x-ray-imaging

Scientists used advanced X-ray imaging techniques to discover a double-helix structure in narwhal tusks, which contributes to their strength and may record environmental changes over time.

This paper introduces a contrast-invariant deep ptychography neural network that uses a factorization strategy to decouple learned object texture from measurement scaling, enabling consistent reconstructions across varying illumination conditions. The method achieves up to 5x reduction in Fourier error over the previous PtychoPINN-torch baseline across multiple experimental datasets.

The paper introduces CXR-MAX, a large-scale benchmark for evaluating reasoning alignment in non-stationary environments using X-ray data from multiple MLLMs.