A practical artificial intelligence framework for legal age estimation using clavicle computed tomography scans
2026-03-18 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new computer method to estimate a person's legal age using CT scans of the collarbone, which is important for legal and forensic cases. Their method automatically finds the collarbone in the images, selects important slices using AI explanations, and provides age estimates with clear uncertainty measures. Tested on over a thousand post-mortem scans, their approach was more accurate than human experts and previous techniques. The model focuses on key parts of the collarbone related to age and can be used to support decisions in forensic practice.
Legal age estimationClavicle CT scansConvolutional neural networksIntegrated GradientsConformal predictionMedico-legal forensicsMean absolute errorEpiphysisConnected-component methodForensic decision support
Authors
Javier Venema, Stefano De Luca, Pablo Mesejo, Óscar Ibáñez
Abstract
Legal age estimation plays a critical role in forensic and medico-legal contexts, where decisions must be supported by accurate, robust, and reproducible methods with explicit uncertainty quantification. While prior artificial intelligence (AI)-based approaches have primarily focused on hand radiographs or dental imaging, clavicle computed tomography (CT) scans remain underexplored despite their documented effectiveness for legal age estimation. In this work, we present an interpretable, multi-stage pipeline for legal age estimation from clavicle CT scans. The proposed framework combines (i) a feature-based connected-component method for automatic clavicle detection that requires minimal manual annotation, (ii) an Integrated Gradients-guided slice selection strategy used to construct the input data for a multi-slice convolutional neural network that estimates legal age, and (iii) conformal prediction intervals to support uncertainty-aware decisions in accordance with established international protocols. The pipeline is evaluated on 1,158 full-body post-mortem CT scans from a public forensic dataset (the New Mexico Decedent Image Database). The final model achieves state-of-the-art performance with a mean absolute error (MAE) of 1.55 $\pm$ 0.16 years on a held-out test set, outperforming both human experts (MAE of approximately 1.90 years) and previous methods (MAEs above 1.75 years in our same dataset). Furthermore, conformal prediction enables configurable coverage levels aligned with forensic requirements. Attribution maps indicate that the model focuses on anatomically relevant regions of the medial clavicular epiphysis. The proposed method, which is currently being added as part of the Skeleton-ID software (https://skeleton-id.com/skeleton-id/), is intended as a decision-support component within multi-factorial forensic workflows.