Dual-energy image noise reduction on an interventional x-ray system

Nikolau, Ethan P.; Whitehead, Joseph F.; Wagner, Martin; Laeseke, Paul F.; Speidel, Michael A.

doi:10.1117/12.2612259

Cited by 2 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have focused on synthetic DE imaging using artificial intelligence. A few models use U-Net and multilevel wavelet convolutional neural network (CNN) [16][17][18][19] for shallow structures, which is associated with reduced processing capacity and low estimation accuracy. Considering that our methodology uses chest X-ray images acquired from various angles from CT images, these problems can increase when learning from irregular data.…”

Section: Introductionmentioning

confidence: 99%

Framework for dual‐energy‐like chest radiography image synthesis from single‐energy computed tomography based on cycle‐consistent generative adversarial network

Lee

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundDual‐energy (DE) chest radiography (CXR) enables the selective imaging of two relevant materials, namely, soft tissue and bone structures, to better characterize various chest pathologies (i.e., lung nodule, bony lesions, etc.) and potentially improve CXR‐based diagnosis. Recently, deep‐learning‐based image synthesis techniques have attracted considerable attention as alternatives to existing DE methods (i.e., dual‐exposure‐based and sandwich‐detector‐based methods) because software‐based bone‐only and bone‐suppression images in CXR could be useful.PurposeThe objective of this study was to develop a new framework for DE‐like CXR image synthesis from single‐energy computed tomography (CT) based on a cycle‐consistent generative adversarial network.MethodsThe core techniques of the proposed framework are divided into three categories: (1) data configuration from the generation of pseudo CXR from single energy CT, (2) learning of the developed network architecture using pseudo CXR and pseudo‐DE imaging using a single‐energy CT, and (3) inference of the trained network on real single‐energy CXR. We performed a visual inspection and comparative evaluation using various metrics and introduced a figure of image quality (FIQ) to consider the effects of our framework on the spatial resolution and noise in terms of a single index through various test cases.ResultsOur results indicate that the proposed framework is effective and exhibits potential synthetic imaging ability for two relevant materials: soft tissue and bone structures. Its effectiveness was validated, and its ability to overcome the limitations associated with DE imaging techniques (e.g., increase in exposure dose owing to the requirement of two acquisitions, and emphasis on noise characteristics) via an artificial intelligence technique was presented.ConclusionsThe developed framework addresses X‐ray dose issues in the field of radiation imaging and enables pseudo‐DE imaging with single exposure.

show abstract

Section: Introductionmentioning

confidence: 99%

Framework for dual‐energy‐like chest radiography image synthesis from single‐energy computed tomography based on cycle‐consistent generative adversarial network

Lee

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…copper) between the two detector layers for adequate spectral separation (Cai et al 2023 ), and x-ray absorption in this filter layer may reduce the detection efficiency and noise performance of dual-layer FPDs for non-spectral imaging sequences. Fast-kV switching can also introduce dual-energy imaging to C-arms (Müller et al 2016 , Speidel et al 2019 , Nikolau et al 2022 ), but offers no additional benefits for non-spectral applications, and furthermore may result in misregistration artifacts caused by patient motion during the transition time between the two tube potentials. Lastly, a more cost-effective approach than using PCDs is to replace the a-Si:H transistors in EIDs with CMOS (Jain et al 2015 , Sheth et al 2018 , Job et al 2019 , Abiola et al 2020 , Sheth et al 2020 ) to reduce electronic noise, improve spatial resolution, reduce lag, and increase the maximum frame rate.…”

Section: Discussionmentioning

confidence: 99%

“…120 kV) and lower (e.g. 60 kV) tube potentials (Müller et al 2016 , Speidel et al 2019 , Nikolau et al 2022 ). This approach has demonstrated potential for dual-energy subtraction angiography (DESA) as an alternative to traditional DSA to mitigate misregistration artifacts caused by the subtraction of the early mask image from the later contrast-enhanced images.…”

Section: Introductionmentioning

confidence: 99%

Photon counting-energy integrating hybrid flat panel detector systems for image-guided interventions: an experimental proof-of-concept

Treb

Haemisch²,

Ullberg

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Current C-arm x-ray systems equipped with scintillator-based flat panel detectors (FPDs) lack sufficient low-contrast detectability and spectral, high-resolution capabilities much desired for certain interventional procedures. Semiconductor-based direct-conversion photon counting detectors (PCDs) offer these imaging capabilities, although the cost of full field-of-view (FOV) PCD is still too high at the moment. The purpose of this work was to present a hybrid photon counting-energy integrating flat panel detector design as a cost-effective solution to high-quality interventional imaging. Approach: In the proposed hybrid detector design, the central scintillator and thin-film transistor elements in the FPD are replaced with a semiconductor PCD module to upgrade the imaging capabilities of the C-arm system while preserving the full FOV coverage. The central PCD module can be used for high-quality 2D and 3D region-of-interest imaging with improved spatial- and temporal-resolution as well as spectral resolving capability. An experimental proof-of-concept was conducted using a 30x2.5 cm^2 CdTe PCD and a 40x30 cm^2 CsI(Tl)-aSi(H) FPD. Main Results: Phantom and in vivo animal studies show 1) improved visualization of small stent wires in both 2D and 3D images due to the better spatial resolution of the PCD; 2) dual-energy angiography imaging capability by using the spectral PCD; 3) better conspicuity of small peripheral iodinated vessels (contrast-to-noise ratio improvement range: [29%, 151%]); 4) the central PCD outputs can be fused seamlessly with the surrounding scintillator detector outputs to provide full field imaging: a post-processing chain was developed by leveraging the PCD's spectral information to match the image contrast of PCD images to the surrounding scintillator detector, followed by spatial filtering of the PCD image to match noise texture and spatial resolution. Significance: The hybrid FPD design provides a cost-effective option to upgrade C-arm systems with spectral and ultra-high resolution capabilities without interfering with the clinical need for full FOV imaging.

show abstract

Dual-energy image noise reduction on an interventional x-ray system

Cited by 2 publications

References 11 publications

Framework for dual‐energy‐like chest radiography image synthesis from single‐energy computed tomography based on cycle‐consistent generative adversarial network

Framework for dual‐energy‐like chest radiography image synthesis from single‐energy computed tomography based on cycle‐consistent generative adversarial network

Photon counting-energy integrating hybrid flat panel detector systems for image-guided interventions: an experimental proof-of-concept

Contact Info

Product

Resources

About