Vessel-GAN: Angiographic reconstructions from myocardial CT perfusion with explainable generative adversarial networks
dc.contributor.author | Wu, Chulin | |
dc.contributor.author | Zhang, Heye | |
dc.contributor.author | Chen, Jiaqi | |
dc.contributor.author | Gao, Zhifan | |
dc.contributor.author | Zhang, Pengfei | |
dc.contributor.author | Muhammad, Khan | |
dc.contributor.author | Del Ser, Javier | |
dc.contributor.institution | IA | |
dc.date.issued | 2022-05 | |
dc.description | Publisher Copyright: © 2021 Elsevier B.V. | |
dc.description.abstract | Dynamic CT angiography derived from CT perfusion data can obviate a separate coronary CT angiography and the use of ionizing radiation and contrast agent, thereby enhancing patient safety. However, the image quality of dynamic CT angiography is inferior to standard CT angiography images in many studies. This paper proposes an explainable generative adversarial network named vessel-GAN, which resorts to explainable knowledge-based artificial intelligence to perform image translation with increased trustworthiness. Specifically, we design a loss term to better learn the representations of blood vessels in CT angiography images. The loss term based on expert knowledge guides the generator to focus its training on the important features predicted by the discriminator. Additionally, we propose a generator architecture that effectively fuses spatio-temporal representations and further enhances temporal consistency, thereby improving the quality of the generated CT angiography images. The experiment is conducted on a dataset consisting of 232 patients with suspected coronary artery stenosis. Experimental results show that the PSNR value of vessel-GAN is 28.32 dB, SSIM value is 0.91 and MAE value is 47.36. To validate the effectiveness of the proposed synthesis method, we compare that with other image translation frameworks and GAN-based methods. Compared to other image translation methods, the proposed method vessel-GAN can generate more clearly visible blood vessels from source perfusion images. The CTA images generated by vessel-GAN are closer to the real CTA due to the use of adversarial learning. Compared with other GAN-based methods, vessel-GAN can produce sharper and more homogeneous outputs, including realistic vascular structures. The experiment demonstrates that the explainable generative adversarial network has superior performance for it can better control how models learn. Overall, the CT angiography images generated by vessel-GAN can potentially replace a separate standard CT angiography, allowing the possibility of “one-stop” cardiac examination for high-risk coronary artery disease patients who need assessment of myocardial ischemia. | en |
dc.description.sponsorship | This work was funded by the Key-Area Research and Development Program of Guangdong Province ( 2019B010110001 ), the Shenzhen Science and Technology Program (Grant No. GX WD20201231165807008 , 20200825113400001 ), the Natural Science Foundation of Guangdong Province ( 2020B1515120061 ), the National Youth Talent Support Program ( RC2020-01 ), the Guangdong Natural Science Funds for Distinguished Young Scholar ( 2019B151502031 ), the National Natural Science Foundation of China ( 62101606 , U1801265 , U1908211 ), and the Department of Education of the Basque Government through the Consolidated Research Group MATHMODE ( IT1294-19 ). | |
dc.description.status | Peer reviewed | |
dc.format.extent | 12 | |
dc.identifier.citation | Wu , C , Zhang , H , Chen , J , Gao , Z , Zhang , P , Muhammad , K & Del Ser , J 2022 , ' Vessel-GAN : Angiographic reconstructions from myocardial CT perfusion with explainable generative adversarial networks ' , Future Generation Computer Systems , vol. 130 , pp. 128-139 . https://doi.org/10.1016/j.future.2021.12.007 | |
dc.identifier.doi | 10.1016/j.future.2021.12.007 | |
dc.identifier.issn | 0167-739X | |
dc.identifier.url | http://www.scopus.com/inward/record.url?scp=85122322272&partnerID=8YFLogxK | |
dc.language.iso | eng | |
dc.relation.ispartof | Future Generation Computer Systems | |
dc.relation.projectID | Department of Education of the Basque Government, IT1294-19 | |
dc.relation.projectID | Guangdong Natural Science Funds for Distinguished Young Scholar, 2019B151502031 | |
dc.relation.projectID | National Natural Science Foundation of China, NSFC, U1908211-62101606-U1801265 | |
dc.relation.projectID | Natural Science Foundation of Guangdong Province, RC2020-01-2020B1515120061 | |
dc.relation.projectID | Science, Technology and Innovation Commission of Shenzhen Municipality, 20200825113400001-GX WD20201231165807008 | |
dc.relation.projectID | Special Project for Research and Development in Key areas of Guangdong Province, 2019B010110001 | |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.subject.keywords | Angiography | |
dc.subject.keywords | Explainable AI | |
dc.subject.keywords | Generative adversarial networks | |
dc.subject.keywords | Medical image processing | |
dc.subject.keywords | Myocardial CT perfusion | |
dc.subject.keywords | Software | |
dc.subject.keywords | Hardware and Architecture | |
dc.subject.keywords | Computer Networks and Communications | |
dc.subject.keywords | SDG 3 - Good Health and Well-being | |
dc.title | Vessel-GAN: Angiographic reconstructions from myocardial CT perfusion with explainable generative adversarial networks | en |
dc.type | journal article |