3D Level Set Segmentation method and apparatus for Medical Image

The present invention relates to a 3D level set segmentation method for a medical image which comprises the following steps of: allocating indexes for structure information recorded in level set data vector information to each of a plurality of core units that are multi-cores of a GPU; reading a cor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SEO U DEOK, KIM CHEOL HWAN, JANG TAEK JIN, YE BYOUNG HUN, KIM DONG HYEON
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator SEO U DEOK
KIM CHEOL HWAN
JANG TAEK JIN
YE BYOUNG HUN
KIM DONG HYEON
description The present invention relates to a 3D level set segmentation method for a medical image which comprises the following steps of: allocating indexes for structure information recorded in level set data vector information to each of a plurality of core units that are multi-cores of a GPU; reading a corresponding voxel recorded in the structure information corresponding to an index allocated to each of the plurality of core units and structure information for surrounding voxels of the voxel, calculating a level of the corresponding voxel based on the structure information and updating the level of the corresponding voxel with the calculated level; and deriving an object area from the updated level of the voxel. The plurality of core units that are multi-cores process level calculation and update of the voxel in parallel. 본 발명은 의료 영상에 대한 3D 레벨 세트 분할 방법에 관한 것으로, GPU의 멀티 코어인 다수의 코어부 각각에 레벨 세트 데이터 벡터정보에 기록된 구조체 정보들에 대한 인덱스를 할당하는 단계; 상기 인덱스를 할당받은 다수의 코어부 각각이 할당받은 인덱스에 대응되는 구조체 정보에 기록된 해당 복셀 및 그 복셀의 주변 복셀들에 대한 구조체 정보들을 독출하고, 상기 구조체 정보들을 토대로 해당 복셀의 레벨을 산출하고, 산출된 레벨로 해당 복셀의 레벨을 갱신하는 단계; 및 갱신된 복셀의 레벨들로 오브젝트 영역을 도출하는 단계;를 구비하며, 상기 멀티 코어인 다수의 코어부는 상기 복셀의 레벨 산출 및 갱신을 병렬 처리하는 것을 특징으로 한다.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20210046889A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20210046889A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20210046889A3</originalsourceid><addsrcrecordid>eNrjZHAwdlHwSS1LzVEITi0B4vTc1LySxJLM_DyF3NSSjPwUhcQ8IC4oSCxKLCktVkjLL1LwTU3JTE7MUfDMTUxP5WFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8d5BRgZGhgYGJmYWFpaOxsSpAgD5bTEa</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>3D Level Set Segmentation method and apparatus for Medical Image</title><source>esp@cenet</source><creator>SEO U DEOK ; KIM CHEOL HWAN ; JANG TAEK JIN ; YE BYOUNG HUN ; KIM DONG HYEON</creator><creatorcontrib>SEO U DEOK ; KIM CHEOL HWAN ; JANG TAEK JIN ; YE BYOUNG HUN ; KIM DONG HYEON</creatorcontrib><description>The present invention relates to a 3D level set segmentation method for a medical image which comprises the following steps of: allocating indexes for structure information recorded in level set data vector information to each of a plurality of core units that are multi-cores of a GPU; reading a corresponding voxel recorded in the structure information corresponding to an index allocated to each of the plurality of core units and structure information for surrounding voxels of the voxel, calculating a level of the corresponding voxel based on the structure information and updating the level of the corresponding voxel with the calculated level; and deriving an object area from the updated level of the voxel. The plurality of core units that are multi-cores process level calculation and update of the voxel in parallel. 본 발명은 의료 영상에 대한 3D 레벨 세트 분할 방법에 관한 것으로, GPU의 멀티 코어인 다수의 코어부 각각에 레벨 세트 데이터 벡터정보에 기록된 구조체 정보들에 대한 인덱스를 할당하는 단계; 상기 인덱스를 할당받은 다수의 코어부 각각이 할당받은 인덱스에 대응되는 구조체 정보에 기록된 해당 복셀 및 그 복셀의 주변 복셀들에 대한 구조체 정보들을 독출하고, 상기 구조체 정보들을 토대로 해당 복셀의 레벨을 산출하고, 산출된 레벨로 해당 복셀의 레벨을 갱신하는 단계; 및 갱신된 복셀의 레벨들로 오브젝트 영역을 도출하는 단계;를 구비하며, 상기 멀티 코어인 다수의 코어부는 상기 복셀의 레벨 산출 및 갱신을 병렬 처리하는 것을 특징으로 한다.</description><language>eng ; kor</language><subject>CALCULATING ; COMPUTING ; COUNTING ; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS ; PHYSICS</subject><creationdate>2021</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210429&amp;DB=EPODOC&amp;CC=KR&amp;NR=20210046889A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25566,76549</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210429&amp;DB=EPODOC&amp;CC=KR&amp;NR=20210046889A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SEO U DEOK</creatorcontrib><creatorcontrib>KIM CHEOL HWAN</creatorcontrib><creatorcontrib>JANG TAEK JIN</creatorcontrib><creatorcontrib>YE BYOUNG HUN</creatorcontrib><creatorcontrib>KIM DONG HYEON</creatorcontrib><title>3D Level Set Segmentation method and apparatus for Medical Image</title><description>The present invention relates to a 3D level set segmentation method for a medical image which comprises the following steps of: allocating indexes for structure information recorded in level set data vector information to each of a plurality of core units that are multi-cores of a GPU; reading a corresponding voxel recorded in the structure information corresponding to an index allocated to each of the plurality of core units and structure information for surrounding voxels of the voxel, calculating a level of the corresponding voxel based on the structure information and updating the level of the corresponding voxel with the calculated level; and deriving an object area from the updated level of the voxel. The plurality of core units that are multi-cores process level calculation and update of the voxel in parallel. 본 발명은 의료 영상에 대한 3D 레벨 세트 분할 방법에 관한 것으로, GPU의 멀티 코어인 다수의 코어부 각각에 레벨 세트 데이터 벡터정보에 기록된 구조체 정보들에 대한 인덱스를 할당하는 단계; 상기 인덱스를 할당받은 다수의 코어부 각각이 할당받은 인덱스에 대응되는 구조체 정보에 기록된 해당 복셀 및 그 복셀의 주변 복셀들에 대한 구조체 정보들을 독출하고, 상기 구조체 정보들을 토대로 해당 복셀의 레벨을 산출하고, 산출된 레벨로 해당 복셀의 레벨을 갱신하는 단계; 및 갱신된 복셀의 레벨들로 오브젝트 영역을 도출하는 단계;를 구비하며, 상기 멀티 코어인 다수의 코어부는 상기 복셀의 레벨 산출 및 갱신을 병렬 처리하는 것을 특징으로 한다.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHAwdlHwSS1LzVEITi0B4vTc1LySxJLM_DyF3NSSjPwUhcQ8IC4oSCxKLCktVkjLL1LwTU3JTE7MUfDMTUxP5WFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8d5BRgZGhgYGJmYWFpaOxsSpAgD5bTEa</recordid><startdate>20210429</startdate><enddate>20210429</enddate><creator>SEO U DEOK</creator><creator>KIM CHEOL HWAN</creator><creator>JANG TAEK JIN</creator><creator>YE BYOUNG HUN</creator><creator>KIM DONG HYEON</creator><scope>EVB</scope></search><sort><creationdate>20210429</creationdate><title>3D Level Set Segmentation method and apparatus for Medical Image</title><author>SEO U DEOK ; KIM CHEOL HWAN ; JANG TAEK JIN ; YE BYOUNG HUN ; KIM DONG HYEON</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20210046889A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SEO U DEOK</creatorcontrib><creatorcontrib>KIM CHEOL HWAN</creatorcontrib><creatorcontrib>JANG TAEK JIN</creatorcontrib><creatorcontrib>YE BYOUNG HUN</creatorcontrib><creatorcontrib>KIM DONG HYEON</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SEO U DEOK</au><au>KIM CHEOL HWAN</au><au>JANG TAEK JIN</au><au>YE BYOUNG HUN</au><au>KIM DONG HYEON</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>3D Level Set Segmentation method and apparatus for Medical Image</title><date>2021-04-29</date><risdate>2021</risdate><abstract>The present invention relates to a 3D level set segmentation method for a medical image which comprises the following steps of: allocating indexes for structure information recorded in level set data vector information to each of a plurality of core units that are multi-cores of a GPU; reading a corresponding voxel recorded in the structure information corresponding to an index allocated to each of the plurality of core units and structure information for surrounding voxels of the voxel, calculating a level of the corresponding voxel based on the structure information and updating the level of the corresponding voxel with the calculated level; and deriving an object area from the updated level of the voxel. The plurality of core units that are multi-cores process level calculation and update of the voxel in parallel. 본 발명은 의료 영상에 대한 3D 레벨 세트 분할 방법에 관한 것으로, GPU의 멀티 코어인 다수의 코어부 각각에 레벨 세트 데이터 벡터정보에 기록된 구조체 정보들에 대한 인덱스를 할당하는 단계; 상기 인덱스를 할당받은 다수의 코어부 각각이 할당받은 인덱스에 대응되는 구조체 정보에 기록된 해당 복셀 및 그 복셀의 주변 복셀들에 대한 구조체 정보들을 독출하고, 상기 구조체 정보들을 토대로 해당 복셀의 레벨을 산출하고, 산출된 레벨로 해당 복셀의 레벨을 갱신하는 단계; 및 갱신된 복셀의 레벨들로 오브젝트 영역을 도출하는 단계;를 구비하며, 상기 멀티 코어인 다수의 코어부는 상기 복셀의 레벨 산출 및 갱신을 병렬 처리하는 것을 특징으로 한다.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; kor
recordid cdi_epo_espacenet_KR20210046889A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS
PHYSICS
title 3D Level Set Segmentation method and apparatus for Medical Image
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T08%3A05%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=SEO%20U%20DEOK&rft.date=2021-04-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20210046889A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true