Stomach tissue classification using autofluorescence spectroscopy and machine learning.
Autofluorescence
Histology
Machine learning
Spectroscopy
Journal
Surgical endoscopy
ISSN: 1432-2218
Titre abrégé: Surg Endosc
Pays: Germany
ID NLM: 8806653
Informations de publication
Date de publication:
08 2023
08 2023
Historique:
received:
15
12
2022
accepted:
26
03
2023
medline:
14
7
2023
pubmed:
14
4
2023
entrez:
13
4
2023
Statut:
ppublish
Résumé
Determination of stomach tumor location and invasion depth requires delineation of gastric histological structure, which has hitherto been widely accomplished by histochemical staining. In recent years, alternative histochemical evaluation methods have been pursued to accelerate intraoperative diagnosis, often by bypassing the time-consuming step of dyeing. Owing to strong endogenous signals from coenzymes, metabolites, and proteins, autofluorescence spectroscopy is a favorable candidate technique to achieve this aim. We investigated stomach tissue slices and block specimens using a fast fluorescence imaging scanner. To obtain histological information from broad and structureless fluorescence spectra, we analyzed tens of thousands of spectra with multiple machine-learning algorithms and built a tissue classification model trained with dissected gastric tissues. A machine-learning-based spectro-histological model was built based on the autofluorescence spectra measured from stomach tissue samples with delineated and validated histological structures. The scores from a principal components analysis were employed as input features, and prediction accuracy was confirmed to be 92.0%, 90.1%, and 91.4% for mucosa, submucosa, and muscularis propria, respectively. We investigated the tissue samples in both sliced and block forms using a fast fluorescence imaging scanner. We successfully demonstrated differentiation of multiple tissue layers of well-defined specimens with the guidance of a histologist. Our spectro-histology classification model is applicable to histological prediction for both tissue blocks and slices, even though only sliced samples were trained.
Sections du résumé
BACKGROUND AND OBJECTIVES
Determination of stomach tumor location and invasion depth requires delineation of gastric histological structure, which has hitherto been widely accomplished by histochemical staining. In recent years, alternative histochemical evaluation methods have been pursued to accelerate intraoperative diagnosis, often by bypassing the time-consuming step of dyeing. Owing to strong endogenous signals from coenzymes, metabolites, and proteins, autofluorescence spectroscopy is a favorable candidate technique to achieve this aim.
MATERIALS AND METHODS
We investigated stomach tissue slices and block specimens using a fast fluorescence imaging scanner. To obtain histological information from broad and structureless fluorescence spectra, we analyzed tens of thousands of spectra with multiple machine-learning algorithms and built a tissue classification model trained with dissected gastric tissues.
RESULTS
A machine-learning-based spectro-histological model was built based on the autofluorescence spectra measured from stomach tissue samples with delineated and validated histological structures. The scores from a principal components analysis were employed as input features, and prediction accuracy was confirmed to be 92.0%, 90.1%, and 91.4% for mucosa, submucosa, and muscularis propria, respectively. We investigated the tissue samples in both sliced and block forms using a fast fluorescence imaging scanner.
CONCLUSION
We successfully demonstrated differentiation of multiple tissue layers of well-defined specimens with the guidance of a histologist. Our spectro-histology classification model is applicable to histological prediction for both tissue blocks and slices, even though only sliced samples were trained.
Identifiants
pubmed: 37055665
doi: 10.1007/s00464-023-10053-6
pii: 10.1007/s00464-023-10053-6
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
5825-5835Subventions
Organisme : NIBIB NIH HHS
ID : P41 EB015871
Pays : United States
Organisme : NIBIB NIH HHS
ID : P41EB015871
Pays : United States
Informations de copyright
© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Références
Schnell M, Mittal S, Falahkheirkhah K, Mittal A, Yeh K, Kenkel S, Kajdacsy-Balla A, Carney PS, Bhargava R (2020) All-digital histopathology by infrared-optical hybrid microscopy. Proc Natl Acad Sci 117:3388–3396. https://doi.org/10.1073/pnas.1912400117
doi: 10.1073/pnas.1912400117
pubmed: 32015103
pmcid: 7035604
Anderson TA, Kang JW, Gubin T, Dasari RR, So PTC (2016) Raman spectroscopy differentiates each tissue from the skin to the spinal cord: a novel method for epidural needle placement? Anesthesiology 125:793–804. https://doi.org/10.1097/ALN.0000000000001249
doi: 10.1097/ALN.0000000000001249
pubmed: 27466032
Nazarian S, Gkouzionis I, Kawka M, Jamroziak M, Lloyd J, Darzi A, Patel N, Elson DS, Peters CJ (2022) Real-time tracking and classification of tumor and nontumor tissue in upper gastrointestinal cancers using diffuse reflectance spectroscopy for resection margin assessment. JAMA Surg. https://doi.org/10.1001/jamasurg.2022.3899
doi: 10.1001/jamasurg.2022.3899
pubmed: 36069888
pmcid: 9453631
Rivenson Y, Wang H, Wei Z, de Haan K, Zhang Y, Wu Y, Günaydın H, Zuckerman JE, Chong T, Sisk AE, Westbrook LM, Wallace WD, Ozcan A (2019) Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning. Nat Biomed Eng 3:466–477. https://doi.org/10.1038/s41551-019-0362-y
doi: 10.1038/s41551-019-0362-y
pubmed: 31142829
Yoon HM, Kim H, Sohn DK, Park SC, Chang HJ, Oh JH, Dasari RR, So PTC, Kang JW (2021) Dual modal spectroscopic tissue scanner for colorectal cancer diagnosis. Surg Endosc 35:4363–4370. https://doi.org/10.1007/s00464-020-07929-2
doi: 10.1007/s00464-020-07929-2
pubmed: 32875410
Myszczynska MA, Ojamies PN, Lacoste AMB, Neil D, Saffari A, Mead R, Hautbergue GM, Holbrook JD, Ferraiuolo L (2020) Applications of machine learning to diagnosis and treatment of neurodegenerative diseases. Nat Rev Neurol 16:440–456. https://doi.org/10.1038/s41582-020-0377-8
doi: 10.1038/s41582-020-0377-8
pubmed: 32669685
Liu Y, Jain A, Eng C, Way DH, Lee K, Bui P, Kanada K, de Oliveira MG, Gallegos J, Gabriele S, Gupta V, Singh N, Natarajan V, Hofmann-Wellenhof R, Corrado GS, Peng LH, Webster DR, Ai D, Huang SJ, Liu Y, Dunn RC, Coz D (2020) A deep learning system for differential diagnosis of skin diseases. Nat Med 26:900–908. https://doi.org/10.1038/s41591-020-0842-3
doi: 10.1038/s41591-020-0842-3
pubmed: 32424212
Croce AC, Bottiroli G (2014) Autofluorescence spectroscopy and imaging: a tool for biomedical research and diagnosis. Eur J Histochem. https://doi.org/10.4081/ejh.2014.2461
doi: 10.4081/ejh.2014.2461
pubmed: 25578980
pmcid: 4289852
Kuehn A, Graf A, Wenzel U, Princz S, Mantz H, Hessling M (2015) Development of a highly sensitive spectral camera for cartilage monitoring using fluorescence spectroscopy. J Sens Syst 4:289–294. https://doi.org/10.5194/jsss-4-289-2015
doi: 10.5194/jsss-4-289-2015
Wu Y, Qu JY (2006) Autofluorescence spectroscopy of epithelial tissues. JBO. https://doi.org/10.1117/12362741
doi: 10.1117/12362741
pubmed: 17212545
Sun Y, Sun Y, Stephens D, Xie H, Phipps J, Saroufeem R, Southard J, Elson DS, Marcu L (2011) Dynamic tissue analysis using time- and wavelength-resolved fluorescence spectroscopy for atherosclerosis diagnosis. Opt Expr 19:3890–3901. https://doi.org/10.1364/OE.19.003890
doi: 10.1364/OE.19.003890
Wu Y, Xi P, Qu JY, Cheung T-H, Yu M-Y (2004) Depth-resolved fluorescence spectroscopy reveals layered structure of tissue. Opt Expr 12:3218–3223. https://doi.org/10.1364/OPEX.12.003218
doi: 10.1364/OPEX.12.003218
Rice WL, Kaplan DL, Georgakoudi I (2010) Two-photon microscopy for non-invasive, quantitative monitoring of stem cell differentiation. PLoS ONE 5:e10075. https://doi.org/10.1371/journal.pone.0010075
doi: 10.1371/journal.pone.0010075
pubmed: 20419124
pmcid: 2855700
Schaefer PM, Kalinina S, Rueck A, von Arnim CAF, von Einem B (2019) NADH autofluorescence—a marker on its way to boost bioenergetic research. Cytometry A 95:34–46. https://doi.org/10.1002/cyto.a.23597
doi: 10.1002/cyto.a.23597
pubmed: 30211978
Seo I, Tseng SH, Cula GO, Bargo PR, Kollias N (2009) Fluorescence spectroscopy for endogenous porphyrins in human facial skin. Photonic Therapeutics and Diagnostics V. SPIE, Bellingham
Minamikawa T, Matsuo H, Kato Y, Harada Y, Otsuji E, Yanagisawa A, Tanaka H, Takamatsu T (2016) Simplified and optimized multispectral imaging for 5-ALA-based fluorescence diagnosis of malignant lesions. Sci Rep 6:25530. https://doi.org/10.1038/srep25530
doi: 10.1038/srep25530
pubmed: 27149301
pmcid: 4857744
Islam MS, Honma M, Nakabayashi T, Kinjo M, Ohta N (2013) pH Dependence of the fluorescence lifetime of FAD in solution and in cells. Int J Mol Sci 14:1952–1963. https://doi.org/10.3390/ijms14011952
doi: 10.3390/ijms14011952
pubmed: 23334475
pmcid: 3565358
Lin F, Zhang C, Li Y, Yan J, Xu Y, Pan Y, Hu R, Liu L, Liu L, Qu J, Qu J (2021) Human serum albumin gradient in serous ovarian cancer cryosections measured by fluorescence lifetime. Biomed Opt Expr 12:1195–1204. https://doi.org/10.1364/BOE.415456
doi: 10.1364/BOE.415456
Unger J, Unger J, Unger J, Hebisch C, Phipps JE, Lagarto JL, Kim H, Darrow MA, Bold RJ, Marcu L, Marcu L, Marcu L (2020) Real-time diagnosis and visualization of tumor margins in excised breast specimens using fluorescence lifetime imaging and machine learning. Biomed Opt Expr 11:1216–1230. https://doi.org/10.1364/BOE.381358
doi: 10.1364/BOE.381358
Awasthi K, Chang F-L, Hsieh P-Y, Hsu H-Y, Ohta N (2020) Characterization of endogenous fluorescence in nonsmall lung cancerous cells: a comparison with nonmalignant lung normal cells. J Biophoton 13:e201960210. https://doi.org/10.1002/jbio.201960210
doi: 10.1002/jbio.201960210
Lue N, Kang JW, Yu C-C, Barman I, Dingari NC, Feld MS, Dasari RR, Fitzmaurice M (2012) Portable optical fiber probe-based spectroscopic scanner for rapid cancer diagnosis: a new tool for intraoperative margin assessment. PLoS ONE 7:e30887. https://doi.org/10.1371/journal.pone.0030887
doi: 10.1371/journal.pone.0030887
pubmed: 22303465
pmcid: 3267755
DaCosta RS, Lilge LD, Kost J, Cirroco M, Hassaram S, NEM Md, Wilson BC (1997) Confocal fluorescence microscopy, microspectrofluorimetry, and modeling studies of laser-induced fluorescence endoscopy (LIFE) of human colon tissue. Laser-Tissue Interaction VIII. SPIE, Bellingham, pp 98–107
doi: 10.1117/12.275463
Izuishi K, Tajiri H, Fujii T, Boku N, Ohtsu A, Ohnishi T, Ryu M, Kinoshita T, Yoshida S (1999) The histological basis of detection of adenoma and cancer in the colon by autofluorescence endoscopic imaging. Endoscopy 31:511–516. https://doi.org/10.1055/s-1999-57
doi: 10.1055/s-1999-57
pubmed: 10533733
Kang JW, Lim SY, Galindo LH, Yoon H, Dasari RR, So PTC, Kim HM (2020) Analysis of subcutaneous swine fat via deep raman spectroscopy using a fiber-optic probe. Analyst 145:4421–4426. https://doi.org/10.1039/D0AN00707B
doi: 10.1039/D0AN00707B
pubmed: 32441278
pmcid: 7329574