Unsupervised hyperspectral data mining and bioimaging by information entropy and self-modeling curve resolution

Unsupervised estimation of the dimensionality of hyperspectral microspectroscopy datasets containing pure and mixed spectral features, and extraction of their representative endmember spectra, remains a challenge in biochemical data mining. We report a new versatile algorithm building on semi-nonneg...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pedersen, Simon Vilms, Walther, Anders R, Callanan, Anthony, Stevens, Molly M, Hedegaard, Martin A. B, Arnspang, Eva C
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 Pedersen, Simon Vilms
Walther, Anders R
Callanan, Anthony
Stevens, Molly M
Hedegaard, Martin A. B
Arnspang, Eva C
description Unsupervised estimation of the dimensionality of hyperspectral microspectroscopy datasets containing pure and mixed spectral features, and extraction of their representative endmember spectra, remains a challenge in biochemical data mining. We report a new versatile algorithm building on semi-nonnegativity constrained self-modeling curve resolution and information entropy, to estimate the quantity of separable biochemical species from hyperspectral microspectroscopy, and extraction of their representative spectra. The algorithm is benchmarked with established methods from satellite remote sensing, spectral unmixing, and clustering. To demonstrate the widespread applicability of the developed algorithm, we collected hyperspectral datasets using spontaneous Raman, Coherent Anti-stokes Raman Scattering and Fourier Transform IR, of seven reference compounds, an oil-in-water emulsion, and tissue-engineered extracellular matrices on poly-L-lactic acid and porcine jejunum-derived small intestine submucosa scaffolds seeded with bovine chondrocytes. We show the potential of the developed algorithm by consolidating hyperspectral molecular information with sample microstructure, pertinent to fields ranging from gastrophysics to regenerative medicine.
doi_str_mv 10.48550/arxiv.2210.03238
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_03238</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_03238</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-ec3c642eb2b40da84a8e6c9362866b880879dae12e9310738ab856cfe1fad61e3</originalsourceid><addsrcrecordid>eNotj8tOhDAUhrtxYUYfwJV9AcbSQilLM_GWTOJmXJPT9jA2gZa0QOTtBXR1Lvny5_8IecjZsVBlyZ4g_rj5yPn6YIILdUvCl0_TgHF2CS39XtY1DWjGCB21MALtnXf-SsFbql1wPVy3Uy_U-TbEHkYXPEU_xjAsO5Wwa7M-WOw20ExxRhoxhW7a0Dty00KX8P5_Hsjl9eVyes_On28fp-dzBrJSGRphZMFRc10wC6oAhdLUQnIlpVaKqaq2gDnHWuSsEgq0KqVpMW_ByhzFgTz-xe7GzRDX4nFpNvNmNxe_7yRW_g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Unsupervised hyperspectral data mining and bioimaging by information entropy and self-modeling curve resolution</title><source>arXiv.org</source><creator>Pedersen, Simon Vilms ; Walther, Anders R ; Callanan, Anthony ; Stevens, Molly M ; Hedegaard, Martin A. B ; Arnspang, Eva C</creator><creatorcontrib>Pedersen, Simon Vilms ; Walther, Anders R ; Callanan, Anthony ; Stevens, Molly M ; Hedegaard, Martin A. B ; Arnspang, Eva C</creatorcontrib><description>Unsupervised estimation of the dimensionality of hyperspectral microspectroscopy datasets containing pure and mixed spectral features, and extraction of their representative endmember spectra, remains a challenge in biochemical data mining. We report a new versatile algorithm building on semi-nonnegativity constrained self-modeling curve resolution and information entropy, to estimate the quantity of separable biochemical species from hyperspectral microspectroscopy, and extraction of their representative spectra. The algorithm is benchmarked with established methods from satellite remote sensing, spectral unmixing, and clustering. To demonstrate the widespread applicability of the developed algorithm, we collected hyperspectral datasets using spontaneous Raman, Coherent Anti-stokes Raman Scattering and Fourier Transform IR, of seven reference compounds, an oil-in-water emulsion, and tissue-engineered extracellular matrices on poly-L-lactic acid and porcine jejunum-derived small intestine submucosa scaffolds seeded with bovine chondrocytes. We show the potential of the developed algorithm by consolidating hyperspectral molecular information with sample microstructure, pertinent to fields ranging from gastrophysics to regenerative medicine.</description><identifier>DOI: 10.48550/arxiv.2210.03238</identifier><language>eng</language><subject>Quantitative Biology - Quantitative Methods ; Statistics - Computation</subject><creationdate>2022-10</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/2210.03238$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.03238$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Pedersen, Simon Vilms</creatorcontrib><creatorcontrib>Walther, Anders R</creatorcontrib><creatorcontrib>Callanan, Anthony</creatorcontrib><creatorcontrib>Stevens, Molly M</creatorcontrib><creatorcontrib>Hedegaard, Martin A. B</creatorcontrib><creatorcontrib>Arnspang, Eva C</creatorcontrib><title>Unsupervised hyperspectral data mining and bioimaging by information entropy and self-modeling curve resolution</title><description>Unsupervised estimation of the dimensionality of hyperspectral microspectroscopy datasets containing pure and mixed spectral features, and extraction of their representative endmember spectra, remains a challenge in biochemical data mining. We report a new versatile algorithm building on semi-nonnegativity constrained self-modeling curve resolution and information entropy, to estimate the quantity of separable biochemical species from hyperspectral microspectroscopy, and extraction of their representative spectra. The algorithm is benchmarked with established methods from satellite remote sensing, spectral unmixing, and clustering. To demonstrate the widespread applicability of the developed algorithm, we collected hyperspectral datasets using spontaneous Raman, Coherent Anti-stokes Raman Scattering and Fourier Transform IR, of seven reference compounds, an oil-in-water emulsion, and tissue-engineered extracellular matrices on poly-L-lactic acid and porcine jejunum-derived small intestine submucosa scaffolds seeded with bovine chondrocytes. We show the potential of the developed algorithm by consolidating hyperspectral molecular information with sample microstructure, pertinent to fields ranging from gastrophysics to regenerative medicine.</description><subject>Quantitative Biology - Quantitative Methods</subject><subject>Statistics - Computation</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOhDAUhrtxYUYfwJV9AcbSQilLM_GWTOJmXJPT9jA2gZa0QOTtBXR1Lvny5_8IecjZsVBlyZ4g_rj5yPn6YIILdUvCl0_TgHF2CS39XtY1DWjGCB21MALtnXf-SsFbql1wPVy3Uy_U-TbEHkYXPEU_xjAsO5Wwa7M-WOw20ExxRhoxhW7a0Dty00KX8P5_Hsjl9eVyes_On28fp-dzBrJSGRphZMFRc10wC6oAhdLUQnIlpVaKqaq2gDnHWuSsEgq0KqVpMW_ByhzFgTz-xe7GzRDX4nFpNvNmNxe_7yRW_g</recordid><startdate>20221006</startdate><enddate>20221006</enddate><creator>Pedersen, Simon Vilms</creator><creator>Walther, Anders R</creator><creator>Callanan, Anthony</creator><creator>Stevens, Molly M</creator><creator>Hedegaard, Martin A. B</creator><creator>Arnspang, Eva C</creator><scope>ALC</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20221006</creationdate><title>Unsupervised hyperspectral data mining and bioimaging by information entropy and self-modeling curve resolution</title><author>Pedersen, Simon Vilms ; Walther, Anders R ; Callanan, Anthony ; Stevens, Molly M ; Hedegaard, Martin A. B ; Arnspang, Eva C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-ec3c642eb2b40da84a8e6c9362866b880879dae12e9310738ab856cfe1fad61e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Quantitative Biology - Quantitative Methods</topic><topic>Statistics - Computation</topic><toplevel>online_resources</toplevel><creatorcontrib>Pedersen, Simon Vilms</creatorcontrib><creatorcontrib>Walther, Anders R</creatorcontrib><creatorcontrib>Callanan, Anthony</creatorcontrib><creatorcontrib>Stevens, Molly M</creatorcontrib><creatorcontrib>Hedegaard, Martin A. B</creatorcontrib><creatorcontrib>Arnspang, Eva C</creatorcontrib><collection>arXiv Quantitative Biology</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pedersen, Simon Vilms</au><au>Walther, Anders R</au><au>Callanan, Anthony</au><au>Stevens, Molly M</au><au>Hedegaard, Martin A. B</au><au>Arnspang, Eva C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unsupervised hyperspectral data mining and bioimaging by information entropy and self-modeling curve resolution</atitle><date>2022-10-06</date><risdate>2022</risdate><abstract>Unsupervised estimation of the dimensionality of hyperspectral microspectroscopy datasets containing pure and mixed spectral features, and extraction of their representative endmember spectra, remains a challenge in biochemical data mining. We report a new versatile algorithm building on semi-nonnegativity constrained self-modeling curve resolution and information entropy, to estimate the quantity of separable biochemical species from hyperspectral microspectroscopy, and extraction of their representative spectra. The algorithm is benchmarked with established methods from satellite remote sensing, spectral unmixing, and clustering. To demonstrate the widespread applicability of the developed algorithm, we collected hyperspectral datasets using spontaneous Raman, Coherent Anti-stokes Raman Scattering and Fourier Transform IR, of seven reference compounds, an oil-in-water emulsion, and tissue-engineered extracellular matrices on poly-L-lactic acid and porcine jejunum-derived small intestine submucosa scaffolds seeded with bovine chondrocytes. We show the potential of the developed algorithm by consolidating hyperspectral molecular information with sample microstructure, pertinent to fields ranging from gastrophysics to regenerative medicine.</abstract><doi>10.48550/arxiv.2210.03238</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.03238
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_03238
source arXiv.org
subjects Quantitative Biology - Quantitative Methods
Statistics - Computation
title Unsupervised hyperspectral data mining and bioimaging by information entropy and self-modeling curve resolution
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T03%3A56%3A52IST&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%20data%20mining%20and%20bioimaging%20by%20information%20entropy%20and%20self-modeling%20curve%20resolution&rft.au=Pedersen,%20Simon%20Vilms&rft.date=2022-10-06&rft_id=info:doi/10.48550/arxiv.2210.03238&rft_dat=%3Carxiv_GOX%3E2210_03238%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