{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:36:40Z","timestamp":1773801400819,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Capturing accurate dynamic information of moving organs is essential for functional assessment using non-invasive imaging modalities. Achieving high temporal resolution visualization of physiological processes remains a critical challenge in dynamic magnetic resonance imaging (MRI) when reconstructing from extremely limited acquisitions. We introduce an unsupervised zero-shot reconstruction framework combining Implicit Neural Representation (INR) with manifold learning, capable of reconstructing dynamic MRI data at unprecedented temporal resolutions (less than 10 ms per frame for 2D imaging, less than 400 ms per frame for 3D imaging). \nThe framework employs learnable low-dimensional manifold vectors to autonomously capture motion in real time directly from undersampled data, and dynamically condition coordinate-based spatial representations to generate high-fidelity image sequences.\nThrough a novel spatiotemporal coarse-to-fine (C2F) optimization strategy, our method outperforms current state-of-the-art (SOTA) techniques across multiple imaging scenarios, including cardiac, speech and dynamic-contrast-enhanced (DCE) abdominal MRI, demonstrating robust performance under challenging motion patterns and contrast dynamics.\nThe learned manifolds additionally provide intuitive visualization of motion and contrast evolution during imaging.\nThese advances indicate strong clinical potential for applications requiring extreme temporal resolution while maintaining both anatomical and temporal fidelity.<\/jats:p>","DOI":"10.1609\/aaai.v40i5.37395","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:10:52Z","timestamp":1773789052000},"page":"3930-3938","source":"Crossref","is-referenced-by-count":0,"title":["Zero-shot Implicit Neural Manifold Representation (INMR) for Ultra-high Temporal Resolution Dynamic MRI"],"prefix":"10.1609","volume":"40","author":[{"given":"Jie","family":"Feng","sequence":"first","affiliation":[]},{"given":"Rui","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Haikun","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Yuyao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Hongjiang","family":"Wei","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37395\/41357","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37395\/41357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:10:52Z","timestamp":1773789052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i5.37395","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}