Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning
Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free technique for biomedical and mineralogical imaging which can suffer from low signal to noise ratios. Here we demonstrate the use of an unsupervised deep learning neural network for rapid and automatic denoising of SRS images:...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | 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 | Abdolghader, Pedram Ridsdale, Andrew Grammatikopoulos, Tassos Resch, Gavin Legare, Francois Stolow, Albert Pegoraro, Adrian F Tamblyn, Isaac |
| description | Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free
technique for biomedical and mineralogical imaging which can suffer from low
signal to noise ratios. Here we demonstrate the use of an unsupervised deep
learning neural network for rapid and automatic denoising of SRS images: UHRED
(Unsupervised Hyperspectral Resolution Enhancement and Denoising). UHRED is
capable of one-shot learning; only one hyperspectral image is needed, with no
requirements for training on previously labelled datasets or images.
Furthermore, by applying a k-means clustering algorithm to the processed data,
we demonstrate automatic, unsupervised image segmentation, yielding, without
prior knowledge of the sample, intuitive chemical species maps, as shown here
for a lithium ore sample. |
| doi_str_mv | 10.48550/arxiv.2104.08338 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2104_08338</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2104_08338</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-cf21d23e7ea92b8de2b3a14f3aa207170d9e1a9ab91e665ec8c71de98a76be623</originalsourceid><addsrcrecordid>eNotkM9Og0AYxLl4MNUH8OS-ALh_gF28mVptk5omUs_kY_eDbgILWSiRk68urZ5mMjOZwy8IHhiNYpUk9An8t50izmgcUSWEug1-vtxw7tFPdkBDtvNihx716KEh-WjbcwPjUnxCC458WO27QXf9THYt1Eg27gROY4tufCav6Do7WFcTcIbkWF9iGG3nyGSBHByG-akblx32ZI_g3bK9C24qaAa8_9dVcHzbHNfbcH94361f9iGkUoW64sxwgRIh46UyyEsBLK4EAKeSSWoyZJBBmTFM0wS10pIZzBTItMSUi1Xw-Hd7JVD03rbg5-JCoriSEL-67lwn</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning</title><source>arXiv.org</source><creator>Abdolghader, Pedram ; Ridsdale, Andrew ; Grammatikopoulos, Tassos ; Resch, Gavin ; Legare, Francois ; Stolow, Albert ; Pegoraro, Adrian F ; Tamblyn, Isaac</creator><creatorcontrib>Abdolghader, Pedram ; Ridsdale, Andrew ; Grammatikopoulos, Tassos ; Resch, Gavin ; Legare, Francois ; Stolow, Albert ; Pegoraro, Adrian F ; Tamblyn, Isaac</creatorcontrib><description>Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free
technique for biomedical and mineralogical imaging which can suffer from low
signal to noise ratios. Here we demonstrate the use of an unsupervised deep
learning neural network for rapid and automatic denoising of SRS images: UHRED
(Unsupervised Hyperspectral Resolution Enhancement and Denoising). UHRED is
capable of one-shot learning; only one hyperspectral image is needed, with no
requirements for training on previously labelled datasets or images.
Furthermore, by applying a k-means clustering algorithm to the processed data,
we demonstrate automatic, unsupervised image segmentation, yielding, without
prior knowledge of the sample, intuitive chemical species maps, as shown here
for a lithium ore sample.</description><identifier>DOI: 10.48550/arxiv.2104.08338</identifier><language>eng</language><subject>Physics - Applied Physics ; Physics - Optics</subject><creationdate>2021-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2104.08338$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2104.08338$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Abdolghader, Pedram</creatorcontrib><creatorcontrib>Ridsdale, Andrew</creatorcontrib><creatorcontrib>Grammatikopoulos, Tassos</creatorcontrib><creatorcontrib>Resch, Gavin</creatorcontrib><creatorcontrib>Legare, Francois</creatorcontrib><creatorcontrib>Stolow, Albert</creatorcontrib><creatorcontrib>Pegoraro, Adrian F</creatorcontrib><creatorcontrib>Tamblyn, Isaac</creatorcontrib><title>Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning</title><description>Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free
technique for biomedical and mineralogical imaging which can suffer from low
signal to noise ratios. Here we demonstrate the use of an unsupervised deep
learning neural network for rapid and automatic denoising of SRS images: UHRED
(Unsupervised Hyperspectral Resolution Enhancement and Denoising). UHRED is
capable of one-shot learning; only one hyperspectral image is needed, with no
requirements for training on previously labelled datasets or images.
Furthermore, by applying a k-means clustering algorithm to the processed data,
we demonstrate automatic, unsupervised image segmentation, yielding, without
prior knowledge of the sample, intuitive chemical species maps, as shown here
for a lithium ore sample.</description><subject>Physics - Applied Physics</subject><subject>Physics - Optics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkM9Og0AYxLl4MNUH8OS-ALh_gF28mVptk5omUs_kY_eDbgILWSiRk68urZ5mMjOZwy8IHhiNYpUk9An8t50izmgcUSWEug1-vtxw7tFPdkBDtvNihx716KEh-WjbcwPjUnxCC458WO27QXf9THYt1Eg27gROY4tufCav6Do7WFcTcIbkWF9iGG3nyGSBHByG-akblx32ZI_g3bK9C24qaAa8_9dVcHzbHNfbcH94361f9iGkUoW64sxwgRIh46UyyEsBLK4EAKeSSWoyZJBBmTFM0wS10pIZzBTItMSUi1Xw-Hd7JVD03rbg5-JCoriSEL-67lwn</recordid><startdate>20210414</startdate><enddate>20210414</enddate><creator>Abdolghader, Pedram</creator><creator>Ridsdale, Andrew</creator><creator>Grammatikopoulos, Tassos</creator><creator>Resch, Gavin</creator><creator>Legare, Francois</creator><creator>Stolow, Albert</creator><creator>Pegoraro, Adrian F</creator><creator>Tamblyn, Isaac</creator><scope>GOX</scope></search><sort><creationdate>20210414</creationdate><title>Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning</title><author>Abdolghader, Pedram ; Ridsdale, Andrew ; Grammatikopoulos, Tassos ; Resch, Gavin ; Legare, Francois ; Stolow, Albert ; Pegoraro, Adrian F ; Tamblyn, Isaac</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-cf21d23e7ea92b8de2b3a14f3aa207170d9e1a9ab91e665ec8c71de98a76be623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Physics - Applied Physics</topic><topic>Physics - Optics</topic><toplevel>online_resources</toplevel><creatorcontrib>Abdolghader, Pedram</creatorcontrib><creatorcontrib>Ridsdale, Andrew</creatorcontrib><creatorcontrib>Grammatikopoulos, Tassos</creatorcontrib><creatorcontrib>Resch, Gavin</creatorcontrib><creatorcontrib>Legare, Francois</creatorcontrib><creatorcontrib>Stolow, Albert</creatorcontrib><creatorcontrib>Pegoraro, Adrian F</creatorcontrib><creatorcontrib>Tamblyn, Isaac</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Abdolghader, Pedram</au><au>Ridsdale, Andrew</au><au>Grammatikopoulos, Tassos</au><au>Resch, Gavin</au><au>Legare, Francois</au><au>Stolow, Albert</au><au>Pegoraro, Adrian F</au><au>Tamblyn, Isaac</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning</atitle><date>2021-04-14</date><risdate>2021</risdate><abstract>Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free
technique for biomedical and mineralogical imaging which can suffer from low
signal to noise ratios. Here we demonstrate the use of an unsupervised deep
learning neural network for rapid and automatic denoising of SRS images: UHRED
(Unsupervised Hyperspectral Resolution Enhancement and Denoising). UHRED is
capable of one-shot learning; only one hyperspectral image is needed, with no
requirements for training on previously labelled datasets or images.
Furthermore, by applying a k-means clustering algorithm to the processed data,
we demonstrate automatic, unsupervised image segmentation, yielding, without
prior knowledge of the sample, intuitive chemical species maps, as shown here
for a lithium ore sample.</abstract><doi>10.48550/arxiv.2104.08338</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2104.08338 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2104_08338 |
| source | arXiv.org |
| subjects | Physics - Applied Physics Physics - Optics |
| title | Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T20%3A40%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Unsupervised%20Hyperspectral%20Stimulated%20Raman%20Microscopy%20Image%20Enhancement:%20Denoising%20and%20Segmentation%20via%20One-Shot%20Deep%20Learning&rft.au=Abdolghader,%20Pedram&rft.date=2021-04-14&rft_id=info:doi/10.48550/arxiv.2104.08338&rft_dat=%3Carxiv_GOX%3E2104_08338%3C/arxiv_GOX%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 |