Automated segmentation of mucosal change in rhinosinusitis patients

Rhinosinusitis is a sinonasal disease affecting 16% of the population. Volumetric segmentation can provide objective data that is useful when determining stage and therapeutic response. An automated volumetric segmentation method was developed and tested. Four patients underwent baseline and follow-up CT scans. For each patient, five sections were outlined by two otolaryngologists and the automated method. The median Dice coefficient between otolaryngologists was 0.74. The otolaryngologist and automated segmentations demonstrated acceptable agreement with a median Dice coefficient of 0.61. This automated method represents the first step in the creation of a computerized system for the quantitative 3D analysis of rhinosinusitis.

[1]  Ralph Metson,et al.  The Health Impact of Chronic Sinusitis in Patients Seeking Otolaryngologic Care , 1995 .

[2]  David R. Haynor,et al.  PET-CT image registration in the chest using free-form deformations , 2003, IEEE Transactions on Medical Imaging.

[3]  M. Stewart,et al.  Evidence-based medicine in rhinology , 2008, Current opinion in otolaryngology & head and neck surgery.

[4]  V. Lund,et al.  The Lund-Mackay staging system for chronic rhinosinusitis: How is it used and what does it predict? , 2007, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[5]  N. Jones,et al.  CT of the paranasal sinuses: a review of the correlation with clinical, surgical and histopathological findings. , 2002, Clinical otolaryngology and allied sciences.

[6]  Michael A Kaliner,et al.  The diagnosis and management of sinusitis: a practice parameter update. , 2005, The Journal of allergy and clinical immunology.

[7]  J D Osguthorpe,et al.  Adult rhinosinusitis: diagnosis and management. , 2001, American family physician.

[8]  D. Kennedy,et al.  Staging for Rhinosinusitis , 1997, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[9]  S.G. Armato,et al.  A general method for the identification and repair of concavities in segmented medical images , 2008, 2008 IEEE Nuclear Science Symposium Conference Record.