Zobrazeno 1 - 10
of 255
pro vyhledávání: '"Zhiyun, Xue"'
Publikováno v:
New Microbes and New Infections, Vol 62, Iss , Pp 101457- (2024)
Background: Large vision models (LVM) pretrained by large datasets have demonstrated their enormous capacity to understand visual patterns and capture semantic information from images. We proposed a novel method of knowledge domain adaptation with pr
Externí odkaz:
https://doaj.org/article/dcf99ad4b280495cb10479abeb0dac30
Publikováno v:
Frontiers in Artificial Intelligence, Vol 7 (2024)
IntroductionDeep learning (DL) has significantly advanced medical image classification. However, it often relies on transfer learning (TL) from models pretrained on large, generic non-medical image datasets like ImageNet. Conversely, medical images p
Externí odkaz:
https://doaj.org/article/c42fa8389bb047e381e6a63b3ae2ac69
Publikováno v:
Diagnostics, Vol 14, Iss 17, p 1984 (2024)
In an era of rapid advancements in artificial intelligence (AI) technologies, particularly in medical imaging and natural language processing, strategic efforts to leverage AI’s capabilities in analyzing complex medical data and integrating it into
Externí odkaz:
https://doaj.org/article/18c08791ce074c829f6943bf5357b1cf
Autor:
Sivaramakrishnan Rajaraman, Ghada Zamzmi, Feng Yang, Zhaohui Liang, Zhiyun Xue, Sameer Antani
Publikováno v:
PLOS Digital Health, Vol 3, Iss 1, p e0000286 (2024)
Model initialization techniques are vital for improving the performance and reliability of deep learning models in medical computer vision applications. While much literature exists on non-medical images, the impacts on medical images, particularly c
Externí odkaz:
https://doaj.org/article/f13c5ef0a8b34190be5eacc540f60b09
Autor:
Feng Yang, Ghada Zamzmi, Sandeep Angara, Sivaramakrishnan Rajaraman, Andre Aquilina, Zhiyun Xue, Stefan Jaeger, Emmanouil Papagiannakis, Sameer K. Antani
Publikováno v:
IEEE Access, Vol 11, Pp 21300-21312 (2023)
Artificial Intelligence (AI)-based medical computer vision algorithm training and evaluations depend on annotations and labeling. However, variability between expert annotators introduces noise in training data that can adversely impact the performan
Externí odkaz:
https://doaj.org/article/776814b036a647198c131238f7593824
Publikováno v:
Frontiers in Artificial Intelligence; 2024, p1-13, 13p
Autor:
Anabik Pal, Zhiyun Xue, Brian Befano, Ana Cecilia Rodriguez, L. Rodney Long, Mark Schiffman, Sameer Antani
Publikováno v:
IEEE Access, Vol 9, Pp 53266-53275 (2021)
Cervical cancer is caused by the persistent infection of certain types of the Human Papillomavirus (HPV) and is a leading cause of female mortality particularly in low and middle-income countries (LMIC). Visual inspection of the cervix with acetic ac
Externí odkaz:
https://doaj.org/article/9ba19d6158344d45be56a4b715773fc0
Autor:
Kanan T. Desai, Kayode O. Ajenifuja, Adekunbiola Banjo, Clement A. Adepiti, Akiva Novetsky, Cathy Sebag, Mark H. Einstein, Temitope Oyinloye, Tamara R. Litwin, Matt Horning, Fatai Olatunde Olanrewaju, Mufutau Muphy Oripelaye, Esther Afolabi, Oluwole O. Odujoko, Philip E. Castle, Sameer Antani, Ben Wilson, Liming Hu, Courosh Mehanian, Maria Demarco, Julia C. Gage, Zhiyun Xue, Leonard R. Long, Li Cheung, Didem Egemen, Nicolas Wentzensen, Mark Schiffman
Publikováno v:
Infectious Agents and Cancer, Vol 15, Iss 1, Pp 1-13 (2020)
Abstract Background Accelerated global control of cervical cancer would require primary prevention with human papillomavirus (HPV) vaccination in addition to novel screening program strategies that are simple, inexpensive, and effective. We present t
Externí odkaz:
https://doaj.org/article/272fafd888d3448d89d9a234a5b91421
Publikováno v:
Diagnostics, Vol 13, Iss 6, p 1068 (2023)
Domain shift is one of the key challenges affecting reliability in medical imaging-based machine learning predictions. It is of significant importance to investigate this issue to gain insights into its characteristics toward determining controllable
Externí odkaz:
https://doaj.org/article/f7f70ad7753541669b1267f5cd6bff5c
Publikováno v:
Diagnostics, Vol 13, Iss 4, p 747 (2023)
Deep learning (DL) models are state-of-the-art in segmenting anatomical and disease regions of interest (ROIs) in medical images. Particularly, a large number of DL-based techniques have been reported using chest X-rays (CXRs). However, these models
Externí odkaz:
https://doaj.org/article/dcfbbb7ca4464ca4b6d95027cac4a0d2