Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learning
Not on the map. Why?
Abstract (arXiv)
Contrast-enhanced magnetic resonance imaging (CE-MRI) is crucial for tumor detection and diagnosis, but the use of gadolinium-based contrast agents (GBCAs) in clinical settings raises safety concerns due to potential health risks. To circumvent these issues while preserving diagnostic accuracy, we propose a novel Transformer with Localization Prompts (TLP) framework for synthesizing CE-MRI from non-contrast MR images. Our architecture introduces three key innovations: a hierarchical backbone that uses efficient Transformer to process multi-scale features; a multi-stage fusion system consisting of Local and Global Fusion modules that hierarchically integrate complementary information via spatial attention operations and cross-attention mechanisms, respectively; and a Fuzzy Prompt Generation (FPG) module that enhances the TLP model's generalization by emulating radiologists' manual annotation through stochastic feature perturbation. The framework uniquely enables interactive clinical integration by allowing radiologists to input diagnostic prompts during inference, synergizing artificial intelligence with medical expertise. This research establishes a new paradigm for contrast-free MRI synthesis while addressing critical clinical needs for safer diagnostic procedures. Codes are available at https://github.com/ChanghuiSu/TLP.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 21 of its 47 references that are in the map. First posted on arXiv 3 Mar 2025.
Builds on
21 of 47 references.
References · 21
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
- 2017Non-local Neural Networkscited by 2,290
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
- 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
9 more
- 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
- 2022Unsupervised Medical Image Translation with Adversarial Diffusion Modelscited by 191
- 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
- 2020Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesiscited by 86
- 2023Unified Multi-Modal Image Synthesis for Missing Modality Imputationcited by 39
- 2017Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images using Weakly-Supervised Joint Convolutional Sparse Codingcited by 33
- 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generationcited by 33
- 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
- 2023Synthesis of Contrast-Enhanced Breast MRI Using Multi-b-Value DWI-based Hierarchical Fusion Network with Attention Mechanismcited by 8
Built on by
Citing papers per year: 2025: 3.
3 papers.