1
|
Kwon T, Choi DI, Hwang J, Lee T, Lee I, Cho S. Panoramic dental tomosynthesis imaging by use of CBCT projection data. Sci Rep 2023; 13:8817. [PMID: 37258603 DOI: 10.1038/s41598-023-35805-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Accepted: 05/24/2023] [Indexed: 06/02/2023] Open
Abstract
Dental CBCT and panoramic images are important imaging modalities used in dental diagnosis and treatment planning. In order to acquire a panoramic image without an additional panoramic scan, in this study, we proposed a method of reconstructing a panoramic image by extracting panoramic projection data from dental CBCT projection data. After specifying the patient's dental arch from the patient's CBCT image, panoramic projection data are extracted from the CBCT projection data along the appropriate panoramic scan trajectory that fits the dental arch. A total of 40 clinical human datasets and one head phantom dataset were used to test the proposed method. The clinical human dataset used in this study includes cases in which it is difficult to reconstruct panoramic images from CBCT images, such as data with severe metal artifacts or data without teeth. As a result of applying the panoramic image reconstruction method proposed in this study, we were able to successfully acquire panoramic images from the CBCT projection data of various patients. The proposed method acquires a universally applicable panoramic image that is less affected by CBCT image quality and metal artifacts by extracting panoramic projection data from dental CBCT data and reconstructing a panoramic image.
Collapse
Affiliation(s)
- Taejin Kwon
- Department of Nuclear and Quantum Engineering (NQE), Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea
| | - Da-In Choi
- Department of Nuclear and Quantum Engineering (NQE), Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea
| | - Jaehong Hwang
- Department of Nuclear and Quantum Engineering (NQE), Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea
| | - Taewon Lee
- Department of Nuclear and Quantum Engineering (NQE), Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea
| | - Inje Lee
- Department of ICT, Dentium Co., Ltd., Suwon, Korea
| | - Seungryong Cho
- Department of Nuclear and Quantum Engineering (NQE), Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea.
- KAIST Institutes for ITC and HST, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Korea.
| |
Collapse
|
2
|
Bilgir E, Bayrakdar İŞ, Çelik Ö, Orhan K, Akkoca F, Sağlam H, Odabaş A, Aslan AF, Ozcetin C, Kıllı M, Rozylo-Kalinowska I. An artifıcial ıntelligence approach to automatic tooth detection and numbering in panoramic radiographs. BMC Med Imaging 2021; 21:124. [PMID: 34388975 PMCID: PMC8361658 DOI: 10.1186/s12880-021-00656-7] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2020] [Accepted: 06/30/2021] [Indexed: 11/18/2022] Open
Abstract
Background Panoramic radiography is an imaging method for displaying maxillary and mandibular teeth together with their supporting structures. Panoramic radiography is frequently used in dental imaging due to its relatively low radiation dose, short imaging time, and low burden to the patient. We verified the diagnostic performance of an artificial intelligence (AI) system based on a deep convolutional neural network method to detect and number teeth on panoramic radiographs. Methods The data set included 2482 anonymized panoramic radiographs from adults from the archive of Eskisehir Osmangazi University, Faculty of Dentistry, Department of Oral and Maxillofacial Radiology. A Faster R-CNN Inception v2 model was used to develop an AI algorithm (CranioCatch, Eskisehir, Turkey) to automatically detect and number teeth on panoramic radiographs. Human observation and AI methods were compared on a test data set consisting of 249 panoramic radiographs. True positive, false positive, and false negative rates were calculated for each quadrant of the jaws. The sensitivity, precision, and F-measure values were estimated using a confusion matrix. Results The total numbers of true positive, false positive, and false negative results were 6940, 250, and 320 for all quadrants, respectively. Consequently, the estimated sensitivity, precision, and F-measure were 0.9559, 0.9652, and 0.9606, respectively. Conclusions The deep convolutional neural network system was successful in detecting and numbering teeth. Clinicians can use AI systems to detect and number teeth on panoramic radiographs, which may eventually replace evaluation by human observers and support decision making.
Collapse
Affiliation(s)
- Elif Bilgir
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskişehir, Turkey
| | - İbrahim Şevki Bayrakdar
- Center of Research and Application for Computer Aided Diagnosis and Treatment in Health, Eskisehir Osmangazi University, Eskisehir, Turkey
| | - Özer Çelik
- Center of Research and Application for Computer Aided Diagnosis and Treatment in Health, Eskisehir Osmangazi University, Eskisehir, Turkey
| | - Kaan Orhan
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara, Turkey
| | - Fatma Akkoca
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskişehir, Turkey
| | - Hande Sağlam
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskişehir, Turkey
| | - Alper Odabaş
- Department of Mathematics-Computer, Faculty of Science, Eskisehir Osmangazi University, Eskisehir, Turkey
| | - Ahmet Faruk Aslan
- Department of Mathematics-Computer, Faculty of Science, Eskisehir Osmangazi University, Eskisehir, Turkey
| | | | - Musa Kıllı
- Faculty of Dentistry, Eskisehir Osmangazi University, Eskişehir, Turkey
| | - Ingrid Rozylo-Kalinowska
- Department of Dental and Maxillofacial Radiodiagnostics, Medical University of Lublin, ul. Doktora Witolda Chodźki 6, 20-093, Lublin, Poland.
| |
Collapse
|
3
|
Svenson B, Båth M, Karlsson R, Persson B. A comparison of perceived diagnostic image quality in direct digital panoramic images between standard and advanced external GOP image processing. Acta Odontol Scand 2019; 77:560-565. [PMID: 31146623 DOI: 10.1080/00016357.2019.1618912] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
Abstract
Objective: The objective of the present study was to study the effect of adaptive image processing (GOP processing) on the visibility of anatomical structures in direct digital panoramic images. Material and methods: The study comprised panoramic images of 50 consecutive adult individuals aged 18-60 years. Nine dentists working with dental radiology compared the structural image quality of all standard-processed and GOP-processed panoramic images for six anatomical structures, using a six-point scale for visual grading characteristics analysis. Results: For all anatomic structures a statistically significant difference in favour of the GOP was found. Conclusions: The present study shows that it is possible to improve perceived diagnostic image quality of direct digital panoramic radiography using GOP technology compared to the manufacturers' standard processing. Manufacturers' image-processing programs can be further developed, as there is a possibility of improving the perceived diagnostic content of an image with external processing.
Collapse
Affiliation(s)
- Björn Svenson
- Department of Dental Research, Postgraduate Dental Education Center, Örebro, Sweden
- School of Health and Medical Sciences, Örebro University, Örebro, Sweden
| | - Magnus Båth
- Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, Gothenburg, Sweden
- Department of Radiation Physics, Institute of Clinical Sciences at Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Reet Karlsson
- Department of Radiology, Skaraborg Hospital Skövde, Skövde, Sweden
| | - Bo Persson
- Department of Radiology, Skaraborg Hospital Skövde, Skövde, Sweden
| |
Collapse
|
4
|
Kim S, Ra JB. Dynamic focal plane estimation for dental panoramic radiography. Med Phys 2019; 46:4907-4917. [PMID: 31520417 DOI: 10.1002/mp.13823] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2019] [Revised: 09/02/2019] [Accepted: 09/03/2019] [Indexed: 11/10/2022] Open
Abstract
PURPOSE The digital panoramic radiography is widely used in dental clinics and provides the anatomical information of the intraoral structure along the predefined arc-shaped path. Since the intraoral structure varies depending on the patient, however, it is nearly impossible to design a common and static focal path or plane fitted to the dentition of all patients. In response, we introduce an imaging algorithm for digital panoramic radiography that can provide a focused panoramic radiographic image for all patients, by automatically estimating the best focal plane for each patient. METHODS The aim of this study is to improve the image quality of dental panoramic radiography based on a three-dimensional (3D) dynamic focal plane. The plane is newly introduced to represent the arbitrary 3D intraoral structure of each patient. The proposed algorithm consists of three steps: preprocessing, focal plane estimation, and image reconstruction. We first perform preprocessing to improve the accuracy of focal plane estimation. The 3D dynamic focal plane is then estimated by adjusting the position of the image plane so that object boundaries in the neighboring projection data are aligned or focused on the plane. Finally, a panoramic radiographic image is reconstructed using the estimated dynamic focal plane. RESULTS The proposed algorithm is evaluated using a numerical phantom dataset and four clinical human datasets. In order to examine the image quality improvement owing to the proposed algorithm, we generate panoramic radiographic images based on a conventional static focal plane and estimated 3D dynamic focal planes, respectively. Experimental results show that the image quality is dramatically improved for all datasets using the 3D dynamic focal planes that are estimated from the proposed algorithm. CONCLUSIONS We propose an imaging algorithm for digital panoramic radiography that provides improved image quality by estimating dynamic focal planes fitted to each individual patient's intraoral structure.
Collapse
Affiliation(s)
- Seungeon Kim
- School of Electrical Engineering, KAIST, Daejeon, Republic of Korea
| | - Jong Beom Ra
- School of Electrical Engineering, KAIST, Daejeon, Republic of Korea
| |
Collapse
|
5
|
Suryani IR, Villegas NS, Shujaat S, De Grauwe A, Azhari A, Sitam S, Jacobs R. Image quality assessment of pre-processed and post-processed digital panoramic radiographs in paediatric patients with mixed dentition. Imaging Sci Dent 2019; 48:261-268. [PMID: 30607350 PMCID: PMC6305780 DOI: 10.5624/isd.2018.48.4.261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2018] [Revised: 08/31/2018] [Accepted: 09/23/2018] [Indexed: 12/01/2022] Open
Abstract
Purpose To determine the impact of an image processing technique on diagnostic accuracy of digital panoramic radiographs for the assessment of anatomical structures in paediatric patients with mixed dentition. Materials and Methods The study consisted of 50 digital panoramic radiographs of children aged from 6 to 12 years, which were later on processed using a dedicated image processing method. A modified clinical image quality evaluation chart was used to evaluate the diagnostic accuracy of anatomical structures in maxillary and mandibular anterior and maxillary premolar region of processed images. Results A statistically significant difference was observed between pre and post-processed evaluation of anatomical structures (P<0.05) in the maxillary and mandibular anterior region. The anterior region was found to be more accurate in post-processed images. No significant difference was observed in the maxillary premolar region (P>0.05). The Inter-observer and intra-observer reliability of both pre and post processed images were excellent (>0.82) for anterior region and good (>0.63) for premolar region. Conclusion The application of image processing technique in digital panoramic radiography can be considered a reliable method for improving the quality of anatomical structures in paediatric patients with mixed dentition.
Collapse
Affiliation(s)
- Isti Rahayu Suryani
- Department of Dentomaxillofacial Radiology, Universitas Gadjah Mada, Yogyakarta, Indonesia
| | - Natalia Salvo Villegas
- Department of Oral and Maxillofacial Radiology, Universidad de Los Andes, Santiago, Chile
| | - Sohaib Shujaat
- OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven and Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium
| | - Annelore De Grauwe
- OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven and Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium
| | - Azhari Azhari
- Department of Dental Radiology, University of Padjajaran, Bandung, Indonesia
| | - Suhardjo Sitam
- Department of Dental Radiology, University of Padjajaran, Bandung, Indonesia
| | - Reinhilde Jacobs
- OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven and Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium.,Division of Oral Diagnostics and Rehabilitation, Department of Dental Medicine, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
6
|
Yasar F, Yesilova E, Apaydın B. The effects of compression on the image quality of digital panoramic radiographs. Clin Oral Investig 2011; 16:719-26. [PMID: 21732088 DOI: 10.1007/s00784-011-0587-y] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2011] [Accepted: 06/22/2011] [Indexed: 10/18/2022]
Abstract
Size reduction through compression is an important issue that needs to be investigated for possible effects on image quality. The aim of the present study was to evaluate the subjective image quality of digital panoramic radiographs which were lossless and lossy compressed for the visualization of various anatomical structures. Fifty-five digital panoramic radiographs in Tagged Image File Format (Tiff) were used in the study. Two types of lossy (Joint Photographic Experts Group (Jpeg)) and one type of lossless (Lempel-Ziv-Welch) compression were applied to the original radiographs. These radiographs were evaluated by two observers separately for the visibility of some anatomical structures with visual grading. Mean quality number for each radiograph was obtained. The differences between the mean quality numbers in each compression and original image mode were evaluated with Friedman test. Pair-wise comparisons revealed that there were statistically significant differences between all groups (p = 0.000) for all comparisons except for Jpeg_1 and Jpeg_2 groups. Kappa statistics was used to evaluate inter- and intra-observer agreements. Intra-observer agreements were ranging from 0.229 to 1.000 and inter-observer agreements were ranging from 0.154 to 1.000. The observers had better inter- and intra-observer agreements in highly compressed Jpeg_1 images. The anatomical structures evaluated in this study had better visibility in Tiff images than Jpeg images except for mandibular canal and mental foramen. While Jpeg compressed images offer high inter- and intra-observer agreements, the visibility of anatomical structures are better in Tiff images except for mandibular canal and mental foramen.
Collapse
Affiliation(s)
- Füsun Yasar
- Maxillofacial Radiology Department, Dentistry Faculty, Selcuk University, Kampüs, Konya 42079, Turkey.
| | | | | |
Collapse
|
7
|
Baksi BG, Alpöz E, Sogur E, Mert A. Perception of anatomical structures in digitally filtered and conventional panoramic radiographs: a clinical evaluation. Dentomaxillofac Radiol 2010; 39:424-30. [PMID: 20841460 DOI: 10.1259/dmfr/30570374] [Citation(s) in RCA: 24] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
OBJECTIVES The aims of the study were to compare subjective image quality of clinical images obtained with a storage phosphor plate (SPP)-based digital and conventional film-based panoramic system for the visualization of various anatomical structures and to evaluate the effect of various processing algorithms on image interpretation. METHODS Panoramic radiographs were taken in 42 patients both with film and with a SPP system. SPP images were treated with shadow, sharpen, negative, greyscale sigma and greyscale exponential filters. Four observers subjectively evaluated films and unfiltered and filtered SPP images for the visibility of anatomical structures with various radiodensities as well as for overall image quality on a three-point rating scale. The statistical methods used were Kruskal-Wallis, odds ratio analysis and Cohen's kappa. RESULTS No statistically significant difference was found between film and unfiltered digital images except for low-contrast structures (P > 0.05). Film images were preferred for the visibility of low-contrast structures (P < 0.05). Best overall image quality was obtained with sharpened images (P < 0.05) followed by films and unfiltered digital images. Among all filtered images, sharpened ones received the highest ratings for the visibility of all anatomical structures (P < 0.05). The intra- and interobserver agreement ranged between moderate and substantial and between fair and moderate, respectively. CONCLUSIONS Film and unfiltered SPP-based panoramic images performed equally well in terms of overall quality; however, films were best for the perception of low-contrast structures. The sharpening filter may be recommended for enhancing SPP panoramic images to improve the visual perception of most of the anatomical structures as well as overall quality.
Collapse
Affiliation(s)
- B G Baksi
- Department of Oral Diagnosis & Radiology, School of Dentistry, Ege University, Turkey
| | | | | | | |
Collapse
|
8
|
Modern dental imaging: a review of the current technology and clinical applications in dental practice. Eur Radiol 2010; 20:2637-55. [PMID: 20544352 DOI: 10.1007/s00330-010-1836-1] [Citation(s) in RCA: 106] [Impact Index Per Article: 7.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2010] [Revised: 04/15/2010] [Accepted: 04/29/2010] [Indexed: 02/02/2023]
Abstract
A review of modern imaging techniques commonly used in dental practice and their clinical applications is presented. The current dental examinations consist of intraoral imaging with digital indirect and direct receptors, while extraoral imaging is divided into traditional tomographic/panoramic imaging and the more recently introduced cone beam computed tomography. Applications, limitations and current trends of these dental "in-office" radiographic techniques are discussed.
Collapse
|
9
|
Angelopoulos C, Thomas SL, Thomas S, Hechler S, Hechler S, Parissis N, Hlavacek M. Comparison between digital panoramic radiography and cone-beam computed tomography for the identification of the mandibular canal as part of presurgical dental implant assessment. J Oral Maxillofac Surg 2008; 66:2130-5. [PMID: 18848113 DOI: 10.1016/j.joms.2008.06.021] [Citation(s) in RCA: 124] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2006] [Revised: 03/07/2007] [Accepted: 06/17/2008] [Indexed: 11/28/2022]
Abstract
PURPOSE A variety of imaging modalities (eg, panoramic radiography, tomography, or computed tomography [CT]) were compared for their efficiency in the identification of the mandibular canal. The recently introduced cone-beam computed tomography (CBCT) seems to be a promising imaging modality which also reduces patient exposure considerably, compared with ordinary CT. The literature includes no studies comparing its performance in such delicate tasks as mandibular-canal identification with other traditionally used imaging modalities. The goal of this study was to compare CBCT reformatted panoramic images and digital panoramic images for the identification of the mandibular canal as part of preimplant assessment. MATERIALS AND METHODS Panoramic images, generated by 3 different imaging modalities used for general maxillofacial diagnosis and preimplant assessment, were compared: CBCT reformatted panoramic images (I-CAT; Imaging Sciences, Hatfield, PA), direct (charge-coupled device-based) panoramic radiographs (DIMAX; Planmeca, Helsinki, Finland), and digital panoramic radiographs based on a storage phosphor system (DENOPTIX; Gendex, Chicago, IL). We used 3 independent groups of images (40 in each group) from patients examined by one of the above imaging modalities over a period of 6 months. In total, 68 randomly selected mandibular canals (out of a possible 80) per imaging modality were evaluated. Four experienced raters evaluated the images of each modality in 3 sessions under standardized conditions for clarity in the visualization of the mandibular canal in 3 locations, using a 4-point scale. RESULTS The CBCT reformatted panoramic images outperformed the digital panoramic images in the identification of the mandibular canal. CONCLUSIONS Due to the fact that the CBCT images were reformatted slices of the maxilla and mandible, they were free of magnification, superimposition of neighboring structures, and other problems inherent to panoramic radiology. This may result in very clear images that better depict the mandibular canal.
Collapse
Affiliation(s)
- Christos Angelopoulos
- Division of Oral and Maxillofacial Radiology, College of Dental Medicine, Columbia University, New York, NY 10032, USA.
| | | | | | | | | | | | | |
Collapse
|