Abstract

Abstract. Respiratory motion degrades abdominal T2 HASTE MRI in low- and middle-income countries where vendor motion-correction li- censes are unavailable and failed scans are deleted during routine PACS cleanup, precluding supervised training. To address this, we introduce NIMARC-MRI, the first public abdominal MRI dataset from West Africa, comprising 139 clean HASTE, 25 native motion-degraded HASTE, and 79 paired HASTE–TSE TRIGGER acquisitions from a Nigerian centre operating 1.5 T Siemens scanner without integrated motion-correction licenses. A 2D U-Net with 7.7 million parameters was trained on 3D- consistent synthetic respiratory motion necessitated by local infrastruc- ture reality and validated via a three-tier strategy: held-out synthetic data, blinded radiologist Likert scoring on native real motion, and cross- sequence TRIGGER generalisation. On synthetic test data the model achieved SSIM 0.863 ± 0.042 and PSNR 30.06 ± 1.80 dB. On native real motion, however, blinded radiologist and radiographer scores showed no significant improvement (mean Likert 4.06 ± 0.55 original versus 4.04 ± 0.61 corrected, P = 0.914), with 28% of cases rated worse after cor- rection. Cross-sequence TRIGGER evaluation showed modest SSIM im- provement (0.404 ± 0.073 versus 0.334 ± 0.055, P < 0.001) without radiologist-perceived gain. These findings demonstrate that conserva- tive synthetic motion fails to capture clinical motion severity, expos- ing a reproducible synthetic-to-real gap. NIMARC-MRI dataset is being prepared for controlled Zenodo release pending final ethics clearance to benchmark LMIC abdominal MRI-AI. The aim is to establish a repro- ducible baseline for motion correction in resource-constrained settings.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MIRASOL_047.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/MIRASOL_047_supp.pdf

Link to Open Review

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

BibTex

@InProceedings{ZubAbd_NIMARCMRI_MICCAISAT2026,
        author = { Zubair, Abdulrazaq A. AND Muhammad, Nafiu Musa AND Krah, Simeon AND Ibrahim, Ummasalma Usman AND Abdumumin, Yusuf Tijjani AND Tijjani, Ismail Ismail AND Ibrahim, Ummulkhairi AND Anas, Alyasaa AND Yakubu, Mubaraq AND Muhammad, Abbas Rabiu},
        title = { { NIMARC-MRI: Abdominal HASTE Dataset and a Baseline U-Net Exposing the Synthetic-to-Real Gap in Low-Resource Motion Correction } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17265},
        month = {pending},
        page = {pending}
}


back to top