Depth resolved pencil beam radiography using AI -- a proof of principle study

TL;DR

This study demonstrates that deep learning can utilize scattered photon information in x-ray imaging to resolve superimposed structures, providing a new approach to depth resolution in planar radiography.

Contribution

The paper introduces a novel method using AI to analyze scattered photons for depth resolution in x-ray imaging, a significant advancement over traditional transmission-only techniques.

Findings

Achieved 91% accuracy in material identification along the beam

High sensitivity (0.91) and specificity (0.95) in classification

Proof of principle for using scatter analysis to infer depth information

Abstract

AIMS: Clinical radiographic imaging is seated upon the principle of differential keV photon transmission through an object. At clinical x-ray energies the scattering of photons causes signal noise and is utilized solely for transmission measurements. However, scatter - particularly Compton scatter, is characterizable. In this work we hypothesized that modern radiation sources and detectors paired with deep learning techniques can use scattered photon information constructively to resolve superimposed attenuators in planar x-ray imaging. METHODS: We simulated a monoenergetic x-ray imaging system consisting of a pencil beam x-ray source directed at an imaging target positioned in front of a high spatial- and energy-resolution detector array. The signal was analyzed by a convolutional neural network, and a description of scattering material along the axis of the beam was derived. The system was virtually designed/tested using Monte Carlo processing of simple phantoms consisting of 10 pseudo-randomly stacked air/bone/water materials, and the network was trained by solving a classification problem. RESULTS: The average accuracy of the material identification along the beam was 0.91 +- 0.01, with slightly higher accuracy towards the entrance/exit peripheral surfaces of the object. The average sensitivity and specificity was 0.91 and 0.95, respectively. CONCLUSIONS: Our work provides proof of principle that deep learning techniques can be used to analyze scattered photon patterns which can constructively contribute to the information content in radiography, here used to infer depth information in a traditional 2D planar setup. This principle, and our results, demonstrate that the information in Compton scattered photons may provide a basis for further development. The ability to scale performance to the clinic remains unexplored and requires further study.