Medical image registration is widely used in image-guided therapy and image-guided surgery to esti-mate spatial correspondence between planning and treatment images.However,most methods based on intensity have the problems of matching ambiguity and ignoring the influence of weak correspondence areas on the overall registration.In this study,we propose a novel general-purpose registration algorithm based on free-form defor-mation by non-subsampled contour let transform and saliency map,which can reduce the matching ambiguities and maintain the topological structure of weak correspondence areas.An optimization method based on Markov random fields is used to optimize the registration process.Experiments on four public datasets from brain,car-diac,and lung have demonstrated the general applicability and the accuracy of our algorithm compared with two state-of-the-art methods.

CHANG Qing;YANG Wenyou;CHEN Lanlan

School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China

上海交通大学学报（英文版）

[1]CHANG Qing;YANG Wenyou;CHEN Lanlan-.Deformable Registration Algorithm via Non-subsampled Contour let Transform and Saliency Map)[J].上海交通大学学报（英文版）,2022(04):452-462

Deformable,Registration,Algorithm,via,Non,subsampled,Contour,let,Transform,Saliency,Map,Medical,registration,widely,used,guided,therapy,surgery,esti,mate,spatial,correspondence,between,planning,treatment,images,However,most,methods,intensity,have,problems,matching,ambiguity,ignoring,influence,weak,areas,overall,In,this,study,propose,novel,general,purpose,algorithm,free,defor,mation,by,contour,transform,saliency,map,which,can,reduce,ambiguities,maintain,topological,structure,An,optimization,Markov,random,fields,optimize,process,Experiments,four,public,datasets,from,brain,car,diac,lung,demonstrated,applicability,accuracy,compared,two,state,art

0.681016