Ultrasonic image denoising method based on unsupervised learning model
The invention discloses an ultrasonic image denoising method based on an unsupervised learning model, and belongs to the technical field of image processing, and the method comprises the steps: S1, collecting a noisy ultrasonic image, carrying out the denoising processing of the noisy ultrasonic ima...
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 | XIE SHENGHUA GAN JIANHONG WANG LIPING HE TONGLI YIN LIXUE ZHANG HONGMEI |
| description | The invention discloses an ultrasonic image denoising method based on an unsupervised learning model, and belongs to the technical field of image processing, and the method comprises the steps: S1, collecting a noisy ultrasonic image, carrying out the denoising processing of the noisy ultrasonic image, and respectively constructing the sub-images of the noisy ultrasonic image and the denoised ultrasonic image; s2, constructing a loss function based on the sub-image of the noisy ultrasonic image and the sub-image of the de-noised ultrasonic image; s3, based on the loss function, determining a target function for training the ultrasonic image denoising network, and training the target function; and S4, processing a to-be-denoised ultrasonic image by using the trained ultrasonic image denoising network to obtain a denoised ultrasonic image. According to the method, the dependence of the model on a data sample is reduced, the inference ability of deep learning is fully exerted, a Noisy-Clean image pair does not n |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118212153A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118212153A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118212153A3</originalsourceid><addsrcrecordid>eNrjZHALzSkpSizOz8tMVsjMTUxPVUhJzcvPLM7MS1fITS3JyE9RSEosTk1RyM9TKM0rLi1ILSrLBPFzUhOL8sCq8lNSc3gYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSbyzn6GhhZGhkaGpsaMxMWoAY6kz7w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Ultrasonic image denoising method based on unsupervised learning model</title><source>esp@cenet</source><creator>XIE SHENGHUA ; GAN JIANHONG ; WANG LIPING ; HE TONGLI ; YIN LIXUE ; ZHANG HONGMEI</creator><creatorcontrib>XIE SHENGHUA ; GAN JIANHONG ; WANG LIPING ; HE TONGLI ; YIN LIXUE ; ZHANG HONGMEI</creatorcontrib><description>The invention discloses an ultrasonic image denoising method based on an unsupervised learning model, and belongs to the technical field of image processing, and the method comprises the steps: S1, collecting a noisy ultrasonic image, carrying out the denoising processing of the noisy ultrasonic image, and respectively constructing the sub-images of the noisy ultrasonic image and the denoised ultrasonic image; s2, constructing a loss function based on the sub-image of the noisy ultrasonic image and the sub-image of the de-noised ultrasonic image; s3, based on the loss function, determining a target function for training the ultrasonic image denoising network, and training the target function; and S4, processing a to-be-denoised ultrasonic image by using the trained ultrasonic image denoising network to obtain a denoised ultrasonic image. According to the method, the dependence of the model on a data sample is reduced, the inference ability of deep learning is fully exerted, a Noisy-Clean image pair does not n</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=20240618&DB=EPODOC&CC=CN&NR=118212153A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240618&DB=EPODOC&CC=CN&NR=118212153A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>XIE SHENGHUA</creatorcontrib><creatorcontrib>GAN JIANHONG</creatorcontrib><creatorcontrib>WANG LIPING</creatorcontrib><creatorcontrib>HE TONGLI</creatorcontrib><creatorcontrib>YIN LIXUE</creatorcontrib><creatorcontrib>ZHANG HONGMEI</creatorcontrib><title>Ultrasonic image denoising method based on unsupervised learning model</title><description>The invention discloses an ultrasonic image denoising method based on an unsupervised learning model, and belongs to the technical field of image processing, and the method comprises the steps: S1, collecting a noisy ultrasonic image, carrying out the denoising processing of the noisy ultrasonic image, and respectively constructing the sub-images of the noisy ultrasonic image and the denoised ultrasonic image; s2, constructing a loss function based on the sub-image of the noisy ultrasonic image and the sub-image of the de-noised ultrasonic image; s3, based on the loss function, determining a target function for training the ultrasonic image denoising network, and training the target function; and S4, processing a to-be-denoised ultrasonic image by using the trained ultrasonic image denoising network to obtain a denoised ultrasonic image. According to the method, the dependence of the model on a data sample is reduced, the inference ability of deep learning is fully exerted, a Noisy-Clean image pair does not n</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>eNrjZHALzSkpSizOz8tMVsjMTUxPVUhJzcvPLM7MS1fITS3JyE9RSEosTk1RyM9TKM0rLi1ILSrLBPFzUhOL8sCq8lNSc3gYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSbyzn6GhhZGhkaGpsaMxMWoAY6kz7w</recordid><startdate>20240618</startdate><enddate>20240618</enddate><creator>XIE SHENGHUA</creator><creator>GAN JIANHONG</creator><creator>WANG LIPING</creator><creator>HE TONGLI</creator><creator>YIN LIXUE</creator><creator>ZHANG HONGMEI</creator><scope>EVB</scope></search><sort><creationdate>20240618</creationdate><title>Ultrasonic image denoising method based on unsupervised learning model</title><author>XIE SHENGHUA ; GAN JIANHONG ; WANG LIPING ; HE TONGLI ; YIN LIXUE ; ZHANG HONGMEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118212153A3</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>XIE SHENGHUA</creatorcontrib><creatorcontrib>GAN JIANHONG</creatorcontrib><creatorcontrib>WANG LIPING</creatorcontrib><creatorcontrib>HE TONGLI</creatorcontrib><creatorcontrib>YIN LIXUE</creatorcontrib><creatorcontrib>ZHANG HONGMEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>XIE SHENGHUA</au><au>GAN JIANHONG</au><au>WANG LIPING</au><au>HE TONGLI</au><au>YIN LIXUE</au><au>ZHANG HONGMEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Ultrasonic image denoising method based on unsupervised learning model</title><date>2024-06-18</date><risdate>2024</risdate><abstract>The invention discloses an ultrasonic image denoising method based on an unsupervised learning model, and belongs to the technical field of image processing, and the method comprises the steps: S1, collecting a noisy ultrasonic image, carrying out the denoising processing of the noisy ultrasonic image, and respectively constructing the sub-images of the noisy ultrasonic image and the denoised ultrasonic image; s2, constructing a loss function based on the sub-image of the noisy ultrasonic image and the sub-image of the de-noised ultrasonic image; s3, based on the loss function, determining a target function for training the ultrasonic image denoising network, and training the target function; and S4, processing a to-be-denoised ultrasonic image by using the trained ultrasonic image denoising network to obtain a denoised ultrasonic image. According to the method, the dependence of the model on a data sample is reduced, the inference ability of deep learning is fully exerted, a Noisy-Clean image pair does not n</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118212153A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Ultrasonic image denoising method based on unsupervised learning model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T02%3A38%3A41IST&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=XIE%20SHENGHUA&rft.date=2024-06-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118212153A%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 |