Projects

Molecular typing prediction and clinical application evaluation of glioma based on multi-source heterogeneous information
This project proposes a research project based on real clinical data and analyzes multimodal brain MRI images and Pathological images through fusion of deep learning techniques. WHO classification and molecular markers of glioma can be obtained before operation by exploring the imaging appearance of gene mutations so that the most reasonable diagnosis and treatment program was aided to formulate.
Multimodal brain MRI image analysis
This project puts forward a research plan of brain tumour characteristics based on large sample real clinical data, constructs an integrated hybrid deep learning neural network, realizes automatic recognition and classification of multimodal brain tumour images, improves the practical level of relevant research, improves the efficiency and accuracy of medical image diagnosis, and diagnoses brain tumors. Discontinuation and treatment provide technical support.
Research on CAD system for skin diseases
In this project, convolutional neural network is used to recognize the most common skin diseases in China based on clinical images, and a complete set of assistant diagnosis system for skin diseases is proposed.
Air Quality Estimation Based on Visibility Detection
This project proposes a research plan based on visual air quality, aiming at developing corresponding algorithms, extracting visibility and other feature information from image data, and estimating the relationship between image feature information and urban air quality by means of machine learning. Compared with the existing urban air quality monitoring methods, the approach proposed in this project has many advantages, such as simple and intuitive estimation results, large observation range, abundant data space-time information, low layout cost, easy to use in large quantities and so on. It is expected to become an important supplement to the existing air quality monitoring methods.
tunnel shotcreting robot
This project puts forward the R&D and industrialization planning of intelligent shotcreting robot. It is planned to upgrade the existing products through intelligent transformation and the construction of Internet of Things platform, so as to reduce the technical requirements of the equipment to the operator and improve the maintenance efficiency of the equipment