This study compares two different methods for the task of brain segmentation in rodent MR-images, a convolutional neural network (CNN) and majority voting of a registration based atlas (RBA) , and how limited training data affect their performance. The CNN was implemented in Tensorflow. The RBA performs better on average when using a training set with fewer than 20 images but the CNN achieves a higher median dice-score with a training set of 19 images.
|Publication status||Published - 2018|
|Event||Joint Annual Meeting ISMRM-ESMRMB 2018 - Paris Expo Porte de Versailles, Paris, France|
Duration: 16 Jun 2018 → 21 Jun 2018
|Conference||Joint Annual Meeting ISMRM-ESMRMB 2018|
|Location||Paris Expo Porte de Versailles|
|Period||16/06/2018 → 21/06/2018|