Arthur Longuefosse

Postdoctoral Researcher

RIKEN Center for Integrative Medical Sciences (IMS), Medical Data Deep Learning Team, Tokyo

arthur.longuefosse [at] riken.jp · arthur.longuefosse [at] gmail.com

CV Google Scholar GitHub LinkedIn

About

I am a postdoctoral researcher in the Medical Data Deep Learning Team at the RIKEN Center for Integrative Medical Sciences (IMS) in Tokyo, led by Jun Seita, which I joined in October 2025. My research focuses on deep learning for medical image analysis, including cross-modality synthesis (MR-to-CT, CBCT-to-CT, missing MRI sequences), anatomically guided learning, segmentation, and representation learning for multiplexed tissue imaging.

I received my PhD in Computer Science from the University of Bordeaux (LaBRI) in December 2024, working on lung MR-to-CT synthesis under the supervision of Pascal Desbarats and Fabien Baldacci.

News

• 2026Our paper From Intensity to Anatomy: Optimizing nnU-Net for MR-to-CT Translation on SynthRAD2025 was published at ISBI 2026.
• 2026The SynthRAD2025 challenge report is out on arXiv.
• 2025Short paper on channel-independent representation learning for multiplexed imaging at MIDL.
• Oct 2025Joined the Medical Data Deep Learning Team at RIKEN IMS, Tokyo, as a postdoctoral researcher.
• Sep 20252nd place in both the MR-to-CT and CBCT-to-CT tasks of the SynthRAD2025 challenge (method paper).
• Dec 2024PhD in Computer Science, University of Bordeaux.

Publications

Journal articles

Anatomical feature-prioritized loss for enhanced MR to CT translation Arthur Longuefosse, Baudouin Denis de Senneville, Gaël Dournes, Ilyes Benlala, Fabien Baldacci, Pascal Desbarats Physics in Medicine & Biology, 70(14), 145012, 2025 [Paper]

Generating High-Resolution Synthetic CT from Lung MRI with Ultrashort Echo Times: Initial Evaluation in Cystic Fibrosis Arthur Longuefosse, Julien Raoult, Ilyes Benlala, Baudouin Denis de Senneville, Thomas Benkert, Julie Macey, Stéphanie Bui, Patrick Berger, Gilbert Ferretti, Jean-Yves Gaubert, Renan Liberge, Antoine Hutt, Baptiste Morel, François Laurent, Fabien Baldacci, Gaël Dournes Radiology, 308(1), e230052, 2023 [Paper]

Conference and workshop papers

From Intensity to Anatomy: Optimizing nnU-Net for MR-to-CT Translation on SynthRAD2025 Arthur Longuefosse, Javier Sequeiro González, Fabien Baldacci, Jun Seita IEEE International Symposium on Biomedical Imaging (ISBI), 2026 [Paper]

Preserving Marker Specificity with Lightweight Channel-Independent Representation Learning Simon Gutwein, Arthur Longuefosse, Jun Seita, Sabine Taschner-Mandl, Roxane Licandro Medical Imaging with Deep Learning (MIDL), short paper, 2025 [OpenReview][arXiv]

Multi-modal Brain MRI Synthesis with nnU-Net: Exploring Segmentation Performance and Cross-Modality Relationships Cecilia Diana-Albelda, Arthur Longuefosse, Álvaro García-Martín, Jesus Bescos Simulation and Synthesis in Medical Imaging (SASHIMI), MICCAI workshop, LNCS 16085, pp. 52–62, 2025 [Paper]

Adapted nnU-Net: A Robust Baseline for Cross-Modality Synthesis and Medical Image Inpainting Arthur Longuefosse, Edern Le Bot, Baudouin Denis de Senneville, Rémi Giraud, Boris Mansencal, Pierrick Coupé, Pascal Desbarats, Fabien Baldacci Simulation and Synthesis in Medical Imaging (SASHIMI), MICCAI workshop, pp. 24–33, 2024 [Paper]

Incorporating 3D Information in 2.5D Networks: Strategies for MR to CT Synthesis Arthur Longuefosse, Baudouin Denis de Senneville, Gaël Dournes, Ilyes Benlala, Pascal Desbarats, Fabien Baldacci IEEE International Symposium on Biomedical Imaging (ISBI), 2024 [Paper]

On the Use of Perceptual Loss for Fine Structure Generation: Illustration on Lung MR to CT Synthesis Arthur Longuefosse, Baudouin Denis de Senneville, Gaël Dournes, Ilyes Benlala, Pascal Desbarats, Fabien Baldacci IEEE International Symposium on Biomedical Imaging (ISBI), 2024 [Paper]

MR to CT Synthesis Using GANs: A Practical Guide Applied to Thoracic Imaging Arthur Longuefosse, Baudouin Denis de Senneville, Gaël Dournes, Ilyes Benlala, François Laurent, Fabien Baldacci, Pascal Desbarats VISIGRAPP 2023 – IVAPP, Vol. 3, pp. 268–274, 2023 [PDF]

Lung CT Synthesis Using GANs with Conditional Normalization on Registered Ultrashort Echo-Time MRI Arthur Longuefosse, Gaël Dournes, Ilyes Benlala, Baudouin Denis de Senneville, François Laurent, Pascal Desbarats, Fabien Baldacci IEEE International Symposium on Biomedical Imaging (ISBI), 2023

Preprints

CAPS: Clinically-Verifiable Anatomy-Prioritized Synthesis for Missing MRI Imputation in Brain Tumor Segmentation Cecilia Diana-Albelda, Arthur Longuefosse, et al. arXiv:2610.28179, 2026 under review[arXiv]

Generating Synthetic Computed Tomography for Radiotherapy: SynthRAD2025 Challenge Report Viktor Rogowski, Maarten L. Terpstra, Niklas Wahl, et al. (including Arthur Longuefosse) arXiv:2605.13555, 2026 [arXiv]

Deep Learning-Based Cross-Anatomy CT Synthesis Using Adapted nnResU-Net with Anatomical Feature Prioritized Loss Javier Sequeiro González, Arthur Longuefosse, Miguel Díaz Benito, Álvaro García Martín, Fabien Baldacci arXiv:2509.22394, 2025 – SynthRAD2025, 2nd place [arXiv]

Thesis

Deep Learning for MR to CT Translation in Thoracic Imaging Arthur Longuefosse PhD thesis, University of Bordeaux, 2024

Code

• nnUNet_translation — nnU-Net adapted for medical image-to-image translation (e.g. MR → synthetic CT): the self-configuring pipeline with a regression output and translation losses (L1, AFP).
• NIfTI-to-HTML Evaluator — zero-backend medical image evaluation and PACS-style viewer in the browser (code).

Teaching

• Perception & Interaction — Master ASPIC (2nd year), University of Bordeaux, 2023–2024: image processing, SLAM, introduction to deep learning.
• Introduction to Computer Science — Bachelor (1st year), University of Bordeaux, 2021–2023.
• Supervision of Master 2 research interns, 2021–2024.