https://3demmethods.i2pc.es/index.php?action=history&feed=atom&title=2025Vivas_iceFinder 2026-09-26T17:47:13Z Revision history for this page on the wiki MediaWiki 1.44.2 https://3demmethods.i2pc.es/index.php?title=2025Vivas_iceFinder&diff=5287&oldid=prev 2026-09-26T15:37:11Z

<p>Created page with &quot;== Citation == A. Vivas-Lago, D. Castaño-Díez, Few-shot learning for non-vitrified ice segmentation, Scientific Reports, 15, 1, 5501, (2025). == Abstract == This study introduces Ice Finder, a novel tool for quantifying crystalline ice in cryo-electron tomography, addressing a critical gap in existing methodologies. We present the first application of the meta-learning paradigm to this field, demonstrating that diverse tomographic tasks across datasets can be unified...&quot;</p> <p><b>New page</b></p><div>== Citation ==<br /> A. Vivas-Lago, D. Castaño-Díez, Few-shot learning for non-vitrified ice segmentation, Scientific Reports, 15, 1, 5501, (2025).<br /> <br /> == Abstract ==<br /> This study introduces Ice Finder, a novel tool for quantifying crystalline ice in cryo-electron tomography, addressing a critical gap in existing methodologies. We present the first application of the meta-learning paradigm to this field, demonstrating that diverse tomographic tasks across datasets can be unified under a single meta-learning framework. By leveraging few-shot learning, our approach enhances domain generalization and adaptability to domain shifts, enabling rapid adaptation to new datasets with minimal examples. Ice Finder&#039;s performance is evaluated on a comprehensive set of in situ datasets from EMPIAR, showcasing its ease of use, fast processing capabilities, and millisecond inference times.<br /> <br /> == Keywords ==<br /> cryo-electron tomography, non-vitrified ice segmentation, crystalline ice, few-shot learning, meta-learning, Ice Finder, <br /> <br /> == Links ==<br /> https://doi.org/10.1038/s41598-025-86308-0</div>

Vilas