Anatomically constrained CT image translation for heterogeneous blood vessel segmentation

Giammarco La Barbera (Télécom Paris),* Haithem Boussaid (Philips Research Paris), Francesco Maso (Télécom Paris), Sabine Sarnacki (IMAG2, Imagine Institute), Rouet Laurence (Philips Research Paris), Pietro Gori (Télécom Paris), Isabelle Bloch (Télécom Paris)
The 33rd British Machine Vision Conference


Anatomical structures such as blood vessels in contrast-enhanced CT (ceCT) images can be challenging to segment due to the variability in contrast medium diffusion. The combined use of ceCT and contrast-free (CT) CT images can improve the segmentation performances, but at the cost of a double radiation exposure. To limit the radiation dose, generative models could be used to synthesize one modality, instead of acquiring it. The CycleGAN approach has recently attracted particular attention because it alleviates the need for paired data that are difficult to obtain. Despite the great performances demonstrated in the literature, limitations still remain when dealing with 3D volumes generated slice by slice from unpaired datasets with different fields of view. We present an extension of CycleGAN to generate high fidelity images, with good structural consistency, in this context. We leverage anatomical constraints and automatic region of interest selection by adapting the Self-Supervised Body Regressor. These constraints enforce anatomical consistency and allow feeding anatomically-paired input images to the algorithm. Results show qualitative and quantitative improvements, compared to state-of-the-art methods, on the translation task between ceCT and CT images (and vice versa). Moreover, using the CT images produced by our algorithm, we achieve blood vessel segmentation performance on par with the segmentation performance using real CT images.



author    = {Giammarco La Barbera and Haithem Boussaid and Francesco  Maso  and Sabine Sarnacki and Rouet Laurence and Pietro Gori and Isabelle Bloch},
title     = {Anatomically constrained CT image translation for heterogeneous blood vessel segmentation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year      = {2022},
url       = {}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection