https://doi.org/10.1140/epjp/s13360-026-07569-w
Regular Article
Development of a model machine learning for design radiation shielding for mammography
Faculty of Basic Sciences, Imam Hossein University, Tehran, Iran
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
3
December
2025
Accepted:
12
March
2026
Published online:
16
April
2026
Abstract
This study introduces a breakthrough in radiation shielding: A novel, lead-free composite engineered through an artificial neural network (ANN) framework uniquely grounded in first-principles photon interaction physics. Trained on quantum mechanical cross-sections and validated against experimental benchmarks, the ANN accurately predicts energy- and thickness-dependent linear attenuation coefficients across the mammography X-ray spectrum (20–40 kVp), with exceptional fidelity in the critical 20–40 keV range. The optimized composite, composed of strategically weighted high-Z elements (Mo, I, Sn, Sb, and Ba) leverages synergistic K-edge alignment to maximize photoelectric absorption per unit mass, achieving unprecedented attenuation efficiency: > 98% at just 0.2 mm thickness and > 99.9% beyond 0.5 mm for polyenergetic 40 kVp spectra. Notably, the material offers over 40% of the attenuation power of lead at a lower density, enabling the fabrication of lightweight shields that are ideal for wearable aprons, mobile barriers, and aerospace applications. Spectral analysis confirms the smart beam hardening behavior, while HVL/TVL metrics confirm exponential attenuation dynamics consistent with fundamental radiological theory. By linking atomic-scale quantum electrodynamics with macroscopic engineering performance, this work establishes a new paradigm for AI-based materials design that transforms radiation protection from a passive constraint to an active, tunable, and sustainable agent for safer medical imaging and next-generation industrial radiography.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2026
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
