Cerebral perfusion computed tomography(PCT)is an important imaging modality for evaluating cere-brovascular diseases and stroke symptoms.With wide-spread public concern about the potential cancer risks and health hazards associated with cumulative radiation expo-sure in PCT imaging,considerable research has been conducted to reduce the radiation dose in X-ray-based brain perfusion imaging.Reducing the dose of X-rays causes severe noise and artifacts in PCT images.To solve this problem,we propose a deep learning method called NCS-Unet.The exceptional characteristics of non-sub-sampled contourlet transform(NSCT)and the Sobel filter are introduced into NCS-Unet.NSCT decomposes the convolved features into high-and low-frequency compo-nents.The decomposed high-frequency component retains image edges,contrast imaging traces,and noise,whereas the low-frequency component retains the main image information.The Sobel filter extracts the contours of the original image and the imaging traces caused by the con-trast agent decay.The extracted information is added to NCS-Unet to improve its performance in noise reduction and artifact removal.Qualitative and quantitative analyses demonstrated that the proposed NCS-Unet can improve the quality of low-dose cone-beam CT perfusion reconstruc-tion images and the accuracy of perfusion parameter calculations.

Southeast University,Nanjing 210096,China;School of Cyber Science and Engineering,Southeast University,Nanjing 210096,China;Key Laboratory of Computer Network and Information Integration(Southeast University),Ministry of Education,Nanjing 210096,China;Department of Radiology,General Hospital of the Northern Theater of the Chinese People's Liberation Army,Shenyang 110016,China;Laboratory of Image Science and Technology,The School of Computer Science and Engineering,Southeast University,Nanjing 210096,China;Department of Radiology,Nanjing Drum Tower Hospital,The Affiliated Hospital of Nanjing University Medical School,Nanjing 210008,China;Jiangsu Key Laboratory of Molecular and Functional Imaging,Department of Radiology,Zhongda Hospital,Southeast University,Nanjing 210009,China;Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing,School of Computer Science and Engineering,Southeast University,Nanjing 210096,China

[1]Kai Chen;Li-Bo Zhang;Jia-Shun Liu;Yuan Gao;Zhan Wu;Hai-Chen Zhu;Chang-Ping Du;Xiao-Li Mai;Chun-Feng Yang;Yang Chen-.Robust restoration of low-dose cerebral perfusion CT images using NCS-Unet)[J].核技术（英文版）,2022(03):62-76

brovascular,convolved

Robust,restoration,low,dose,cerebral,perfusion,images,using,NCS,Unet,Cerebral,computed,tomography,PCT,important,imaging,modality,evaluating,diseases,stroke,symptoms,With,wide,spread,public,concern,about,potential,cancer,risks,health,hazards,associated,cumulative,radiation,expo,sure,considerable,research,has,been,conducted,reduce,brain,Reducing,rays,causes,severe,noise,artifacts,To,solve,this,problem,we,deep,learning,method,called,exceptional,characteristics,sub,sampled,contourlet,transform,NSCT,Sobel,filter,are,introduced,into,decomposes,features,high,frequency,nents,decomposed,component,retains,edges,contrast,traces,whereas,main,information,extracts,contours,original,caused,by,agent,decay,extracted,added,improve,its,performance,reduction,removal,Qualitative,quantitative,analyses,demonstrated,that,proposed,quality,cone,beam,reconstruc,accuracy,parameter,calculations

0.578881