Sub-second photon dose prediction via transformer neural networks

Background: Fast dose calculation is critical for online and real-time adaptive therapy workflows. While modern physics-based dose algorithms must compromise accuracy to achieve low computation times, deep learning models can potentially perform dose prediction tasks with both high fidelity and speed. Purpose: We present a deep learning...

A novel capsule-based selfrecovery system with a chloride ion trigger

Steel is prone to corrosion induced by chloride ions, which is a serious threat to reinforced concrete structures, especially in marine environments. In this work, we report a novel capsule-based selfrecovery system that utilizes chloride ions as a trigger. These capsules, which are functionalized via a smart response to chloride ions, are...