Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0715
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-09T06:35:25.852074Z
status: published
lens: g_space
sector: health
headline: First-stage assessment of AI-based anatomical measurement accuracy for the Cameriere European dental age estimation method
dek: Aim This study represents the first methodological stage of a broader AI-assisted Cameriere European dental age estimation workflow. The aim of this first stage was to evaluate the performance of YOLOv8-based deep learning models in automatically detecting the anatomical landmarks and apical structures required for the Cameriere European method. Rather than directly estimating dental age, the proposed system was designed to automate the measurement-related inputs needed for subsequent Cameriere European-based ag…
gain_title: YOLOv8x-pose and YOLOv8x-seg models automated landmark detection and apical segmentation for the Cameriere European method in children aged 5-13, achieving high detection accuracy and low measurement error in a first-stage validation.
problem_title: (none)
trace_subject: (none)
gain_reading: YOLOv8x-pose and YOLOv8x-seg models automated landmark detection and apical segmentation for the Cameriere European method in children aged 5-13, achieving high detection accuracy and low measurement error in a first-stage validation.
gain_evidence: YOLOv8-based pose and segmentation models demonstrated technical feasibility for automating anatomical measurement extraction required for the Cameriere European dental age estimation method.
problem_reading: (none)
problem_evidence: (none)
quick_read: This first-stage retrospective validation evaluated YOLOv8-based models to automate the anatomical inputs for the Cameriere European dental age estimation method using 4,050 panoramic radiographs of children aged 5-13. A YOLOv8x-pose model detected open-apex landmarks and a YOLOv8x-seg model segmented closed apices, with performance compared to manual reference annotations from CranioCatch software.

Automating these measurements could reduce manual effort in forensic and pediatric dental age assessment, but the study stops at measurement accuracy and does not demonstrate end-to-end age estimation accuracy. Whether AI-derived measurements translate into equivalent or improved age estimates versus manual Cameriere assessment and chronological age remains untested and requires further integration and validation.
limitation: Findings represent measurement-level validation only; dental age was not calculated and AI-derived measurements have not yet been integrated into the Cameriere European formula or compared to chronological age.
tag: Evidence-backed gain
key_points: Retrospective study included 4,050 panoramic radiographs of boys and girls aged 5-13 years, with 3,796 images used for pose model and 2,971 for segmentation model due to anatomical eligibility. | Two models were developed: YOLOv8x-pose for open-apex landmark detection and tooth-length reference point localization, and YOLOv8x-seg for closed-apex segmentation. | Annotations were performed using CranioCatch software according to a standardized protocol and compared with manual reference annotations.
rundown: The study used 4,050 panoramic radiographs of children aged 5-13, developing a YOLOv8x-pose model for open-apex landmarks and a YOLOv8x-seg model for closed-apex segmentation, with annotations done in CranioCatch software.

Performance was reported as mAP_0.5 0.963 and mAP_0.5:0.95 0.842 for the pose model, with recall 0.928, precision 0.918, MAE 0.0032, RMSE 0.0045, SMAPE 2.09% and R8 0.9992, supporting technical feasibility at the measurement level.

Authors explicitly frame this as first-stage validation, noting dental age was not calculated and further work is needed to integrate AI measurements into the Cameriere formula and compare against manual assessment and chronological age.
sources:
- peer_reviewed | International Journal of Legal Medicine | https://doi.org/10.1007/s00414-026-03950-7 | 2026-08-08
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

56ddf6e7c7a0e6eab5fdd0b563abc0d860f9b073d270c2c9d41d211769f8e48c

previous

0000000000000000000000000000000000000000000000000000000000000000