also looks at the current approaches for interstitial PDT and research options into increasing PDT's glioma treatment efficacy through exploiting both physical and biological-based approaches to maximize PDT selectivity and therapeutic index, particularly in brain adjacent to tumor (BAT). Potential reasons for failing to demonstrate a significant survival advantage in prior PDT clinical trials will become evident in light of the improved understanding of glioma biology and PDT dosimetry.

It is time-consuming and error-prone to manually determine whether there is a brain tumour in an image. However, traditional automatic classification algorithms have certain limitations, which makes the automation of brain tumour classification still a challenging problem. In this article, a new method for the automatic classification of brain tumours is proposed, combining neural network models with transfer learning methods to improve or solve the problem of slow iteration and long time-consuming model generation, improve accuracy, and reduce parameters. In short, the convolutional neural network model (CNN) is combined with the method of transfer learning to achieve automatic image classification on the Brain Tumour Detection 2020 dataset provided by Model Whale. More specifically, during the experiment, Tensorflow was selected as the deep learning framework. First, the transfer learning method was used, and imagenet weights were used. Then, the Comparing model performance by changing the choice of the backbone network of the CNN. Select the accuracy rate as the evaluation index, compare the performance of the model, use binary cross-entropy as the loss function, and the optimizer uses adam. In this paper, three backbone networks, VGG, MobileNet and ResNet, are compared. Experimental results indicate that the automatic classification of brain tumours with the combination of the CNN model and transfer learning method has better performance and the VGG model has the best performance.