Fernanda Nogueira-Reis1,2, Nermin Morgan2,3, Stefanos Nomidis4, Adriaan Van Gerven4, Nicolly Oliveira-Santos1,2, Reinhilde Jacobs5,6, Cinthia Pereira Machado Tabchoury7. 1. Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas (UNICAMP), Av. Limeira 901, Piracicaba, São Paulo, 13414‑903, Brazil. 2. OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, KU Leuven & Oral and Maxillofacial Surgery, University Hospitals Leuven, Kapucijnenvoer 33, 3000, Leuven, Belgium. 3. Department of Oral Medicine, Faculty of Dentistry, Mansoura University, Mansoura , 35516, Dakahlia, Egypt. 4. Relu BV, Kapeldreef 60, 3000, Louvain, Belgium. 5. OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, KU Leuven & Oral and Maxillofacial Surgery, University Hospitals Leuven, Kapucijnenvoer 33, 3000, Leuven, Belgium. reinhilde.jacobs@ki.se. 6. Department of Dental Medicine, Karolinska Institutet, Box 4064, 141 04, Huddinge, Stockholm, Sweden. reinhilde.jacobs@ki.se. 7. Department of Biosciences, Division of Biochemistry, Piracicaba Dental School, University of Campinas (UNICAMP), Av. Limeira 901, Piracicaba, São Paulo, 13414‑903, Brazil.
Abstract
OBJECTIVE: To qualitatively and quantitatively assess integrated segmentation of three convolutional neural network (CNN) models for the creation of a maxillary virtual patient (MVP) from cone-beam computed tomography (CBCT) images. MATERIALS AND METHODS: A dataset of 40 CBCT scans acquired with different scanning parameters was selected. Three previously validated individual CNN models were integrated to achieve a combined segmentation of maxillary complex, maxillary sinuses, and upper dentition. Two experts performed a qualitative assessment, scoring-integrated segmentations from 0 to 10 based on the number of required refinements. Furthermore, experts executed refinements, allowing performance comparison between integrated automated segmentation (AS) and refined segmentation (RS) models. Inter-observer consistency of the refinements and the time needed to create a full-resolution automatic segmentation were calculated. RESULTS: From the dataset, 85% scored 7-10, and 15% were within 3-6. The average time required for automated segmentation was 1.7 min. Performance metrics indicated an excellent overlap between automatic and refined segmentation with a dice similarity coefficient (DSC) of 99.3%. High inter-observer consistency of refinements was observed, with a 95% Hausdorff distance (HD) of 0.045 mm. CONCLUSION: The integrated CNN models proved to be fast, accurate, and consistent along with a strong interobserver consistency in creating the MVP. CLINICAL RELEVANCE: The automated segmentation of these structures simultaneously could act as a valuable tool in clinical orthodontics, implant rehabilitation, and any oral or maxillofacial surgical procedures, where visualization of MVP and its relationship with surrounding structures is a necessity for reaching an accurate diagnosis and patient-specific treatment planning.
OBJECTIVE: To qualitatively and quantitatively assess integrated segmentation of three convolutional neural network (CNN) models for the creation of a maxillary virtual patient (MVP) from cone-beam computed tomography (CBCT) images. MATERIALS AND METHODS: A dataset of 40 CBCT scans acquired with different scanning parameters was selected. Three previously validated individual CNN models were integrated to achieve a combined segmentation of maxillary complex, maxillary sinuses, and upper dentition. Two experts performed a qualitative assessment, scoring-integrated segmentations from 0 to 10 based on the number of required refinements. Furthermore, experts executed refinements, allowing performance comparison between integrated automated segmentation (AS) and refined segmentation (RS) models. Inter-observer consistency of the refinements and the time needed to create a full-resolution automatic segmentation were calculated. RESULTS: From the dataset, 85% scored 7-10, and 15% were within 3-6. The average time required for automated segmentation was 1.7 min. Performance metrics indicated an excellent overlap between automatic and refined segmentation with a dice similarity coefficient (DSC) of 99.3%. High inter-observer consistency of refinements was observed, with a 95% Hausdorff distance (HD) of 0.045 mm. CONCLUSION: The integrated CNN models proved to be fast, accurate, and consistent along with a strong interobserver consistency in creating the MVP. CLINICAL RELEVANCE: The automated segmentation of these structures simultaneously could act as a valuable tool in clinical orthodontics, implant rehabilitation, and any oral or maxillofacial surgical procedures, where visualization of MVP and its relationship with surrounding structures is a necessity for reaching an accurate diagnosis and patient-specific treatment planning.
Authors: Li Wang; Ken Chung Chen; Yaozong Gao; Feng Shi; Shu Liao; Gang Li; Steve G F Shen; Jin Yan; Philip K M Lee; Ben Chow; Nancy X Liu; James J Xia; Dinggang Shen Journal: Med Phys Date: 2014-04 Impact factor: 4.071
Authors: Pieter-Jan Verhelst; Andreas Smolders; Thomas Beznik; Jeroen Meewis; Arne Vandemeulebroucke; Eman Shaheen; Adriaan Van Gerven; Holger Willems; Constantinus Politis; Reinhilde Jacobs Journal: J Dent Date: 2021-08-20 Impact factor: 4.379