Title
Artificial intelligence versus surface microhardness testing in evaluating fluoride remineralization: An in vitro study
Authors
Priyatam Maruti Karade1, Nitish Mittal2, Gouri R. Reddy3, Jasmine Marwaha4,*, Surya Dahiya5 & Vipin Arora6
Affiliation
1Department of Conservative Dentistry and Endodontics, Bharati Vidyapeeth (Deemed To Be University) Dental College and Hospital, Sangli, Maharashtra, India; 2Department of Conservative Dentistry and Endodontics, Desh Bhagat Dental College and Hospital; Gobindgarh, Punjab, India; 3Department of Dentistry, Shri Atal Bihari Vajpayee Medical College and Research Institute, Bengaluru, Karnataka, India; 4Department of Conservative Dentistry and Endodontics, National Dental College and Hospital, Derabassi, Punjab, India; 5Department of Conservative Dentistry & Endodontics, MMCDSR, Mullana, Ambala, Haryana, India;
Priyatam Maruti Karade - E-mail: priyatam.karade@bharatividyapeeth.edu
Nitish Mittal - E-mail: nmittal_1@yahoo.co.in
Gouri R. Reddy - E-mail: dr.gourireddy@gmail.com
Jasmine Marwaha - E-mail: drjasminemarwaha@gmail.com
Surya Dahiya - E-mail: drsuryadahiya@gmail.com
Vipin Arora - E-mail: vipinendodontist@gmail.com
Article Type
Research Article
Date
Received September 1, 2026; Revised September 30, 2026; Accepted
September 30, 2026, Published September 30, 2026
Abstract
Surface microhardness testing is widely used to quantify enamel remineralization, but it is destructive and cannot easily provide rapid image-based prediction of fluoride response. Therefore, it is of interest to compare the artificial intelligence-based image analysis with Vickers surface microhardness testing for evaluating fluoride-mediated remineralization of artificial enamel lesions. One hundred and twenty enamel blocks were demineralized and allocated to five groups (n=24 each): fluoride varnish, fluoride dentifrice slurry, nano-hydroxyapatite, CPP-ACP and control, followed by pH cycling for 14 days. Fluoride varnish produced the highest microhardness recovery (72.8 ± 8.9%), followed by fluoride dentifrice slurry (61.4 ± 7.6%) and the artificial intelligence model predicted microhardness recovery with RČ=0.89, MAE=6.3 VHN and classification accuracy of 88.6%. Thus, artificial intelligence based image analysis showed strong agreement with surface microhardness testing and may provide a rapid non-destructive adjunct for evaluating enamel remineralization.
Keywords
Artificial intelligence (AI), surface microhardness, fluoride, remineralization, enamel, vickers hardness, dental caries
Citation
Karade et al. Bioinformation 22(9): 5532-5536 (2026)
Edited by
Ashwini Dhopte
ISSN
0973-2063
Publisher
License
This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.
