Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Weidi Xie"'
Autor:
Qiaoyu Zheng, Weike Zhao, Chaoyi Wu, Xiaoman Zhang, Lisong Dai, Hengyu Guan, Yuehua Li, Ya Zhang, Yanfeng Wang, Weidi Xie
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-16 (2024)
Abstract Developing a generalist radiology diagnosis system can greatly enhance clinical diagnostics. In this paper, we introduce RadDiag, a foundational model supporting 2D and 3D inputs across various modalities and anatomies, using a transformer-b
Externí odkaz:
https://doaj.org/article/68f5e7af74704252abfa5512b61b9d7b
Autor:
Pengcheng Qiu, Chaoyi Wu, Xiaoman Zhang, Weixiong Lin, Haicheng Wang, Ya Zhang, Yanfeng Wang, Weidi Xie
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-15 (2024)
Abstract The development of open-source, multilingual medical language models can benefit a wide, linguistically diverse audience from different regions. To promote this domain, we present contributions from the following: First, we construct a multi
Externí odkaz:
https://doaj.org/article/e16c538885c34cea9f239ebe75c9e61b
Publikováno v:
Nature Communications, Vol 14, Iss 1, Pp 1-12 (2023)
Abstract While multi-modal foundation models pre-trained on large-scale data have been successful in natural language understanding and vision recognition, their use in medical domains is still limited due to the fine-grained nature of medical tasks
Externí odkaz:
https://doaj.org/article/a8dbe7e4a3664abbbf0cd84b4ff0be2e
Autor:
Linde S. Hesse, Moska Aliasi, Felipe Moser, Monique C. Haak, Weidi Xie, Mark Jenkinson, Ana I.L. Namburete
Publikováno v:
NeuroImage, Vol 254, Iss , Pp 119117- (2022)
The quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and
Externí odkaz:
https://doaj.org/article/728388ab9f8a4b549b2c11b1d36566d0
Publikováno v:
IEEE Robotics and Automation Letters. 8:1959-1966
Drones equipped with cameras can significantly enhance human ability to perceive the world because of their remarkable maneuverability in 3D space. Ironically, object detection for drones has always been conducted in the 2D image space, which fundame
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7162c39c185e8cd39b55320b0565032a
https://doi.org/10.1109/lra.2023.3245421
https://doi.org/10.1109/lra.2023.3245421
Publikováno v:
IEEE Journal of Biomedical and Health Informatics. :1-13
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f14bda4cd53fa37daf4e07ee470baf4
https://doi.org/10.1109/jbhi.2023.3240844
https://doi.org/10.1109/jbhi.2023.3240844
In this paper, we consider the problem of enhancing self-supervised visual-language pre-training (VLP) with medical-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice. In particular, we make the follo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c4ab6ae2b1780e2e1419a30b9a6912f
https://doi.org/10.1101/2023.01.10.23284412
https://doi.org/10.1101/2023.01.10.23284412
Publikováno v:
Polymers for Advanced Technologies. 32:4415-4423
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ecab12383e5bb10c9db0d94305595268
https://doi.org/10.1002/pat.5443
https://doi.org/10.1002/pat.5443
Publikováno v:
Polymers for Advanced Technologies. 32:2252-2261
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a6be76e7e04ac3b11a58f8fac9b9aa6
https://doi.org/10.1002/pat.5259
https://doi.org/10.1002/pat.5259
In this paper, we present a framework for reading analog clocks in natural images or videos. Specifically, we make the following contributions: First, we create a scalable pipeline for generating synthetic clocks, significantly reducing the requireme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ec55c02832e85e98562cb3051fbc568
https://doi.org/10.1109/cvpr52688.2022.00254
https://doi.org/10.1109/cvpr52688.2022.00254