Deep learning to assess bone quality from panoramic radiographs: the feasibility of clinical application through comparison with an implant surgeon and cone-beam computed tomography
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: Bone quality is one of the most important clinical factors for the primary stability and successful osseointegration of dental implants. This preliminary pilot study aimed to evaluate the clinical applicability of deep learning (DL) for assessing bone quality using panoramic (PA) radiographs compared with an implant surgeon’s subjective tactile sense and cone-beam computed tomography (CBCT) values. Methods: In total, PA images of 2,270 edentulous sites for implant placement were selected, and the corresponding CBCT relative gray value measurements and bone quality classification were performed using 3-dimensional dental image analysis software. Based on the pre-trained and fine-tuned ResNet-50 architecture, the bone quality classification of PA images was classified into 4 levels, from D1 to D4, and Spearman correlation analyses were performed with the implant surgeon’s tactile sense and CBCT values. Results: The classification accuracy of DL was evaluated using a test dataset comprising 454 cropped PA images, and it achieved an area under the receiving characteristic curve of 0.762 (95% confidence interval [CI], 0.714–0.810). Spearman correlation analysis of bone quality showed significant positive correlations with the CBCT classification (r=0.702; 95% CI, 0.651–0.747; P<0.001) and the surgeon’s tactile sense (r=0.658; 95% CI, 0.600–0.708, P<0.001) versus the DL classification. Conclusions: DL classification using PA images showed a significant and consistent correlation with CBCT classification and the surgeon’s tactile sense in classifying the bone quality at the implant placement site. Further research based on high-quality quantitative datasets is essential to increase the reliability and validity of this method for actual clinical applications.
Abstract
Purpose: Bone quality is one of the most important clinical factors for the primary stability and successful osseointegration of dental implants. This preliminary pilot study aimed to evaluate the clinical applicability of deep learning (DL) for assessing bone quality using panoramic (PA) radiographs compared with an implant surgeon’s subjective tactile sense and cone-beam computed tomography (CBCT) values. Methods: In total, PA images of 2,270 edentulous sites for implant placement were selected, and the corresponding CBCT relative gray value measurements and bone quality classification were performed using 3-dimensional dental image analysis software. Based on the pre-trained and fine-tuned ResNet-50 architecture, the bone quality classification of PA images was classified into 4 levels, from D1 to D4, and Spearman correlation analyses were performed with the implant surgeon’s tactile sense and CBCT values. Results: The classification accuracy of DL was evaluated using a test dataset comprising 454 cropped PA images, and it achieved an area under the receiving characteristic curve of 0.762 (95% confidence interval [CI], 0.714–0.810). Spearman correlation analysis of bone quality showed significant positive correlations with the CBCT classification (r=0.702; 95% CI, 0.651–0.747; P<0.001) and the surgeon’s tactile sense (r=0.658; 95% CI, 0.600–0.708, P<0.001) versus the DL classification. Conclusions: DL classification using PA images showed a significant and consistent correlation with CBCT classification and the surgeon’s tactile sense in classifying the bone quality at the implant placement site. Further research based on high-quality quantitative datasets is essential to increase the reliability and validity of this method for actual clinical applications.
참고문헌 (40)
- Quirynen M, "Implant therapy : 40 years of experience", Periodontol 2000, 66, pp.7~12 (2014)
- Lee JH, "Incidence and pattern of implant fractures : a long-term follow-up multicenter study", Clin Implant Dent Relat Res, 20, pp.463~469 (2018)
- Howe MS, "Long-term(10-year)dental implant survival : a systematic review and sensitivity meta-analysis", J Dent, 84, pp.9~21 (2019)
- Park YS, "Evaluation of failed implants and reimplantation at sites of previous dental implant failure : survival rates and risk factors", J Periodontal Implant Sci, 52, pp.230~241 (2022)
- Chrcanovic BR, "Bone quality and quantity and dental implant failure : a systematic review and meta-analysis", Int J Prosthodont, 30, pp.219~237 (2017)
- Shapurian T, "Quantitative evaluation of bone density using the Hounsfield index", Int J Oral Maxillofac Implants, 21, pp.290~297 (2006)
- De Vos W, "Cone-beam computerized tomography(CBCT)imaging of the oral and maxillofacial region : a systematic review of the literature", Int J Oral Maxillofac Implants, 38, pp.609~625 (2009)
- Fokas G, "Accuracy of linear measurements on CBCT images related to presurgical implant treatment planning : a systematic review", Clin Oral Implants Res, 29(Suppl 16), pp.393~415 (2018)
- Naitoh M, "Evaluation of voxel values in mandibular cancellous bone : relationship between cone-beam computed tomography and multislice helical computed tomography", Clin Oral Implants Res, 20, pp.503~506 (2009)
- Pauwels R, "Variability of dental cone beam CT grey values for density estimations", Br J Radiol, 86, pp.20120135~ (2013)
- Shen D, "Deep learning in medical image analysis", Annu Rev Biomed Eng, 19, pp.221~248 (2017)
- Lee JH, "Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm", J Periodontal Implant Sci, 48, pp.114~123 (2018)
- Lee JH, "Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm", J Dent, 77, pp.106~111 (2018)
- Lee JH, "Diagnosis of cystic lesions using panoramic and cone beam computed tomographic images based on deep learning neural network", Oral Dis, 26, pp.152~158 (2020)
- Mohammad-Rahimi H, "Deep learning in periodontology and oral implantology : A scoping review", J Periodontal Res, 57, pp.942~951 (2022)
- Lee JH, "Deep learning improves implant classification by dental professionals : a multi-center evaluation of accuracy and efficiency", J Periodontal Implant Sci, 52, pp.220~229 (2022)
- Lee DW, "Artificial intelligence in fractured dental implant detection and classification : evaluation using dataset from two dental hospitals", Diagnostics(Basel), 11, pp.233~ (2021)
- Yong TH, "QCBCT-NET for direct measurement of bone mineral density from quantitative cone-beam CT : a human skull phantom study", Sci Rep, 11, pp.15083~ (2021)
- Huang N, "Predicting the risk of dental implant loss using deep learning", J Clin Periodontol, 49, pp.872~883 (2022)
- de Oliveira RC, "Assessments of trabecular bone density at implant sites on CT images", Oral Surg Oral Med Oral Pathol Oral Radiol Endod, 105, pp.231~238 (2008)
- Misch CE, "Contemporary implant dentistry" (1999), Mosby
- Jeong KI, "Consideration of various bone quality evaluation methods", Implant Dent, 22, pp.55~59 (2013)
- He K, "Deep residual learning for image recognition", Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770~778 (2016), IEEE
- Park W, "Identification of dental implant systems using a large-scale multicenter data set", J Dent Res, 102, pp.727~733 (2023)
- Friberg B, "Early failures in 4, 641 consecutively placed Brånemark dental implants : a study from stage 1 surgery to the connection of completed prostheses", Int J Oral Maxillofac Implants, 6, pp.142~146 (1991)
- Lekholm U, "Osseointegration in clinical dentistry", pp.199~209 (1985), Quintessence Publishing Company
- Pauwels R, "CBCT-based bone quality assessment : are Hounsfield units applicable?", Dentomaxillofac Radiol, 44, pp.20140238~ (2015)
- Akdeniz BG, "Evaluation of bone height and bone density by computed tomography and panoramic radiography for implant recipient sites", J Oral Implantol, 26, pp.114~119 (2000)
- Taguchi A, "Trabecular bone pattern of the mandible. Comparison of panoramic radiography with computed tomography", Dentomaxillofac Radiol, 26, pp.85~89 (1997)
- Guerrero ME, "Does cone-beam CT alter treatment plans? Comparison of preoperative implant planning using panoramic versus cone-beam CT images", Imaging Sci Dent, 44, pp.121~128 (2014)
- Rokn A, "Tactile sense of the surgeon in determining bone density when placing dental implant", Implant Dent, 23, pp.697~703 (2014)
- Lee S, "Bone density assessments of dental implant sites : 3. Bone quality evaluation during osteotomy and implant placement", Int J Oral Maxillofac Implants, 22, pp.208~212 (2007)
- Rushton VE, "The quality of panoramic radiographs in a sample of general dental practices", Br Dent J, 186, pp.630~633 (1999)
- Dhillon M, "Positioning errors and quality assessment in panoramic radiography", Imaging Sci Dent, 42, pp.207~212 (2012)
- van der Stelt PF, "Panoramic radiographs in dental diagnostics", Ned Tijdschr Tandheelkd, 123, pp.181~187 (2016)
- Ridao-Sacie C, "Radiological assessment of periapical status using the periapical index : comparison of periapical radiography and digital panoramic radiography", Int Endod J, 40, pp.433~440 (2007)
- Lee JH, "Efficacy of deep convolutional neural network algorithm for the identification and classification of dental implant systems, using panoramic and periapical radiographs : a pilot study", Medicine(Baltimore), 99, pp.e20787~ (2020)
- Lee JH, "A performance comparison between automated deep learning and dental professionals in classification of dental implant systems from dental imaging : a multi-center study", Diagnostics(Basel), 10, pp.910~ (2020)
- Park W, "Automated deep learning for classification of dental implant radiographs using a large multi-center dataset", Sci Rep, 13, pp.4862~ (2023)
- Molly L, "Bone density and primary stability in implant therapy", Clin Oral Implants Res, 17(Suppl 2), pp.124~135 (2006)