Automatic segmentation of the nasal cavity and paranasal sinuses from cone-beam CT images

PurposeA patient-specific upper airway model is important for clinical, education, and research applications. Cone-beam computed tomography (CBCT) is used for imaging the upper airway but automatic segmentation is limited by noise and the complex anatomy. A multi-step level set segmentation scheme was developed for CBCT volumetric head scans to create a 3D model of the nasal cavity and paranasal sinuses.MethodsGaussian mixture model thresholding and morphological operators are first employed to automatically locate the region of interest and to initialize the active contour. Second, the active contour driven by the Kullback–Leibler (K–L) divergence energy in a level set framework to segment the upper airway. The K–L divergence asymmetry is used to directly minimize the K–L divergence energy on the probability density function of the image intensity. Finally, to refine the segmentation result, an anisotropic localized active contour is employed which defines the local area based on shape prior information. The method was tested on ten CBCT data sets. The results were evaluated by the Dice coefficient, the volumetric overlap error (VOE), precision, recall, and $$F$$F-score and compared with expert manual segmentation and existing methods.ResultsThe nasal cavity and paranasal sinuses were segmented in CBCT images with a median accuracy of 95.72 % [93.82–96.72 interquartile range] by Dice, 8.73 % [6.79–12.20] by VOE, 94.69 % [93.80–94.97] by precision, 97.73 % [92.70–98.79] by recall, and 95.72 % [93.82–96.69] by $$F$$F-score.ConclusionAutomated CBCT segmentation of the airway and paranasal sinuses was highly accurate in a test sample of clinical scans. The method may be useful in a variety of clinical, education, and research applications.

[1]  Ronald Fedkiw,et al.  Level set methods and dynamic implicit surfaces , 2002, Applied mathematical sciences.

[2]  Akitoshi Katsumata,et al.  Improved inspection of the lateral pharyngeal recess using cone-beam computed tomography in the upright position , 2008, Oral Radiology.

[3]  Reyes Enciso,et al.  Imaging software accuracy for 3-dimensional analysis of the upper airway. , 2012, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[4]  Michael H. F. Wilkinson,et al.  Efficient 2-D Grayscale Morphological Transformations With Arbitrary Flat Structuring Elements , 2008, IEEE Transactions on Image Processing.

[5]  T. Young,et al.  Epidemiology of obstructive sleep apnea: a population health perspective. , 2002, American journal of respiratory and critical care medicine.

[6]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[7]  H. Qin,et al.  Non-viral environmental risk factors for nasopharyngeal carcinoma: a systematic review. , 2012, Seminars in cancer biology.

[8]  R Jacobs,et al.  Comparison between effective radiation dose of CBCT and MSCT scanners for dentomaxillofacial applications. , 2009, European journal of radiology.

[9]  H. Bosmans,et al.  Effective dose range for dental cone beam computed tomography scanners. , 2012, European journal of radiology.

[10]  C Flores-Mir,et al.  Three-dimensional segmentation of the upper airway using cone beam CT: a systematic review. , 2012, Dento maxillo facial radiology.

[11]  Reyes Enciso,et al.  Evaluation of cross-section airway configuration of obstructive sleep apnea. , 2007, Oral surgery, oral medicine, oral pathology, oral radiology, and endodontics.

[12]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[13]  Allen R. Tannenbaum,et al.  Localizing Region-Based Active Contours , 2008, IEEE Transactions on Image Processing.

[14]  Mehmet Celenk,et al.  Upper airway detection and visualization from cone beam image slices. , 2010, Journal of X-ray science and technology.

[15]  Hongjian Shi,et al.  Upper airway segmentation and dimensions estimation from cone-beam CT image datasets , 2006, International Journal of Computer Assisted Radiology and Surgery.

[16]  E LorensenWilliam,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987 .

[17]  Yogesh Rathi,et al.  Image Segmentation Using Active Contours Driven by the Bhattacharyya Gradient Flow , 2007, IEEE Transactions on Image Processing.

[18]  Juan Martin Palomo,et al.  Measuring the airway in 3 dimensions: a reliability and accuracy study. , 2010, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[19]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[20]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[21]  A. Katsumata,et al.  Image artifact in dental cone-beam CT. , 2006, Oral surgery, oral medicine, oral pathology, oral radiology, and endodontics.

[22]  G. Swennen,et al.  Cone-beam computerized tomography imaging and analysis of the upper airway: a systematic review of the literature. , 2011, International journal of oral and maxillofacial surgery.

[23]  Philippe Poignet,et al.  Innovative endoscopic sino-nasal and anterior skull base robotics , 2013, International Journal of Computer Assisted Radiology and Surgery.

[24]  Richard Coles,et al.  Summary health statistics for U.S. adults: national health interview survey, 2012. , 2014, Vital and health statistics. Series 10, Data from the National Health Survey.

[25]  A. Basu,et al.  Airway Segmentation and Measurement in CT Images , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Koutaro Maki,et al.  Three-dimensional analysis of the airway with cone-beam computed tomography. , 2011, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.