ABVS image sequence lump segmentation combining interlayer information and double attention
The invention discloses an ABVS image sequence lump segmentation method combining interlayer information and double attention. Comprising ABVS image data preprocessing, deep neural network model construction, loss function definition, model training and result generation. In data preprocessing, a cu...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| 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 | LI XUANBO YANG XINWU |
| description | The invention discloses an ABVS image sequence lump segmentation method combining interlayer information and double attention. Comprising ABVS image data preprocessing, deep neural network model construction, loss function definition, model training and result generation. In data preprocessing, a current frame image containing a lump in an ABVS sequence and a front frame image and a rear frame image form a three-channel single 2D image, then the image is cut, and finally the size of the image is adjusted to 224 * 224. In the step of constructing the deep neural network model, on the basis of a U-Net design architecture, all coding layers are changed into sk-blocks, and an improved channel attention module is added to a jump link part. And the network structure is gradually formed. The invention provides a new thought for intelligent segmentation of ABVS image sequence lumps, and is an invention for the first time in combination with interlayer information in the field of 2D segmentation.
本发明公开了一种结合层间信息和双注意力的A |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118037743A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118037743A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118037743A3</originalsourceid><addsrcrecordid>eNrjZIh2dAoLVsjMTUxPVShOLSxNzUtOVcgpzS0A8tJzU_NKEksy8_MUkvNzkzLzMvPSFTLzSlKLchIrU4uAzLT8olyIgsS8FIWU_NKknFSFxJISoD6gIA8Da1piTnEqL5TmZlB0cw1x9tBNLciPTy0uSExOzUstiXf2MzS0MDA2NzcxdjQmRg0AlKg7-Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ABVS image sequence lump segmentation combining interlayer information and double attention</title><source>esp@cenet</source><creator>LI XUANBO ; YANG XINWU</creator><creatorcontrib>LI XUANBO ; YANG XINWU</creatorcontrib><description>The invention discloses an ABVS image sequence lump segmentation method combining interlayer information and double attention. Comprising ABVS image data preprocessing, deep neural network model construction, loss function definition, model training and result generation. In data preprocessing, a current frame image containing a lump in an ABVS sequence and a front frame image and a rear frame image form a three-channel single 2D image, then the image is cut, and finally the size of the image is adjusted to 224 * 224. In the step of constructing the deep neural network model, on the basis of a U-Net design architecture, all coding layers are changed into sk-blocks, and an improved channel attention module is added to a jump link part. And the network structure is gradually formed. The invention provides a new thought for intelligent segmentation of ABVS image sequence lumps, and is an invention for the first time in combination with interlayer information in the field of 2D segmentation.
本发明公开了一种结合层间信息和双注意力的A</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2024</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&date=20240514&DB=EPODOC&CC=CN&NR=118037743A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240514&DB=EPODOC&CC=CN&NR=118037743A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LI XUANBO</creatorcontrib><creatorcontrib>YANG XINWU</creatorcontrib><title>ABVS image sequence lump segmentation combining interlayer information and double attention</title><description>The invention discloses an ABVS image sequence lump segmentation method combining interlayer information and double attention. Comprising ABVS image data preprocessing, deep neural network model construction, loss function definition, model training and result generation. In data preprocessing, a current frame image containing a lump in an ABVS sequence and a front frame image and a rear frame image form a three-channel single 2D image, then the image is cut, and finally the size of the image is adjusted to 224 * 224. In the step of constructing the deep neural network model, on the basis of a U-Net design architecture, all coding layers are changed into sk-blocks, and an improved channel attention module is added to a jump link part. And the network structure is gradually formed. The invention provides a new thought for intelligent segmentation of ABVS image sequence lumps, and is an invention for the first time in combination with interlayer information in the field of 2D segmentation.
本发明公开了一种结合层间信息和双注意力的A</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZIh2dAoLVsjMTUxPVShOLSxNzUtOVcgpzS0A8tJzU_NKEksy8_MUkvNzkzLzMvPSFTLzSlKLchIrU4uAzLT8olyIgsS8FIWU_NKknFSFxJISoD6gIA8Da1piTnEqL5TmZlB0cw1x9tBNLciPTy0uSExOzUstiXf2MzS0MDA2NzcxdjQmRg0AlKg7-Q</recordid><startdate>20240514</startdate><enddate>20240514</enddate><creator>LI XUANBO</creator><creator>YANG XINWU</creator><scope>EVB</scope></search><sort><creationdate>20240514</creationdate><title>ABVS image sequence lump segmentation combining interlayer information and double attention</title><author>LI XUANBO ; YANG XINWU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118037743A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LI XUANBO</creatorcontrib><creatorcontrib>YANG XINWU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LI XUANBO</au><au>YANG XINWU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ABVS image sequence lump segmentation combining interlayer information and double attention</title><date>2024-05-14</date><risdate>2024</risdate><abstract>The invention discloses an ABVS image sequence lump segmentation method combining interlayer information and double attention. Comprising ABVS image data preprocessing, deep neural network model construction, loss function definition, model training and result generation. In data preprocessing, a current frame image containing a lump in an ABVS sequence and a front frame image and a rear frame image form a three-channel single 2D image, then the image is cut, and finally the size of the image is adjusted to 224 * 224. In the step of constructing the deep neural network model, on the basis of a U-Net design architecture, all coding layers are changed into sk-blocks, and an improved channel attention module is added to a jump link part. And the network structure is gradually formed. The invention provides a new thought for intelligent segmentation of ABVS image sequence lumps, and is an invention for the first time in combination with interlayer information in the field of 2D segmentation.
本发明公开了一种结合层间信息和双注意力的A</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118037743A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | ABVS image sequence lump segmentation combining interlayer information and double attention |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T14%3A17%3A29IST&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=LI%20XUANBO&rft.date=2024-05-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118037743A%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 |