arXiv Computer Vision August 25, 2026 By Rory Bell, Artemis Bouzaki, Jiaming Cao, Jasmine Morrison, Chelsea Sargeant

Multimodal pseudo-CT synthesis for PET attenuation correction using separate modality encoding and topogram conditioning

Read the original on arXiv Computer Vision →

The paper presents a multimodal 3D patch-based U‑Net for generating pseudo‑CT images from non‑attenuation‑corrected PET (NAC‑PET), MRI, and 2D topograms. It employs separate PET and MR encoders, multi‑scale feature fusion, and FiLM‑based topogram conditioning at the bottleneck to integrate complementary cross‑modal information while reducing dependence on precise voxel‑wise correspondence. The authors participated in the BIC‑MAC Challenge and released their final model on GitHub.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

multimodal

arXiv Computer Vision

Aug 25

Region-Weighted Losses and Model Fusion for Cross-Modal PET Attenuation Correction

The paper presents a method for the BIC-MAC challenge, aiming to generate pseudo‑CT images from NAC‑PET, DIXON MRI, and a topogram, and to evaluate both the pseudo‑CT and the resulting attenuation‑corrected PET. The authors improve upon a 3D U‑Net baseline by focusing on loss design: they compute an L1 error in the Carney attenuation‑coefficient space, weighted by anatomical region, and incorporate DIXON MRI as additional input only after this loss was applied. Finally, they fuse two independently trained models via a fixed convex combination, achieving better performance than either model alone and topping the public validation leaderboard.

By Khoa Tuan Nguyen, Joris Vankerschaver, Wesley De Neve

multimodal benchmarks

arXiv AI

Jun 12

Dual-Domain Equivariant Generative Adversarial Network for Multimodal CT-PET Synthesis

arXiv:2606. 13341v1 Announce Type: cross Abstract: We present a Dual-Domain Equivariant Generative Adversarial Network (DDE-GAN) for multimodal CT-PET image synthesis.

By Gabriel Steele, Alzahra Altalib, Alessandro Perelli

diffusion multimodal safety

arXiv Computer Vision

Aug 21

FermatSyn: SAM2-Enhanced Bidirectional Mamba with Isotropic Spiral Scanning for Multi-Modal Medical Image Synthesis

arXiv:2505. 07687v4 Announce Type: replace-cross Abstract: Multi-modal medical image synthesis is pivotal for alleviating clinical data scarcity, yet existing methods fail to reconcile global anatomical consistency with high-fidelity local detail.

By Feng Yuan, Yifan Gao, Haoyue Li, Xin Gao

llms computer-vision fine-tuning multimodal benchmarks safety

arXiv Computer Vision

3d ago

Mamba-driven MRI-to-CT Synthesis for MRI-only Radiotherapy Planning

arXiv:2603.23295v2 Announce Type: replace Abstract: Radiotherapy workflows for oncological patients increasingly rely on multi-modal medical imaging, commonly involving both Magnetic Resonance Imagin...

By Konstantinos Barmpounakis, Theodoros P. Vagenas, Maria Vakalopoulou, George K. Matsopoulos

diffusion computer-vision multimodal

arXiv Computer Vision

3d ago

Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays

arXiv:2603.26509v2 Announce Type: replace Abstract: Computed tomography (CT) provides rich 3D anatomical detail but is often constrained by high radiation exposure, substantial costs, and limited ava...

By Martin Rath, Morteza Ghahremani, Yitong Li, Ashkan Taghipour, Marcus Makowski, Christian Wachinger

diffusion benchmarks

arXiv AI

Jun 29

MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction

arXiv:2603. 03710v3 Announce Type: replace-cross Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness.

By Seunghoi Kim, Chen Jin, Henry F. J. Tregidgo, Matteo Figini, Daniel C. Alexander

diffusion computer-vision multimodal safety

One email a morning, machine-written

Related stories

Region-Weighted Losses and Model Fusion for Cross-Modal PET Attenuation Correction

Dual-Domain Equivariant Generative Adversarial Network for Multimodal CT-PET Synthesis

FermatSyn: SAM2-Enhanced Bidirectional Mamba with Isotropic Spiral Scanning for Multi-Modal Medical Image Synthesis

Mamba-driven MRI-to-CT Synthesis for MRI-only Radiotherapy Planning

Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays

MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction