# Bridging Synthetic-to-Real Gaps: Frequency-Aware Perturbation and Selection for Single-shot Multi-Parametric Mapping Reconstruction

arXiv: https://arxiv.org/abs/2503.03475 · HTML: https://mlsanity.com/paper/2503.03475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 18 of 18)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Statistical Aspects of Wasserstein Distances](https://mlsanity.com/paper/1806.05500/) (2018)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations](https://mlsanity.com/paper/2008.05571/) (2020)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Physics-driven Synthetic Data Learning for Biomedical Magnetic Resonance](https://mlsanity.com/paper/2203.11178/) (2022)
- [Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learning](https://mlsanity.com/paper/1904.05168/) (2019)
- [SuperDTI: Ultrafast diffusion tensor imaging and fiber tractography with deep learning](https://mlsanity.com/paper/2002.01031/) (2020)
- [DIFFnet: Diffusion parameter mapping network generalized for input diffusion gradient schemes and bvalues](https://mlsanity.com/paper/2102.02463/) (2021)
- [Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies](https://mlsanity.com/paper/2401.16564/) (2024)
- [Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection](https://mlsanity.com/paper/2108.09178/) (2021)
- [ASC: Appearance and Structure Consistency for Unsupervised Domain Adaptation in Fetal Brain MRI Segmentation](https://mlsanity.com/paper/2310.14172/) (2023)
- [Adaptation of Surgical Activity Recognition Models Across Operating Rooms](https://mlsanity.com/paper/2207.03083/) (2022)
- [Segmentation-guided Domain Adaptation and Data Harmonization of Multi-device Retinal Optical Coherence Tomography using Cycle-Consistent Generative Adversarial Networks](https://mlsanity.com/paper/2208.14635/) (2022)
- [Model-based Synthetic Data-driven Learning (MOST-DL): Application in Single-shot T2 Mapping with Severe Head Motion Using Overlapping-echo Acquisition](https://mlsanity.com/paper/2107.14521/) (2021)
- [FlexDTI: Flexible diffusion gradient encoding scheme-based highly efficient diffusion tensor imaging using deep learning](https://mlsanity.com/paper/2308.01173/) (2023)

## Abstract (arXiv)

Data-centric artificial intelligence (AI) has remarkably advanced medical imaging, with emerging methods using synthetic data to address data scarcity while introducing synthetic-to-real gaps. Unsupervised domain adaptation (UDA) shows promise in ground truth-scarce tasks, but its application in reconstruction remains underexplored. Although multiple overlapping-echo detachment (MOLED) achieves ultra-fast multi-parametric reconstruction, extending its application to various clinical scenarios, the quality suffers from deficiency in mitigating the domain gap, difficulty in maintaining structural integrity, and inadequacy in ensuring mapping accuracy. To resolve these issues, we proposed frequency-aware perturbation and selection (FPS), comprising Wasserstein distance-modulated frequency-aware perturbation (WDFP) and hierarchical frequency-aware selection network (HFSNet), which integrates frequency-aware adaptive selection (FAS), compact FAS (cFAS) and feature-aware architecture integration (FAI). Specifically, perturbation activates domain-invariant feature learning within uncertainty, while selection refines optimal solutions within perturbation, establishing a robust and closed-loop learning pathway. Extensive experiments on synthetic data, along with diverse real clinical cases from 5 healthy volunteers, 94 ischemic stroke patients, and 46 meningioma patients, demonstrate the superiority and clinical applicability of FPS. Furthermore, FPS is applied to diffusion tensor imaging (DTI), underscoring its versatility and potential for broader medical applications. The code is available at https://github.com/flyannie/FPS.