Machine learning-based prediction of glioma margin from 5-ALA induced PpIX fluorescence spectroscopy.
Aminolevulinic Acid
/ metabolism
Biomarkers, Tumor
Brain Neoplasms
/ diagnosis
Cell Line, Tumor
Cluster Analysis
Computer Simulation
Glioma
/ diagnosis
Humans
Machine Learning
Margins of Excision
Pilot Projects
Predictive Value of Tests
Prognosis
Protoporphyrins
/ chemistry
Spectrometry, Fluorescence
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
29 01 2020
29 01 2020
Historique:
received:
05
07
2019
accepted:
06
01
2020
entrez:
31
1
2020
pubmed:
31
1
2020
medline:
14
7
2020
Statut:
epublish
Résumé
Gliomas are infiltrative brain tumors with a margin difficult to identify. 5-ALA induced PpIX fluorescence measurements are a clinical standard, but expert-based classification models still lack sensitivity and specificity. Here a fully automatic clustering method is proposed to discriminate glioma margin. This is obtained from spectroscopic fluorescent measurements acquired with a recently introduced intraoperative set up. We describe a data-driven selection of best spectral features and show how this improves results of margin prediction from healthy tissue by comparison with the standard biomarker-based prediction. This pilot study based on 10 patients and 50 samples shows promising results with a best performance of 77% of accuracy in healthy tissue prediction from margin tissue.
Identifiants
pubmed: 31996727
doi: 10.1038/s41598-020-58299-7
pii: 10.1038/s41598-020-58299-7
pmc: PMC6989497
doi:
Substances chimiques
Biomarkers, Tumor
0
Protoporphyrins
0
Aminolevulinic Acid
88755TAZ87
protoporphyrin IX
C2K325S808
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1462Références
Louis, D. N. et al. The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol. 131, 803–820, https://doi.org/10.1007/s00401-016-1545-1 (2016).
doi: 10.1007/s00401-016-1545-1
pubmed: 27157931
Petrecca, K., Guiot, M.-C., Panet-Raymond, V. & Souhami, L. Failure pattern following complete resection plus radiotherapy and temozolomide is at the resection margin in patients with glioblastoma. J. Neuro-Oncology 111, 19–23, https://doi.org/10.1007/s11060-012-0983-4 (2013).
doi: 10.1007/s11060-012-0983-4
Laws, E. R. et al. Survival following surgery and prognostic factors for recently diagnosed malignant glioma: data from the Glioma Outcomes Project. J. Neurosurg. 99, 467–473, https://doi.org/10.3171/jns.2003.99.3.0467 (2003).
doi: 10.3171/jns.2003.99.3.0467
pubmed: 12959431
Lacroix, M. & Toms, S. A. Maximum Safe Resection of Glioblastoma Multiforme. J. Clin. Oncol. 32, 727–728, https://doi.org/10.1200/JCO.2013.53.2788 (2014).
doi: 10.1200/JCO.2013.53.2788
pubmed: 24516027
Li, Y. M., Suki, D., Hess, K. & Sawaya, R. The influence of maximum safe resection of glioblastoma on survival in 1229 patients: Can we do better than gross-total resection? J. Neurosurg. 124, 977–988, https://doi.org/10.3171/2015.5.JNS142087 (2016).
doi: 10.3171/2015.5.JNS142087
pubmed: 26495941
Haj, A. et al. Extent of resection in newly diagnosed glioblastoma: Impact of a specialized neuro-oncology care center. Brain Sci. 8, 5, https://doi.org/10.3390/brainsci8010005 (2018).
doi: 10.3390/brainsci8010005
Wu, G. N., Ford, J. M. & Alger, J. R. MRI measurement of the uptake and retention of motexafin gadolinium in glioblastoma multiforme and uninvolved normal human brain. J. Neuro-Oncology 77, 95–103, https://doi.org/10.1007/s11060-005-9101-1 (2006).
doi: 10.1007/s11060-005-9101-1
Nabavi, A. et al. Serial Intraoperative Magnetic Resonance Imaging of Brain Shift. Neurosurgery 48, 787–798, https://doi.org/10.1097/00006123-200104000-00019 (2001).
doi: 10.1097/00006123-200104000-00019
pubmed: 11322439
Kubben, P. L. et al. Intraoperative MRI-guided resection of glioblastoma multiforme: a systematic review. The Lancet Oncol. 12, 1062–1070, https://doi.org/10.1016/S1470-2045(11)70130-9 (2011).
doi: 10.1016/S1470-2045(11)70130-9
pubmed: 21868286
Senft, C. et al. Intraoperative MRI guidance and extent of resection in glioma surgery: a randomised, controlled trial. The Lancet Oncol. 12, 997–1003, https://doi.org/10.1016/S1470-2045(11)70196-6 (2011).
doi: 10.1016/S1470-2045(11)70196-6
pubmed: 21868284
Stummer, W. et al. Technical Principles for Protoporphyrin-IX-Fluorescence Guided Microsurgical Resection of Malignant Glioma Tissue. Acta Neurochir. 140, 995–1000, https://doi.org/10.1007/s007010050206 (1998).
doi: 10.1007/s007010050206
pubmed: 9856241
Bravo, J. J. et al. Hyperspectral data processing improves PpIX contrast during fluorescence guided surgery of human brain tumors. Sci. Reports 7, 9455, https://doi.org/10.1038/s41598-017-09727-8 (2017).
doi: 10.1038/s41598-017-09727-8
Hadjipanayis, C. G., Widhalm, G. & Stummer, W. What is the surgical benefit of utilizing 5-Aminolevulinic acid for fluorescence-guided surgery of malignant gliomas? Neurosurgery 77, 663–673, https://doi.org/10.1227/NEU.0000000000000929 (2015).
doi: 10.1227/NEU.0000000000000929
pubmed: 26308630
pmcid: 4615466
Jaber, M. et al. Is visible aminolevulinic acid-induced fluorescence an independent biomarker for prognosis in histologically confirmed (World Health Organization 2016) low-grade gliomas? Neurosurgery 84, 1214–1224, https://doi.org/10.1093/neuros/nyy365 (2019).
doi: 10.1093/neuros/nyy365
pubmed: 30107580
Valdés, P. A. et al. Quantitative, spectrally-resolved intraoperative fluorescence imaging. Sci. Reports 2, 798, https://doi.org/10.1038/srep00798 (2012).
doi: 10.1038/srep00798
Valdés, P. A. et al. System and methods for wide-field quantitative fluorescence imaging during neurosurgery. Opt. Lett. 38, 2786–2788, https://doi.org/10.1364/OL.38.002786 (2013).
doi: 10.1364/OL.38.002786
pubmed: 23903142
Valdés, P. A. et al. Quantitative fluorescence using 5-aminolevulinic acid-induced protoporphyrin IX biomarker as a surgical adjunct in low-grade glioma surgery. J. Neurosurg. 123, 771–780, https://doi.org/10.3171/2014.12.JNS14391 (2015).
doi: 10.3171/2014.12.JNS14391
pubmed: 26140489
pmcid: 4646619
Ando, T. et al. Precise comparison of protoporphyrin IX fluorescence spectra with pathological results for brain tumor tissue identification. Brain Tumor Pathol. 28, 43–51, https://doi.org/10.1007/s10014-010-0002-4 (2011).
doi: 10.1007/s10014-010-0002-4
pubmed: 21188542
Montcel, B., Mahieu-Williame, L., Armoiry, X., Meyronet, D. & Guyotat, J. Two-peaked 5-ALA-induced PpIX fluorescence emission spectrum distinguishes glioblastomas from low grade gliomas and infiltrative component of glioblastomas. Biomed. Opt. Express 4, 548–558, https://doi.org/10.1364/BOE.4.000548 (2013).
doi: 10.1364/BOE.4.000548
pubmed: 23577290
pmcid: 3617717
Zanello, M. et al. Multimodal optical analysis discriminates freshly extracted human sample of gliomas, metastases and meningiomas from their appropriate controls. Sci. Reports 7, 41724, https://doi.org/10.1038/srep41724 (2017).
doi: 10.1038/srep41724
Dietel, W., Fritsch, C., Pottier, R. H. & Wendenburg, R. 5-aminolaevulinic-acid-induced formation of different porphyrins and their photomodifications. Lasers Med. Sci. 12, 226–236, https://doi.org/10.1007/BF02765103 (1997).
doi: 10.1007/BF02765103
pubmed: 20803330
Figueredo, A. J. & Wolf, P. S. A. Assortative pairing and life history strategy. Hum. Nat. 20, 317–330, https://doi.org/10.1007/s12110-009-9068-2 (2009).
doi: 10.1007/s12110-009-9068-2
Alston, L. et al. Spectral complexity of 5-ala induced ppix fluorescence in guided surgery: a clinical study towards the discrimination of healthy tissue and margin boundaries in high and low grade gliomas. Biomed. Opt. Express 10, 2478–2492, https://doi.org/10.1364/BOE.10.002478 (2019).
doi: 10.1364/BOE.10.002478
pubmed: 31149380
pmcid: 6524587
Hope, C. K. & Higham, S. M. Evaluating the effect of local pH on fluorescence emissions from oral bacteria of the genus Prevotella. J. Biomed. Opt. 21, 084003, https://doi.org/10.1117/1.JBO.21.8.084003 (2016).
doi: 10.1117/1.JBO.21.8.084003
Montcel, B. et al. 5-ALA-induced PpIX fluorescence in gliomas resection: spectral complexity of the emission spectrum in the infiltrative compound. In SPIE Proceedings, 8804, 880409 (Optical Society of America, 2013).
Alston, L. M. et al. Interventional fluorescence spectroscopy: preliminary results to detect tumor margins during glioma resection with two fluorescence spectra of PpIX. In SPIE Proc. 10411, 104110C, https://doi.org/10.1117/12.2286110 (Optical Society of America, 2017).
Schwarz, G. Estimating the dimension of a model. The Annals Stat. 6, 461–464, https://doi.org/10.1214/aos/1176344136 (1978).
doi: 10.1214/aos/1176344136
Tibshirani, R., Walther, G. & Hastie, T. Estimating the number of clusters in a data set via the gap statistic. J. Royal Stat. Soc. Ser. B (Statistical Methodol.) 63, 411–423, https://doi.org/10.1111/1467-9868.00293 (2001).
doi: 10.1111/1467-9868.00293
Pearson, K. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, Dublin Philos. Mag. J. Sci. 2, 559–572, https://doi.org/10.1080/14786440109462720 (1901).
doi: 10.1080/14786440109462720
Cattell, R. B. The scree test for the number of factors. Multivar. Behav. Res. 1, 245, https://doi.org/10.1207/s15327906mbr0102_10 (1966).
doi: 10.1207/s15327906mbr0102_10
Andersson, H., Baechi, T., Hoechl, M. & Richter, C. Autofluorescence of living cells. J. microscopy 191, 1–7, https://doi.org/10.1046/j.1365-2818.1998.00347.x (1998).
doi: 10.1046/j.1365-2818.1998.00347.x
Minamikawa, T. et al. Simplified and optimized multispectral imaging for 5-ALA-based fluorescence diagnosis of malignant lesions. Sci. Reports 6, 25530, https://doi.org/10.1038/srep25530 (2016).
doi: 10.1038/srep25530
Warburg, O., Wind, F. & Negelein, E. The metabolism of tumors in the body. The J. Gen. Physiol. 8, 519–530 (1927).
doi: 10.1085/jgp.8.6.519
Van Der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).
Dietel, W., Pottier, R., Pfister, W., Schleier, P. & Zinner, K. 5-Aminolaevulinic acid (ALA) induced formation of different fluorescent porphyrins: A study of the biosynthesis of porphyrins by bacteria of the human digestive tract. J. Photochem. Photobiol. B: Biol. 86, 77–86, https://doi.org/10.1016/j.jphotobiol.2006.07.006 (2007).
doi: 10.1016/j.jphotobiol.2006.07.006
Alston, L., Rousseau, D., Hébert, M., Mahieu-Williame, L. & Montcel, B. Nonlinear relation between concentration and fluorescence emission of protoporphyrin IX in calibrated phantoms. J. Biomed. Opt. 23, 097002, https://doi.org/10.1117/1.JBO.23.9.097002 (2018).
doi: 10.1117/1.JBO.23.9.097002
Bellman, R. & Kalaba, R. Reduction of dimensionality, dynamic programming, and control processes. J. Basic Eng 83, 82–84 (1961).
doi: 10.1115/1.3658896
Steinbach, M., Ertöz, L. & Kumar, V. The challenges of clustering high dimensional data. In Wille, L. T. (ed.) New Directions in Statistical Physics: Econophysics, Bioinformatics, and Pattern Recognition, 273–309, https://doi.org/10.1007/978-3-662-08968-2_16 (Springer Berlin Heidelberg, Berlin, Heidelberg, 2004).
doi: 10.1007/978-3-662-08968-2_16
Jolliffe Ian, T. & Cadima, J. Principal component analysis: a review and recent developments. Philos. Transactions Royal Soc. A: Math. Phys. Eng. Sci. 374, 20150202, https://doi.org/10.1098/rsta.2015.0202 (2016).
doi: 10.1098/rsta.2015.0202
MacQueen, J. Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics, 281–297 (University of California Press, Berkeley, Calif., 1967).
Dempster, A. P., Laird, N. M. & Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Stat. Soc. Ser. B (Methodological) 39, 1–22, https://doi.org/10.1111/j.2517-6161.1977.tb01600.x (1977).
doi: 10.1111/j.2517-6161.1977.tb01600.x
Bishop, C. M. Pattern Recognition And Machine Learning, 1st ed. 2006. corr. 2nd printing 2011 edn (Springer-Verlag New York Inc., New York, 2006).