Physics-informed Deep Learning for Dual-Energy Computed Tomography Image Processing

Poirot, Maarten G.; Bergmans, Rick H. J.; Thomson, Bart R.; Jolink, Florine C.; Moum, Sarah J.; González, R Gilberto; Lev, Michael H.; Tan, Can Ozan; Gupta, Rajiv

doi:10.1038/s41598-019-54176-0

Cited by 38 publications

(23 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For rods within the training mask (1-9), the CNN explicitly preserves the chain B contrast (maximum error by magnitude, 0.33 HU). For rods outside of the training mask and in the training halo (10)(11)(12)(13)(14)(15), however, the CNN spectral extrapolation results are less consistent, particularly for the 2 and 15 mg/mL iodine rods (contrast estimation errors: −17.34 and −28.89 HU, respectively). Compared with the much smaller average errors seen in the testing data (Fig.…”

Section: B Gammex Phantommentioning

confidence: 98%

“…This includes a growing body of work on CNN‐based postreconstruction denoising for reproducing full‐dose CT data from low‐dose CT data 9–11 . More relevant here, this also includes several papers demonstrating the advantages of spatial contextual information in the problems of material decomposition 12–14 and the synthesis of noncontrast images 15 and monochromatic images 16 . More broadly, application of deep learning to the problem of spectral extrapolation is motivated by prior successes in a number of closely related image processing problems, including inpainting, 17 pan‐sharpening, 18 and assigning color to grayscale images 19 …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning based spectral extrapolation for dual‐source, dual‐energy x‐ray computed tomography

et al. 2020

View full text Add to dashboard Cite

Purpose: 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. Methods: 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. Results: 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. Conclusions: Even with a moderate amount of training data, deep learning ...

show abstract

Section: B Gammex Phantommentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Deep learning based spectral extrapolation for dual‐source, dual‐energy x‐ray computed tomography

et al. 2020

View full text Add to dashboard Cite

show abstract

“…There has been increasing work in physics-informed AI/deep learning (e.g., [89]), and image reconstruction is no exception. The goal here is to combine the power of the AI paradigm with our existing knowledge of the imaging physics and statistical modeling, seeking a hybrid new image reconstruction methodology that exploits the best of AI with the best of our understanding of imaging physics and reconstruction.…”

Section: B Regularization By Deep-learned Analysismentioning

confidence: 99%

Deep Learning for PET Image Reconstruction

Reader

Corda-DrIncan

Mehranian

et al. 2021

IEEE Trans. Radiat. Plasma Med. Sci.

170

View full text Add to dashboard Cite

This article reviews the use of a subdiscipline of artificial intelligence (AI), deep learning, for the reconstruction of images in positron emission tomography (PET). Deep learning can be used either directly or as a component of conventional reconstruction, in order to reconstruct images from noisy PET data. The review starts with an overview of conventional PET image reconstruction and then covers the principles of general linear and convolution-based mappings from data to images, and proceeds to consider nonlinearities, as used in convolutional neural networks (CNNs). The direct deep-learning methodology is then reviewed in the context of PET reconstruction. Direct methods learn the imaging physics and statistics from scratch, not relying on a priori knowledge of these models of the data. In contrast, model-based or physics-informed deep-learning uses existing advances in PET image reconstruction, replacing conventional components with deep-learning data-driven alternatives, such as for the regularization. These methods use trusted models of the imaging physics and noise distribution, while relying on training data examples to learn deep mappings for regularization and resolution recovery. After reviewing the main examples of these approaches in the literature, the review finishes with a brief look ahead to future directions.

show abstract

“…In some patients, particularly those with a large body habitus and those scanned with low-dose, the iterative reconstruction methods can have high noise and artifacts. A recent study reported that physics-informed and anatomic information-trained CNNbased DL could help reconstruct non-contrast single-energy CT from DECT scans with higher fidelity than the processed DECT image datasets [122]. At the time of writing this manuscript, AiCE has been FDA approved for commercial use.…”

Section: Emerging Technologies and Dl-based Reconstructionmentioning

confidence: 99%

Artificial intelligence in image reconstruction: The change is here

Singh

Wang

et al. 2020

Physica Medica

View full text Add to dashboard Cite

Innovations in CT have been impressive among imaging and medical technologies in both the hardware and software domain. The range and speed of CT scanning improved from the introduction of multidetector-row CT scanners with wide-array detectors and faster gantry rotation speeds. To tackle concerns over rising radiation doses from its increasing use and to improve image quality, CT reconstruction techniques evolved from filtered back projection to commercial release of iterative reconstruction techniques, and recently, of deep learning (DL)based image reconstruction. These newer reconstruction techniques enable improved or retained image quality versus filtered back projection at lower radiation doses. DL can aid in image reconstruction with training data without total reliance on the physical model of the imaging process, unique artifacts of PCD-CT due to charge sharing, K-escape, fluorescence x-ray emission, and pulse pileups can be handled in the data-driven fashion. With sufficiently reconstructed images, a well-designed network can be trained to upgrade image quality over a practical/clinical threshold or define new/killer applications. Besides, the much smaller detector pixel for PCD-CT can lead to huge computational costs with traditional model-based iterative reconstruction methods whereas deep networks can be much faster with training and validation. In this review, we present techniques, applications, uses, and limitations of deep learning-based image reconstruction methods in CT.

show abstract

Physics-informed Deep Learning for Dual-Energy Computed Tomography Image Processing

Cited by 38 publications

References 28 publications

Deep learning based spectral extrapolation for dual‐source, dual‐energy x‐ray computed tomography

Deep learning based spectral extrapolation for dual‐source, dual‐energy x‐ray computed tomography

Deep Learning for PET Image Reconstruction

Artificial intelligence in image reconstruction: The change is here

Contact Info

Product

Resources

About