A showcase of ÉTS researchers’ publications and other contributions

CycleGAN for style transfer in X-ray angiography


Downloads per month over past year

Tmenova, Oleksandra, Martin, Rémi and Duong, Luc. 2019. « CycleGAN for style transfer in X-ray angiography ». International Journal of Computer Assisted Radiology and Surgery, vol. 14, nº 10. pp. 1785-1794.
Compte des citations dans Scopus : 20.

[thumbnail of Duong-L-2019-19292.pdf]
Duong-L-2019-19292.pdf - Accepted Version
Use licence: All rights reserved to copyright holder.

Download (9MB) | Preview


Purpose -- We aim to perform generation of angiograms for various vascular structures as a mean of data augmentation in learning tasks. The task is to enhance the realism of vessels images generated from an anatomically realistic cardiorespiratory simulator to make them look like real angiographies. Methods -- The enhancement is performed by applying the CycleGAN deep network for transferring the style of real angiograms acquired during percutaneous interventions into a data set composed of realistically simulated arteries. Results -- The cycle consistency was evaluated by comparing an input simulated image with the one obtained after two cycles of image translation. An average structural similarity (SSIM) of 0.948 on our data sets has been obtained. The vessel preservation was measured by comparing segmentations of an input image and its corresponding enhanced image using Dice coefficient. Conclusions -- We proposed an application of the CycleGAN deep network for enhancing the artificial data as an alternative to classical data augmentation techniques for medical applications, particularly focused on angiogram generation. We discussed success and failure cases, explaining conditions for the realistic data augmentation which respects both the complex physiology of arteries and the various patterns and textures generated by X-ray angiography.

Item Type: Peer reviewed article published in a journal
Duong, Luc
Affiliation: Génie logiciel et des technologies de l'information
Date Deposited: 26 Aug 2019 20:03
Last Modified: 19 May 2022 19:30

Actions (login required)

View Item View Item