Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
Abstract
:Featured Application
Abstract
1. Introduction
2. Materials and Methods
2.1. Patients
2.2. Image Acquisition
2.3. Image Processing
2.4. Calculation of Perfusion and Oxygenation Parameters
2.5. Artificial Neural Network
2.6. Statistical Analysis
3. Results
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Lee, E.J.; TerBrugge, K.; Mikulis, D.; Choi, D.S.; Bae, J.M.; Lee, S.K.; Moon, S.Y. Diagnostic value of peritumoral minimum apparent diffusion coefficient for differentiation of glioblastoma multiforme from solitary metastatic lesions. AJR Am. J. Roentgenol. 2011, 196, 71–76. [Google Scholar] [CrossRef]
- Bauer, A.H.; Erly, W.; Moser, F.G.; Maya, M.; Nael, K. Differentiation of solitary brain metastasis from glioblastoma multiforme: A predictive multiparametric approach using combined MR diffusion and perfusion. Neuroradiology 2015, 57, 697–703. [Google Scholar] [CrossRef] [PubMed]
- Li, X.; Wang, D.; Liao, S.; Guo, L.; Xiao, X.; Liu, X.; Xu, Y.; Hua, J.; Pillai, J.J.; Wu, Y. Discrimination between glioblastoma and solitary brain metastasis: Comparison of inflow-based vascular-space-occupancy and dynamic susceptibility contrast MR imaging. AJNR Am. J. Neuroradiol. 2020, 41, 583–590. [Google Scholar] [CrossRef]
- Artzi, M.; Bressler, I.; Ben Bashat, D. Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis. J. Magn. Reason. Imaging 2019, 50, 519–528. [Google Scholar] [CrossRef] [PubMed]
- Preibisch, C.; Shi, K.; Kluge, A.; Lukas, M.; Wiestler, B.; Gottler, J.; Gempt, J.; Ringel, F.; Al Jaberi, M.; Schlegel, J.; et al. Characterizing hypoxia in human glioma: A simultaneous multimodal MRI and PET study. NMR Biomed. 2017, 30, e3775. [Google Scholar] [CrossRef] [PubMed]
- Stadlbauer, A.; Zimmermann, M.; Kitzwogerer, M.; Oberndorfer, S.; Rossler, K.; Dorfler, A.; Buchfelder, M.; Heinz, G. MR imaging-derived oxygen metabolism and neovascularization characterization for grading and IDH gene mutation detection of gliomas. Radiology 2017, 283, 799–809. [Google Scholar] [CrossRef] [Green Version]
- Wen, P.Y.; Kesari, S. Malignant gliomas in adults. N. Engl. J. Med. 2008, 359, 492–507. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Noroxe, D.S.; Poulsen, H.S.; Lassen, U. Hallmarks of glioblastoma: A systematic review. ESMO Open 2016, 1, e000144. [Google Scholar] [CrossRef] [PubMed]
- Stupp, R.; Mason, W.P.; van den Bent, M.J.; Weller, M.; Fisher, B.; Taphoorn, M.J.; Belanger, K.; Brandes, A.A.; Marosi, C.; Bogdahn, U.; et al. Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma. N. Engl. J. Med. 2005, 352, 987–996. [Google Scholar] [CrossRef]
- Montemurro, N.; Fanelli, G.N.; Scatena, C.; Ortenzi, V.; Pasqualetti, F.; Mazzanti, C.M.; Morganti, R.; Paiar, F.; Naccarato, A.G.; Perrini, P. Surgical outcome and molecular pattern characterization of recurrent glioblastoma multiforme: A single-center retrospective series. Clin. Neurol. Neurosurg. 2021, 207, 106735. [Google Scholar] [CrossRef]
- Stadlbauer, A.; Oberndorfer, S.; Zimmermann, M.; Renner, B.; Buchfelder, M.; Heinz, G.; Doerfler, A.; Kleindienst, A.; Roessler, K. Physiologic MR imaging of the tumor microenvironment revealed switching of metabolic phenotype upon recurrence of glioblastoma in humans. J Cereb. Blood Flow Metab. 2020, 40, 528–538. [Google Scholar] [CrossRef]
- Montemurro, N.; Perrini, P.; Rapone, B. Clinical risk and overall survival in patients with diabetes mellitus, hyperglycemia and glioblastoma multiforme. A review of the current literature. Int. J. Environ. Res. Public Health 2020, 17, 8501. [Google Scholar] [CrossRef]
- Pope, W.B. Brain metastases: Neuroimaging. Handb. Clin. Neurol. 2018, 149, 89–112. [Google Scholar] [PubMed]
- Smirniotopoulos, J.G.; Murphy, F.M.; Rushing, E.J.; Rees, J.H.; Schroeder, J.W. Patterns of contrast enhancement in the brain and meninges. Radiographics 2007, 27, 525–551. [Google Scholar] [CrossRef] [PubMed]
- Ostrom, Q.T.; Wright, C.H.; Barnholtz-Sloan, J.S. Brain metastases: Epidemiology. Handb. Clin. Neurol. 2018, 149, 27–42. [Google Scholar] [PubMed]
- Giordana, M.T.; Cordera, S.; Boghi, A. Cerebral metastases as first symptom of cancer: A clinico-pathologic study. J. Neurooncol. 2000, 50, 265–273. [Google Scholar] [CrossRef]
- Server, A.; Orheim, T.E.; Graff, B.A.; Josefsen, R.; Kumar, T.; Nakstad, P.H. Diagnostic examination performance by using microvascular leakage, cerebral blood volume, and blood flow derived from 3-T dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging in the differentiation of glioblastoma multiforme and brain metastasis. Neuroradiology 2011, 53, 319–330. [Google Scholar]
- Blasel, S.; Jurcoane, A.; Franz, K.; Morawe, G.; Pellikan, S.; Hattingen, E. Elevated peritumoural rCBV values as a mean to differentiate metastases from high-grade gliomas. Acta Neurochir. 2010, 152, 1893–1899. [Google Scholar] [CrossRef]
- Lee, E.J.; Ahn, K.J.; Lee, E.K.; Lee, Y.S.; Kim, D.B. Potential role of advanced MRI techniques for the peritumoural region in differentiating glioblastoma multiforme and solitary metastatic lesions. Clin. Radiol. 2013, 68, e689–e697. [Google Scholar] [CrossRef]
- Malone, H.; Yang, J.; Hershman, D.L.; Wright, J.D.; Bruce, J.N.; Neugut, A.I. Complications following stereotactic needle biopsy of intracranial tumors. World Neurosurg. 2015, 84, 1084–1089. [Google Scholar] [CrossRef]
- Swinburne, N.C.; Schefflein, J.; Sakai, Y.; Oermann, E.K.; Titano, J.J.; Chen, I.; Tadayon, S.; Aggarwal, A.; Doshi, A.; Nael, K. Machine learning for semi-automated classification of glioblastoma, brain metastasis and central nervous system lymphoma using magnetic resonance advanced imaging. Ann. Transl. Med. 2019, 7, 232. [Google Scholar] [CrossRef]
- Askaner, K.; Rydelius, A.; Engelholm, S.; Knutsson, L.; Latt, J.; Abul-Kasim, K.; Sundgren, P.C. Differentiation between glioblastomas and brain metastases and regarding their primary site of malignancy using dynamic susceptibility contrast MRI at 3T. J. Neuroradiol. 2019, 46, 367–372. [Google Scholar] [CrossRef] [PubMed]
- Tsolaki, E.; Svolos, P.; Kousi, E.; Kapsalaki, E.; Fountas, K.; Theodorou, K.; Tsougos, I. Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data. Int. J. Comput. Assist. Radiol. Surg. 2013, 8, 751–761. [Google Scholar] [CrossRef] [PubMed]
- Lehmann, P.; Saliou, G.; de Marco, G.; Monet, P.; Souraya, S.E.; Bruniau, A.; Vallee, J.N.; Ducreux, D. Cerebral peritumoral oedema study: Does a single dynamic MR sequence assessing perfusion and permeability can help to differentiate glioblastoma from metastasis? Eur. J. Radiol. 2012, 81, 522–527. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Asgari, S.; Rohrborn, H.J.; Engelhorn, T.; Stolke, D. Intra-operative characterization of gliomas by near-infrared spectroscopy: Possible association with prognosis. Acta Neurochir. 2003, 145, 453–459. [Google Scholar] [CrossRef] [PubMed]
- Hardee, M.E.; Zagzag, D. Mechanisms of glioma-associated neovascularization. Am. J. Pathol. 2012, 181, 1126–1141. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Cho, J.; Kee, Y.; Spincemaille, P.; Nguyen, T.D.; Zhang, J.; Gupta, A.; Zhang, S.; Wang, Y. Cerebral metabolic rate of oxygen (CMRO2) mapping by combining quantitative susceptibility mapping (QSM) and quantitative blood oxygenation level-dependent imaging (qBOLD). Magn. Reason. Med. 2018, 80, 1595–1604. [Google Scholar] [CrossRef] [PubMed]
- Kurz, F.T.; Buschle, L.R.; Rotkopf, L.T.; Herzog, F.S.; Sterzik, A.; Schlemmer, H.P.; Kampf, T.; Bendszus, M.; Heiland, S.; Ziener, C.H. Dependence of the frequency distribution around a sphere on the voxel orientation. Z. Med. Phys. 2021. [Google Scholar] [CrossRef]
- Hubertus, S.; Thomas, S.; Cho, J.; Zhang, S.; Wang, Y.; Schad, L.R. Using an artificial neural network for fast mapping of the oxygen extraction fraction with combined QSM and quantitative BOLD. Magn. Reson. Med. 2019, 82, 2199–2211. [Google Scholar] [CrossRef]
- Alsop, D.C.; Detre, J.A.; Golay, X.; Gunther, M.; Hendrikse, J.; Hernandez-Garcia, L.; Lu, H.; MacIntosh, B.J.; Parkes, L.M.; Smits, M.; et al. Recommended implementation of arterial spin-labeled perfusion MRI for clinical applications: A consensus of the ISMRM perfusion study group and the European consortium for ASL in dementia. Magn. Reson. Med. 2015, 73, 102–116. [Google Scholar] [CrossRef] [Green Version]
- Dong, F.; Li, Q.; Jiang, B.; Zhu, X.; Zeng, Q.; Huang, P.; Chen, S.; Zhang, M. Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers. Eur. Radiol. 2020, 30, 3015–3022. [Google Scholar] [CrossRef]
- Ma, Y.; Mazerolle, E.L.; Cho, J.; Sun, H.; Wang, Y.; Pike, G.B. Quantification of brain oxygen extraction fraction using QSM and a hyperoxic challenge. Magn. Reason. Med. 2020, 84, 3271–3285. [Google Scholar] [CrossRef]
- Hubertus, S.; Thomas, S.; Cho, J.; Zhang, S.; Wang, Y.; Schad, L.R. Comparison of gradient echo and gradient echo sampling of spin echo sequence for the quantification of the oxygen extraction fraction from a combined quantitative susceptibility mapping and quantitative BOLD (QSM+qBOLD) approach. Magn. Reason. Med. 2019, 82, 1491–1503. [Google Scholar] [CrossRef]
- Cho, J.; Zhang, S.; Kee, Y.; Spincemaille, P.; Nguyen, T.D.; Hubertus, S.; Gupta, A.; Wang, Y. Cluster analysis of time evolution (CAT) for quantitative susceptibility mapping (QSM) and quantitative blood oxygen level-dependent magnitude (qBOLD)-based oxygen extraction fraction (OEF) and cerebral metabolic rate of oxygen (CMRO2) mapping. Magn. Reason. Med. 2020, 83, 844–857. [Google Scholar] [CrossRef] [PubMed]
- Wenz, H.; Maros, M.E.; Meyer, M.; Forster, A.; Haubenreisser, H.; Kurth, S.; Schoenberg, S.O.; Flohr, T.; Leidecker, C.; Groden, C.; et al. Image quality of 3rd generation spiral cranial dual-source CT in combination with an advanced model iterative reconstruction technique: A prospective intra-individual comparison study to standard sequential cranial CT using identical radiation dose. PLoS ONE 2015, 10, e0136054. [Google Scholar] [CrossRef] [PubMed]
- Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
- Maros, M.E.; Capper, D.; Jones, D.T.W.; Hovestadt, V.; von Deimling, A.; Pfister, S.M.; Benner, A.; Zucknick, M.; Sill, M. Machine learning workflows to estimate class probabilities for precision cancer diagnostics on DNA methylation microarray data. Nat. Protoc. 2020, 15, 479–512. [Google Scholar] [CrossRef]
- Shrot, S.; Salhov, M.; Dvorski, N.; Konen, E.; Averbuch, A.; Hoffmann, C. Application of MR morphologic, diffusion tensor, and perfusion imaging in the classification of brain tumors using machine learning scheme. Neuroradiology 2019, 61, 757–765. [Google Scholar] [CrossRef]
- Fanelli, G.N.; Grassini, D.; Ortenzi, V.; Pasqualetti, F.; Montemurro, N.; Perrini, P.; Naccarato, A.G.; Scatena, C. Decipher the glioblastoma microenvironment: The first milestone for new groundbreaking therapeutic strategies. Genes 2021, 12, 445. [Google Scholar] [CrossRef]
- Guan, Z.; Lan, H.; Cai, X.; Zhang, Y.; Liang, A.; Li, J. Blood-brain barrier, cell junctions, and tumor microenvironment in brain metastases, the biological prospects and dilemma in therapies. Front. Cell Dev. Biol. 2021, 9, 722917. [Google Scholar] [CrossRef] [PubMed]
- Sunwoo, L.; Yun, T.J.; You, S.H.; Yoo, R.E.; Kang, K.M.; Choi, S.H.; Kim, J.H.; Sohn, C.H.; Park, S.W.; Jung, C.; et al. Differentiation of glioblastoma from brain metastasis: Qualitative and quantitative analysis using arterial spin labeling MR imaging. PLoS ONE 2016, 11, e0166662. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Fink, K.R.; Fink, J.R. Imaging of brain metastases. Surg. Neurol. Int. 2013, 4, S209–S219. [Google Scholar] [CrossRef] [PubMed]
- Hubertus, S.; Thomas, S.; Cho, J.; Zhang, S.; Kovanlikaya, I.; Wang, Y.; Schad, L.R. In MRI-based oxygen extraction fraction and cerebral metabolic rate of oxygen mapping in high-grade glioma using a combined quantitative susceptibility mapping and quantitative blood oxygenation level-dependent approach. In Proceedings of the International Society for Magnetic Resonance in Medicine, Montréal, QC, Canada, 11–16 May 2019; p. 0391. [Google Scholar]
- Bonekamp, D.; Mouridsen, K.; Radbruch, A.; Kurz, F.T.; Eidel, O.; Wick, A.; Schlemmer, H.P.; Wick, W.; Bendszus, M.; Ostergaard, L.; et al. Assessment of tumor oxygenation and its impact on treatment response in bevacizumab-treated recurrent glioblastoma. J. Cereb. Blood Flow Metab. 2017, 37, 485–494. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Kickingereder, P.; Brugnara, G.; Hansen, M.B.; Nowosielski, M.; Pfluger, I.; Schell, M.; Isensee, F.; Foltyn, M.; Neuberger, U.; Kessler, T.; et al. Noninvasive characterization of tumor angiogenesis and oxygenation in bevacizumab-treated recurrent glioblastoma by using dynamic susceptibility MRI: Secondary analysis of the European Organization for Research and Treatment of Cancer 26101 trial. Radiology 2020, 297, 164–175. [Google Scholar] [CrossRef] [PubMed]
- Yordanova, Y.N.; Duffau, H. Supratotal resection of diffuse gliomas—An overview of its multifaceted implications. Neurochirurgie 2017, 63, 243–249. [Google Scholar] [CrossRef] [PubMed]
Region | Feature | Accuracy | Sensitivity | Specificity | AUC (Range) |
---|---|---|---|---|---|
OEF | 81% | 87% | 75% | 0.79 (0.76–0.84) | |
CET | CBF | 71% | 70% | 71% | 0.67 (0.55–0.73) |
CMRO2 | 63% | 27% | 95% | 0.52 (0.41–0.68) | |
OEF | 68% | 70% | 66% | 0.65 (0.46–0.82) | |
NET2 | CBF | 73% | 54% | 89% | 0.69 (0.64–0.75) |
CMRO2 | 73% | 44% | 99% | 0.66 (0.61–0.71) | |
OEF | 69% | 60% | 78% | 0.66 (0.55–0.77) | |
CET/NET2 | CBF | 75% | 63% | 86% | 0.80 (0.77–0.82) |
CMRO2 | 83% | 85% | 82% | 0.85 (0.73–0.93) | |
Best combined | OEFCET + CMRO2 CET/NET2 | 93% | 99% | 88% | 0.94 (0.88–0.96) |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Baazaoui, H.; Hubertus, S.; Maros, M.E.; Mohamed, S.A.; Förster, A.; Schad, L.R.; Wenz, H. Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study. Appl. Sci. 2021, 11, 9928. https://doi.org/10.3390/app11219928
Baazaoui H, Hubertus S, Maros ME, Mohamed SA, Förster A, Schad LR, Wenz H. Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study. Applied Sciences. 2021; 11(21):9928. https://doi.org/10.3390/app11219928
Chicago/Turabian StyleBaazaoui, Hakim, Simon Hubertus, Máté E. Maros, Sherif A. Mohamed, Alex Förster, Lothar R. Schad, and Holger Wenz. 2021. "Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study" Applied Sciences 11, no. 21: 9928. https://doi.org/10.3390/app11219928
APA StyleBaazaoui, H., Hubertus, S., Maros, M. E., Mohamed, S. A., Förster, A., Schad, L. R., & Wenz, H. (2021). Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study. Applied Sciences, 11(21), 9928. https://doi.org/10.3390/app11219928