Abstract
We present a fully convolutional neural network (ConvNet), named RatLesNetv2, for segmenting lesions in rodent magnetic resonance (MR) brain images. RatLesNetv2 architecture resembles an autoencoder and it incorporates residual blocks that facilitate its optimization. RatLesNetv2 is trained end to end on three-dimensional images and it requires no preprocessing. We evaluated RatLesNetv2 on an exceptionally large dataset composed of 916 T2-weighted rat brain MRI scans of 671 rats at nine different lesion stages that were used to study focal cerebral ischemia for drug development. In addition, we compared its performance with three other ConvNets specifically designed for medical image segmentation. RatLesNetv2 obtained similar to higher Dice coefficient values than the other ConvNets and it produced much more realistic and compact segmentations with notably fewer holes and lower Hausdorff distance. The Dice scores of RatLesNetv2 segmentations also exceeded inter-rater agreement of manual segmentations. In conclusion, RatLesNetv2 could be used for automated lesion segmentation, reducing human workload and improving reproducibility. RatLesNetv2 is publicly available at https://github.com/jmlipman/RatLesNetv2.
Highlights
Rodents frequently serve as models for human brain diseases
We extend our earlier conference paper (Valverde et al, 2019) by (1) improving our previous convolutional neural network (ConvNet) (Valverde et al, 2019) with a deeper and different architecture and providing an ablation study (Meyes et al, 2019) justifying certain architectural choices; (2) evaluating the generalization capability of our model on a considerably larger and more heterogeneous data set via Dice coefficient, compactness and Hausdorff distance under different training settings; and (3) making RatLesNetv2 publicly available
We showed that RatLesNetv2 yielded similar or better Dice coefficients and Hausdorff distances, and notably more compact segmentations than other convolutional neural networks (Çiçek et al, 2016; Chen et al, 2018a; Valverde et al, 2019)
Summary
Rodents frequently serve as models for human brain diseases. They account for more than 80% of the animals used in research in recent years (Dutta and Sengupta, 2016). In addition to basic research, rodent models are important in, for example, drug discovery and the development of new treatments. In vivo imaging of rodents is used for monitoring disease progression and therapeutic response in longitudinal studies. Magnetic resonance imaging (MRI) is essential in pre-clinical studies for conducting quantitative analyses due to its non-invasiveness and versatility. The quantification of brain lesions requires segmenting the lesions, and the lack of reliable tools to automate rodent brain lesion segmentation forces researchers to segment these images manually
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
