Enhancement of Perivascular Spaces Using Densely Connected Deep Convolutional Neural Network
| Autor: | Euijin Jung, Sang-Hyun Park, Xiaopeng Zong, Philip Chikontwe, Weili Lin, Dinggang Shen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
General Computer Science
Computer science Feature extraction Perivascular spaces 02 engineering and technology Convolutional neural network Article Convolution Image (mathematics) White matter 03 medical and health sciences 0302 clinical medicine deep convolutional neural network MRI enhancement 0202 electrical engineering electronic engineering information engineering medicine General Materials Science Perivascular space skip connections medicine.diagnostic_test business.industry Deep learning General Engineering Magnetic resonance imaging Pattern recognition Human brain medicine.anatomical_structure densely connected network 020201 artificial intelligence & image processing Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business lcsh:TK1-9971 030217 neurology & neurosurgery |
| Zdroj: | IEEE Access, Vol 7, Pp 18382-18391 (2019) |
| ISSN: | 2169-3536 |
| Popis: | Perivascular spaces (PVS) in the human brain are related to various brain diseases. However, it is difficult to quantify them due to their thin and blurry appearance. In this paper, we introduce a deep-learning-based method, which can enhance a magnetic resonance (MR) image to better visualize the PVS. To accurately predict the enhanced image, we propose a very deep 3D convolutional neural network that contains densely connected networks with skip connections. The proposed networks can utilize rich contextual information derived from low-level to high-level features and effectively alleviate the gradient vanishing problem caused by the deep layers. The proposed method is evaluated on 17 7T MR images by a twofold cross-validation. The experiments show that our proposed network is much more effective to enhance the PVS than the previous PVS enhancement methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|