Average spectra for both tissue classes, with standard error regions.
<p>Differential normalized fluorescence curves, or the difference of sarcoma from healthy averaged spectra, are shown in green, arbitrarily positioned at 1.2 for ease of visualization. <b>(A)</b> Averaged spectra for each tissue class without individual spectra normalization. Spect...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852026050534440960 |
|---|---|
| author | Ashutosh P. Raman (19825936) |
| author2 | Tanner J. Zachem (19825939) Sarah Plumlee (19825942) Christine Park (10261868) William Eward (19825945) Patrick J. Codd (14979591) Weston Ross (19825948) |
| author2_role | author author author author author author |
| author_facet | Ashutosh P. Raman (19825936) Tanner J. Zachem (19825939) Sarah Plumlee (19825942) Christine Park (10261868) William Eward (19825945) Patrick J. Codd (14979591) Weston Ross (19825948) |
| author_role | author |
| dc.creator.none.fl_str_mv | Ashutosh P. Raman (19825936) Tanner J. Zachem (19825939) Sarah Plumlee (19825942) Christine Park (10261868) William Eward (19825945) Patrick J. Codd (14979591) Weston Ross (19825948) |
| dc.date.none.fl_str_mv | 2024-10-09T17:33:30Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pdig.0000602.g005 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Average_spectra_for_both_tissue_classes_with_standard_error_regions_/27197698 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Medicine Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified use machine learning support vector machines support vector machine machine learning approaches involve many challenges following study builds first known study current surgical instrumentation box ann architecture biomedical sensing landscape based spectroscopic signatures automate photonic diagnosis tissue healing difficulty implementing classification algorithms interpretable algorithms classification accuracies normal tissue ambiguous tissue utilizes autofluorescence tumor boundary substantial research standard risks previously devised precise determination nearest neighbors logistic regression interpret data direct applications curve scores critical need clear way care platform |
| dc.title.none.fl_str_mv | Average spectra for both tissue classes, with standard error regions. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <p>Differential normalized fluorescence curves, or the difference of sarcoma from healthy averaged spectra, are shown in green, arbitrarily positioned at 1.2 for ease of visualization. <b>(A)</b> Averaged spectra for each tissue class without individual spectra normalization. Spectra are scaled between 0 and 1.0 through division by global maximum intensity. Standard errors are provided as shaded regions around average spectra. Spectra are observed to significantly deviate in intensity between 450 and 650 nm, but converge around the 700 nm region. <b>(B)</b> Normalized spectra with standard error shaded regions. Every spectra is normalized prior to averaging by class, using 500 nm intensity division per spectra, then averaged data is all divided by the global maximum intensity.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_bcdffc8dbf1cddb932d33fdc26f4f7d5 |
| identifier_str_mv | 10.1371/journal.pdig.0000602.g005 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27197698 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Average spectra for both tissue classes, with standard error regions.Ashutosh P. Raman (19825936)Tanner J. Zachem (19825939)Sarah Plumlee (19825942)Christine Park (10261868)William Eward (19825945)Patrick J. Codd (14979591)Weston Ross (19825948)MedicineBiotechnologyCancerSpace ScienceBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifieduse machine learningsupport vector machinessupport vector machinemachine learning approachesinvolve many challengesfollowing study buildsfirst known studycurrent surgical instrumentationbox ann architecturebiomedical sensing landscapebased spectroscopic signaturesautomate photonic diagnosistissue healing difficultyimplementing classification algorithmsinterpretable algorithmsclassification accuraciesnormal tissueambiguous tissueutilizes autofluorescencetumor boundarysubstantial researchstandard riskspreviously devisedprecise determinationnearest neighborslogistic regressioninterpret datadirect applicationscurve scorescritical needclear waycare platform<p>Differential normalized fluorescence curves, or the difference of sarcoma from healthy averaged spectra, are shown in green, arbitrarily positioned at 1.2 for ease of visualization. <b>(A)</b> Averaged spectra for each tissue class without individual spectra normalization. Spectra are scaled between 0 and 1.0 through division by global maximum intensity. Standard errors are provided as shaded regions around average spectra. Spectra are observed to significantly deviate in intensity between 450 and 650 nm, but converge around the 700 nm region. <b>(B)</b> Normalized spectra with standard error shaded regions. Every spectra is normalized prior to averaging by class, using 500 nm intensity division per spectra, then averaged data is all divided by the global maximum intensity.</p>2024-10-09T17:33:30ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pdig.0000602.g005https://figshare.com/articles/figure/Average_spectra_for_both_tissue_classes_with_standard_error_regions_/27197698CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/271976982024-10-09T17:33:30Z |
| spellingShingle | Average spectra for both tissue classes, with standard error regions. Ashutosh P. Raman (19825936) Medicine Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified use machine learning support vector machines support vector machine machine learning approaches involve many challenges following study builds first known study current surgical instrumentation box ann architecture biomedical sensing landscape based spectroscopic signatures automate photonic diagnosis tissue healing difficulty implementing classification algorithms interpretable algorithms classification accuracies normal tissue ambiguous tissue utilizes autofluorescence tumor boundary substantial research standard risks previously devised precise determination nearest neighbors logistic regression interpret data direct applications curve scores critical need clear way care platform |
| status_str | publishedVersion |
| title | Average spectra for both tissue classes, with standard error regions. |
| title_full | Average spectra for both tissue classes, with standard error regions. |
| title_fullStr | Average spectra for both tissue classes, with standard error regions. |
| title_full_unstemmed | Average spectra for both tissue classes, with standard error regions. |
| title_short | Average spectra for both tissue classes, with standard error regions. |
| title_sort | Average spectra for both tissue classes, with standard error regions. |
| topic | Medicine Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified use machine learning support vector machines support vector machine machine learning approaches involve many challenges following study builds first known study current surgical instrumentation box ann architecture biomedical sensing landscape based spectroscopic signatures automate photonic diagnosis tissue healing difficulty implementing classification algorithms interpretable algorithms classification accuracies normal tissue ambiguous tissue utilizes autofluorescence tumor boundary substantial research standard risks previously devised precise determination nearest neighbors logistic regression interpret data direct applications curve scores critical need clear way care platform |