[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121702-en":3,"doc-seo-121702-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121702,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",7,"Healthcare","SUPERVISED MACHINE LEARNINGTECHNIQUE FOR REDUCTION OF RADIATION DOSE IN COMPUTED TOMOGRAPHY IMAGING","Substantial radiation dose reduction in computed tomography (CT) imaging is achieved with supervised machine-learning dose-reduction techniques. The approach enhances low-dose images beyond noise reduction by learning mappings from low-radiation dosage inputs to higher-dose, higher-quality “teaching” CT images. Trained converters generate ongoing high-dose-like outputs from low-dose scans and can be integrated with other radiation dose reduction strategies such as adaptive exposure and iterative reconstruction.","(19)United States  \n(54)SUPERVISED MACHINE LEARNINGTECHNIQUE FOR REDUCTION OFRADIATION DOSE IN COMPUTEDTOMOGRAPHY IMAGING  \n(71)Applicant:THE UNIVERSITY OF CHICAGO,Chicago,IL(US)  \n(72)Inventor:Kenji Suzuki,Homewood,IL(US)  \n(73)Assignee:The University of Chicago,Chicago,IL(US)  \n(21)Appl.No.:  \n14/423,997  \nAug.30,2013  \n(22)PCT Filed:  \n(86)PCT No.:PCT/US13/57641§371(c)(1),  \n(2)Date:Feb.25,2015  \nRelated U.S.Application Data  \n(60)Provisional application No.61/695,698,filed on Aug.  \n31,2012.  \nPublication Classification  \n(51)Int.Cl.  \nA61B6/00  \n(2006.01)  \n(2006.01)  \nG06K 9/66  \nG06T5/50  \n(2006.01)  \n(2006.01)  \nA61B 6/03  \nG06T 5/00  \n(2006.01)  \n(52)U.S.Cl.  \nCPC…………A61B 6/5211(2013.01);A61B 6/032(2013.01);A61B6/542(2013.01);A61B6/5282(2013.01);G06T 5/002(2013.01);G06T 5/50(2013.01);G06K9/66(2013.01);G06T2207/10081(2013.01);G06T 2207/30061(2013.01)  \nABSTRACT  \n(57)  \nSubstantial reduction of the radiation dose in computedtomography(CT)imaging is shown using a machine-learningdose-reduction technique.Techniques are provided that(1)enhance low-radiation dosage images,beyond just reducingnoise,and (2)may be combined with other approaches,suchas adaptive exposure techniques and iterative reconstruction,for radiation dose reduction.  \nPatent Application PublicationJul.23,2015 Sheet 1 of 7US 2015/0201895 A1  \nFigure 1  \nNon-training ultra-ultra-LDCTimage (e.g.,0.1 mSv)(SNR=4.2 dB)  \nFigure 3A  \nOutput HD-like CT image(SNR=9.7 dB)  \nFigure 3B  \nPatent Application Publication  \nJul.23,2015 Sheet 3of 7  \nUS 2015/0201895A]  \nOriginal ULDCT (0.1 mSv)image (SNRave =3.4 dB)  \nFigure 4A  \nCorresponding HD-like CT outputimage of the trained MTANNconverter(SNRave =14.3 dB)  \nFigure 4B  \nPatent Application Publication  \nJul.23,2015 Sheet 4 of 7  \nUS 2015/0201895A]  \nPatent Application Publication  \nJul.23,2015 Sheet 5of 7  \nOriginal ULDCT(0.1 mSv)image (SNRave=3.4 dB)  \nCorresponding HD-like CT outputimage of the trained MTANNconverter(SNRave=14.3 dB)Figure 5B  \nUS 2015/0201895A1  \nFigure 5A  \nULDCT (0.1 mSv)image(SNRave=5.4 dB±2.6 dB)  \nFigure 6A  \nPatent Application Publication  \nJul.23,2015 Sheet 6of 7  \nReference HDCT(1.5mSv)image(SNRave=16.9 dB±1.4 dB)  \nUS 2015/0201895A1  \nFigure 6B  \nJul.23,2015 Sheet 7 of 7  \nPatent Application Publication  \nFigure 7  \nUS 2015/0201895A  \n1  \n# SUPERVISED MACHINE LEARNINGTECHNIQUE FOR REDUCTION OFRADIATION DOSE IN COMPUTEDTOMOGRAPHY IMAGING\n\nCROSS-REFERENCE TO RELATEDAPPLICATIONS  \n[0001]This application claims the benefit of U.S.applica-tion Ser.No.61/695,698,filed Aug.31,2012,entitled“Super-vised Machine Learning Technique For Reduction Of Radia-tion Dose In Computed Tomography Imaging,\"which ishereby incorporated by reference in its entirety.  \nFIELD OF THE INVENTION  \n[0002]The invention relates generally to the field of medi-cal imaging and more particularly to techniques for convert-ing low-dose quality computed tomography images intohigher quality computed tomography images.  \nBACKGROUND  \n[0003]Computed tomography(CT)and various,othermedical imaging techniques have been used to detect cancerin patients.CTimages,forexample,allow medical personnelto screen for tissue anomalies,classifying them based onindicators such as abnormal or normal,lesion or non-lesion,and malignant or benign.Conventional CT image analysisand interpretation and cancer detection and diagnosis tech-niques involve a radiologist assessing volumes of CT imagedata ofa subject tissue.Given the volume of data,however,itcan be difficult to identify and fully assess CT image data forcancer detection.CT image analysis is known to result inmis-diagnoses in some instances,resulting from false posi-tive determinations that lower overall efficiency ofCT imageanalysis as a viable detection technique.There are automatedtechniques for CTimage analysis,e.g.,automated techniquesfor detecting lung nodules in CT scans.Yet,these automatedtechniques are nonetheless limited and,as with non-auto-mated techniques,are benefited by using hig","cbCaicQF5rTzbXuO","https://ap.wps.com/l/cbCaicQF5rTzbXuO","pdf",810084,1,14,"English","en",105,"# ABSTRACT\n## TECHNIQUES AND TRAINING APPROACH\n## FIELD OF THE INVENTION\n## BACKGROUND AND MOTIVATION\n## SUMMARY OF THE INVENTION","[{\"question\":\"What problem does the invention address in CT imaging?\",\"answer\":\"The invention targets the tradeoff between radiation dosage and image quality, where low-dose CT increases noise and artifacts and can hinder accurate analysis and detection.\"},{\"question\":\"How does the supervised machine-learning technique work?\",\"answer\":\"It trains on paired low-dose CT inputs and higher-dose “teaching” CT images, learning the relationship so the system can convert new low-dose images into high-dose-like outputs.\"},{\"question\":\"What additional strategies can be combined with this technique?\",\"answer\":\"The method may be combined with adaptive exposure techniques and iterative reconstruction to further reduce radiation dose while improving image quality.\"}]","SUPERVISED MACHINE LEARNINGTECHNIQUE FOR REDUCTION OF RADIATION DOSE IN COMPUTED TOMOGRAPHY IMAGING | PDF",1785806344,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"supervised-machine-learning-technique-for-reduction-of-radiation-dose-in-computed-tomography-imaging","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/supervised-machine-learning-technique-for-reduction-of-radiation-dose-in-computed-tomography-imaging/121702/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the invention address in CT imaging?","Question",{"text":75,"@type":76},"The invention targets the tradeoff between radiation dosage and image quality, where low-dose CT increases noise and artifacts and can hinder accurate analysis and detection.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the supervised machine-learning technique work?",{"text":80,"@type":76},"It trains on paired low-dose CT inputs and higher-dose “teaching” CT images, learning the relationship so the system can convert new low-dose images into high-dose-like outputs.",{"name":82,"@type":73,"acceptedAnswer":83},"What additional strategies can be combined with this technique?",{"text":84,"@type":76},"The method may be combined with adaptive exposure techniques and iterative reconstruction to further reduce radiation dose while improving image quality.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]