aceArtificial intelligence-based photographic detection of pink esthetic score attributes using a hybrid deep learning segmentation pipeline: a method development study
This study aimed to develop and internally validate a novel anatomy-driven artificial intelligence (AI) system for automated postoperative Pink Esthetic Score (PES) evaluation from intraoral photographs. Unlike most existing AI approaches, which rely on end-to-end prediction, the proposed pipeline derives PES attributes from anatomically grounded measurements. A hybrid analytical pipeline integrating instance segmentation and rule-based measurement was developed. Tooth crown segmentation was performed using Mask…
"Dental xray maxillary teeth - cat (110 is very mobile)" by mariposavet is licensed under CC BY 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/2.0/.
Researchers developed and internally validated an anatomy-driven AI system to automate postoperative Pink Esthetic Score evaluation from intraoral photographs, using Mask R-CNN for tooth crowns and YOLOv11 for gingiva to derive measurements rather than end-to-end prediction. Tested against independent expert scoring of 82 photographs, the system reached 91.5% accuracy for mesial papilla and 82.9% to 86.6% for other attributes, with 57.3% exact total-score agreement.
Automated, transparent PES scoring could make esthetic outcome assessment more reproducible for dental research and postoperative monitoring, reducing reliance on subjective expert rating. As of the August 2026 publication date, evidence is limited to internal validation on a small postoperative photo set with an R8 of 0.49 and framing as a research-setting approach, leaving external validity, diverse patient populations, and clinical workflow integration unproven.
- Developed anatomy-driven AI pipeline integrating Mask R-CNN for tooth crown and YOLOv11 for gingival segmentation with rule-based measurement.
- Reference standard was independent expert scoring of 82 postoperative intraoral photographs used for internal validation.
- Regression metrics reported mean absolute error of 0.76, root mean squared error of 1.35, and R8 value of 0.49 for total PES.
A hybrid Mask R-CNN and YOLOv11 segmentation pipeline automated postoperative Pink Esthetic Score attribute assessment from intraoral photographs with over 82% accuracy per attribute and 79.3% total-score agreement within one point of experts.
The rundown
The pipeline performed tooth crown segmentation using Mask R-CNN and gingival segmentation using YOLOv11, then extracted anatomical features converted into ordinal PES attributes through data-driven threshold calibration derived from the training dataset.
Evaluation used diagnostic accuracy, confusion matrix analyses, and regression metrics to compare automated scores to expert assessments, reporting per-attribute accuracies and total-score agreement rates.
Sources
- Peer-reviewedScientific Reports2026-08-01
How should this claim be treated?
The debate