Surface smoothness: cartilage biomarkers for knee OA beyond the radiologist

Sudhakar Tummala, Erik B. Dam

1 Citation (Scopus)

Abstract

Fully automatic imaging biomarkers may allow quantification of patho-physiological processes that a radiologist would not be able to assess reliably. This can introduce new insight but is problematic to validate due to lack of meaningful ground truth expert measurements. Rather than quantification accuracy, such novel markers must therefore be validated against clinically meaningful end-goals such as the ability to allow correct diagnosis. We present a method for automatic cartilage surface smoothness quantification in the knee joint. The quantification is based on a curvature flow method used on tibial and femoral cartilage compartments resulting from an automatic segmentation scheme. These smoothness estimates are validated for their ability to diagnose osteoarthritis and compared to smoothness estimates based on manual expert segmentations and to conventional cartilage volume quantification. We demonstrate that the fully automatic markers eliminate the time required for radiologist annotations, and in addition provide a diagnostic marker superior to the evaluated semi-manual markers.
Original languageEnglish
Title of host publicationMedical Imaging 2010 : image processing
EditorsBenoit M. Dawant, David R. Haynor
Number of pages8
PublisherSPIE - International Society for Optical Engineering
Publication date2010
Article number762323
ISBN (Print)9780819480248
DOIs
Publication statusPublished - 2010
EventMedical Imaging 2010: image processing - San Diego, United States
Duration: 14 Feb 201016 Feb 2010

Conference

ConferenceMedical Imaging 2010
Country/TerritoryUnited States
CitySan Diego
Period14/02/201016/02/2010
SeriesProgress in Biomedical Optics and Imaging
Number33
Volume11
ISSN1605-7422

Fingerprint

Dive into the research topics of 'Surface smoothness: cartilage biomarkers for knee OA beyond the radiologist'. Together they form a unique fingerprint.

Cite this