Background And Objective: Diffusion models have demonstrated their ability in image generation and solving inverse problems like restoration. Unlike most existing deep-learning based image restoration techniques which rely on unpaired or paired data for degradation awareness, diffusion models offer an unsupervised degradation independent alternative. This is well-suited in the context of restoring artifact-corrupted Magnetic Resonance Images (MRI), where it is impractical to exactly model the degradations apriori. In MRI, multiple corruptions arise, for instance, from patient movement compounded by undersampling artifacts from the acquisition settings.
Methods: To tackle this scenario, we propose AutoDPS, an unsupervised method for corruption removal in brain MRI based on Diffusion Posterior Sampling. Our method (i) performs motion-related corruption parameter estimation using a blind iterative solver, and (ii) utilizes the knowledge of the undersampling pattern when the corruption consists of both motion and undersampling artifacts. We incorporate this corruption operation during sampling to guide the generation in recovering high-quality images.
Results: Despite being trained to denoise and tested on completely unseen corruptions, our method AutoDPS has shown ∼ 1.63 dB of improvement in PSNR over baselines for realistic 3D motion restoration and ∼ 0.5 dB of improvement for random motion with undersampling. Additionally, our experiments demonstrate AutoDPS's resilience to noise and its generalization capability under domain shift, showcasing its robustness and adaptability.
Conclusion: In this paper, we propose an unsupervised method that removes multiple corruptions, mainly motion with undersampling, in MRI images which are essential for accurate diagnosis. The experiments show promising results on realistic and composite artifacts with higher improvement margins as compared to other methods. Our code is available at https://github.com/arunima101/AutoDPS/tree/master.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.cmpb.2025.108684 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Elastographic magnetization prepared imaging with rapid encoding.
Magn Reson Med
March 2025
Department of Biomedical Engineering, University of Delaware, Newark, Delaware, USA.
Purpose: To introduce a novel sequence for achieving fast, whole-brain MR elastography data through the introduction of a magnetization preparation block for motion encoding along with rapid imaging readouts.
Theory And Methods: We implemented MRE motion encoding in a magnetization preparation pulse sequence block, where spins are excited, motion encoded, and then stored longitudinally. This magnetization is accessed through a train of rapid gradient echoes and encoded with a 3D stack-of-spirals trajectory.
Hybrid transformer-CNN network-driven optical-scanning undersampling for photoacoustic remote sensing microscopy.
Photoacoustics
April 2025
College of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin 300072, China.
Imaging speed is critical for photoacoustic microscopy as it affects the capability to capture dynamic biological processes and support real-time clinical applications. Conventional approaches for increasing imaging speed typically involve high-repetition-rate lasers, which pose a risk of thermal damage to samples. Here, we propose a deep-learning-driven optical-scanning undersampling method for photoacoustic remote sensing (PARS) microscopy, accelerating imaging acquisition while maintaining a constant laser repetition rate and reducing laser dosage.
View Article and Find Full Text PDFJoint coil sensitivity and motion correction in parallel MRI with a self-calibrating score-based diffusion model.
Med Image Anal
February 2025
School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy, Shanghai Jiao Tong University, Shanghai, China. Electronic address:
Magnetic Resonance Imaging (MRI) stands as a powerful modality in clinical diagnosis. However, it faces challenges such as long acquisition time and vulnerability to motion-induced artifacts. While many existing motion correction algorithms have shown success, most fail to account for the impact of motion artifacts on coil sensitivity map (CSM) estimation during fast MRI reconstruction.
View Article and Find Full Text PDFDiffusion-prepared imaging with amplitude navigation for correction of motion-induced signal loss.
Magn Reson Med
March 2025
Radiology, Stanford University, Stanford, California, USA.
Purpose: Diffusion-prepared imaging is a flexible alternative to conventional spin-echo diffusion-weighted EPI that allows selection of different imaging readouts and k-space traversals, and permits control of image contrast or image artifacts. We investigate a new signal model and reconstruction for diffusion-prepared imaging that addresses signal variations caused by motion-sensitizing diffusion gradients.
Methods: A signal model, sampling theory, and reconstruction framework were developed assuming that motion-induced phases and the measured signals are random variables.
Hybrid attention structure preserving network for reconstruction of under-sampled OCT images.
Sci Rep
March 2025
College of Information and Engineering, Hebei GEO University, Hebei, China.
Optical coherence tomography (OCT) is a non-invasive, high-resolution imaging technology that provides cross-sectional images of tissues. Dense acquisition of A-scans along the fast axis is required to obtain high digital resolution images. However, the dense acquisition will increase the acquisition time, causing the discomfort of patients.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!