Machine learning-based differentiation between multiple sclerosis and glioma WHO II°-IV° using O-(2-[18F] fluoroethyl)-L-tyrosine positron emission tomography

Journal of Neuro-Oncology - Tập 152 - Trang 325-332 - 2021
Sied Kebir1,2,3, Laurèl Rauschenbach3,4, Manuel Weber5, Lazaros Lazaridis1,2,3, Teresa Schmidt1,2, Kathy Keyvani6, Niklas Schäfer7, Asma Milia8, Lale Umutlu9, Daniela Pierscianek4, Martin Stuschke10, Michael Forsting9, Ulrich Sure4, Christoph Kleinschnitz11, Gerald Antoch12, Patrick M. Colletti13, Domenico Rubello14, Ken Herrmann5, Ulrich Herrlinger7, Björn Scheffler2,3, Ralph A. Bundschuh15, Martin Glas1,2,3,7
1Division of Clinical Neurooncology, Department of Neurology, University Hospital Essen, University Duisburg-Essen, Essen, Germany
2West German Cancer Center (WTZ), German Cancer Consortium (DKTK), University Hospital Essen, University Duisburg-Essen, Partner Site University Hospital Essen, Essen, Germany
3DKFZ Division of Translational Neurooncology at the West German Cancer Center (WTZ), German Cancer Consortium (DKTK), Partner Site University Hospital Essen, Essen, Germany
4Department of Neurosurgery and Spine Surgery, University Hospital Essen, University Duisburg-Essen, Essen, Germany
5Department of Nuclear Medicine, University Hospital Essen, University Duisburg-Essen, Essen, Germany
6Institute of Neuropathology, University Hospital Essen, University Duisburg-Essen, Essen, Germany
7Division of Clinical Neurooncology, Department of Neurology, University Hospital Bonn, University of Bonn, Bonn, Germany
8Department of Pulmonology and Cardiology, Petrus Hospital Academic Teaching, Wuppertal, Germany
9Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Essen, Germany
10Department of Radiotherapy, University Hospital Essen, University Duisburg-Essen, Essen, Germany
11Department of Neurology, University Hospital Essen, University Duisburg-Essen, Essen, Germany
12Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, University of Düsseldorf, Düsseldorf, Germany
13Department of Radiology, University of Southern California, Los Angeles, USA
14Department of Nuclear Medicine, Radiology, Neuroradiology, Clinical Pathology, S. Maria Della Misericordia Hospital, Rovigo, Italy
15Department of Nuclear Medicine, University Hospital Bonn, University of Bonn, Bonn, Germany

Tóm tắt

This study aimed to test the diagnostic significance of FET-PET imaging combined with machine learning for the differentiation between multiple sclerosis (MS) and glioma II°-IV°. Our database was screened for patients in whom FET-PET imaging was performed for the diagnostic workup of newly diagnosed lesions evident on MRI and suggestive of glioma. Among those, we identified patients with histologically confirmed glioma II°-IV°, and those who later turned out to have MS. For each group, tumor-to-brain ratio (TBR) derived features of FET were determined. A support vector machine (SVM) based machine learning algorithm was constructed to enhance classification ability, and Receiver Operating Characteristic (ROC) analysis with area under the curve (AUC) metric served to ascertain model performance. A total of 41 patients met selection criteria, including seven patients with MS and 34 patients with glioma. TBR values were significantly higher in the glioma group (TBRmax glioma vs. MS: p = 0.002; TBRmean glioma vs. MS: p = 0.014). In a subgroup analysis, TBR values significantly differentiated between MS and glioblastoma (TBRmax glioblastoma vs. MS: p = 0.0003, TBRmean glioblastoma vs. MS: p = 0.0003) and between MS and oligodendroglioma (ODG) (TBRmax ODG vs. MS: p = 0.003; TBRmean ODG vs. MS: p = 0.01). The ability to differentiate between MS and glioma II°-IV° increased from 0.79 using standard TBR analysis to 0.94 using a SVM based machine learning algorithm. FET-PET imaging may help differentiate MS from glioma II°-IV° and SVM based machine learning approaches can enhance classification performance.

Tài liệu tham khảo

Browne P, Chandraratna D, Angood C, Tremlett H, Baker C, Taylor BV, Thompson AJ (2014) Atlas of multiple sclerosis 2013: a growing global problem with widespread inequity. Neurology 83:1022–1024. https://doi.org/10.1212/wnl.0000000000000768 Thompson AJ, Banwell BL, Barkhof F, Carroll WM, Coetzee T, Comi G, Correale J, Fazekas F, Filippi M, Freedman MS, Fujihara K, Galetta SL, Hartung HP, Kappos L, Lublin FD, Marrie RA, Miller AE, Miller DH, Montalban X, Mowry EM, Sorensen PS, Tintore M, Traboulsee AL, Trojano M, Uitdehaag BMJ, Vukusic S, Waubant E, Weinshenker BG, Reingold SC, Cohen JA (2018) Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol 17:162–173. https://doi.org/10.1016/s1474-4422(17)30470-2 Hardy TA (2019) Pseudotumoral demyelinating lesions: diagnostic approach and long-term outcome. Curr Opin Neurol 32:467–474. https://doi.org/10.1097/wco.0000000000000683 Jakola AS, Skjulsvik AJ, Myrmel KS, Sjavik K, Unsgard G, Torp SH, Aaberg K, Berg T, Dai HY, Johnsen K, Kloster R, Solheim O (2017) Surgical resection versus watchful waiting in low-grade gliomas. Ann Oncol 28:1942–1948. https://doi.org/10.1093/annonc/mdx230 Hayashi T, Kumabe T, Jokura H, Fujihara K, Shiga Y, Watanabe M, Higano S, Shirane R (2003) Inflammatory demyelinating disease mimicking malignant glioma. J Nucl Med 44:565–569 Kebir S, Gaertner FC, Mueller M, Nelles M, Simon M, Schafer N, Stuplich M, Schaub C, Niessen M, Mack F, Bundschuh R, Greschus S, Essler M, Glas M, Herrlinger U (2016) (18)F-fluoroethyl-L-tyrosine positron emission tomography for the differential diagnosis of tumefactive multiple sclerosis versus glioma: a case report. Oncol Lett 11:2195–2198. https://doi.org/10.3892/ol.2016.4189 Pakos EE, Tsekeris PG, Chatzidimou K, Goussia AC, Markoula S, Argyropoulou MI, Pitouli EG, Konitsiotis S (2005) Astrocytoma-like multiple sclerosis. Clin Neurol Neurosurg 107:152–157. https://doi.org/10.1016/j.clineuro.2004.06.003 Balloy G, Pelletier J, Suchet L, Lebrun C, Cohen M, Vermersch P, Zephir H, Duhin E, Gout O, Deschamps R, Le Page E, Edan G, Labauge P, Carra-Dallieres C, Rumbach L, Berger E, Lejeune P, Devos P, N’Kendjuo JB, Coustans M, Auffray-Calvier E, Daumas-Duport B, Michel L, Lefrere F, Laplaud DA, Brosset C, Derkinderen P, de Seze J, Wiertlewski S, Francophone S (2018) Inaugural tumor-like multiple sclerosis: clinical presentation and medium-term outcome in 87 patients. J Neurol 265:2251–2259. https://doi.org/10.1007/s00415-018-8984-7 Kim DS, Na DG, Kim KH, Kim JH, Kim E, Yun BL, Chang KH (2009) Distinguishing tumefactive demyelinating lesions from glioma or central nervous system lymphoma: added value of unenhanced CT compared with conventional contrast-enhanced MR imaging. Radiology 251:467–475. https://doi.org/10.1148/radiol.2512072071 Law I, Albert NL, Arbizu J, Boellaard R, Drzezga A, Galldiks N, la Fougere C, Langen KJ, Lopci E, Lowe V, McConathy J, Quick HH, Sattler B, Schuster DM, Tonn JC, Weller M (2019) Joint EANM/EANO/RANO practice guidelines/SNMMI procedure standards for imaging of gliomas using PET with radiolabelled amino acids and [(18) F] FDG: version 1.0. Eur J Nucl Med Mol Imaging 46:540–557. https://doi.org/10.1007/s00259-018-4207-9 Pauleit D, Floeth F, Herzog H, Hamacher K, Tellmann L, Muller HW, Coenen HH, Langen KJ (2003) Whole-body distribution and dosimetry of O-(2-[18F] fluoroethyl)-L-tyrosine. Eur J Nucl Med Mol Imaging 30:519–524. https://doi.org/10.1007/s00259-003-1118-0 Pauleit D, Zimmermann A, Stoffels G, Bauer D, Risse J, Fluss MO, Hamacher K, Coenen HH, Langen KJ (2006) 18F-FET PET compared with 18F-FDG PET and CT in patients with head and neck cancer. J Nucl Med 47:256–261 Rau FC, Weber WA, Wester HJ, Herz M, Becker I, Kruger A, Schwaiger M, Senekowitsch-Schmidtke R (2002) O-(2-[(18) F] Fluoroethyl) - L-tyrosine (FET): a tracer for differentiation of tumour from inflammation in murine lymph nodes. Eur J Nucl Med Mol Imaging 29:1039–1046. https://doi.org/10.1007/s00259-002-0821-6 Chang CH, Wang HE, Wu SY, Fan KH, Tsai TH, Lee TW, Chang SR, Liu RS, Chen CF, Chen CH, Fu YK (2006) Comparative evaluation of FET and FDG for differentiating lung carcinoma from inflammation in mice. Anticancer Res 26:917–925 Barbagallo M, Albatly AA, Schreiner S, Hayward-Konnecke HK, Buck A, Kollias SS, Huellner MW (2018) Value of 18F-FET PET in patients with suspected tumefactive demyelinating disease-preliminary experience from a retrospective analysis. Clin Nucl Med 43:e385–e391. https://doi.org/10.1097/rlu.0000000000002244 Floeth FW, Pauleit D, Sabel M, Reifenberger G, Stoffels G, Stummer W, Rommel F, Hamacher K, Langen KJ (2006) 18F-FET PET differentiation of ring-enhancing brain lesions. J Nucl Med 47:776–782 Pichler R, Dunzinger A, Wurm G, Pichler J, Weis S, Nussbaumer K, Topakian R, Aigner RM (2010) Is there a place for FET PET in the initial evaluation of brain lesions with unknown significance? Eur J Nucl Med Mol Imaging 37:1521–1528. https://doi.org/10.1007/s00259-010-1457-6 Rapp M, Heinzel A, Galldiks N, Stoffels G, Felsberg J, Ewelt C, Sabel M, Steiger HJ, Reifenberger G, Beez T, Coenen HH, Floeth FW, Langen KJ (2013) Diagnostic performance of 18F-FET PET in newly diagnosed cerebral lesions suggestive of glioma. J Nucl Med 54:229–235. https://doi.org/10.2967/jnumed.112.109603 Hashimoto S, Inaji M, Nariai T, Kobayashi D, Sanjo N, Yokota T, Ishii K, Taketoshi M (2019) Usefulness of [(11) C] methionine PET in the differentiation of tumefactive multiple sclerosis from high grade astrocytoma. Neurol Med Chir 59:176–183. https://doi.org/10.2176/nmc.oa.2018-0287 Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25:44–56. https://doi.org/10.1038/s41591-018-0300-7 Kebir S, Lazaridis L, Weber M, Deuschl C, Stoppek AK, Schmidt T, Monninghoff C, Blau T, Keyvani K, Umutlu L, Pierscianek D, Forsting M, Stuschke M, Antoch G, Sure U, Kleinschnitz C, Scheffler B, Colletti PM, Rubello D, Herrmann K, Glas M (2019) Comparison of L-Methyl-11C-methionine PET with magnetic resonance spectroscopy in detecting newly diagnosed glioma. Clin Nucl Med 44:e375–e381. https://doi.org/10.1097/rlu.0000000000002577 Kebir S, Weber M, Lazaridis L, Deuschl C, Schmidt T, Monninghoff C, Keyvani K, Umutlu L, Pierscianek D, Forsting M, Sure U, Stuschke M, Kleinschnitz C, Scheffler B, Colletti PM, Rubello D, Rischpler C, Glas M (2019) Hybrid 11C-MET PET/MRI combined with “machine learning” in glioma diagnosis according to the revised glioma WHO classification 2016. Clin Nucl Med 44:214–220. https://doi.org/10.1097/rlu.0000000000002398 Vallieres M, Kay-Rivest E, Perrin LJ, Liem X, Furstoss C, Aerts H, Khaouam N, Nguyen-Tan PF, Wang CS, Sultanem K, Seuntjens J, El Naqa I (2017) Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep 7:10117. https://doi.org/10.1038/s41598-017-10371-5 Wiyaporn K, Tocharoenchai C, Pusuwan P, Ekjeen T, Leaungwutiwong S, Thanyarak S (2010) Factors affecting standardized uptake value (SUV) of positron emission tomography (PET) imaging with l8F-FDG. J Med Assoc Thai 93:108–114 Drzezga A, Souvatzoglou M, Eiber M, Beer AJ, Fürst S, Martinez-Möller A, Nekolla SG, Ziegler S, Ganter C, Rummeny EJ, Schwaiger M (2012) First clinical experience with integrated whole-body PET/MR: comparison to PET/CT in patients with oncologic diagnoses. J Nucl Med 53:845–855. https://doi.org/10.2967/jnumed.111.098608 Boss A, Bisdas S, Kolb A, Hofmann M, Ernemann U, Claussen CD, Pfannenberg C, Pichler BJ, Reimold M, Stegger L (2010) Hybrid PET/MRI of intracranial masses: initial experiences and comparison to PET/CT. J Nucl Med 51:1198–1205. https://doi.org/10.2967/jnumed.110.074773 Lapa C, Linsenmann T, Monoranu CM, Samnick S, Buck AK, Bluemel C, Czernin J, Kessler AF, Homola GA, Ernestus RI, Lohr M, Herrmann K (2014) Comparison of the amino acid tracers 18F-FET and 18F-DOPA in high-grade glioma patients. J Nucl Med 55:1611–1616. https://doi.org/10.2967/jnumed.114.140608 Louis DN, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee WK, Ohgaki H, Wiestler OD, Kleihues P, Ellison DW (2016) 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 Huang S, Cai N, Pacheco PP, Narrandes S, Wang Y, Xu W (2018) Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics 15:41–51. https://doi.org/10.21873/cgp.20063 Jordan MI, Mitchell TM (2015) Machine learning: trends, perspectives, and prospects. Science 349:255–260. https://doi.org/10.1126/science.aaa8415 Smits A, Baumert BG (2011) The clinical value of PET with amino acid tracers for gliomas WHO grade II. Int J Mol Imaging 2011:372509. https://doi.org/10.1155/2011/372509 Glotsos D, Spyridonos P, Cavouras D, Ravazoula P, Dadioti PA, Nikiforidis G (2005) An image-analysis system based on support vector machines for automatic grade diagnosis of brain-tumour astrocytomas in clinical routine. Med Inform Internet Med 30:179–193. https://doi.org/10.1080/14639230500077444 Filss CP, Albert NL, Böning G, Kops ER, Suchorska B, Stoffels G, Galldiks N, Shah NJ, Mottaghy FM, Bartenstein P, Tonn JC, Langen KJ (2017) O-(2-[(18) F] fluoroethyl)-L-tyrosine PET in gliomas: influence of data processing in different centres. EJNMMI Res 7:64. https://doi.org/10.1186/s13550-017-0316-x Cunliffe CH, Fischer I, Monoky D, Law M, Revercomb C, Elrich S, Kopp MJ, Zagzag D (2009) Intracranial lesions mimicking neoplasms. Arch Pathol Lab Med 133:101–123. https://doi.org/10.1043/1543-2165-133.1.101
Thông tin
Thông tin xuất bản

Journal of Neuro-Oncology

Tập 152

325-332

Thông tin tác giả