1
|
Schneider L, Rischke R, Krois J, Krasowski A, Büttner M, Mohammad-Rahimi H, Chaurasia A, Pereira NS, Lee JH, Uribe SE, Shahab S, Koca-Ünsal RB, Ünsal G, Martinez-Beneyto Y, Brinz J, Tryfonos O, Schwendicke F. Federated vs Local vs Central Deep Learning of Tooth Segmentation on Panoramic Radiographs. J Dent 2023; 135:104556. [PMID: 37209769 DOI: 10.1016/j.jdent.2023.104556] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Revised: 05/16/2023] [Accepted: 05/17/2023] [Indexed: 05/22/2023] Open
Abstract
OBJECTIVE Federated Learning (FL) enables collaborative training of artificial intelligence (AI) models from multiple data sources without directly sharing data. Due to the large amount of sensitive data in dentistry, FL may be particularly relevant for oral and dental research and applications. This study, for the first time, employed FL for a dental task, automated tooth segmentation on panoramic radiographs. METHODS We employed a dataset of 4,177 panoramic radiographs collected from nine different centers (n = 143 to n = 1881 per center) across the globe and used FL to train a machine learning model for tooth segmentation. FL performance was compared against Local Learning (LL), i.e., training models on isolated data from each center (assuming data sharing not to be an option). Further, the performance gap to Central Learning (CL), i.e., training on centrally pooled data (based on data sharing agreements) was quantified. Generalizability of models was evaluated on a pooled test dataset from all centers. RESULTS For 8 out of 9 centers, FL outperformed LL with statistical significance (p<0.05); only the center providing the largest amount of data FL did not have such an advantage. For generalizability, FL outperformed LL across all centers. CL surpassed both FL and LL for performance and generalizability. CONCLUSION If data pooling (for CL) is not feasible, FL is shown to be a useful alternative to train performant and, more importantly, generalizable deep learning models in dentistry, where data protection barriers are high. CLINICAL SIGNIFICANCE This study proves the validity and utility of FL in the field of dentistry, which encourages researchers to adopt this method to improve the generalizability of dental AI models and ease their transition to the clinical environment.
Collapse
Affiliation(s)
- Lisa Schneider
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité - University Medicine Berlin, Berlin, Germany; ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland
| | - Roman Rischke
- Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany
| | - Joachim Krois
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland
| | - Aleksander Krasowski
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité - University Medicine Berlin, Berlin, Germany; ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland
| | - Martha Büttner
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité - University Medicine Berlin, Berlin, Germany; ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland
| | - Hossein Mohammad-Rahimi
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Shahid Beheshti University of Medical Sciences, Tehran, Iran Dental school, Iran
| | - Akhilanand Chaurasia
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Oral Medicine and Radiology, Faculty of Dental Sciences, King George's Medical University, Lucknow, India
| | - Nielsen S Pereira
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Private Practice in Oral and Maxillofacial Radiology, Rio de Janeiro, Brazil
| | - Jae-Hong Lee
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Periodontology, College of Dentistry and Institute of Oral Bioscience, Jeonbuk National University, Jeonju, Korea
| | - Sergio E Uribe
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Conservative Dentistry Oral Health, Riga Stradins University, Riga, Latvia; School of Dentistry, Universidad Austral de Chile, Valdivia, Chile; Baltic Biomaterials Centre of Excellence, Headquarters at Riga Technical University, Riga, Latvia
| | - Shahriar Shahab
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Oral and Maxillofacial Radiology, School of Dentistry, Shahed University of Medical Sciences, Tehran, Iran
| | - Revan Birke Koca-Ünsal
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Periodontology, Faculty of Dentistry, University of Kyrenia, Kyrenia, Cyprus
| | - Gürkan Ünsal
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Near East University, Nicosia, Cyprus
| | | | - Janet Brinz
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Conservative Dentistry and Periodontology, University Hospital, LMU Munich, Munich, Germany
| | - Olga Tryfonos
- ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland; Department of Periodontology and Oral Biochemistry, Academic Centre for Dentistry Amsterdam, Amsterdam, the Netherlands
| | - Falk Schwendicke
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité - University Medicine Berlin, Berlin, Germany; ITU/WHO Focus Group on AI for Health, Topic Group Dental Diagnostics and Digital Dentistry, Geneva, Switzerland.
| |
Collapse
|
2
|
Schwendicke F, Chaurasia A, Wiegand T, Uribe SE, Fontana M, Akota I, Tryfonos O, Krois J. Artificial intelligence for oral and dental healthcare: Core education curriculum. J Dent 2023; 128:104363. [PMID: 36410581 DOI: 10.1016/j.jdent.2022.104363] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2022] [Revised: 11/09/2022] [Accepted: 11/11/2022] [Indexed: 11/22/2022] Open
Abstract
OBJECTIVES Artificial intelligence (AI) is swiftly entering oral health services and dentistry, while most providers show limited knowledge and skills to appraise dental AI applications. We aimed to define a core curriculum for both undergraduate and postgraduate education, establishing a minimum set of outcomes learners should acquire when taught about oral and dental AI. METHODS Existing curricula and other documents focusing on literacy of medical professionals around AI were screened and relevant items extracted. Items were scoped and adapted using expert interviews with members of the IADR's e-oral health group, the ITU/WHO's Focus Group AI for Health and the Association for Dental Education in Europe. Learning outcome levels were defined and each item assigned to a level. Items were systematized into domains and a curricular structure defined. The resulting curriculum was consented using an online Delphi process. RESULTS Four domains of learning outcomes emerged, with most outcomes being on the "knowledge" level: (1) Basic definitions and terms, the reasoning behind AI and the principle of machine learning, the idea of training, validating and testing models, the definition of reference tests, the contrast between dynamic and static AI, and the problem of AI being a black box and requiring explainability should be known. (2) Use cases, the required types of AI to address them, and the typical setup of AI software for dental purposes should be taught. (3) Evaluation metrics, their interpretation, the relevant impact of AI on patient or societal health outcomes and associated examples should be considered. (4) Issues around generalizability and representativeness, explainability, autonomy and accountability and the need for governance should be highlighted. CONCLUSION Both educators and learners should consider this core curriculum during planning, conducting and evaluating oral and dental AI education. CLINICAL SIGNIFICANCE A core curriculum on oral and dental AI may help to increase oral and dental healthcare providers' literacy around AI, allowing them to critically appraise AI applications and to use them consciously and on an informed basis.
Collapse
Affiliation(s)
- Falk Schwendicke
- Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Berlin, Germany; ITU/WHO Focus Group AI on Health, Topic Group Dentistry, Switzerland.
| | - Akhilanand Chaurasia
- ITU/WHO Focus Group AI on Health, Topic Group Dentistry, Switzerland; Department of Oral Medicine and Radiology, King George's Medical University, Lucknow, India
| | - Thomas Wiegand
- ITU/WHO Focus Group AI on Health, Topic Group Dentistry, Switzerland; Technical University Berlin, Berlin, Germany
| | - Sergio E Uribe
- ITU/WHO Focus Group AI on Health, Topic Group Dentistry, Switzerland; Bioinformatics Lab & Dept of Conservative Dentistry and Oral Health, Riga Stradins University, Riga, Latvia; School of Dentistry, Universidad Austral de Chile, Valdivia, Chile
| | - Margherita Fontana
- Cariology, Restorative Sciences & Endodontics, University of Michigan, Ann Arbor, United States
| | - Ilze Akota
- Department of Oral and Maxillofacial surgery, Riga Stradins University, Riga, Latvia
| | - Olga Tryfonos
- ITU/WHO Focus Group AI on Health, Topic Group Dentistry, Switzerland; Department of Periodontology and Oral Biochemistry, Academic Centre for Dentistry Amsterdam (ACTA), University of Amsterdam and Vrije Universiteit Amsterdam, Amsterdam, The Netherland
| | - Joachim Krois
- Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Berlin, Germany; ITU/WHO Focus Group AI on Health, Topic Group Dentistry, Switzerland
| | | |
Collapse
|
3
|
Feher B, Kuchler U, Schwendicke F, Schneider L, Cejudo Grano de Oro JE, Xi T, Vinayahalingam S, Hsu TMH, Brinz J, Chaurasia A, Dhingra K, Gaudin RA, Mohammad-Rahimi H, Pereira N, Perez-Pastor F, Tryfonos O, Uribe SE, Hanisch M, Krois J. Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning. Diagnostics (Basel) 2022; 12:diagnostics12081968. [PMID: 36010318 PMCID: PMC9406703 DOI: 10.3390/diagnostics12081968] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2022] [Revised: 08/09/2022] [Accepted: 08/11/2022] [Indexed: 11/24/2022] Open
Abstract
The detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesion to other anatomical structures, to establish a preliminary classification. Here, we aimed to emulate clinical diagnostic reasoning step by step by using a combined object detection and image segmentation approach on panoramic radiographs (OPGs). We used a multicenter training dataset of 855 OPGs (all positives) and an evaluation set of 384 OPGs (240 negatives). We further compared our models to an international human control group of ten dental professionals from seven countries. The object detection model achieved an average precision of 0.42 (intersection over union (IoU): 0.50, maximal detections: 100) and an average recall of 0.394 (IoU: 0.50–0.95, maximal detections: 100). The classification model achieved a sensitivity of 0.84 for odontogenic cysts and 0.56 for non-odontogenic cysts as well as a specificity of 0.59 for odontogenic cysts and 0.84 for non-odontogenic cysts (IoU: 0.30). The human control group achieved a sensitivity of 0.70 for odontogenic cysts, 0.44 for non-odontogenic cysts, and 0.56 for OPGs without cysts as well as a specificity of 0.62 for odontogenic cysts, 0.95 for non-odontogenic cysts, and 0.76 for OPGs without cysts. Taken together, our results show that a combined object detection and image segmentation approach is feasible in emulating the human clinical diagnostic reasoning process in classifying cystic lesions of the jaw.
Collapse
Affiliation(s)
- Balazs Feher
- Department of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, 1090 Vienna, Austria
- Competence Center Oral Biology, University Clinic of Dentistry, Medical University of Vienna, 1090 Vienna, Austria
- Correspondence: ; Tel.: +43-1-40070-2623
| | - Ulrike Kuchler
- Department of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, 1090 Vienna, Austria
| | - Falk Schwendicke
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, Germany
| | - Lisa Schneider
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, Germany
| | - Jose Eduardo Cejudo Grano de Oro
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, Germany
| | - Tong Xi
- Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, 6525 GA Nijmegen, The Netherlands
| | - Shankeeth Vinayahalingam
- Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, 6525 GA Nijmegen, The Netherlands
| | - Tzu-Ming Harry Hsu
- Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | - Janet Brinz
- Department of Restorative Dentistry, Ludwig-Maximilians-University of Munich, 80336 Munich, Germany
| | - Akhilanand Chaurasia
- Department of Oral Medicine and Radiology, Faculty of Dental Sciences, King George’s Medical University, Lucknow 226003, India
| | - Kunaal Dhingra
- Periodontics Division, Centre for Dental Education and Research, All India Institute of Medical Sciences, New Delhi 110029, India
| | - Robert Andre Gaudin
- Department of Oral and Maxillofacial Surgery, Charité—University Medicine Berlin, 14197 Berlin, Germany
- Berlin Institute of Health, 10178 Berlin, Germany
| | - Hossein Mohammad-Rahimi
- Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran 1416634793, Iran
| | - Nielsen Pereira
- Private Practice in Oral and Maxillofacial Radiology, Rio de Janeiro 22430-000, Brazil
| | - Francesc Perez-Pastor
- Servei Salut Dental, Gerencia Atencio Primaria, Institut Balear de la Salut, 07003 Palma, Spain
| | - Olga Tryfonos
- Department of Periodontology and Oral Biochemistry, Academic Centre for Dentistry Amsterdam, 1081 LA Amsterdam, The Netherlands
| | - Sergio E. Uribe
- Department of Conservative Dentistry & Oral Health, Riga Stradins University, LV-1007 Riga, Latvia
- School of Dentistry, Universidad Austral de Chile, Valdivia 5110566, Chile
- Baltic Biomaterials Centre of Excellence, Headquarters at Riga Technical University, LV-1658 Riga, Latvia
| | - Marcel Hanisch
- Department of Oral and Maxillofacial Surgery, University Clinic Münster, 48143 Münster, Germany
| | - Joachim Krois
- Department of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, Germany
| |
Collapse
|