Deep learning based spectral extrapolation for dual-source, dual-energy x-ray computed tomography.
Abstract
<h4>Purpose</h4>Data completion is commonly employed in dual-source, dual-energy computed
tomography (CT) when physical or hardware constraints limit the field of view (FoV)
covered by one of two imaging chains. Practically, dual-energy data completion is
accomplished by estimating missing projection data based on the imaging chain with
the full FoV and then by appropriately truncating the analytical reconstruction of
the data with the smaller FoV. While this approach works well in many clinical applications,
there are applications which would benefit from spectral contrast estimates over the
larger FoV (spectral extrapolation)-e.g. model-based iterative reconstruction, contrast-enhanced
abdominal imaging of large patients, interior tomography, and combined temporal and
spectral imaging.<h4>Methods</h4>To document the fidelity of spectral extrapolation
and to prototype a deep learning algorithm to perform it, we assembled a data set
of 50 dual-source, dual-energy abdominal x-ray CT scans (acquired at Duke University
Medical Center with 5 Siemens Flash scanners; chain A: 50 cm FoV, 100 kV; chain B:
33 cm FoV, 140 kV + Sn; helical pitch: 0.8). Data sets were reconstructed using ReconCT
(v14.1, Siemens Healthineers): 768 × 768 pixels per slice, 50 cm FoV, 0.75 mm slice
thickness, "Dual-Energy - WFBP" reconstruction mode with dual-source data completion.
A hybrid architecture consisting of a learned piecewise linear transfer function (PLTF)
and a convolutional neural network (CNN) was trained using 40 scans (five scans reserved
for validation, five for testing). The PLTF learned to map chain A spectral contrast
to chain B spectral contrast voxel-wise, performing an image domain analog of dual-source
data completion with approximate spectral reweighting. The CNN with its U-net structure
then learned to improve the accuracy of chain B contrast estimates by copying chain
A structural information, by encoding prior chain A, chain B contrast relationships,
and by generalizing feature-contrast associations. Training was supervised, using
data from within the 33-cm chain B FoV to optimize and assess network performance.<h4>Results</h4>Extrapolation
performance on the testing data confirmed our network's robustness and ability to
generalize to unseen data from different patients, yielding maximum extrapolation
errors of 26 HU following the PLTF and 7.5 HU following the CNN (averaged per target
organ). Degradation of network performance when applied to a geometrically simple
phantom confirmed our method's reliance on feature-contrast relationships in correctly
inferring spectral contrast. Integrating our image domain spectral extrapolation network
into a standard dual-source, dual-energy processing pipeline for Siemens Flash scanner
data yielded spectral CT data with adequate fidelity for the generation of both 50 keV
monochromatic images and material decomposition images over a 30-cm FoV for chain
B when only 20 cm of chain B data were available for spectral extrapolation.<h4>Conclusions</h4>Even
with a moderate amount of training data, deep learning methods are capable of robustly
inferring spectral contrast from feature-contrast relationships in spectral CT data,
leading to spectral extrapolation performance well beyond what may be expected at
face value. Future work reconciling spectral extrapolation results with original projection
data is expected to further improve results in outlying and pathological cases.
Type
Journal articlePermalink
https://hdl.handle.net/10161/24254Published Version (Please cite this version)
10.1002/mp.14324Publication Info
Clark, Darin P; Schwartz, Fides R; Marin, Daniele; Ramirez-Giraldo, Juan C; & Badea,
Cristian T (2020). Deep learning based spectral extrapolation for dual-source, dual-energy x-ray computed
tomography. Medical physics, 47(9). pp. 4150-4163. 10.1002/mp.14324. Retrieved from https://hdl.handle.net/10161/24254.This is constructed from limited available data and may be imprecise. To cite this
article, please review & use the official citation provided by the journal.
Collections
More Info
Show full item recordScholars@Duke
Cristian Tudorel Badea
Professor in Radiology
Our lab's research focus lies primarily in developing novel quantitative imaging systems,
reconstruction algorithms and analysis methods. My major expertise is in preclinical
CT.
Currently, we are particularly interested in developing novel strategies for spectral
CT imaging using nanoparticle-based contrast agents for theranostics (i.e. therapy
and diagnostics).
We are also engaged in developin
Darin Clark
Assistant Professor in Radiology
Daniele Marin
Associate Professor of Radiology
Liver Imaging Dual Energy CT CT Protocol Optimization Dose Reduction Strategies for
Abdominal CT Applications
Fides Regina Schwartz
Research Associate, Senior
My passion is for radiology research. As a resident, I was invited to present my research
at international conferences (Journees Fracophones de la Radiologie, Paris, European
Congress of Radiology, RSNA) and these experiences inspired me to focus on research.
I completed medical school in Heidelberg, Germany and Pamplona, Spain (through the
ERASMUS scholarship program). During that time, I also completed internships in California,
Bahrein, Barcelona and New Orleans). I completed my radiolo
Alphabetical list of authors with Scholars@Duke profiles.

Articles written by Duke faculty are made available through the campus open access policy. For more information see: Duke Open Access Policy
Rights for Collection: Scholarly Articles
Works are deposited here by their authors, and represent their research and opinions, not that of Duke University. Some materials and descriptions may include offensive content. More info