Evaluating severity of white matter lesions from computed tomography images with convolutional neural network
- PDF / 957,373 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 7 Downloads / 239 Views
DIAGNOSTIC NEURORADIOLOGY
Evaluating severity of white matter lesions from computed tomography images with convolutional neural network Johanna Pitkänen 1 & Juha Koikkalainen 2 & Tuomas Nieminen 2 & Ivan Marinkovic 1 & Sami Curtze 1 & Gerli Sibolt 1 & Hanna Jokinen 1,3 & Daniel Rueckert 4 & Frederik Barkhof 5,6,7 & Reinhold Schmidt 8 & Leonardo Pantoni 9 & Philip Scheltens 10 & Lars-Olof Wahlund 11 & Antti Korvenoja 12 & Jyrki Lötjönen 2 & Timo Erkinjuntti 1 & Susanna Melkas 1 Received: 6 November 2019 / Accepted: 24 March 2020 # The Author(s) 2020
Abstract Purpose Severity of white matter lesion (WML) is typically evaluated on magnetic resonance images (MRI), yet the more accessible, faster, and less expensive method is computed tomography (CT). Our objective was to study whether WML can be automatically segmented from CT images using a convolutional neural network (CNN). The second aim was to compare CT segmentation with MRI segmentation. Methods The brain images from the Helsinki University Hospital clinical image archive were systematically screened to make CT-MRI image pairs. Selection criteria for the study were that both CT and MRI images were acquired within 6 weeks. In total, 147 image pairs were included. We used CNN to segment WML from CT images. Training and testing of CNN for CT was performed using 10-fold cross-validation, and the segmentation results were compared with the corresponding segmentations from MRI. Results A Pearson correlation of 0.94 was obtained between the automatic WML volumes of MRI and CT segmentations. The average Dice similarity index validating the overlap between CT and FLAIR segmentations was 0.68 for the Fazekas 3 group. Conclusion CNN-based segmentation of CT images may provide a means to evaluate the severity of WML and establish a link between CT WML patterns and the current standard MRI-based visual rating scale. Keywords Cerebral small vessel disease . Convolutional neural network . Computed tomography . Machine learning . White matter lesions
* Johanna Pitkänen [email protected]
7
NIHR Biomedical Research Centre at University College London Hospitals NHS Foundation Trust and University College London, London, England, UK
1
Department of Neurology, University of Helsinki and Helsinki University Hospital, PO Box 302, 00029 HUS Helsinki, Finland
8
Department of Neurology, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, Netherlands
2
Combinostics Ltd., Tampere, Finland and VTT Technical Research Centre of Finland, Tampere, Finland
9
L. Sacco Department of Biomedical and Clinical Sciences, University of Milan, Milan, Italy
10
Alzheimer Center and Department of Neurology, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, Netherlands
3
Department of Psychology and Logopedics, Faculty of Medicine, University of Helsinki, Helsinki, Finland
4
Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, UK
5
Department of Radiology and Nuclear Medicine, Neuroscience Campus Amster
Data Loading...
