arXiv Computer Vision August 21, 2026 By Junkai Liu, Nay Aung, Theodoros N. Arvanitis, Joao A. C. Lima, Steffen E. Petersen, Le Zhang

Exploiting Completeness Perception with Diffusion Transformer for Unified 3D MRI Synthesis

Read the original on arXiv Computer Vision →

arXiv:2602. 18400v3 Announce Type: replace-cross Abstract: Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in clinical practice.

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.

arXiv AI

Jun 17

Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis

arXiv:2606. 17989v1 Announce Type: cross Abstract: Multi-contrast magnetic resonance imaging (MRI) provides complementary information for clinical diagnosis.

By Yonghao Chen, Sicheng Yang, Rui Tang, Lei Zhu

diffusion

arXiv AI

Jun 19

BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation

arXiv:2606. 19651v1 Announce Type: new Abstract: Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented cohorts, simulate disease trajectories, and support privacy-preserving data sharing.

By Max Van Puyvelde, Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert

llms rag diffusion nlp benchmarks safety

arXiv AI

Jun 16

Unified Multimodal Model for Brain MRI Imputation and Understanding

arXiv:2606. 16484v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold great potential for medicine, as they inherit knowledge from LLM and allow multiple data modalities to be integrated, analysed and interpreted in natural language.

By Zhiyun Song, Che Liu, Tian Xia, Avinash Kori, Wenjia Bai

llms rag multimodal safety

Hugging Face Trending Papers

Jun 25

Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis

Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and privacy restrictions. To address this, we propose a 4D controllable generative framework for anatomically consistent data augmentation.

diffusion computer-vision safety

arXiv Machine Learning

Jun 18

Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Masks

arXiv:2606. 18354v1 Announce Type: cross Abstract: Recent advances in generative machine learning models have significantly improved medical imaging, offering promising solutions for data augmentation, privacy preservation, and improved model generalization.

By Muge Zhang, Muhammad Ali Khaliq, Jamal Alsakran, Byeong Kil Lee, Jeeho Ryoo

diffusion computer-vision safety

arXiv AI

Jun 26

Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis

arXiv:2606. 26764v1 Announce Type: cross Abstract: Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and privacy restrictions.

By Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang, Lingxiao Zhao, Xin Gao

diffusion computer-vision safety

One email a morning, machine-written

Related stories

Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis

BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation

Unified Multimodal Model for Brain MRI Imputation and Understanding

Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis

Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Masks

Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis