Top

Published in:

01-12-2020 | Magnetic Resonance Imaging | Research article

Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

Authors: Sha-Sha Zhao, Xiu-Long Feng, Yu-Chuan Hu, Yu Han, Qiang Tian, Ying-Zhi Sun, Jie Zhang, Xiang-Wei Ge, Si-Chao Cheng, Xiu-Li Li, Li Mao, Shu-Ning Shen, Lin-Feng Yan, Guang-Bin Cui, Wen Wang

Published in: BMC Neurology | Issue 1/2020

Abstract

Background

The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1 CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy.

Methods

Thirty-six patients with histologically confirmed ODGs underwent T1 CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1 CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist’s assessment were also compared.

Results

Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1 CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists’ assessment.

Conclusions

Machine-learning based on radiomics of T1 CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

Available only for authorised users

Van Den Bent MJ, Bromberg JE, Buckner J. Low-grade and anaplastic oligodendroglioma. Handb Clin Neurol. 2016;134:361–80. https://doi.org/10.1016/B978-0-12-802997-8.00022-0.CrossRef

Bromberg JE, van den Bent MJ. Oligodendrogliomas: molecular biology and treatment. Oncologist. 2009;14(2):155–63. https://doi.org/10.1634/theoncologist.2008-0248.CrossRefPubMed

Jenkins RB, Blair H, Ballman KV, et al. A t (1;19)(q10;p10) mediates the combined deletions of 1p and 19q and predicts a better prognosis of patients with oligodendroglioma. Cancer Res. 2006;66(20):9852–61. https://doi.org/10.1158/0008-5472.CAN-06-1796.CrossRefPubMed

Koeller KK, Rushing EJ. From the archives of the AFIP: Oligodendroglioma and its variants: radiologic-pathologic correlation. Radiographics. 2005;25(6):1669–88. https://doi.org/10.1148/rg.256055137.CrossRefPubMed

Louis DN, Ohgaki H, Wiestler OD, et al. The 2007 WHO classification of tumours of the central nervous system. Acta Neuropathol. 2007;114(2):97–109. https://doi.org/10.1007/s00401-007-0243-4.CrossRefPubMedPubMedCentral

Osborn AG. Osborn's brain: imaging, pathology, and anatomy (1st edition). Salt Lake City, UT: Amirsys, Inc.; 2012.

Al-Okaili RN, Krejza J, Wang S, Woo JH, Melhem ER. Advanced MR imaging techniques in the diagnosis of intraaxial brain tumors in adults. Radiographics. 2006;26(Suppl 1):S173–89. https://doi.org/10.1148/rg.26si065513.CrossRefPubMed

Law M, Yang S, Wang H, et al. Glioma grading: sensitivity, specificity, and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging. AJNR Am J Neuroradiol. 2003;24(10):1989–98. http://doi.org.PubMedPubMedCentral

Lev MH, Ozsunar Y, Henson JW, et al. Glial tumor grading and outcome prediction using dynamic spin-echo MR susceptibility mapping compared with conventional contrast-enhanced MR: confounding effect of elevated rCBV of oligodendrogliomas [corrected]. AJNR Am J Neuroradiol. 2004;25(2):214–21. http://doi.org.PubMedPubMedCentral

10.

Chawla S, Wang S, Wolf RL, et al. Arterial spin-labeling and MR spectroscopy in the differentiation of gliomas. AJNR Am J Neuroradiol. 2007;28(9):1683–9. https://doi.org/10.3174/ajnr.A0673.CrossRefPubMedPubMedCentral

11.

Lacerda S, Law M. Magnetic resonance perfusion and permeability imaging in brain tumors. Neuroimaging Clin N Am. 2009;19(4):527–57. https://doi.org/10.1016/j.nic.2009.08.007.CrossRefPubMed

12.

Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, They Are Data. Radiology. 2016;278(2):563–77. https://doi.org/10.1148/radiol.2015151169.CrossRefPubMed

13.

Prasanna P, Patel J, Partovi S, Madabhushi A, Tiwari P. Radiomic features from the peritumoral brain parenchyma on treatment-naive multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: Preliminary findings. 2017;27(10):4188–97. https://doi.org/10.1007/s00330-016-4637-3.CrossRefPubMedPubMedCentral

14.

Huang YQ, Liang CH, He L, et al. Development and validation of a Radiomics Nomogram for preoperative prediction of lymph node metastasis in colorectal Cancer. J Clin Oncol. 2016;34(18):2157–64. https://doi.org/10.1200/JCO.2015.65.9128.CrossRefPubMed

15.

Horvat N, Veeraraghavan H, Khan M, et al. MR Imaging of Rectal Cancer: Radiomics Analysis to Assess Treatment Response after Neoadjuvant Therapy. 2018;287(3):833–43. https://doi.org/10.1148/radiol.2018172300.CrossRefPubMed

16.

Tian Q, Yan LF, Zhang X. Radiomics strategy for glioma grading using texture features from multiparametric MRI; 2018. https://doi.org/10.1002/jmri.26010.CrossRef

17.

Kalinli A, Sarikoc F, Akgun H, Ozturk F. Performance comparison of machine learning methods for prognosis of hormone receptor status in breast cancer tissue samples. Comput Methods Prog Biomed. 2013;110(3):298–307. https://doi.org/10.1016/j.cmpb.2012.12.005.CrossRef

18.

Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJ. Machine learning methods for quantitative Radiomic biomarkers. Sci Rep. 2015;5:13087. https://doi.org/10.1038/srep13087.CrossRefPubMedPubMedCentral

19.

Chae HD, Park CM, Park SJ, Lee SM, Kim KG, Goo JM. Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas. Radiology. 2014;273(1):285–93. https://doi.org/10.1148/radiol.14132187.CrossRefPubMed

20.

Vamvakas A, Williams SC, Theodorou K, et al. Imaging biomarker analysis of advanced multiparametric MRI for glioma grading. Phys Med. 2019;60:188–98. https://doi.org/10.1016/j.ejmp.2019.03.014.CrossRefPubMed

21.

Yushkevich PA, Yang G, Gerig G. ITK-SNAP: an interactive tool for semi-automatic segmentation of multi-modality biomedical images. Conf Proc IEEE Eng Med Biol Soc. 2016;2016:3342–5. https://doi.org/10.1109/EMBC.2016.7591443.CrossRefPubMedCentral

22.

Tagliamonte SA, Baayen RH. Models, forests and trees of York English: was/were variation as a case study for statistical practice. Language Variation & Change. 2012;24(2):135–78. https://doi.org/10.1017/S0954394512000129..CrossRef

23.

Cui Z, Xia Z, Su M, Shu H, Gong G. Disrupted white matter connectivity underlying developmental dyslexia: a machine learning approach. Hum Brain Mapp. 2016;37(4):1443–58. https://doi.org/10.1002/hbm.23112.CrossRefPubMedPubMedCentral

24.

Suh HB, Choi YS, Bae S, et al. Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach. Eur Radiol. 2018;28(9):3832–9. https://doi.org/10.1007/s00330-018-5368-4.CrossRefPubMed

25.

Takahashi S, Takahashi W, Tanaka S, et al. Radiomics analysis for Glioma malignancy evaluation using diffusion kurtosis and tensor imaging. Int J Radiat Oncol Biol Phys. 2019;105(4):784–791. https://doi.org/10.1016/j.ijrobp.2019.07.011.CrossRefPubMed

26.

Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014;5:4006. https://doi.org/10.1038/ncomms5006.CrossRefPubMed

27.

Rudie JD, Rauschecker AM, Bryan RN, Davatzikos C, Mohan S. Emerging applications of artificial intelligence in Neuro-oncology. Radiology. 2019;290(3):607–18. https://doi.org/10.1148/radiol.2018181928.CrossRefPubMed

28.

Sengupta A, Ramaniharan AK, Gupta RK, Agarwal S, Singh A. Glioma grading using a machine-learning framework based on optimized features obtained from T1 perfusion MRI and volumes of tumor components. J Magn Reson Imaging. 2019;50(4):1295–306. https://doi.org/10.1002/jmri.26704.CrossRefPubMed

29.

Williams LH, Drew T. Distraction in diagnostic radiology: how is search through volumetric medical images affected by interruptions? Cogn Res Princ Implic. 2017;2(1):12. https://doi.org/10.1186/s41235-017-0050-y.CrossRefPubMedPubMedCentral

30.

Waite S, Kolla S, Jeudy J, et al. Tired in the Reading room: the influence of fatigue in radiology. J Am Coll Radiol. 2017;14(2):191–7. https://doi.org/10.1016/j.jacr.2016.10.009.CrossRefPubMed

31.

Lee CS, Nagy PG, Weaver SJ, Newman-Toker DE. Cognitive and system factors contributing to diagnostic errors in radiology. AJR Am J Roentgenol. 2013;201(3):611–7. https://doi.org/10.2214/AJR.12.10375.CrossRefPubMed

32.

Thrall JH, Li X, Li Q, et al. Artificial Intelligence and Machine Learning in Radiology: Opportunities, Challenges, Pitfalls, and Criteria for Success. J Am Coll Radiol. 2018;15(3 Pt B):504–8. https://doi.org/10.1016/j.jacr.2017.12.026.CrossRefPubMed

Title: Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images
Authors: Sha-Sha Zhao
Xiu-Long Feng
Yu-Chuan Hu
Yu Han
Qiang Tian
Ying-Zhi Sun
Jie Zhang
Xiang-Wei Ge
Si-Chao Cheng
Xiu-Li Li
Li Mao
Shu-Ning Shen
Lin-Feng Yan
Guang-Bin Cui
Wen Wang
Publication date: 01-12-2020
Publisher: BioMed Central
Keywords: Magnetic Resonance Imaging
Magnetic Resonance Imaging
Oligodendroglioma
Published in: BMC Neurology / Issue 1/2020
Electronic ISSN: 1471-2377
DOI: https://doi.org/10.1186/s12883-020-1613-y

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

Abstract

Background

Methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2020

Abnormal blood pressure circadian rhythms are relevant to cerebral infarction and Leukoaraiosis in hypertensive patients

Oral neuromuscular training in patients with dysphagia after stroke: a prospective, randomized, open-label study with blinded evaluators

Severe pain-related adverse events of percutaneous dilatational tracheostomy performed by a neurointensivist compared with conventional surgical tracheostomy in neurocritically ill patients

Protocol of a randomized open label multicentre trial comparing continuous intrajejunal levodopa infusion with deep brain stimulation in Parkinson’s disease - the INfusion VErsus STimulation (INVEST) study

Feasibility of an integrated multidisciplinary geriatric rehabilitation programme for older stroke patients: a process evaluation

Clinical-radiological dissociation in a patient with nitrous oxide-induced subacute combined degeneration: a case report