Depth resolved pencil beam radiography using AI - A proof of principle study Journal Article


Authors: Häggström, I.; Carter, L. M.; Fuchs, T. J.; Kesner, A. L.
Article Title: Depth resolved pencil beam radiography using AI - A proof of principle study
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 setup maximizes information capture of transmitted photons by measuring off-axis scatter location and energy. 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: from our simulations we were able to resolve traversed material depth information to a high degree, within our simple imaging task. 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 there is information in Compton scattered photons, and this may provide a basis for further development. The work was limited by simple testing scenarios and without yet integrating complexities or optimizations. The ability to scale performance to the clinic remains unexplored and requires further study. © 2022 IOP Publishing Ltd and Sissa Medialab.
Keywords: medical imaging; photons; image reconstruction methods; image reconstruction; computer aided diagnosis; learning systems; image reconstruction algorithm; learning algorithms; deep learning; computer-aided; convolutional neural networks; compton imaging; medical-image reconstruction methods and algorithms, computer-aided diagnosis; medical-image reconstruction methods and algorithms, computer-aided software; ability testing; x ray detectors; x ray radiography; medical image reconstruction; medical-image reconstruction method and algorithm, computer-aided diagnose; medical-image reconstruction method and algorithm, computer-aided software
Journal Title: Journal of Instrumentation
Volume: 17
Issue: 6
ISSN: 1748-0221
Publisher: Institute of Physics Publishing Ltd.  
Date Published: 2022-06-01
Start Page: P06012
Language: English
DOI: 10.1088/1748-0221/17/06/p06012
PROVIDER: scopus
PMCID: PMC11210439
PUBMED: 38938475
DOI/URL:
Notes: Article -- Export Date: 1 August 2022 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Adam Leon Kesner
    68 Kesner
  2. Lukas M Carter
    79 Carter