Abstract #2728

Brain Segmentation in Rodent MR-Images Using Convolutional Neural Networks

Björn Sigurðsson¹, Sune Darkner², Stefan Sommer², Kristian Nygaard Mortensen¹, Simon Sanggaard³, Serhii Kostrikov⁴, and Maiken Nedergaard^1,5

¹Center for translational neuromedicine, University of Copenhagen, Copenhagen, Denmark, ²Department of Computer Science, University of Copenhagen, Copenhagen, Denmark, ³Department of Anesthesiology, Yale School of Medicine, New Haven, CT, United States, ⁴Institut for Mikro- og Nanoteknologi, Technical University of Denmark, Kgs. Lyngby, Denmark, ⁵Department of Neurosurgery, University of Rochester, Rochester, NY, United States

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.

This abstract and the presentation materials are available to members only; a login is required.

Join Here