Generation of Annotated Brain Tumor MRIs with Tumor-induced Tissue Deformations for Training and Assessment of Neural Networks

Hristina Uzunova, Jan Ehrhardt, Heinz Handels

In: Anne L. Martel , Purang Abolmaesumi , Danail Stoyanov , Diana Mateus , Maria A. Zuluaga , S. Kevin Zhou , Daniel Racoceanu , Leo Joskowicz (Hrsg.). Medical Image Computing and Computer Assisted Intervention -- MICCAI 2020. Medical Image Computing and Computer Assisted Intervention (MICCAI-2020) October 4-8 Lima/Virtual Peru Seiten 501-511 ISBN 978-3-030-59719-1 Springer International Publishing 2020.


Machine learning methods heavily rely on the availability of large annotated datasets of a certain domain for training. However, freely available datasets of patients with pathologies rarely contain annotations of normal structures, thus cannot be used as ground truth for various image processing methods. To overcome this issue, we propose a topology preserving unpaired domain translation method, including an explicit pathology integration to generate annotated ground truth data of pathological domains. Moreover, we integrate a novel inverse probabilistic approach to generate deformations of the surrounding caused by pathological tissue. Our experiments show the necessity for annotated pathological data for algorithm evaluation. Furthermore, when training neural networks on healthy data and testing on real pathological images, the results are strongly impaired. By generating training data with pathologies using the proposed method, the performance of segmentation and registration methods increases significantly. The best results are achieved by also integrating pathology-induced tissue deformations.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence