Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks
Files
Self archived version
final draftDate
2019Author(s)
Unique identifier
10.1007/978-3-030-32692-0_23Metadata
Show full item recordMore information
Self-archived item
Citation
Valverde, JM. Shatillo, A. De Feo, R. Gröhn, O. Sierra, A. Tohka, J. (2019). Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks. Machine Learning in Medical Imaging. MLMI 2019, 11861, 195-202. 10.1007/978-3-030-32692-0_23.Rights
Abstract
Manual segmentation of rodent brain lesions from magnetic resonance images (MRIs) is an arduous, time-consuming and subjective task that is highly important in pre-clinical research. Several automatic methods have been developed for different human brain MRI segmentation, but little research has targeted automatic rodent lesion segmentation. The existing tools for performing automatic lesion segmentation in rodents are constrained by strict assumptions about the data. Deep learning has been successfully used for medical image segmentation. However, there has not been any deep learning approach specifically designed for tackling rodent brain lesion segmentation. In this work, we propose a novel Fully Convolutional Network (FCN), RatLesNet, for the aforementioned task. Our dataset consists of 131 T2-weighted rat brain scans from 4 different studies in which ischemic stroke was induced by transient middle cerebral artery occlusion. We compare our method with two other 3D FCNs originally developed for anatomical segmentation (VoxResNet and 3D-U-Net) with 5-fold cross-validation on a single study and a generalization test, where the training was done on a single study and testing on three remaining studies. The labels generated by our method were quantitatively and qualitatively better than the predictions of the compared methods. The average Dice coefficient achieved in the 5-fold cross-validation experiment with the proposed approach was 0.88, between 3.7% and 38% higher than the compared architectures. The presented architecture also outperformed the other FCNs at generalizing on different studies, achieving the average Dice coefficient of 0.79.
Keywords
Link to the original item
http://dx.doi.org/10.1007/978-3-030-32692-0_23Publisher
Springer International PublishingCollections
- Terveystieteiden tiedekunta [1793]