Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks
Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2017-01-01
|
| Series: | NeuroImage: Clinical |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S221315821730147X |
| _version_ | 1811324792236670976 |
|---|---|
| author | Liang Chen Paul Bentley Daniel Rueckert |
| author_facet | Liang Chen Paul Bentley Daniel Rueckert |
| author_sort | Liang Chen |
| collection | DOAJ |
| description | Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs): one is an ensemble of two DeconvNets (Noh et al., 2015), which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net), which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94. Keywords: Acute ischemic lesion segmentation, DWI, Deep learning, Convolutional neural networks |
| first_indexed | 2024-04-13T14:21:40Z |
| format | Article |
| id | doaj.art-3b0ff02b710f4732983c616f08e821a8 |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-04-13T14:21:40Z |
| publishDate | 2017-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-3b0ff02b710f4732983c616f08e821a82022-12-22T02:43:26ZengElsevierNeuroImage: Clinical2213-15822017-01-0115633643Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networksLiang Chen0Paul Bentley1Daniel Rueckert2BioMedIA Group, Department of Computing, Imperial College London, 180 Queen's Gate, London SW7 2AZ, UK; Division of Brain Sciences, Department of Medicine, Imperial College London, Fulham Palace Road, London W6 8RF, UK; Corresponding author.Division of Brain Sciences, Department of Medicine, Imperial College London, Fulham Palace Road, London W6 8RF, UKBioMedIA Group, Department of Computing, Imperial College London, 180 Queen's Gate, London SW7 2AZ, UKStroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs): one is an ensemble of two DeconvNets (Noh et al., 2015), which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net), which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94. Keywords: Acute ischemic lesion segmentation, DWI, Deep learning, Convolutional neural networkshttp://www.sciencedirect.com/science/article/pii/S221315821730147X |
| spellingShingle | Liang Chen Paul Bentley Daniel Rueckert Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks NeuroImage: Clinical |
| title | Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks |
| title_full | Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks |
| title_fullStr | Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks |
| title_full_unstemmed | Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks |
| title_short | Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks |
| title_sort | fully automatic acute ischemic lesion segmentation in dwi using convolutional neural networks |
| url | http://www.sciencedirect.com/science/article/pii/S221315821730147X |
| work_keys_str_mv | AT liangchen fullyautomaticacuteischemiclesionsegmentationindwiusingconvolutionalneuralnetworks AT paulbentley fullyautomaticacuteischemiclesionsegmentationindwiusingconvolutionalneuralnetworks AT danielrueckert fullyautomaticacuteischemiclesionsegmentationindwiusingconvolutionalneuralnetworks |