Deep learning based automatic liver tumor segmentation in CT with shape-based post-processing

Grzegorz Chlebus, Andrea Schenk, Jan Hendrik Moltz, Bram van Ginneken, Horst Karl Hahn, Hans Meine

Abstract: Accurate automatic liver tumor segmentation would have a big impact on liver therapy planning procedures and follow-up reporting, thanks to automation, standardization and incorporation of full volumetric information. In this work, we propose a fully automatic method for liver tumor segmentation in CT images based on a 2D convolutional deep neural network with a shape-based post-processing. We ran our experiments on the LiTS dataset and evaluated detection and segmentation performance. Our proposed method achieves segmentation quality for detected lesions comparable to a human expert and is able to detect 77% of potentially measurable tumor lesions according to the RECIST 1.1 guidelines. We submitted our results to the LiTS challenge achieving state-of-the-art performance.

Keywords: liver, tumor, segmentation, CT, deep learning, convolutional neural network

Author Affiliation: Fraunhofer MEVIS, Radboud University Medical Center, Jacobs University, University of Bremen