EUVIMEDEUVIMED entdecken
Crossref

Temporal AI-assisted compressed sensing for high-resolution, motion-robust small-bowel MR enterography without antiperistaltic agents: a feasibility study

Ziman Xiong, Yufan Wang, Liya Ma, Xiaopeng Song, Wei Mao, Zhen Li, Yaqi Shen

European Radiology · 03.04.2026 · 36 (8) · 6776-6787

DOI: 10.1007/s00330-026-12498-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Radiology, online erschienen am 03.04.2026. Verfasst von Ziman Xiong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Intestine, Small, Artificial Intelligence, Image Interpretation, Computer-Assisted. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: To evaluate whether temporal AI-assisted compressed sensing (tACS) enables high-resolution, motion-robust magnetic resonance enterography (MRE) without antiperistaltic agents and improves acquisition efficiency and motility visualization. MATERIALS AND METHODS: This prospective single-center study enrolled consecutive patients who underwent both routine and tACS MRE on a 3.0-T scanner between October 2024 and June 2025, without antiperistaltic agents. The tACS protocol acquired axial and coronal T2-weighted images (T2WI); the routine protocol included a coronal Cine sequence. Acquisition time and total temporal frames for non-fat-saturated T2WI (routine and tACS) and Cine were recorded to calculate imaging efficiency (frames/min). Primary outcomes included total temporal frames, scan time, efficiency, subjective image-quality scores, apparent signal-to-noise ratio (aSNR), contrast-to-noise ratio (aCNR), maximum local variation sharpness, peri-enteric fat-plane clarity, and ileocecal-valve (ICV) motility. Paired statistical tests compared within-subject differences; Kendall's W assessed inter-reader agreement. RESULTS: Thirty patients completed both protocols. tACS acquired 504 frames in 287 s vs 107 frames in 241 s for the routine protocol, improving efficiency 4.0-fold (105.4 vs 26.6 frames/min; p < 0.001). Subjective image quality favored tACS (median 5.0 vs ≤ 4.0; p < 0.01) with perfect agreement (W = 1.00). Quantitative analysis demonstrated significantly improved sharpness (all p < 0.001) and increased aSNR/aCNR. Fat-plane clarity reached perfect scores in 93% (28/30) with tACS, and ICV motility scoring was superior to Cine (median 3.0 vs 2.0; p < 0.001). CONCLUSIONS: tACS enhances temporal resolution and image quality for MRE without antiperistaltic agents, with minimal extra scan time and potential to simplify clinical workflows. KEY POINTS: Question Can tACS provide high-resolution, motion-robust MRE images without the need for antiperistaltic agents? Findings tACS improved imaging efficiency four-fold while significantly enhancing subjective image quality, sharpness, and motility visualization compared to routine protocols. Clinical relevance tACS enables high-quality MRE without antiperistaltic medication, with the potential to simplify clinical workflows, improve patient comfort, and support reliable visualization of bowel motility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingIntestine, SmallArtificial IntelligenceImage Interpretation, Computer-AssistedHumansFemaleFeasibility StudiesProspective StudiesMaleMiddle AgedAdultMotionAgedSignal-To-Noise RatioGastrointestinal Motility

Stichwörter der Autor:innen

Deep learningFeasibility studiesImage processingIntestinesMagnetic resonance imaging

Autor:innen und Institutionen

  • Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • United Imaging Healthcare, Shanghai, China.
  • Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. yqshen@hust.edu.cn.
  • Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi Hospital, Taiyuan, China. yqshen@hust.edu.cn.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Xiong, Z., Wang, Y., Ma, L., Song, X., Mao, W., Li, Z., & Shen, Y. (2026). Temporal AI-assisted compressed sensing for high-resolution, motion-robust small-bowel MR enterography without antiperistaltic agents: a feasibility study. European Radiology, 36(8), 6776-6787. https://doi.org/10.1007/s00330-026-12498-4

Vancouver

Xiong Z, Wang Y, Ma L, Song X, Mao W, Li Z, et al. Temporal AI-assisted compressed sensing for high-resolution, motion-robust small-bowel MR enterography without antiperistaltic agents: a feasibility study. European Radiology. 2026;36(8):6776-6787. doi:10.1007/s00330-026-12498-4

BibTeX
@article{Xiong2026,
  author = {Xiong, Ziman and Wang, Yufan and Ma, Liya and Song, Xiaopeng and Mao, Wei and Li, Zhen and Shen, Yaqi},
  title = {Temporal AI-assisted compressed sensing for high-resolution, motion-robust small-bowel MR enterography without antiperistaltic agents: a feasibility study},
  journal = {European Radiology},
  year = {2026},
  volume = {36},
  number = {8},
  pages = {6776--6787},
  doi = {10.1007/s00330-026-12498-4}
}
Kostenlos starten →