{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:06:26Z","timestamp":1790208386756,"version":"4.1.0"},"reference-count":69,"publisher":"SPIE-Intl Soc Optical Eng","issue":"09","license":[{"start":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T00:00:00Z","timestamp":1727395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Biomed. Opt."],"published-print":{"date-parts":[[2024,9,27]]},"abstract":"<jats:p>SignificanceLabel-free multimodal imaging methods that can provide complementary structural and chemical information from the same sample are critical for comprehensive tissue analyses. These methods are specifically needed to study the complex tumor-microenvironment where fibrillar collagen\u2019s architectural changes are associated with cancer progression. To address this need, we present a multimodal computational imaging method where mid-infrared spectral imaging (MIRSI) is employed with second harmonic generation (SHG) microscopy to identify fibrillar collagen in biological tissues.AimTo demonstrate a multimodal approach where a morphology-specific contrast mechanism guides an MIRSI method to detect fibrillar collagen based on its chemical signatures.ApproachWe trained a supervised machine learning (ML) model using SHG images as ground truth collagen labels to classify fibrillar collagen in biological tissues based on their mid-infrared hyperspectral images. Five human pancreatic tissue samples (sizes are in the order of millimeters) were imaged by both MIRSI and SHG microscopes. In total, 2.8\u00a0million MIRSI spectra were used to train a random forest (RF) model. The other 68\u00a0million spectra were used to validate the collagen images generated by the RF-MIRSI model in terms of collagen segmentation, orientation, and alignment.ResultsCompared with the SHG ground truth, the generated RF-MIRSI collagen images achieved a high average boundary F-score (0.8 at 4-pixel thresholds) in the collagen distribution, high correlation (Pearson\u2019s R 0.82) in the collagen orientation, and similarly high correlation (Pearson\u2019s R 0.66) in the collagen alignment.ConclusionsWe showed the potential of ML-aided label-free mid-infrared hyperspectral imaging for collagen fiber and tumor microenvironment analysis in tumor pathology samples.<\/jats:p>","DOI":"10.1117\/1.jbo.29.9.093511","type":"journal-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T06:08:22Z","timestamp":1727417302000},"page":"1-14","source":"Crossref","is-referenced-by-count":9,"title":["Machine learning-assisted mid-infrared spectrochemical fibrillar collagen imaging in clinical tissues"],"prefix":"10.1117","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4439-2021","authenticated-orcid":false,"given":"Wihan","family":"Adi","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Department of Biomedical Engineering, Madison, Wisconsin, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuming","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Center for Quantitative Cell Imaging, Madison, Wisconsin, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sydney","family":"Runkle","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Department of Computer Science, Madison, Wisconsin, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8678-670X","authenticated-orcid":false,"given":"Kevin W.","family":"Eliceiri","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Department of Biomedical Engineering, Madison, Wisconsin, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8483-3285","authenticated-orcid":false,"given":"Filiz","family":"Yesilkoy","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Department of Biomedical Engineering, Madison, Wisconsin, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2019.00160"},{"key":"r2","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering8020017"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1186\/1741-7015-4-38"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2407-10-94"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.6740"},{"key":"r6","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.12772"},{"key":"r7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2018.09.009"},{"key":"r8","doi-asserted-by":"publisher","DOI":"10.1369\/0022155414545787"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13205089"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpi.2022.100158"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-98600-w"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1364\/boe.8.004243"},{"key":"r13","article-title":"Leveraging optical anisotropy of the morpho butterfly wing for quantitative, stain-free, and contact-free assessment of biological tissue microstructures","author":"Kirya","year":"2024"},{"key":"r14","doi-asserted-by":"publisher","DOI":"10.1021\/ac1032325"},{"key":"r15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-2914-7_13"},{"key":"r16","doi-asserted-by":"publisher","DOI":"10.1186\/1741-7015-6-11"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2010.11.076"},{"key":"r18","doi-asserted-by":"publisher","DOI":"10.1364\/oe.15.010135"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1134\/s1054660x11170269"},{"key":"r20","doi-asserted-by":"publisher","DOI":"10.1063\/1.5022595"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1002\/sca.21116"},{"key":"r22","doi-asserted-by":"publisher","DOI":"10.1038\/modpathol.2015.97"},{"key":"r23","doi-asserted-by":"publisher","DOI":"10.1038\/nphoton.2012.143"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.8b01632"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1912400117"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.7b00426"},{"key":"r27","doi-asserted-by":"publisher","DOI":"10.1007\/s00216-009-3019-y"},{"key":"r28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0064822"},{"key":"r29","doi-asserted-by":"publisher","DOI":"10.1039\/c6an02080a"},{"key":"r30","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2020-0635-oa"},{"key":"r31","doi-asserted-by":"publisher","DOI":"10.1177\/00037028211063513"},{"key":"r32","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abb8292"},{"key":"r33","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-62403-2"},{"key":"r34","doi-asserted-by":"publisher","DOI":"10.1016\/bs.mcb.2016.01.005"},{"key":"r35","year":"2024"},{"key":"r36","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp184"},{"key":"r37","doi-asserted-by":"publisher","DOI":"10.1038\/nprot.2014.110"},{"key":"r38","article-title":"Find image rotation and scale\u2014MATLAB and simulink example"},{"key":"r39","article-title":"Control point selection tool\u2014MATLAB cpselect"},{"key":"r40","article-title":"Fit 2-D geometric transformation to control point pairs\u2014MATLAB fitgeotform2d"},{"key":"r41","article-title":"Apply geometric transformation to image\u2014MATLAB imwarp"},{"key":"r42","article-title":"Ensemble of bagged decision trees\u2014MATLAB"},{"key":"r43","doi-asserted-by":"publisher","DOI":"10.1023\/a:1010933404324"},{"key":"r44","article-title":"Out-of-bag error\u2014MATLAB"},{"key":"r45","doi-asserted-by":"crossref","DOI":"10.5244\/C.27.32","article-title":"What is a good evaluation measure for semantic segmentation?","author":"Csurka","year":"2013"},{"key":"r46","article-title":"Contour matching score for image segmentation\u2014MATLAB bfscore"},{"key":"r47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28549-8_3"},{"key":"r48","article-title":"Correlation coefficients\u2014MATLAB corrcoef"},{"key":"r49","doi-asserted-by":"publisher","DOI":"10.1093\/ndt\/gfaa301"},{"key":"r50","doi-asserted-by":"publisher","DOI":"10.1016\/j.trsl.2019.02.006"},{"key":"r51","doi-asserted-by":"publisher","DOI":"10.1172\/jci93554"},{"key":"r52","doi-asserted-by":"publisher","DOI":"10.1359\/jbmr.2001.16.10.1821"},{"key":"r53","doi-asserted-by":"publisher","DOI":"10.1016\/j.micron.2010.09.010"},{"key":"r54","first-page":"129","article-title":"Curve-fitting micro-ATR-FTIR studies of the amide I and II bands of type I collagen in archaeological bone materials","author":"Chadefaux","year":"2009"},{"key":"r55","doi-asserted-by":"publisher","DOI":"10.1002\/bip.360271105"},{"key":"r56","doi-asserted-by":"publisher","DOI":"10.1080\/05704928.2018.1426595"},{"key":"r57","doi-asserted-by":"publisher","DOI":"10.1007\/s00223-023-01105-z"},{"key":"r58","doi-asserted-by":"publisher","DOI":"10.1007\/s00216-006-0828-0"},{"key":"r59","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2017.01.015"},{"key":"r60","doi-asserted-by":"publisher","DOI":"10.1110\/ps.0218502"},{"key":"r61","doi-asserted-by":"publisher","DOI":"10.1080\/05704920701829043"},{"key":"r62","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1607896113"},{"key":"r63","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2938-9"},{"key":"r64","doi-asserted-by":"publisher","DOI":"10.1016\/j.trecan.2016.05.004"},{"key":"r65","doi-asserted-by":"publisher","DOI":"10.1117\/1.jbo.25.1.014505"},{"key":"r66","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aav7127"},{"key":"r67","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1600521"},{"key":"r68","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40740-w"},{"key":"r69","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202301208"}],"container-title":["Journal of Biomedical Optics"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-biomedical-optics\/volume-29\/issue-09\/093511\/Machine-learning-assisted-mid-infrared-spectrochemical-fibrillar-collagen-imaging-in\/10.1117\/1.JBO.29.9.093511.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T23:44:26Z","timestamp":1790207066000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-biomedical-optics\/volume-29\/issue-09\/093511\/Machine-learning-assisted-mid-infrared-spectrochemical-fibrillar-collagen-imaging-in\/10.1117\/1.JBO.29.9.093511.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,27]]},"references-count":69,"journal-issue":{"issue":"09","published-online":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jbo.29.9.093511","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.05.22.595393","asserted-by":"object"}]},"ISSN":["1083-3668","1560-2281"],"issn-type":[{"value":"1083-3668","type":"print"},{"value":"1560-2281","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,27]]}}}