Deep learning based prediction of virtual non contrast CT images
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU134358" target="_blank" >RIV/00216305:26220/21:PU134358 - isvavai.cz</a>
Výsledek na webu
<a href="https://dl.acm.org/doi/10.1145/3459104.3460237" target="_blank" >https://dl.acm.org/doi/10.1145/3459104.3460237</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/3459104.3460237" target="_blank" >10.1145/3459104.3460237</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Deep learning based prediction of virtual non contrast CT images
Popis výsledku v původním jazyce
In this paper, we present a method, based on deep learning, for prediction of non-contrast CT image from a single contrast image. For training of this image-to-image translation task, virtual contrast and virtual non-contrast (VNC) images were created from spectral CT data by Philips IntelliSpace Portal (ISP) software. Virtual version of conventional CT (cCT) images and VNC images allows to train paired supervised image-to-image translation models. Two different schemes were tested to train the Convolutional Neural Network (CNN) with U-Net architecture, using standard training with L1/L2 loss as well as training via conditional Generative Adversarial Network (cGAN) with an additional Wasserstein modification (WcGAN). Qualitatively, the proposed method achieves similar results to the original VNC images. However, quantitatively, the trained CNN provides a slightly smaller density reduction in some tissues. The advantage of this approach is that non-contrast image can be predicted from a single conventional CT image, without the need for pre- and post-contrast scan or without a spectral CT scan.
Název v anglickém jazyce
Deep learning based prediction of virtual non contrast CT images
Popis výsledku anglicky
In this paper, we present a method, based on deep learning, for prediction of non-contrast CT image from a single contrast image. For training of this image-to-image translation task, virtual contrast and virtual non-contrast (VNC) images were created from spectral CT data by Philips IntelliSpace Portal (ISP) software. Virtual version of conventional CT (cCT) images and VNC images allows to train paired supervised image-to-image translation models. Two different schemes were tested to train the Convolutional Neural Network (CNN) with U-Net architecture, using standard training with L1/L2 loss as well as training via conditional Generative Adversarial Network (cGAN) with an additional Wasserstein modification (WcGAN). Qualitatively, the proposed method achieves similar results to the original VNC images. However, quantitatively, the trained CNN provides a slightly smaller density reduction in some tissues. The advantage of this approach is that non-contrast image can be predicted from a single conventional CT image, without the need for pre- and post-contrast scan or without a spectral CT scan.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
20601 - Medical engineering
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2021
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
International Conference Proceeding Series (ICPS) - ISEEIE 2021: 2021 International Symposium on Electrical, Electronics and Information Engineering
ISBN
978-1-4503-8983-9
ISSN
2168-4081
e-ISSN
—
Počet stran výsledku
5
Strana od-do
72-76
Název nakladatele
Assiciation for Computing Machinery
Místo vydání
New York, NY, USA
Místo konání akce
Prague
Datum konání akce
22. 11. 2019
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—