Abstract
Introduction
It is useful to know the molecular subtype of lower-grade gliomas (LGG) when deciding on a treatment strategy. This study aims to diagnose this preoperatively.
Methods
A deep learning model was developed to predict the 3-group molecular subtype using multimodal data including magnetic resonance imaging (MRI), positron emission tomography (PET), and computed tomography (CT). The performance was evaluated using leave-one-out cross validation with a dataset containing information from 217 LGG patients.
Results
The model performed best when the dataset contained MRI, PET, and CT data. The model could predict the molecular subtype with an accuracy of 96.6% for the training dataset and 68.7% for the test dataset. The model achieved test accuracies of 58.5%, 60.4%, and 59.4% when the dataset contained only MRI, MRI and PET, and MRI and CT data, respectively. The conventional method used to predict mutations in the isocitrate dehydrogenase (IDH) gene and the codeletion of chromosome arms 1p and 19q (1p/19q) sequentially had an overall accuracy of 65.9%. This is 2.8 percent point lower than the proposed method, which predicts the 3-group molecular subtype directly.
Conclusions
A deep learning model was developed to diagnose the molecular subtype preoperatively based on multi-modality data in order to predict the 3-group classification directly. Cross-validation showed that the proposed model had an overall accuracy of 68.7% for the test dataset. This is the first model to double the expected value for a 3-group classification problem, when predicting the LGG molecular subtype.
Similar content being viewed by others
References
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(6):803–820
Suzuki H, Aoki K, Chiba K et al (2015) Mutational landscape and clonal architecture in grade II and III gliomas. Nat Genet 47(5):458–468
Cancer Genome Atlas Research Network, Brat DJ, Verhaak RG, et al. (2015) Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas. N Engl J Med 372(26):2481–2498
Fukuya Y, Ikuta S, Maruyama T, Nitta M, Saito T, Tsuzuki S, Chernov M, Kawamata T, Muragaki Y (2019) Tumor recurrence patterns after surgical resection of intracranial low-grade gliomas. J Neurooncol 144(3):519–528
Hardesty DA, Sanai N (2012) The value of glioma extent of resection in the modern neurosurgical era. Front Neurol 3:140
Nitta M, Muragaki Y, Maruyama T, Ikuta S, Komori T, Maebayashi K, Iseki H, Tamura M, Saito T, Okamoto S, Chernov M, Hayashi M, Okada Y (2015) Proposed therapeutic strategy for adult low-grade glioma based on aggressive tumor resection. Neurosurg Focus 38(1):E7
Fujii Y, Muragaki Y, Maruyama T, Nitta M, Saito T, Ikuta S, Iseki H, Hongo K, Kawamata T (2018) Threshold of the extent of resection for WHO Grade III gliomas: retrospective volumetric analysis of 122 cases using intraoperative MRI. J Neurosurg 129(1):1–9
Duffau H (2013) A new philosophy in surgery for diffuse low-grade glioma (DLGG): oncological and functional outcomes. Neurochirurgie 59(1):2–8
Wijnenga MMJ, French PJ, Dubbink HJ, Dinjens WNM, Atmodimedjo PN, Kros JM, Smits M, Gahrmann R, Rutten GJ, Verheul JB, Fleischeuer R, Dirven CMF, Vincent AJPE, van den Bent MJ (2018) The impact of surgery in molecularly defined low-grade glioma: an integrated clinical, radiological, and molecular analysis. Neuro Oncol 20(1):103–112
Kawaguchi T, Sonoda Y, Shibahara I, Saito R, Kanamori M, Kumabe T, Tominaga T (2016) Impact of gross total resection in patients with WHO grade III glioma harboring the IDH 1/2 mutation without the 1p/19q co-deletion. J Neurooncol 129(3):505–514
Patel SH, Bansal AG, Young EB, Batchala PP, Patrie JT, Lopes MB, Jain R, Fadul CE, Schiff D (2019) Extent of surgical resection in lower-grade gliomas: differential impact based on molecular subtype. AJNR Am J Neuroradiol 40(7):1149–1155
Cairncross G, Wang M, Shaw E, Jenkins R, Brachman D, Buckner J, Fink K, Souhami L, Laperriere N, Curran W, Mehta M (2013) Phase III trial of chemoradiotherapy for anaplastic oligodendroglioma: long-term results of RTOG 9402. J Clin Oncol 31(3):337–343
van den Bent MJ, Brandes AA, Taphoorn MJ, Kros JM, Kouwenhoven MC, Delattre JY, Bernsen HJ, Frenay M, Tijssen CC, Grisold W, Sipos L, Enting RH, French PJ, Dinjens WN, Vecht CJ, Allgeier A, Lacombe D, Gorlia T, Hoang-Xuan K (2013) Adjuvant procarbazine, lomustine, and vincristine chemotherapy in newly diagnosed anaplastic oligodendroglioma: long-term follow-up of EORTC brain tumor group study 26951. J Clin Oncol 31(3):344–350
van den Bent MJ, Baumert B, Erridge SC et al (2017) Interim results from the CATNON trial (EORTC study 26053–22054) of treatment with concurrent and adjuvant temozolomide for 1p/19q non-co-deleted anaplastic glioma: a phase 3, randomised, open-label intergroup study. Lancet 390(10103):1645–1653
Ruff MW, Uhm J (2018) Anaplastic Glioma: Treatment Approaches in the Era of Molecular Diagnostics. Curr Treat Options Oncol 19(12):61
Liang S, Zhang R, Liang D, Song T, Ai T, Xia C, Xia L, Wang Y (2018) Multimodal 3D DenseNet for IDH genotype prediction in gliomas. Genes (Basel) 9(8)
Akkus Z, Ali I, Sedlář J, Agrawal JP, Parney IF, Giannini C, Erickson BJ (2017) Predicting deletion of chromosomal arms 1p/19q in low-grade gliomas from MR images using machine intelligence. J Digit Imaging 30(4):469–476
Ge C, Gu IY, Jakola AS, Yang J (2018) Deep Learning and Multi-Sensor Fusion for Glioma Classification Using Multistream 2D Convolutional Networks. Conf Proc IEEE Eng Med Biol Soc 2018:5894–5897
Zhou H, Chang K, Bai HX, Xiao B, Su C, Bi WL, Zhang PJ, Senders JT, Vallières M, Kavouridis VK, Boaro A, Arnaout O, Yang L, Huang RY (2019) Machine learning reveals multimodal MRI patterns predictive of isocitrate dehydrogenase and 1p/19q status in diffuse low- and high-grade gliomas. J Neurooncol 142(2):299–307
Wu S, Meng J, Yu Q, Li P, Fu S (2019) Radiomics-based machine learning methods for isocitrate dehydrogenase genotype prediction of diffuse gliomas. J Cancer Res Clin Oncol 145(3):543–550
Lu CF, Hsu FT, Hsieh KL, Kao YJ, Cheng SJ, Hsu JB, Tsai PH, Chen RJ, Huang CC, Yen Y, Chen CY (2018) Machine learning-based radiomics for molecular subtyping of gliomas. Clin Cancer Res 24(18):4429–4436
Tan Y, Zhang ST, Wei JW, Dong D, Wang XC, Yang GQ, Tian J, Zhang H (2019) A radiomics nomogram may improve the prediction of IDH genotype for astrocytoma before surgery. Eur Radiol 29(7):325–3337
Eichinger P, Alberts E, Delbridge C, Trebeschi S, Valentinitsch A, Bette S, Huber T, Gempt J, Meyer B, Schlegel J, Zimmer C, Kirschke JS, Menze BH, Wiestler B (2017) Diffusion tensor image features predict IDH genotype in newly diagnosed WHO grade II/III gliomas. Sci Rep 7(1):13396
Aliotta E, Nourzadeh H, Batchala PP, Schiff D, Lopes MB, Druzgal JT, Mukherjee S, Patel SH (2019) Molecular Subtype Classification in Lower-Grade Glioma with Accelerated DTI. AJNR Am J Neuroradiol 40(9):1458–1463
Arita H, Kinoshita M, Kawaguchi A, Takahashi M, Narita Y, Terakawa Y, Tsuyuguchi N, Okita Y, Nonaka M, Moriuchi S, Takagaki M, Fujimoto Y, Fukai J, Izumoto S, Ishibashi K, Nakajima Y, Shofuda T, Kanematsu D, Yoshioka E, Kodama Y, Mano M, Mori K, Ichimura K, Kanemura Y (2018) Lesion location implemented magnetic resonance imaging radiomics for predicting IDH and TERT promoter mutations in grade II/III gliomas. Sci Rep 8(1):11773
Shofty B, Artzi M, Ben Bashat D, Liberman G, Haim O, Kashanian A, Bokstein F, Blumenthal DT, Ram Z, Shahar T (2018) MRI radiomics analysis of molecular alterations in low-grade gliomas. Int J Comput Assist Radiol Surg 13(4):563–571
Koriyama S, Nitta M, Kobayashi T, Muragaki Y, Suzuki A, Maruyama T, Komori T, Masui K, Saito T, Yasuda T, Hosono J, Okamoto S, Shioyama T, Yamatani H, Kawamata T (2018) A surgical strategy for lower grade gliomas using intraoperative molecular diagnosis. Brain Tumor Pathol 35(3):159–167
Takei H, Shinoda J, Ikuta S, Maruyama T, Muragaki Y, Kawasaki T, Ikegame Y, Okada M, Ito T, Asano Y, Yokoyama K, Nakayama N, Yano H, Iwama T (2019) Usefulness of positron emission tomography for differentiating gliomas according to the 2016 World Health Organization classification of tumors of the central nervous system. J Neurosurg 16:1–10
Kato T, Shinoda J, Oka N, Miwa K, Nakayama N, Yano H, Maruyama T, Muragaki Y, Iwama T (2008) Analysis of 11C-methionine uptake in low-grade gliomas and correlation with proliferative activity. AJNR Am J Neuroradiol 29(10):1867–1871
Saito T, Muragaki Y, Maruyama T, Komori T, Tamura M, Nitta M, Tsuzuki S, Kawamata T (2016) Calcification on CT is a simple and valuable preoperative indicator of 1p/19q loss of heterozygosity in supratentorial brain tumors that are suspected grade II and III gliomas. Brain Tumor Pathol 33(3):175–182
Patel SH, Poisson LM, Brat DJ, Zhou Y, Cooper L, Snuderl M, Thomas C, Franceschi AM, Griffith B, Flanders AE, Golfinos JG, Chi AS, Jain R (2017) T2–FLAIR Mismatch, an Imaging Biomarker for IDH and 1p/19q Status in Lower-grade Gliomas: A TCGA/TCIA Project. Clin Cancer Res 23(20):6078–6085
Broen MPG, Smits M, Wijnenga MMJ, Dubbink HJ, Anten MHME, Schijns OEMG, Beckervordersandforth J, Postma AA, van den Bent MJ (2018) The T2-FLAIR mismatch sign as an imaging marker for non-enhancing IDH-mutant, 1p/19q-intact lower-grade glioma: a validation study. Neuro Oncol 20(10):1393–1399
Brat DJ, Aldape K, Colman H, Holland EC, Louis DN, Jenkins RB, Kleinschmidt-DeMasters BK, Perry A, Reifenberger G, Stupp R, von Deimling A, Weller M (2018) cIMPACT-NOW update 3: recommended diagnostic criteria for "Diffuse astrocytic glioma, IDH-wildtype, with molecular features of glioblastoma, WHO grade IV". Acta Neuropathol 136(5):805–810
Cho HH, Lee SH, Kim J, Park H (2018) Classification of the glioma grading using radiomics analysis. PeerJ 6:e5982
Acknowledgements
The authors are deeply grateful to all of the staff members from the Faculty of Advanced Techno-Surgery (Tokyo Women’s Medical University), especially Dr. Mikhail Chernov, for tremendous support during this study. We would like to thank Editage (www.editage.com) for English language editing.
Funding
The authors do not have any personal, institutional, or financial interests in the drugs, materials, or devices described in this paper.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no conflicts of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Matsui, Y., Maruyama, T., Nitta, M. et al. Prediction of lower-grade glioma molecular subtypes using deep learning. J Neurooncol 146, 321–327 (2020). https://doi.org/10.1007/s11060-019-03376-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11060-019-03376-9