Shallow fully-connected neural networks for ischemic stroke-lesion segmentation in MRI

Christian Lucas, Oskar Maier, Mattias P. Heinrich


Automatic image segmentation of stroke lesions could be of great importance for aiding the treatment decision. Convolutional neural networks obtain high accuracy for this task at the cost of prohibitive computational demand for time-sensitive clinical scenarios. In this work, we study the use of classical fully-connected neural networks (FC-NN) based on hand-crafted features, which achieve much shorter runtimes. We show that recent advances in optimization and regularization of deep learning can be successfully transferred to FC-NNs to improve the training process and achieve comparable accuracy to random decision forests.
Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2017
EditorsK.H. Maier-Hein, T.M. Deserno, H. Handels, T. Tolxdorff
Number of pages6
PublisherSpringer Vieweg, Berlin Heidelberg
Publication date01.03.2017
ISBN (Print)978-3-662-54344-3
ISBN (Electronic)978-3-662-54345-0
Publication statusPublished - 01.03.2017
EventBildverarbeitung für die Medizin 2017
- Heidelberg, Germany
Duration: 12.03.201714.03.2017


Dive into the research topics of 'Shallow fully-connected neural networks for ischemic stroke-lesion segmentation in MRI'. Together they form a unique fingerprint.

Cite this