Exploit 18F-FDG enhanced urinary bladder in PET data for deep learning ground truth generation in CT scans

Christina Gsaxner; Birgit Pfarrkirchner; Lydia Lindner; Norbert Jakse; Jürgen Wallner; Dieter Schmalstieg; Jan Egger

doi:10.1117/12.2292706

Translator Disclaimer

12 March 2018 Exploit ¹⁸F-FDG enhanced urinary bladder in PET data for deep learning ground truth generation in CT scans

Christina Gsaxner, Birgit Pfarrkirchner, Lydia Lindner, Norbert Jakse, Jürgen Wallner, Dieter Schmalstieg, Jan Egger

Author Affiliations +

Proceedings Volume 10578, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging; 105781Z (2018) https://doi.org/10.1117/12.2292706
Event: SPIE Medical Imaging, 2018, Houston, Texas, United States

Abstract

Accurate segmentation of medical images is a key step in medical image processing. As the amount of medical images obtained in diagnostics, clinical studies and treatment planning increases, automatic segmentation algorithms become increasingly more important. Therefore, we plan to develop an automatic segmentation approach for the urinary bladder in computed tomography (CT) images using deep learning. For training such a neural network, a large amount of labeled training data is needed. However, public data sets of medical images with segmented ground truth are scarce. We overcome this problem by generating binary masks of images of the ¹⁸F-FDG enhanced urinary bladder obtained from a multi-modal scanner delivering registered CT and positron emission tomography (PET) image pairs. Since PET images offer good contrast, a simple thresholding algorithm suffices for segmentation. We apply data augmentation to these datasets to increase the amount of available training data. In this contribution, we present algorithms developed with the medical image processing and visualization platform MeVisLab to achieve our goals. With the proposed methods, accurate segmentation masks of the urinary bladder could be generated, and given datasets could be enlarged by a factor of up to 2500.

Citation Download Citation

Christina Gsaxner, Birgit Pfarrkirchner, Lydia Lindner, Norbert Jakse, Jürgen Wallner, Dieter Schmalstieg, and Jan Egger "Exploit ¹⁸F-FDG enhanced urinary bladder in PET data for deep learning ground truth generation in CT scans", Proc. SPIE 10578, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging, 105781Z (12 March 2018); https://doi.org/10.1117/12.2292706

ACCESS THE FULL ARTICLE