TY - GEN
T1 - Multi-channel volumetric neural network for knee cartilage segmentation in cone-beam CT
AU - Maier, Jennifer
AU - Rivera Monroy, Luis Carlos
AU - Syben, Christopher
AU - Jeon, Yejin
AU - Choi, Jang Hwan
AU - Hall, Mary Elizabeth
AU - Levenston, Marc
AU - Gold, Garry
AU - Fahrig, Rebecca
AU - Maier, Andreas
N1 - Funding Information:
Acknowledgement. This work was supported by the Research Training Group 1773 Heterogeneous Image Systems, funded by the German Research Foundation (DFG). Further, the authors acknowledge funding support from NIH 5R01AR065248-03 and NIH Shared Instrument Grant No. S10 RR026714 supporting the zeego@StanfordLab.
Publisher Copyright:
© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020.
PY - 2020
Y1 - 2020
N2 - Analyzing knee cartilage thickness and strain under load can help to further the understanding of the effects of diseases like Osteoarthritis. A precise segmentation of the cartilage is a necessary prerequisite for this analysis. This segmentation task has mainly been addressed in Magnetic Resonance Imaging, and was rarely investigated on contrast-enhanced Computed Tomography, where contrast agent visualizes the border between femoral and tibial cartilage. To overcome the main drawback of manual segmentation, namely its high time investment, we propose to use a 3D Convolutional Neural Network for this task. The presented architecture consists of a V-Net with SeLu activation, and a Tversky loss function. Due to the high imbalance between very few cartilage pixels and many background pixels, a high false positive rate is to be expected. To reduce this rate, the two largest segmented point clouds are extracted using a connected component analysis, since they most likely represent the medial and lateral tibial cartilage surfaces. The resulting segmentations are compared to manual segmentations, and achieve on average a recall of 0.69, which confirms the feasibility of this approach.
AB - Analyzing knee cartilage thickness and strain under load can help to further the understanding of the effects of diseases like Osteoarthritis. A precise segmentation of the cartilage is a necessary prerequisite for this analysis. This segmentation task has mainly been addressed in Magnetic Resonance Imaging, and was rarely investigated on contrast-enhanced Computed Tomography, where contrast agent visualizes the border between femoral and tibial cartilage. To overcome the main drawback of manual segmentation, namely its high time investment, we propose to use a 3D Convolutional Neural Network for this task. The presented architecture consists of a V-Net with SeLu activation, and a Tversky loss function. Due to the high imbalance between very few cartilage pixels and many background pixels, a high false positive rate is to be expected. To reduce this rate, the two largest segmented point clouds are extracted using a connected component analysis, since they most likely represent the medial and lateral tibial cartilage surfaces. The resulting segmentations are compared to manual segmentations, and achieve on average a recall of 0.69, which confirms the feasibility of this approach.
UR - http://www.scopus.com/inward/record.url?scp=85083078146&partnerID=8YFLogxK
U2 - 10.1007/978-3-658-29267-6_14
DO - 10.1007/978-3-658-29267-6_14
M3 - Conference contribution
AN - SCOPUS:85083078146
SN - 9783658292669
T3 - Informatik aktuell
SP - 67
EP - 72
BT - Bildverarbeitung für die Medizin 2020 Algorithmen - Systeme - Anwendungen. Proceedings des Workshops
A2 - Tolxdorff, Thomas
A2 - Deserno, Thomas M.
A2 - Handels, Heinz
A2 - Maier, Andreas
A2 - Maier-Hein, Klaus H.
A2 - Palm, Christoph
PB - Springer
T2 - International workshop on Algorithmen - Systeme - Anwendungen, 2020
Y2 - 15 March 2020 through 17 March 2020
ER -