AI Insight
Researchers developed HMA-Net, a deep learning system that estimates age and sex from dental X-rays by combining full panoramic images with individual tooth representations. The study found that removing redundant jaw-region inputs actually improved performance, achieving a mean age estimation error of 0.51 years and 85.2% sex classification accuracy in 4,293 radiographs from individuals aged 3-18 years. The findings demonstrate that including anatomically plausible but redundant inputs can degrade model performance, and that systematic input auditing can identify which data sources genuinely contribute complementary information.
Why it matters
This work has direct applications in forensic identification and legal age verification cases where dental records are used. The methodology provides a generalizable framework for medical imaging systems to identify and remove redundant inputs, potentially improving diagnostic accuracy while reducing computational complexity and maintaining interpretability.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Age and sex estimation from dental radiographs supports forensic identification and age-dependent legal assessment. Multi-input models may combine global and regional representations, but when these inputs are derived from the same radiograph, they may repeat anatomical information rather than provide complementary signals. We developed HMA-Net, a hierarchical multi-stream anatomical network, together with a task-specific input audit that evaluates whether each candidate representation improves at least one prediction task without materially degrading the other. The model was developed using a retrospective single-centre cohort of 4,293 panoramic radiographs from individuals aged 3-18 years and combined a panoramic-image stream with graph-linked tooth representations. On the held-out test set, the final panoramic-plus-permanent-tooth model achieved a mean absolute age error of 0.51 years and a sex-classification accuracy of 85.2%; 99.4% of age estimates were within 2 years of chronological age. Across three independent training runs, removing the jaw-region stream reduced mean absolute age error from 0.68 +/- 0.01 to 0.52 +/- 0.01 years and increased sex accuracy from 81.3+/- 1.7% to 85.8 +/- 0.8%. Adding 20 deciduous-tooth classes provided no age benefit and reduced sex accuracy by 7.9% relative to the permanent-only representation. The mandibular first molars received the greatest tooth-level attention, and their occlusion impaired both prediction tasks. These findings show that anatomically plausible inputs do not necessarily provide incremental predictive value. Task-specific input auditing can improve joint model performance, reduce input redundancy and preserve anatomically traceable predictions. More broadly, this framework provides a testable approach for selecting correlated inputs in medical-imaging systems in which regional views re-present anatomy already contained in the whole image. Keywords: Forensic odontology; Dental age estimation; Sex classification; Panoramic radiography; Multi-input learning; Anatomical input auditing