{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T12:18:31Z","timestamp":1793276311278,"version":"4.5.0"},"reference-count":38,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Context:<\/jats:title>\n                    <jats:p>Dental caries is among the most common oral diseases worldwide and often goes undetected in its early stages, particularly in underserved regions with limited access to health care. There is an urgent need for early detection tools that are portable, accessible, and powered by artificial intelligence (AI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aims:<\/jats:title>\n                    <jats:p>This study aims to develop an efficient and accurate AI-based system for early caries detection, using deep learning alongside optimization strategies suitable for deployment on mobile devices in real-world settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Settings and Design:<\/jats:title>\n                    <jats:p>A lightweight caries classification system was developed based on the MobileNetV2 architecture, optimized using mixup augmentation, fine-tuning, and quantization-aware training to improve performance and efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods:<\/jats:title>\n                    <jats:p>The primary dataset utilized in this study comprises 500 dental images acquired using a smartphone, while a secondary dataset of 5000 images was sourced from publicly available repositories to enhance model generalization. To further augment the dataset and improve the robustness of the AI-based dental caries detection system, an additional 25,000 images were generated through a series of data augmentation techniques. These included random rotations (\u00b120\u00b0), brightness adjustments (ranging from 0.9 to 1.1), zoom transformations (\u00b110%), positional translations, and horizontal flipping. As a result, the final training dataset consisted of 25,500 images. Model performance was assessed using standard evaluation metrics, namely accuracy, precision, recall, and F1-score. Furthermore, model interpretability was examined through Gradient-weighted Class Activation Mapping (Grad-CAM), providing insights into the regions of interest that contributed most significantly to the model\u2019s predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Statistical Analysis Used:<\/jats:title>\n                    <jats:p>Comparative statistical analysis was conducted to assess improvements over the baseline model using standard classification metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The optimized model achieved 96.0% accuracy and F1-score, with a 72.68% reduction in model size and a 98.28% increase in inference speed. Grad-CAM confirmed anatomically relevant focus.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>The proposed system provides a practical, accurate, and offline AI solution for caries screening in low-resource settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.4103\/jcde.jcde_362_25","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T12:02:57Z","timestamp":1754049777000},"page":"764-771","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":9,"title":["Artificial intelligence for dental caries detection: A mixup, fine-tuning, and quantization approach on the MobileNetV2 model"],"prefix":"10.4103","volume":"28","author":[{"given":"Ahmad Fitri","family":"Boy","sequence":"first","affiliation":[{"name":"Doctoral Program-School of Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia"},{"name":"Department of Information System, Faculty of Information System, STMIK Triguna Dharma, Medan, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akhyar","family":"Akhyar","sequence":"additional","affiliation":[{"name":"Doctoral Program-School of Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia"},{"name":"Department of Mechanical Engineering, Universitas Syiah Kuala, Jln. Syech Abdurrauf Darussalam, Banda Aceh, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teuku Yuliar","family":"Arif","sequence":"additional","affiliation":[{"name":"Doctoral Program-School of Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia"},{"name":"Department of Electrical and Computer Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syahrial","family":"Syahrial","sequence":"additional","affiliation":[{"name":"Doctoral Program-School of Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia"},{"name":"Department of Electrical and Computer Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,8,1]]},"reference":[{"key":"R1-20250806","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1186\/s12903-025-06086-z","article-title":"Global, regional, and national caries of permanent teeth incidence, prevalence, and disability-adjusted life years, 1990-2021: Analysis for the global burden of disease study","volume":"25","author":"Li","year":"2025","journal-title":"BMC Oral Health"},{"key":"R2-20250806","doi-asserted-by":"crossref","first-page":"364","DOI":"10.4103\/0972-0707.164032","article-title":"Comparative clinical evaluation of the efficacy of a new method for caries diagnosis and excavation","volume":"18","author":"Peskersoy","year":"2015","journal-title":"J Conserv Dent"},{"key":"R3-20250806","doi-asserted-by":"crossref","first-page":"401","DOI":"10.4103\/JCDE.JCDE_172_25","article-title":"Revolutionizing the diagnosis of dental caries using artificial intelligence-based methods","volume":"28","author":"Marwaha","year":"2025","journal-title":"J Conserv Dent Endod"},{"key":"R4-20250806","doi-asserted-by":"crossref","first-page":"3649","DOI":"10.3390\/diagnostics13243649","article-title":"Detection, diagnosis, and monitoring of early caries: The future of individualized dental care","volume":"13","author":"Abdelaziz","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"R5-20250806","doi-asserted-by":"crossref","first-page":"134","DOI":"10.4103\/JCDE.JCDE_274_23","article-title":"Minimal intervention dentistry: What is its clinical application and effectiveness in different continents?A scoping review","volume":"27","author":"Perrone","year":"2024","journal-title":"J Conserv Dent Endod"},{"key":"R6-20250806","doi-asserted-by":"crossref","first-page":"199","DOI":"10.4103\/jcd.jcd_575_22","article-title":"DIAGNOdent versus international caries detection and assessment system in detection of incipient carious lesions: A diagnostic accuracy study","volume":"26","author":"Shaalan","year":"2023","journal-title":"J Conserv Dent"},{"key":"R7-20250806","doi-asserted-by":"crossref","first-page":"1539805","DOI":"10.3389\/fpubh.2025.1539805","article-title":"Strengthening health systems to tackle oral diseases in Africa: Africa centers for disease control and prevention's role","volume":"13","author":"Fol\u00e1yan","year":"2025","journal-title":"Front Public Health"},{"key":"R8-20250806","first-page":"514","article-title":"Artificial intelligence in conservative dentistry and endodontics: A game-changer","volume":"26","author":"Marwaha","year":"2023","journal-title":"J Conserv Dent Endod"},{"key":"R9-20250806","first-page":"1","article-title":"Application of artificial intelligence digital holography technology based on medical sensors in the development of medical image fusion","volume":"33","author":"Zhong","year":"2024","journal-title":"Meas Sens"},{"key":"R10-20250806","doi-asserted-by":"crossref","first-page":"3179","DOI":"10.1007\/s00530-023-01169-9","article-title":"Dental radiology: A convolutional neural network-based approach to detect dental disorders from dental images in a real-time environment","volume":"29","author":"Shafiq","year":"2023","journal-title":"Multimed Syst"},{"key":"R11-20250806","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1186\/s12903-024-04847-w","article-title":"Diagnostic accuracy of artificial intelligence-assisted caries detection: A clinical evaluation","volume":"24","author":"Zhang","year":"2024","journal-title":"BMC Oral Health"},{"key":"R12-20250806","doi-asserted-by":"crossref","first-page":"104654","DOI":"10.1016\/j.micpro.2022.104654","article-title":"Automatic diagnosis and detection of dental caries in bitewing radiographs using pervasive deep gradient based LeNet classifier model","volume":"94","author":"Vimalarani","year":"2022","journal-title":"Microprocess Microsyst"},{"key":"R13-20250806","doi-asserted-by":"crossref","first-page":"5504","DOI":"10.3390\/app12115504","article-title":"Deep learning application in dental caries detection using intraoral photos taken by smartphones","volume":"12","author":"Thanh","year":"2022","journal-title":"Appl Sci"},{"key":"R14-20250806","doi-asserted-by":"crossref","first-page":"102690","DOI":"10.1016\/j.media.2022.102690","article-title":"Symmetry-based regularization in deep breast cancer screening","volume":"83","author":"Castro","year":"2023","journal-title":"Med Image Anal"},{"key":"R15-20250806","doi-asserted-by":"crossref","first-page":"108579","DOI":"10.1016\/j.dib.2022.108579","article-title":"Environmental due diligence data: A novel corpus for training environmental domain NLP models","volume":"45","author":"Aman","year":"2022","journal-title":"Data Brief"},{"key":"R16-20250806","doi-asserted-by":"crossref","first-page":"25193","DOI":"10.1038\/s41598-024-73297-9","article-title":"Multi-label dental disorder diagnosis based on MobileNetV2 and Swin transformer using bagging ensemble classifier","volume":"14","author":"Alsakar","year":"2024","journal-title":"Sci Rep"},{"key":"R17-20250806","doi-asserted-by":"crossref","first-page":"124701","DOI":"10.1016\/j.eswa.2024.124701","article-title":"MobileNetV2 with spatial attention module for traffic congestion recognition in surveillance images","volume":"255","author":"Lin","year":"2024","journal-title":"Expert Syst Appl"},{"key":"R18-20250806","doi-asserted-by":"crossref","first-page":"450","DOI":"10.3390\/bioengineering10040450","article-title":"RVM-GSM: Classification of OCT images of genitourinary syndrome of menopause based on integrated model of local-global information pattern","volume":"10","author":"Song","year":"2023","journal-title":"Bioengineering (Basel)"},{"key":"R19-20250806","doi-asserted-by":"crossref","first-page":"1414524","DOI":"10.3389\/froh.2025.1414524","article-title":"Artificial intelligence-based diagnosis of oral leukoplakia using deep convolutional neural networks Xception and MobileNet-v2","volume":"6","author":"Ramesh","year":"2025","journal-title":"Front Oral Health"},{"key":"R20-20250806","doi-asserted-by":"crossref","first-page":"11168","DOI":"10.1609\/aaai.v38i10.28994","article-title":"Mixup-Induced Domain Extrapolation for Domain Generalization","volume":"38","author":"Cao","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"R21-20250806","doi-asserted-by":"crossref","first-page":"124","DOI":"10.3390\/asi7060124","article-title":"ML-based pain recognition model using mixup data augmentation","volume":"7","author":"Shantharam","year":"2024","journal-title":"Appl Syst Innov"},{"issue":"69","key":"R22-20250806","first-page":"10","article-title":"Suppressing label noise in medical image classification using mixup attention and self-supervised learning","volume":"69","author":"Gao","year":"2024","journal-title":"Phys Med Biol"},{"key":"R23-20250806","doi-asserted-by":"crossref","first-page":"109561","DOI":"10.1016\/j.engappai.2024.109561","article-title":"Fine-tuning language model embeddings to reveal domain knowledge: An explainable artificial intelligence perspective on medical decision making","volume":"139","author":"Krai\u0161nikovi\u0107","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"R24-20250806","doi-asserted-by":"crossref","first-page":"57476","DOI":"10.1109\/ACCESS.2025.3556629","article-title":"Quantization-aware training with dynamic and static pruning","volume":"13","author":"An","year":"2025","journal-title":"IEEE Access"},{"key":"R25-20250806","doi-asserted-by":"crossref","first-page":"23217","DOI":"10.1109\/ACCESS.2022.3154061","article-title":"Data augmentation and transfer learning for brain tumor detection in magnetic resonance imaging","volume":"10","author":"Anaya-Isaza","year":"2022","journal-title":"IEEE access"},{"key":"R26-20250806","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: Fast and flexible image augmentations","volume":"11","author":"Buslaev","year":"2020","journal-title":"Information"},{"key":"R27-20250806","doi-asserted-by":"crossref","first-page":"40827","DOI":"10.1109\/ACCESS.2024.3378730","article-title":"Approach based Lightweight custom convolutional neural network and fine-tuned mobilenet-V2 for ECG arrhythmia signals classification","volume":"12","author":"Bechinia","year":"2024","journal-title":"IEEE Access"},{"key":"R28-20250806","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s11282-024-00741-x","article-title":"Artificial intelligence for caries detection: A novel diagnostic tool using deep learning algorithms","volume":"40","author":"Liu","year":"2024","journal-title":"Oral Radiol"},{"key":"R29-20250806","doi-asserted-by":"crossref","first-page":"120136","DOI":"10.1016\/j.eswa.2023.120136","article-title":"K-mixup: Data augmentation for offline reinforcement learning using mixup in a Koopman invariant subspace","volume":"225","author":"Jang","year":"2023","journal-title":"Expert Syst Appl"},{"key":"R30-20250806","doi-asserted-by":"crossref","first-page":"127521","DOI":"10.1016\/j.eswa.2025.127521","article-title":"Mixup-based maximum distribution difference selection strategy for domain generalization","volume":"281","author":"Wang","year":"2025","journal-title":"Expert Syst Appl"},{"key":"R31-20250806","doi-asserted-by":"crossref","first-page":"125307","DOI":"10.1016\/j.apenergy.2025.125307","article-title":"Electricity terminal multi-label recognition with a \u201cone-versus-all\u201d rejection recognition algorithm based on adaptive distillation increment learning and attention MobileNetV2 network for non-invasive load monitoring","volume":"382","author":"Yin","year":"2025","journal-title":"Appl Energy"},{"key":"R32-20250806","doi-asserted-by":"crossref","first-page":"159611","DOI":"10.1109\/ACCESS.2024.3488093","article-title":"HLQ: Hardware-friendly logarithmic quantization aware training for power-efficient low-precision CNN models","volume":"12","author":"Choi","year":"2024","journal-title":"IEEE Access"},{"key":"R33-20250806","doi-asserted-by":"crossref","first-page":"108306","DOI":"10.1016\/j.compchemeng.2023.108306","article-title":"Hybridization of model-specific and model-agnostic methods for interpretability of neural network predictions: Application to a power plant","volume":"176","author":"Danesh","year":"2023","journal-title":"Comput Chem Eng"},{"key":"R34-20250806","first-page":"309","article-title":"Multi-class diabetic retinopathy classification using transfer learning and MixUp data augmentation","volume":"11","author":"El Yadari","year":"2024","journal-title":"Int Conf Smart Med IoT Artif Intell"},{"key":"R35-20250806","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.3390\/diagnostics11101887","article-title":"Fine-tuning convolutional neural networks for COVID-19 detection from chest X-ray images","volume":"11","author":"Zhao","year":"2021","journal-title":"Diagnostics (Basel)"},{"key":"R36-20250806","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TCAD.2024.3487781","article-title":"HotaQ: Hardware Oriented Token Adaptive Quantization for Large Language Models","author":"Shen","year":"2024","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"R37-20250806","doi-asserted-by":"crossref","first-page":"3171","DOI":"10.1007\/s00330-015-4150-0","article-title":"Effect of display type and room illuminance in chest radiographs","volume":"26","author":"Liukkonen","year":"2016","journal-title":"Eur Radiol"},{"key":"R38-20250806","doi-asserted-by":"crossref","first-page":"e0000046","DOI":"10.1371\/journal.pdig.0000046","article-title":"Artificial intelligence-powered smartphone application, AICaries, improves at-home dental caries screening in children: Moderated and unmoderated usability test","volume":"1","author":"Al-Jallad","year":"2022","journal-title":"PLOS Digit Health"}],"container-title":["Journal of Conservative Dentistry and Endodontics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/JCDE.JCDE_362_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T19:48:47Z","timestamp":1787773727000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/JCDE.JCDE_362_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":38,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.4103\/jcde.jcde_362_25","relation":{},"ISSN":["2950-4716","2950-4708"],"issn-type":[{"value":"2950-4716","type":"print"},{"value":"2950-4708","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"2025-05-25","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-01","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}