Deep learning based prediction of virtual non contrast CT images

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>

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

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

—