A practical artificial intelligence framework for legal age estimation using clavicle computed tomography scans

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.

Figures (8)

• Figure 1: Stages of clavicle ossification as proposed by kellinghaus2010forensic. All images show the MCE, i.e., the region where the clavicle joins the sternum. Individuals from stages 1 to 5 had a mean age of 13.28, 17.81, 21.73, 29.63 and 31.77 years old for males, and of 12.70, 16.28, 21.14, 28.21 and 30.88 years old for females in the work that first applied the method kellinghaus2010forensic. This method was later extended by dividing stages two and three into three sub-stages each. Image reproduced from schmeling2016forensic.
• Figure 2: Overview of the proposed age estimation method. From a full-body CT (A1), the skeleton is automatically segmented by thresholding at 300 Hounsfield Units (A2). All connected components in A2 are extracted, and shape and geometrical features are computed to form a feature vector (A3), which is input to a Random Forest (A4) that estimates the probability of each component being a clavicle (A5). The three components with the highest probabilities are then filtered using anatomical constraints (A6) to ensure a maximum of two clavicles per individual (A7). Each identified clavicle is processed in part B, where the MCE is localized in the original CT using the segmented clavicle. Five equispaced coronal slices are then passed through a five-branch CNN trained for age estimation. Integrated Gradients IntegratedGradients assigns an importance score to each branch, which is used to compute a weighted average of slice positions to identify the most relevant slice. The same procedure is applied to the axial view, while the sagittal view is omitted as it did not improve performance (see \ref{['results_sec']}). The most relevant slices and neighboring slices are input to the LAE model in step C. This process is performed for both clavicles, and the final age estimate is the average of the two. Using the conformal split method lei2018distribution, a prediction interval for the estimated age is also obtained.
• Figure 3: Anatomical constraints for clavicle detection netter2014atlas. Right clavicle is shown in blue. (a) For each clavicle, $Z_l$ is the $Z$ value at the leftmost ($X_{min}$) point, and $Z_r$ for the rightmost one ($X_{max})$. This can be used to detect clavicle laterality (left or right clavicle, denoted as $C_l$ and $C_r$ in (b). (b) Once laterality is defined, the leftmost point of $C_r$ ($A$) must be at the right ($<$) of the rightmost point of $C_l$ ($B$). (c) let $Z_1$ be the height of the innermost (leftmost) point of $C_r$, and $Z_2$ the same for $C_l$. $|Z_1 - Z_2|$ must be below a fixed distance $\epsilon$, with $\epsilon=1$cm in our case.
• Figure 4: Bounding box localization around the MCE. Because of the clavicle's anatomical positioning, it is known that the MCE is closest to the vertex of the bounding box at $(X_{\max}, Y_{\max}, Z_{\min})$, using the coordinate system shown in \ref{['fig:props']}.
• Figure 5: Simplified representation of the proposed architecture used for LAE. It consists of 4 branches that process different slices (2 coronal and 2 axial) using ResNet50 resnet. The output of all branches, consisting of a 1,000-dimensional feature vector is passed to a fully-connected network that we named the fusion network. By doing this, we obtain an end-to-end model for LAE using multi-slice learning.