Yi Fan1,2, Richard Beare3,4, Harold Matthews2,5, Paul Schneider1, Nicky Kilpatrick2,5, John Clement1,2,6, Peter Claes2,7,8, Anthony Penington2,5, Christopher Adamson3. 1. 1 Department of Dentistry, The University of Melbourne , Melbourne, VIC , Australia. 2. 2 Facial Sciences , Murdoch Children's Research Institute, VIC , Australia. 3. 3 Developmental Imaging, Murdoch Children's Research Institute , Melbourne, VIC , Australia. 4. 4 Department of Medicine, Monash University , Melbourne, VIC , Australia. 5. 5 Department of Paediatrics, The University of Melbourne, The Royal Children's Hospital , Melbourne, VIC , Australia. 6. 6 Cranfield Forensic Insititute, Cranfield University , England , UK. 7. 7 Department of Electrical Engineering, KU Leuven , Leuven , Belgium. 8. 8 Medical Imaging Research Center , Leuven , Belgium.
Abstract
OBJECTIVES: : To propose a reliable and practical method for automatically segmenting the mandible from CBCT images. METHODS: : The marker-based watershed transform is a region-growing approach that dilates or "floods" predefined markers onto a height map whose ridges denote object boundaries. We applied this method to segment the mandible from the rest of the CBCT image. The height map was generated to enhance the sharp decreases of intensity at the mandible/tissue border and suppress noise by computing the intensity gradient image of the CBCT itself. Two sets of markers, "mandible" and "background" were automatically placed inside and outside the mandible, respectively in a novel image using image registration. The watershed transform flooded the gradient image by dilating the markers simultaneously until colliding at watershed lines, estimating the mandible boundary. CBCT images of 20 adolescent subjects were chosen as test cases. Segmentation accuracy of the proposed method was evaluated by measuring overlap (Dice similarity coefficient) and boundary agreement against a well-accepted interactive segmentation method described in the literature. RESULTS: : The Dice similarity coefficient was 0.97 ± 0.01 (mean ± SD), indicating almost complete overlap between the automatically and the interactively segmented mandibles. Boundary deviations were predominantly under 1 mm for most of the mandibular surfaces. The errors were mostly from bones around partially erupted wisdom teeth, the condyles and the dental enamels, which had minimal impact on the overall morphology of the mandible. CONCLUSIONS: : The marker-based watershed transform method produces segmentation accuracy comparable to the well-accepted interactive segmentation approach.
OBJECTIVES: : To propose a reliable and practical method for automatically segmenting the mandible from CBCT images. METHODS: : The marker-based watershed transform is a region-growing approach that dilates or "floods" predefined markers onto a height map whose ridges denote object boundaries. We applied this method to segment the mandible from the rest of the CBCT image. The height map was generated to enhance the sharp decreases of intensity at the mandible/tissue border and suppress noise by computing the intensity gradient image of the CBCT itself. Two sets of markers, "mandible" and "background" were automatically placed inside and outside the mandible, respectively in a novel image using image registration. The watershed transform flooded the gradient image by dilating the markers simultaneously until colliding at watershed lines, estimating the mandible boundary. CBCT images of 20 adolescent subjects were chosen as test cases. Segmentation accuracy of the proposed method was evaluated by measuring overlap (Dice similarity coefficient) and boundary agreement against a well-accepted interactive segmentation method described in the literature. RESULTS: : The Dice similarity coefficient was 0.97 ± 0.01 (mean ± SD), indicating almost complete overlap between the automatically and the interactively segmented mandibles. Boundary deviations were predominantly under 1 mm for most of the mandibular surfaces. The errors were mostly from bones around partially erupted wisdom teeth, the condyles and the dental enamels, which had minimal impact on the overall morphology of the mandible. CONCLUSIONS: : The marker-based watershed transform method produces segmentation accuracy comparable to the well-accepted interactive segmentation approach.
Authors: Yi Fan; Anthony Penington; Nicky Kilpatrick; Rita Hardiman; Paul Schneider; John Clement; Peter Claes; Harold Matthews Journal: J Anat Date: 2019-03-04 Impact factor: 2.610
Authors: B J van Leeuwen; P U Dijkstra; J A Dieters; H P J Verbeek; A M Kuijpers-Jagtman; Y Ren Journal: Clin Oral Investig Date: 2022-05-05 Impact factor: 3.606
Authors: Bingjiang Qiu; Hylke van der Wel; Joep Kraeima; Haye Hendrik Glas; Jiapan Guo; Ronald J H Borra; Max Johannes Hendrikus Witjes; Peter M A van Ooijen Journal: J Pers Med Date: 2021-05-01
Authors: Yi Fan; Paul Schneider; Harold Matthews; Wilbur Eugene Roberts; Tianmin Xu; Robert Wei; Peter Claes; John Clement; Nicky Kilpatrick; Anthony Penington Journal: BMC Oral Health Date: 2020-04-16 Impact factor: 2.757