Deep learning based imaging data completion for improved brain disease diagnosis.

Conference Paper

Combining multi-modality brain data for disease diagnosis commonly leads to improved performance. A challenge in using multimodality data is that the data are commonly incomplete; namely, some modality might be missing for some subjects. In this work, we proposed a deep learning based framework for estimating multi-modality imaging data. Our method takes the form of convolutional neural networks, where the input and output are two volumetric modalities. The network contains a large number of trainable parameters that capture the relationship between input and output modalities. When trained on subjects with all modalities, the network can estimate the output modality given the input modality. We evaluated our method on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, where the input and output modalities are MRI and PET images, respectively. Results showed that our method significantly outperformed prior methods.

Full Text

Duke Authors

Cited Authors

  • Li, R; Zhang, W; Suk, H-I; Wang, L; Li, J; Shen, D; Ji, S

Published Date

  • 2014

Published In

  • Med Image Comput Comput Assist Interv

Volume / Issue

  • 17 / Pt 3

Start / End Page

  • 305 - 312

PubMed ID

  • 25320813

Pubmed Central ID

  • PMC4464771

Digital Object Identifier (DOI)

  • 10.1007/978-3-319-10443-0_39

Conference Location

  • Germany