Overview

Medical image synthesis studies how to create or transform images such as MRI, CT, PET, ultrasound, and pathology scans when scans are missing, costly, or scarce. GANs and VAEs, diffusion and flow-matching models, autoregressive generators, and neural representations are conditioned on anatomy, clinical text, masks, acquisition physics, or patient history to translate modalities, model disease progression, and generate training data. The work matters because synthetic images could reduce acquisition burdens, expand underrepresented datasets, and support tasks such as segmentation, diagnosis, and treatment planning. A central challenge is that visual fidelity does not guarantee preservation of lesions, patient-specific anatomy, or downstream clinical utility, while generalization, privacy, and computational cost also remain important concerns.

Latest papers

334 papers31 papers in the last four weeks, down 9% on the four weeks before. 0.2% of all new papers.

May 30, 2025

pyMEAL: A Multi-Encoder Augmentation-Aware-Learning Toolbox for Robust Medical Image Translation

Medical imaging plays a vital role in clinical diagnosis, yet AI-driven imaging methods remain challenged by patient variability, image artifacts, and limited robustness across acquisition conditions. Although deep learning has advanced medical image analysis, 3D image translation remains hindered by limited training data and variability arising from scanner differences, imaging protocols, and patient motion. Conventional data augmentation typically relies on a single transformation pipeline, overlooking augmentation-specific characteristics and limiting representation learning. To address these challenges, we propose Multi-Encoder Augmentation-Aware Learning (MEAL), which processes multiple augmentation variants through dedicated encoder pathways. Three feature integration strategies are investigated: encoder concatenation (MEAL-CC), fusion layer (MEAL-FL), and an adaptive controller block (MEAL-BD). By dynamically weighting augmentation-specific features before decoding, MEAL-BD preserves complementary representations and improves robustness to clinically relevant variability. We evaluate MEAL using CT-to-T1-weighted MRI translation, a clinically relevant task when MRI is unavailable, contraindicated, or delayed. Across predefined and unseen test datasets, MEAL-BD consistently outperformed competing approaches under both geometric perturbations and standard imaging conditions, achieving higher peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). By prioritizing structural fidelity over perceptual realism, MEAL supports clinical interpretation and downstream image analysis rather than replacing diagnostic MRI, demonstrating that augmentation-aware representation learning improves the robustness and clinical applicability of medical image translation.
May 12, 2025

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

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. We propose FermatSyn, which addresses three persistent limitations: (1) SAM2-based Prior Encoder that injects domain-aware anatomical knowledge via LoRA+^{+} efficient fine-tuning of a frozen SAM2 Vision Transformer; (2) Hierarchical Residual Downsampling Module (HRDM) coupled with a Cross-scale Integration Network (CIN) that preserves high-frequency lesion details and adaptively fuses global--local representations; and (3) continuity constrained Fermat Spiral Scanning strategy within a Bidirectional Fermat Scan Mamba (BFS-Mamba), constructing an approximately isotropic receptive field that substantially reduces the directional bias of raster or spiral serialization. Experiments on SynthRAD2023, BraTS2019, BraTS-MEN, and BraTS-MET show FermatSyn surpasses state-of-the-art methods in PSNR, SSIM, FID, and 3D structural consistency. Downstream segmentation on synthesized images yields no significant difference from real-image training (p>0.05p{>}0.05), confirming clinical utility. Code is available at https://github.com/exsinger-hub/ FermatSyn.
May 9, 2025

Decoupling Multi-Contrast Super-Resolution: Self-Supervised Implicit Re-Representation for Unpaired Cross-Modal Synthesis

Multi-contrast super-resolution (MCSR) is crucial for enhancing MRI but current deep learning methods are limited. They typically require large, paired low- and high-resolution (LR/HR) training datasets, which are scarce, and are trained for fixed upsampling scales. While recent self-supervised methods remove the paired data requirement, they fail to leverage valuable population-level priors. In this work, we propose a novel, decoupled MCSR framework that resolves both limitations. We reformulate MCSR into two stages: (1) an unpaired cross-modal synthesis (uCMS) module, trained once on unpaired population data to learn a robust anatomical prior; and (2) a lightweight, patient-specific implicit re-representation (IrR) module. This IrR module is optimized in a self-supervised manner to fuse the population prior with the subject's own LR target data. This design uniquely fuses population-level knowledge with patient-specific fidelity without requiring paired target-domain LR/HR training data or paired cross-modal HR reference-target training data. Here, 'unpaired' refers to the population-level training setting; at subject-specific inference, as in standard MCSR, the method uses a matched HR reference image from another contrast together with the subject's LR target image. By building the IrR module on an implicit neural representation, our framework is also inherently scale-agnostic. Our method demonstrates superior quantitative performance on different datasets, with exceptional robustness at extreme scales (16x, 32x), a regime where competing methods fail. Our work presents a data-efficient, flexible, and computationally lightweight paradigm for MCSR, enabling high-fidelity, arbitrary-scale reconstruction without the need for paired population-level supervision.
Mar 28, 2024

Incorporating synthetic data from diffusion models supports echocardiography downstream tasks

Purpose: Large labeled echocardiography datasets are costly to collect. We use diffusion models to generate synthetic training data for segmentation and cardiac phase classification. Approach: We study three generation approaches on CAMUS: an unconditional image space model, a latent model conditioned on plain English prompts or abstract tokens, and a ControlNet model conditioned on an abstract token and segmentation mask. We evaluate synthesis with Fréchet Inception Distance (FID) and augmentation using segmentation and classification of end diastole and end systole. We also evaluate segmentation within CardiacUDC and directly from CAMUS to CardiacUDC. Results: Conditioning on an abstract token and segmentation mask gives the lowest mean FID, 1.5 compared with 3.2 for the Semantic Diffusion Model. Abstract token augmentation gives the highest classification accuracy, improving ResNet-18 from 83.8% to 87.2% and VGG-16 from 74.5% to 78.7%. Synthetic augmentation gives the highest mean Dice of 87.6% for the CAMUS 2D U-Net and 84.6% for the CardiacUDC nnU-Net. When nnU-Net models are trained on CAMUS and evaluated directly on CardiacUDC, augmentation raises mean Dice from 74.6% to 75.2%. Conclusions: Incorporating synthetic images into training gives modest gains in CAMUS phase classification, segmentation within CAMUS and CardiacUDC, and direct segmentation from CAMUS to CardiacUDC.