There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
Principal Investigator | |
Principal Investigator's Name: | guo hao |
Institution: | Jiamusi University |
Department: | School of Information Electronic Technology |
Country: | |
Proposed Analysis: | Hippocampus segmentation algorithm based on convolutional Neural Network and Multi-view Integration (CNN+BDC-LSTM). First, convolutional neural network was used to segment 2D slice sequences from coronal, sagittal and cross sections, and then the segmentation results from the three views were integrated to obtain the final result. The convolutional neural network is composed of coding part, BI-directional CONVOLUtional LONG and short memory network (BDC-LSTM) and decoding part. In order to obtain multi-scale information and enlarge the receptive field of the convolution layer, asymmetric convolution layer and empty convolution of different sizes are used in the coding part. In addition, BCC-LSTM is used between the encoding and decoding parts to fully mine the relevant information between slice sequences in a single view, thus improving the segmentation accuracy. |
Additional Investigators |