Accurate Automated Volumetry of Cartilage of the Knee using Convolutional Neural Networks: Data from the Osteoarthritis Initiative

accepted for publication
  • Volumetry of cartilage of the knee is needed for knee osteoarthritis (KOA) assessment. It is typically performed manually in a tedious and subjective process. We developed a method for an automated, segmentation-based quantification of cartilage volume by employing 3D Convolutional Neural Networks (CNNs). CNNs were trained in a supervised manner using magnetic resonance imaging data and cartilage volumetry readings performed by clinical experts for 1378 subjects provided by the Osteoarthritis Initiative. It was shown that 3D CNNs are able to achieve volume measures comparable to the magnitude of variation between expert readings and the real in vivo situation. In the future, accurate automated cartilage volumetry might support both, diagnosis of KOA as well as longitudinal analysis of KOA progression.
Metadaten
Author:Alexander Tack, Stefan ZachowORCiD
Document Type:In Proceedings
Parent Title (German):IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
Year of first publication:2018
Preprint:urn:nbn:de:0297-zib-71439