Abstract

Echo planar imaging (EPI) enables rapid magnetic resonance (MR) imaging and is widely used in applications such as diffusion-weighted imaging (DWI) and functional MRI (fMRI). However, EPI is highly susceptible to geometric distortion artifacts, which degrade image quality and hinder accurate diagnosis. We propose a reconstruction framework that leverages AI-learned priors within a model-based approach to correct EPI distortions. The method is evaluated on phantom, brain, and prostate DWI with T2-w FSE geometric reference, including quantitative Dice alignment against expert radiologist annotations. Results demonstrate effective distortion correction and improved structural fidelity over strong baselines without per-dataset fine-tuning.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MLMI_075.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: https://openreview.net/forum?id=1NnnrDYHEa

BibTex

@InProceedings{ChaSud_Modelbased_MICCAISAT2026,
        author = { Chatterjee, Sudhanya AND Shanbhag, Dattesh D. AND Sundaresan, Rajagopalan AND Lan, Patricia AND Wiesinger, Florian AND Guidon, Arnaud},
        title = { { Model-based distortion correction for Magnetic Resonance Echo Planar Imaging } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17272},
        month = {pending},
        page = {pending}
}


back to top