They / He

Postdoctoral researcher

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

conferences

portfolio

publications

Learning a reconnecting regularization term for blood vessel variational segmentation

Published:

The segmentation of blood vessels in medical images is a challenging task as they are thin, connected and tortuous. The detection of a connected vascular network is of the utmost importance in clinical applications (\textit{e.g.} blood flow simulations, vascular network modeling and analysis). Deep learning approaches have been developed to tackle this issue, but they require a large annotated dataset for each new application of interest, which is very challenging to build for vascular networks. In this work, rather than learning the segmentation task, we propose to learn a reconnecting regularization term that learns geometric properties of vascular networks independent of the image modality. Therefore, this term generalizes better than deep learning segmentation models, and can be easily plugged into variational segmentation frameworks to detect vascular networks in different datasets without requiring annotations. We apply this approach on retinal images by training our reconnecting term on the STARE dataset and applying it on the DRIVE dataset. We show that our approach better preserves the connectivity of vascular networks than classic regularization terms in the literature. Finally, we illustrate the generalization power of our reconnecting term by applying it to other types of data.

Sophie Carneiro-Esteves, Antoine Vacavant and Odyssée Merveille. "Learning a reconnecting regularization term for blood vessel variational segmentation" IEEE-EMBS BHI 2021 .

Apprentissage d’un terme de régularisation reconnecteur pour la segmentation variationnelle des vaisseaux sanguins en 3D

Published:

Blood vessels segmentation is a complex task as they are thin, tortuous and low-contrasted. The vascular network connectivity is usually lost during segmentation eventhough it is of the utmost importance for most applications such as modelling or blood flow simulation. In a previous work, we proposed to learn a reconnecting regularisation term which can be used in a variational segmentation scheme for 2D images. In this work, we extend this previous method to 3D imaging. We first adapt our reconnecting term learning process to 3D images and improve the variational segmentation algorithm to increase its stability and efficiency in the 3D context. We show that our regularization term better preserve vascular networks in real images than the classical variational approach and notably improve its global connectivity of almost 10%.

Sophie Carneiro-Esteves, Antoine Vacavant and Odyssée Merveille. "Apprentissage d un terme de régularisation reconnecteur pour la segmentation variationnelle des vaisseaux sanguins en 3D " XXIIIme Colloque Francophone de Traitement du Signal et des Images.

A plug-and-play framework for curvilinear structure segmentation based on a learned reconnecting regularization

Published:

Curvilinear structures are present in various fields in image processing such as blood vessels in medical imaging or roads in remote sensing. Their detection is crucial for many applications. In this article, we propose an unsupervised plug-and-play framework for the segmentation of curvilinear structures that focuses on the preservation of their connectivity. This framework includes an algorithm for generating realistic pairs of connected/disconnected curvilinear structures and a reconnecting regularization operator that can be learned from a synthetic dataset. Once learned, this regularization operator can be plugged into a variational segmentation scheme and used to segment curvilinear structure images without requiring annotations. We demonstrate the interest of our approach on the segmentation of vascular images both in 2D and 3D and compare its results with classic unsupervised and deep learning-based approach. Comparative evaluations against unsupervised classic and deep learning-based methods highlight the superior performance of our approach, showcasing remarkable improvements in preserving the connectivity of curvilinear structures (approximately 90% in 2D and 70% in 3D). We finally showcase the good generalizability behavior of our approach on two different applications : road cracks and porcine corneal cells segmentations.

Sophie Carneiro-Esteves, Antoine Vacavant and Odyssée Merveille. "A plug-and-play framework for curvilinear structure segmentation based on a learned reconnecting regularization" Neurocomputing 2024 .

Restoring Connectivity in Vascular Segmentations using a Learned Post-Processing Model

Published:

Accurate segmentation of vascular networks is essential for computer-aided tools designed to address cardiovascular diseases. Despite more than thirty years of research, it remains a challenge to obtain vascular segmentation results that preserve the connectivity of the underlying vascular network. Yet connectivity is one of the key features of these tools. In this work, we propose a post-processing algorithm aiming to reconnect vascular structures that have been disconnected by a segmentation algorithm. Connectivity being a complex property to model explicitly, we propose to learn this geometric feature either through synthetic data or annotations of the application of interest. The resulting post-processing model can be used on the output of any supervised or unsupervised vascular segmentation algorithm. We show that this post-processing effectively restores the connectivity of vascular networks both in 2D and 3D images, leading to improved overall segmentation results.

Sophie Carneiro-Esteves, Antoine Vacavant and Odyssée Merveille. "Restoring Connectivity in Vascular Segmentations using a Learned Post-Processing Model" TGI3, MICCAI 2024 Workshop .

software

talks

teaching

Informatics and Numeric Society
[182h] Tutorials and Lectures, Undergraduate Level (L1 - L2), INSA Lyon FIMI, 2023-2024

Basics in different areas of computer science and digital: Algorithmic, Programming (Python) and Network. International groups with students from Asia and Latin America.

Signals and Linear Systems
[40 h] Tutorials, Undergraduate Level (L3), CPE Lyon, 2020-2022

Comprehensive study of continuous and discrete-time signals and frequency domain analysis.

Informatics and Numeric Society
[152 h] Tutorials, Undergraduate Level (L1), INSA Lyon FIMI, 2020-2023

Basics in different areas of computer science and digital: Algorithmic, Programming (Python) and Network.