Label-free pathological image feature extraction method based on spatial position information
The invention discloses a label-free pathological image feature extraction method based on spatial position information, which does not need to manually label lesions, constructs a data set and labels by means of a self-supervised algorithm and by using information such as spatial positions and zoom...
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 | ZHANG JINGYI SHE PAN ZHANG BOQIANG WANG YU LIU YICONG LU CHANGQING |
| description | The invention discloses a label-free pathological image feature extraction method based on spatial position information, which does not need to manually label lesions, constructs a data set and labels by means of a self-supervised algorithm and by using information such as spatial positions and zoom magnifications of different pathological image blocks, and is used for extracting pathological image features. And a correlation model is trained, so that extraction of pathological image features and subsequent tasks are completed. Compared with an existing deep learning algorithm based on supervision and weak supervision, the method is easier to implement, on one hand, similar difference data pairs are automatically constructed by utilizing a self-supervised learning mode and spatial position information, manual annotation is not needed, the data set obtaining difficulty is greatly reduced, and a large amount of cost is saved; and on the other hand, a novel training framework is constructed, the similarity diffe |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115439843A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115439843A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115439843A3</originalsourceid><addsrcrecordid>eNqNi70KwjAYRbs4iPoOnw_QoaSCjlIUB3FylfI1vWkD-SOJ4OMbxQdwuufCOcvqceUBplYRoMB59sZPWrIhbXkCKXB-RhBeObLM2juyKNZIAyeMVH4qmS5B8El_Be2Uj5Y_vK4Wik3C5rerans-3btLjeB7lFLCIffdrWl2rTjsW3EU_zhvLlg8zA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Label-free pathological image feature extraction method based on spatial position information</title><source>esp@cenet</source><creator>ZHANG JINGYI ; SHE PAN ; ZHANG BOQIANG ; WANG YU ; LIU YICONG ; LU CHANGQING</creator><creatorcontrib>ZHANG JINGYI ; SHE PAN ; ZHANG BOQIANG ; WANG YU ; LIU YICONG ; LU CHANGQING</creatorcontrib><description>The invention discloses a label-free pathological image feature extraction method based on spatial position information, which does not need to manually label lesions, constructs a data set and labels by means of a self-supervised algorithm and by using information such as spatial positions and zoom magnifications of different pathological image blocks, and is used for extracting pathological image features. And a correlation model is trained, so that extraction of pathological image features and subsequent tasks are completed. Compared with an existing deep learning algorithm based on supervision and weak supervision, the method is easier to implement, on one hand, similar difference data pairs are automatically constructed by utilizing a self-supervised learning mode and spatial position information, manual annotation is not needed, the data set obtaining difficulty is greatly reduced, and a large amount of cost is saved; and on the other hand, a novel training framework is constructed, the similarity diffe</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</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=20221206&DB=EPODOC&CC=CN&NR=115439843A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25547,76298</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221206&DB=EPODOC&CC=CN&NR=115439843A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG JINGYI</creatorcontrib><creatorcontrib>SHE PAN</creatorcontrib><creatorcontrib>ZHANG BOQIANG</creatorcontrib><creatorcontrib>WANG YU</creatorcontrib><creatorcontrib>LIU YICONG</creatorcontrib><creatorcontrib>LU CHANGQING</creatorcontrib><title>Label-free pathological image feature extraction method based on spatial position information</title><description>The invention discloses a label-free pathological image feature extraction method based on spatial position information, which does not need to manually label lesions, constructs a data set and labels by means of a self-supervised algorithm and by using information such as spatial positions and zoom magnifications of different pathological image blocks, and is used for extracting pathological image features. And a correlation model is trained, so that extraction of pathological image features and subsequent tasks are completed. Compared with an existing deep learning algorithm based on supervision and weak supervision, the method is easier to implement, on one hand, similar difference data pairs are automatically constructed by utilizing a self-supervised learning mode and spatial position information, manual annotation is not needed, the data set obtaining difficulty is greatly reduced, and a large amount of cost is saved; and on the other hand, a novel training framework is constructed, the similarity diffe</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi70KwjAYRbs4iPoOnw_QoaSCjlIUB3FylfI1vWkD-SOJ4OMbxQdwuufCOcvqceUBplYRoMB59sZPWrIhbXkCKXB-RhBeObLM2juyKNZIAyeMVH4qmS5B8El_Be2Uj5Y_vK4Wik3C5rerans-3btLjeB7lFLCIffdrWl2rTjsW3EU_zhvLlg8zA</recordid><startdate>20221206</startdate><enddate>20221206</enddate><creator>ZHANG JINGYI</creator><creator>SHE PAN</creator><creator>ZHANG BOQIANG</creator><creator>WANG YU</creator><creator>LIU YICONG</creator><creator>LU CHANGQING</creator><scope>EVB</scope></search><sort><creationdate>20221206</creationdate><title>Label-free pathological image feature extraction method based on spatial position information</title><author>ZHANG JINGYI ; SHE PAN ; ZHANG BOQIANG ; WANG YU ; LIU YICONG ; LU CHANGQING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115439843A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHANG JINGYI</creatorcontrib><creatorcontrib>SHE PAN</creatorcontrib><creatorcontrib>ZHANG BOQIANG</creatorcontrib><creatorcontrib>WANG YU</creatorcontrib><creatorcontrib>LIU YICONG</creatorcontrib><creatorcontrib>LU CHANGQING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG JINGYI</au><au>SHE PAN</au><au>ZHANG BOQIANG</au><au>WANG YU</au><au>LIU YICONG</au><au>LU CHANGQING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Label-free pathological image feature extraction method based on spatial position information</title><date>2022-12-06</date><risdate>2022</risdate><abstract>The invention discloses a label-free pathological image feature extraction method based on spatial position information, which does not need to manually label lesions, constructs a data set and labels by means of a self-supervised algorithm and by using information such as spatial positions and zoom magnifications of different pathological image blocks, and is used for extracting pathological image features. And a correlation model is trained, so that extraction of pathological image features and subsequent tasks are completed. Compared with an existing deep learning algorithm based on supervision and weak supervision, the method is easier to implement, on one hand, similar difference data pairs are automatically constructed by utilizing a self-supervised learning mode and spatial position information, manual annotation is not needed, the data set obtaining difficulty is greatly reduced, and a large amount of cost is saved; and on the other hand, a novel training framework is constructed, the similarity diffe</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115439843A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Label-free pathological image feature extraction method based on spatial position information |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T10%3A50%3A26IST&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=ZHANG%20JINGYI&rft.date=2022-12-06&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115439843A%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 |