Sökning: onr:"swepub:oai:DiVA.org:hh-53055" >
US2Mask :
US2Mask : Image-to-mask generation learning via a conditional GAN for cardiac ultrasound image segmentation
-
- Wang, Gang (författare)
- Chongqing University Of Posts And Telecommunications, Chongqing, China; Imperial College London, London, United Kingdom
-
- Zhou, Mingliang (författare)
- Chongqing University, Chongqing, China
-
- Ning, Xin (författare)
- Chinese Academy Of Sciences, Beijing, China
-
visa fler...
-
- Tiwari, Prayag, 1991- (författare)
- Högskolan i Halmstad,Akademin för informationsteknologi
-
- Zhu, Haobo (författare)
- University Of Oxford, Oxford, United Kingdom
-
- Yang, Guang (författare)
- Imperial College London, London, United Kingdom; Royal Brompton Hospital, London, United Kingdom; National Heart And Lung Institute, London, United Kingdom
-
- Yap, Choon Hwai (författare)
- Imperial College London, London, United Kingdom
-
visa färre...
-
(creator_code:org_t)
- Oxford : Elsevier, 2024
- 2024
- Engelska.
-
Ingår i: Computers in Biology and Medicine. - Oxford : Elsevier. - 0010-4825 .- 1879-0534. ; 172, s. 1-13
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Cardiac ultrasound (US) image segmentation is vital for evaluating clinical indices, but it often demands a large dataset and expert annotations, resulting in high costs for deep learning algorithms. To address this, our study presents a framework utilizing artificial intelligence generation technology to produce multi-class RGB masks for cardiac US image segmentation. The proposed approach directly performs semantic segmentation of the heart's main structures in US images from various scanning modes. Additionally, we introduce a novel learning approach based on conditional generative adversarial networks (CGAN) for cardiac US image segmentation, incorporating a conditional input and paired RGB masks. Experimental results from three cardiac US image datasets with diverse scan modes demonstrate that our approach outperforms several state-of-the-art models, showcasing improvements in five commonly used segmentation metrics, with lower noise sensitivity. Source code is available at https://github.com/energy588/US2mask. © 2024 Elsevier Ltd
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Nyckelord
- Artificial intelligence generation
- Cardiac ultrasound image
- Image segmentation
- Mask learning
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas