What question did this study set out to answer?

The study aims to develop and validate a deep learning cascade for the automated detection and quantification of marginal bone loss on sequential radiographs.

March 10, 2026BMC Oral Health0 citationsOpen Access

A web-based deep learning cascade for automated detection and quantification of marginal bone loss

NANiha Adnan SASyed Muhammad Faizan Ahmed ANAyesha Nooruddin

Key Points

The study aims to develop and validate a deep learning cascade for the automated detection and quantification of marginal bone loss on sequential radiographs.
Developed a cascade of six deep learning models for MBL detection and quantification.
Collected 2,960 dental periapical radiographs after applying exclusion criteria.
Each model was trained iteratively until convergence without predetermined sample size calculations.
Performed rotation correction, implant alignment, ROI detection, implant classification, mesial-distal detection, and MBL estimation using AI.
Evaluated model performance against a reference standard established by dental specialists.
Rotation correction model achieved 98.0% accuracy with an F1 score of 99.0%.
Implant alignment showed a mean absolute error of 3.02 degrees.
ROI detection model reached a mean average precision of 99.4%.
Implant classification achieved a mean average precision of 93.9% with 100% precision.
MBL estimation model attained a mean average precision of 75.0% but no significant differences in scores compared to reference standard (p > 0.05).

Abstract

Marginal Bone Loss (MBL) around dental implants is a key indicator of peri-implantitis. Existing literature evaluates MBL at a single time point, neglecting baseline comparisons and the temporal nature of disease progression. Conventional radiographic assessments remain limited by subjectivity in angulation and magnification. This study aimed to develop and validate a cascade of six Deep Learning (DL) models for automated detection and quantification of MBL on sequential Periapical (PA) radiographs. It further assessed the system’s accuracy against dental specialists and deployed it as a web-based tool. A total of 6,453 PAs of dental implants were collected from institutional centers and an open-access dataset. After applying exclusion criteria, 2,960 PAs remained. Sample size calculation was not applicable due to the multi-model architecture; therefore, each model was trained iteratively until convergence was achieved using these PAs. This Artificial Intelligence (AI)-cascade was designed to perform: rotation correction, implant alignment, Region of Interest (ROI) detection, implant classification, mesial-distal detection, and MBL estimation. Each model was assessed using performance metrics appropriate for its specific task. Thereafter, MBL was estimated on forty pairs of PAs by periodontists and AI-cascade; these were compared against a Reference Standard (RS) established by dental specialists. Agreement between AI-derived and RS measurements was evaluated using the Mann–Whitney U test (p 0.05). The AI-cascade demonstrated reliable performance in detecting and quantifying MBL across sequential PAs, comparable to expert evaluation. Its deployment as a web-based application enables objective peri-implant monitoring, representing a significant advancement in clinical translation of AI for implant diagnostics.

Demander à l'IA

Bookmark

View Full Paper

Cite This Study

Adnan et al. (Sat,) studied this question.

synapsesocial.com/papers/69af944f70916d39fea4b646 https://doi.org/https://doi.org/10.1186/s12903-026-07962-y

Demander à l'IA

Bookmark

View Full Paper