Benjamin Billot

I’m a postdoc at the Medical Vision Group led by Prof. Polina Golland. My research focuses on improving data representation to increase the robustness of systems for the analysis of clinical imaging data.

After completing a MSc in neuro-technology at Imperial College London in 2016, I joined the incubator of start-ups Founders Factory as a member of the AI team. I then pursued a PhD at University College London with Dr. Juan Eugenio Iglesias on developing a domain randomisation strategy for domain-agnostic segmentation of brain MRI (SynthSeg).

In addition to further explore domain randomisation techniques, I’m working on different projects including equivariant networks, registration of fetal MRI, unifying disjoint manual annotation databases to train unified segmentation models.

News

Oct 27, 2023	Great presentations and discussion at the Boston Medical Imaging Workshop that I co-organised with Oula Puonti, Katie Larson, Jon Haitz and Neel Dey.
Oct 19, 2023	Check out our new preprint (accepted at WCACV 2024). Work led by Neel Dey on domain randomisation for segmentation of star-shape objects.
Oct 12, 2023	Loads of great works at MICCAI, always a pleasure to attend!
Jul 10, 2023	Glad to have presented my work at MIDL 2023 on Equivariant Networks for registration of fetal brain MRI !
Mar 1, 2023	SynthSeg (Medical Image Analysis) and SynthSeg 2.0 (PNAS) are out!
Nov 1, 2022	Started my new job at MIT!

Selected publications

Journal
Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets

Benjamin Billot, Magdamo Colin, You Cheng, and 2 more authors

Proceedings of the National Academy of Sciences (PNAS), 2023

Abs Bib HTML PDF

Every year, millions of brain MRI scans are acquired in hospitals, which is a figure considerably larger than the size of any research dataset. Therefore, the ability to analyze such scans could transform neuroimaging research. Yet, their potential remains untapped since no automated algorithm is robust enough to cope with the high variability in clinical acquisitions (MR contrasts, resolutions, orientations, artifacts, and subject populations). Here, we present SynthSeg+, an AI segmentation suite that enables robust analysis of heterogeneous clinical datasets. In addition to whole-brain segmentation, SynthSeg+ also performs cortical parcellation, intracranial volume estimation, and automated detection of faulty segmentations (mainly caused by scans of very low quality). We demonstrate SynthSeg+ in seven experiments, including an aging study on 14,000 scans, where it accurately replicates atrophy patterns observed on data of much higher quality. SynthSeg+ is publicly released as a ready-to-use tool to unlock the potential of quantitative morphometry.
@article{billot_robust_2023, title = {{Robust} machine learning segmentation for large-scale analysis of heterogeneous clinical brain {MRI} datasets}, author = {Billot, Benjamin and Colin, Magdamo and Cheng, You and Das, Sudeshna and Iglesias, Juan Eugenio}, journal = {{Proceedings} of the {National} {Academy} of {Sciences} ({PNAS})}, year = {2023}, volume = {120}, number = {9}, }