Abstract
The aim of the systematic review was to assess recently published studies on diagnostic test accuracy of glioblastoma treatment response monitoring biomarkers in adults, developed through machine learning (ML). Articles published 09/2018–09/2020 were searched for using MEDLINE, EMBASE, and the Cochrane Register. Included study participants were adult patients with high grade glioma who had undergone standard treatment (maximal resection, radiotherapy with concomitant and adjuvant temozolomide) and subsequently underwent follow-up imaging to determine treatment response status (specifically, distinguishing progression/recurrence from progression/recurrence mimics - the target condition). Risk of bias and applicability was assessed with QUADAS 2 methodology. Contingency tables were created for hold-out test sets and recall, specificity, precision, F1-score, balanced accuracy calculated. Fifteen studies were included with 1038 patients in training sets and 233 in test sets. To determine whether there was progression or a mimic, the reference standard combination of follow-up imaging and histopathology at re-operation was applied in 67% (10/15) of studies. External hold-out test sets were used in 27% (4/15) to give ranges of diagnostic accuracy measures: recall = 0.70–1.00; specificity = 0.67–0.90; precision = 0.78–0.88; F1 score = 0.74–0.94; balanced accuracy = 0.74–0.83; AUC = 0.80–0.85. The small numbers of patient included in studies, the high risk of bias and concerns of applicability in the study designs (particularly in relation to the reference standard and patient selection due to confounding), and the low level of evidence, suggest that limited conclusions can be drawn from the data. There is likely good diagnostic performance of machine learning models that use MRI features to distinguish between progression and mimics. The diagnostic performance of ML using implicit features did not appear to be superior to ML using explicit features. There are a range of ML-based solutions poised to become treatment response monitoring biomarkers for glioblastoma. To achieve this, the development and validation of ML models require large, well-annotated datasets where the potential for confounding in the study design has been carefully considered. Therefore, multidisciplinary efforts and multicentre collaborations are necessary.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Stupp, R., et al.: Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma. N. Engl. J. Med. 352, 987–996 (2005). https://doi.org/10.1056/NEJMoa043330
FDA-NIH Biomarker Working Group: BEST (Biomarkers, EndpointS, and other Tools) Resource. Food and Drug Administration (US), Silver Spring. Co-published by National Institutes of Health (US), Bethesda (2016)
MacDonald, D., Cascino, T.L., Schold, S.C., Cairncross, J.G.: Response criteria for phase II studies of supratentorial malignant glioma. J. Clin. Oncol. 8, 1277–1280 (2010). https://doi.org/10.1200/jco.1990.8.7.1277
Wen, P.Y., Macdonald, D.R., Reardon, D.A., Cloughesy, T.F., Sorensen, A.G., Galanis, E.: Updated response assessment criteria for high-grade gliomas: response assessment in neuro- oncology working group. J. Clin. Oncol. 28, 1963–1972 (2010). https://doi.org/10.1200/JCO.2009.26.3541
Booth, T.C., et al.: Neuro-oncology single-photon emission CT: a current overview. Neurographics 01, 108–120 (2011)
Chamberlain, M.C., Glantz, M.J., Chalmers, L., Van Horn, A., Sloan, A.E.: Early necrosis following concurrent Temodar and radiotherapy in patients with glioblastoma. J. Neurooncol. 82, 81–83 (2007). https://doi.org/10.1007/s11060-006-9241-y
Dhermain, F.G., et al.: Advanced MRI and PET imaging for assessment of treatment response in patients with gliomas. Lancet Neurol. 9, 906–920 (2010). https://doi.org/10.1016/S1474-4422(10)70181-2
Brandsma, D., et al.: Clinical features, mechanisms, and management of pseudoprogression in malignant gliomas. Lancet Oncol. 9, 453–461 (2008)
Radbruch, A., et al.: Pseudoprogression in patients with glioblastoma: clinical relevance despite low incidence. Neuro Oncol. 17, 151–159 (2015)
Verma, N., et al.: Differentiating tumor recurrence from treatment necrosis: a review of neuro-oncologic imaging strategies. Neuro Oncol. 15, 515–534 (2013)
Booth, T.C., Williams, M., Luis, A., Cardoso, J., Ashkan, K., Shuaib, H.: Machine learning and glioma imaging biomarkers. Clin. Radiol. 75, 20–32 (2020). https://doi.org/10.1016/j.crad.2019.07.001
Booth, T.C.: An update on machine learning in neuro-oncology diagnostics. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 37–44. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_4
McInnes, M.D.F., Moher, D., Thombs, B.D., McGrath, T.A., Bossuyt, P.M., The PRISMA-DTA Group: Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement. JAMA 319, 388–396 (2018). https://doi.org/10.1001/jama.2017.19163
Bossuyt, P.M., Leeflang, M.M.: Chapter 6: Developing criteria for including studies. In: Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy Version 0.4. The Cochrane Collaboration (2008)
de Vet, H.C.W., Eisinga, A., Riphagen, I.I., Aertgeerts, B., Pewsner, D.: Chapter 7: Searching for studies. In: Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy Version 0.4. The Cochrane Collaboration (2008)
Reitsma, J.B., Rutjes, A.W.S., Whiting, P., Vlassov, V.V., Leeflang, M.M.G., Deeks, J.J.: Chapter 9: Assessing methodological quality. In: Deeks, J.J., Bossuyt, P.M., Gatsonis, C. (eds.) Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy Version 1.0.0. The Cochrane Collaboration (2009). http://srdta.cochrane/org/
Whiting, P.F., et al.: QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann. Intern. Med. 155, 529–536 (2011)
Booth, T.C., et al.: Re: “Tumour progression or pseudoprogression? A review of post-treatment radiological appearances of glioblastoma”. Clin. Radiol. 5, 495–496 (2016)
Booth, T.C., et al.: Comment on “The role of imaging in the management of progressive glioblastoma. A systematic review and evidence-based clinical practice guideline”. J. Neurooncol. 121, 423–424 (2015)
Ellingson, B.M., Wen, P.Y., Cloughesy, T.F.: Modified criteria for radiographic response assessment in glioblastoma clinical trials. Neurotherapeutics 14(2), 307–320 (2017). https://doi.org/10.1007/s13311-016-0507-6
Booth, T.C., et al.: Analysis of heterogeneity in T2-weighted MR images can differentiate pseudoprogression from progression in glioblastoma. PLoS ONE 12, 0176528 (2017). https://doi.org/10.1371/journal.pone.0176528
Gahramanov, S., et al.: Pseudoprogression of glioblastoma after chemo- and radiation therapy: diagnosis by using dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging with ferumoxytol versus gadoteridol and correlation with survival. Radiology 266, 842–852 (2013)
Howick, J., et al.: The Oxford 2011 levels of evidence. Oxford Centre for Evidence-Based Medicine, Oxford (2016). http://www.cebm.net/index.aspx?o=5653
Buwanabala, J., et al.: The (mis)use of imaging criteria in the assessment of glioblastoma treatment response. American Society of Neuroradiology, Boston. Scientific Poster 2616 (2019)
Holdhoff, M., et al.: The consistency of neuropathological diagnoses in patients undergoing surgery for suspected recurrence of glioblastoma. J. Neurooncol. 141(2), 347–354 (2018). https://doi.org/10.1007/s11060-018-03037-3. pmid:30414096
Davatzikos, C., et al.: AI-based prognostic imaging biomarkers for precision neurooncology: the ReSPOND consortium. Neuro Oncol. 22, 886–888 (2020). https://doi.org/10.1093/neuonc/noaa045
Kim, J.Y., et al.: Incorporating diffusion- and perfusion-weighted MRI into a radiomics model improves diagnostic performance for pseudoprogression in glioblastoma patients. Neuro-oncology 21, 404–414 (2019)
Kim, J.Y., Yoon, M.J., Park, J.E., Choi, E.J., Lee, J., Kim, H.S.: Radiomics in peritumoral non-enhancing regions: fractional anisotropy and cerebral blood volume improve prediction of local progression and overall survival in patients with glioblastoma. Neuroradiology 61(11), 1261–1272 (2019). https://doi.org/10.1007/s00234-019-02255-4
Bacchi, S., et al.: Deep learning in the detection of high-grade glioma recurrence using multiple MRI sequences: a pilot study. J. Clin. Neurosci. 70, 11–13 (2019)
Elshafeey, N., et al.: Multicenter study demonstrates radiomic features derived from magnetic resonance perfusion images identify pseudoprogression in glioblastoma. Nat. Commun. 10, 3170 (2019)
Verma, G., et al.: Three-dimensional echo planar spectroscopic imaging for differentiation of true progression from pseudoprogression in patients with glioblastoma. NMR Biomed. 32, 4042 (2019)
Ismail, M., et al.: Shape features of the lesion habitat to differentiate brain tumor progression from pseudoprogression on routine multiparametric MRI: a multisite study. AJNR Am. J. Neuroradiol. 39, 2187–2193 (2018)
Bani-Sadr, A., et al.: Conventional MRI radiomics in patients with suspected early- or pseudo-progression. Neurooncol. Adv. 1, 1–9 (2019)
Gao, X.Y., et al.: Differentiation of treatment-related effects from glioma recurrence using machine learning classifiers based upon pre-and post-contrast T1WI and T2 FLAIR subtraction features: a two-center study. Cancer Manag. Res. 12, 3191–3201 (2020)
Jang, B.S., Jeon, S.H., Kim, I.H., Kim, I.A.: Prediction of pseudoprogression versus progression using machine learning algorithm in glioblastoma. Sci. Rep. 8, 12516 (2018)
Li, M., Tang, H., Chan, M.D., Zhou, X., Qian, X.: DC-AL GAN: pseudoprogression and true tumor progression of glioblastoma multiform image classification based on DCGAN and AlexNet. Med. Phys. 47, 1139–1150 (2020)
Akbari, H., et al.: Histopathology- validated machine learning radiographic biomarker for noninvasive discrimination between true progression and pseudo-progression in glioblastoma. Cancer 0, 1–12 (2020). https://doi.org/10.1002/cncr.32790
Li, X., Xu, G., Cao, Q., Zou, W., Xu, Y., Cong, P.: Identification of glioma pseudoprogression based on gabor dictionary and sparse representation model. NeuroQuantology 16, 43–51 (2018). https://doi.org/10.14704/nq.2018.16.1.1178
Wang, S., et al.: Multiparametric magnetic resonance imaging in the assessment of anti-EGFRvIII chimeric antigen receptor T cell therapy in patients with recurrent glioblastoma. Br. J. Cancer 120, 54–56 (2019)
Yang, K., et al.: Cancer genetic markers according to radiotherapeutic response in patients with primary glioblastoma - radiogenomic approach for precision medicine. Radiother. Oncol. 131, 66–74 (2019)
Lundemann, M., et al.: Feasibility of multi-parametric PET and MRI for prediction of tumour recurrence in patients with glioblastoma. Eur. J. Nucl. Med. Mol. Imaging 46(3), 603–613 (2018). https://doi.org/10.1007/s00259-018-4180-3
Acknowledgements
This work was supported by the Wellcome/EPSRC Centre for Medical Engineering [WT 203148/Z/16/Z], The Royal College of Radiologists and King’s College Hospital Research and Innovation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Supplementary Table S1.
MEDLINE, EMBASE and Cochrane Register search strategies. Recommendations for a sensitive search with low precision; with subject headings with exploded terms; and with no language restrictions, were followed [15].
MEDLINE (OVID). PubMed was included. The search strategy for Title/Abstract terms used a combination of subject headings (MeSH terms) and keywords: Database: Ovid MEDLINE(R) ALL <1946 to September 11, 2020> Search Strategy: -------------------------------------------------------------------------------- 1 exp Glioblastoma/ (25451) 2 high grade glioma.mp. (2986) 3 pseudoprogression.mp. (633) 4 radiomics.mp. (2262) 5 exp Artificial Intelligence/ or exp Machine Learning/ or exp Neural Networks, Computer/ (99521) 6 exp Deep Learning/ (2761) 7 monitoring biomarker.mp. (71) 8 treatment response.mp. (29303) 9 imaging.mp. (2039219) 10 exp Magnetic Resonance Imaging/ or MRI.mp. (544944) 11 pet.mp. (103253) 12 exp Positron-Emission Tomography/ (61544) 13 9 or 10 or 11 or 12 (2117006) 14 1 or 2 or 3 (28462) 15 4 or 5 or 6 or 7 or 8 (130625) 16 13 and 14 and 15 (321) 17 limit 16 to last 2 years (130) 18 13 and 14 (6464) 19 limit 18 to last 2 years (1241) *************************** strategy 17 was insensitive so strategy 19 was employed for final search |
EMBASE (OVID). Subject headings and keywords: Database: Embase <1974 to 2020 Week 37> Search Strategy: -------------------------------------------------------------------------------- 1 exp glioblastoma/ (68063) 2 high grade glioma.mp. (5411) 3 pseudoprogression.mp. (1225) 4 exp radiomics/ (1271) 5 exp machine learning/ or exp artificial intelligence/ (227658) 6 exp deep learning/ (9382) 7 monitoring biomarker.mp. (108) 8 exp treatment response/ (265476) 9 exp multiparametric magnetic resonance imaging/ or exp imaging/ or exp nuclear magnetic resonance imaging/ (1112723) 10 magnetic resonance imaging.mp. (925155) 11 MRI.mp. (445714) 12 PET.mp. or exp positron emission tomography/ (249021) 13 1 or 2 or 3 (72158) 14 4 or 5 or 6 or 7 or 8 (492158) 15 9 or 10 or 11 or 12 (1331815) 16 13 and 15 (14315) 17 limit 16 to last 2 years (3209) 18 limit 17 to exclude medline journals (479) *************************** strategy 18 was employed for final search to prevent duplication from MEDLINE |
Cochrane Register. Epistemonikos review database included, protocols included, CENTRAL (Cochrane central register of controlled trials included which includes https://www.ebscohost.com/nursing/products/cinahl-databases, https://clinicaltrials.gov, https://www.who.int/ictrp/en/). Subject headings and keywords: Date Run: 13/09/2020 15:52:52 ID Search Hits #1 MeSH descriptor: [Glioblastoma] explode all trees 628 #2 high grade glioma 524 #3 pseudoprogression 69 #4 imaging68926 #5 MeSH descriptor: [Magnetic Resonance Imaging] explode all trees 7660 #6 MRI 23753 #7 PET 6912 #8 MeSH descriptor: [Positron-Emission Tomography] explode all trees 988 #9 {OR #1-#3}1167 #10 {OR #4-#8} 79474 #11 {AND #9-#10} 297 strategy 11 was employed for final search |
Health Technology Assessment. https://database.inahta.org/ Subject headings and keywords: ((“Glioblastoma”[mh]) OR (high grade glioma) OR (pseudoprogression)) |
Supplementary Figure S1.
Bar chart showing risk of bias and concerns of applicability assessment
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Booth, T.C. et al. (2020). Machine Learning and Glioblastoma: Treatment Response Monitoring Biomarkers in 2021. In: Kia, S.M., et al. Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-oncology. MLCN RNO-AI 2020 2020. Lecture Notes in Computer Science(), vol 12449. Springer, Cham. https://doi.org/10.1007/978-3-030-66843-3_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-66843-3_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66842-6
Online ISBN: 978-3-030-66843-3
eBook Packages: Computer ScienceComputer Science (R0)