Machine Learning Applications for Differentiation of Glioma from Brain Metastasis—A Systematic Review

Simple Summary We present a systematic review of published reports on machine learning (ML) applications for the differentiation of gliomas from brain metastases by summarizing study characteristics, strengths, and pitfalls. Based on these findings, we present recommendations for future research in this field. Abstract Glioma and brain metastasis can be difficult to distinguish on conventional magnetic resonance imaging (MRI) due to the similarity of imaging features in specific clinical circumstances. Multiple studies have investigated the use of machine learning (ML) models for non-invasive differentiation of glioma from brain metastasis. Many of the studies report promising classification results, however, to date, none have been implemented into clinical practice. After a screening of 12,470 studies, we included 29 eligible studies in our systematic review. From each study, we aggregated data on model design, development, and best classifiers, as well as quality of reporting according to the TRIPOD statement. In a subset of eligible studies, we conducted a meta-analysis of the reported AUC. It was found that data predominantly originated from single-center institutions (n = 25/29) and only two studies performed external validation. The median TRIPOD adherence was 0.48, indicating insufficient quality of reporting among surveyed studies. Our findings illustrate that despite promising classification results, reliable model assessment is limited by poor reporting of study design and lack of algorithm validation and generalizability. Therefore, adherence to quality guidelines and validation on outside datasets is critical for the clinical translation of ML for the differentiation of glioma and brain metastasis.

[1]  M. Kalra,et al.  FDA-regulated AI Algorithms: Trends, Strengths, and Gaps of Validation Studies. , 2021, Academic radiology.

[2]  Ming-Tzer Lin What's Needed to Bridge the Gap Between US FDA Clearance and Real-world Use of AI Algorithms. , 2021, Academic radiology.

[3]  E. Dezamis,et al.  Development of a Machine Learning Classifier Based on Radiomic Features Extracted From Post-Contrast 3D T1-Weighted MR Images to Distinguish Glioblastoma From Solitary Brain Metastasis , 2021, Frontiers in Oncology.

[4]  L. Peng,et al.  Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence , 2021, BMJ Open.

[5]  G. Collins,et al.  Reporting of prognostic clinical prediction models based on machine learning methods in oncology needs to be improved , 2021, Journal of clinical epidemiology.

[6]  Y. Liu,et al.  Handcrafted and Deep Learning-Based Radiomic Models Can Distinguish GBM from Brain Metastasis , 2021, Journal of oncology.

[7]  Nam H. Le,et al.  Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics , 2021, Scientific Reports.

[8]  Zahra Riahi Samani,et al.  Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases , 2021, Scientific Reports.

[9]  E. Mayo-Wilson,et al.  The PRISMA 2020 statement: an updated guideline for reporting systematic reviews , 2021, BMJ.

[10]  S. Bae,et al.  Development and Validation of a Deep Learning–Based Model to Distinguish Glioblastoma from Solitary Brain Metastasis Using Conventional MR Images , 2021, American Journal of Neuroradiology.

[11]  A. Brunetti,et al.  Meningioma MRI radiomics and machine learning: systematic review, quality score assessment, and meta-analysis , 2021, Neuroradiology.

[12]  Juan Miguel Valverde,et al.  Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review , 2021, J. Imaging.

[13]  Alhanoof Althnian,et al.  Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain , 2021, Applied Sciences.

[14]  Rogers F. Silva,et al.  Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning , 2021, Nature Communications.

[15]  R. Meier,et al.  Exploratory Analysis of Qualitative MR Imaging Features for the Differentiation of Glioblastoma and Brain Metastases , 2020, Frontiers in Oncology.

[16]  Ilah Shin,et al.  Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation , 2020, Scientific Reports.

[17]  J. H. Kim,et al.  Brain metastasis detection using machine learning: a systematic review and meta-analysis , 2020, Neuro-oncology.

[18]  Micah J. Sheller,et al.  The future of digital health with federated learning. , 2020, NPJ digital medicine.

[19]  Spyridon Bakas,et al.  Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data , 2020, Scientific Reports.

[20]  H. Kim,et al.  Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation , 2020, Scientific Reports.

[21]  David Moratal,et al.  Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach. , 2020, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[22]  J. Mongan,et al.  Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers. , 2020, Radiology. Artificial intelligence.

[23]  Tarik Tihan,et al.  Machine Learning Decision Tree Models for Differentiation of Posterior Fossa Tumors Using Diffusion Histogram Analysis and Structural MRI Findings , 2020, Frontiers in Oncology.

[24]  P. Huang,et al.  Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region–derived radiomic features and multiple classifiers , 2020, European Radiology.

[25]  Andrea Vedaldi,et al.  Accurate brain age prediction with lightweight deep neural networks , 2019, bioRxiv.

[26]  M. Kitajima,et al.  An initial experience of machine learning based on multi-sequence texture parameters in magnetic resonance imaging to differentiate glioblastoma from brain metastases , 2019, Journal of the Neurological Sciences.

[27]  Peter B. Walker,et al.  Federated Learning for Healthcare Informatics , 2019, Journal of Healthcare Informatics Research.

[28]  Blaz Meden,et al.  Sample-Size Determination Methodologies for Machine Learning in Medical Imaging Research: A Systematic Review , 2019, Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes.

[29]  P. Sundgren,et al.  Differentiation between glioblastomas and brain metastases and regarding their primary site of malignancy using dynamic susceptibility contrast MRI at 3T. , 2019, Journal of neuroradiology. Journal de neuroradiologie.

[30]  Donghai Liang,et al.  Histogram analysis of absolute cerebral blood volume map can distinguish glioblastoma from solitary brain metastasis , 2019, Medicine.

[31]  Xuelei Ma,et al.  Radiomics-Based Machine Learning in Differentiation Between Glioblastoma and Metastatic Brain Tumors , 2019, Front. Oncol..

[32]  D. Ben Bashat,et al.  Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis , 2019, Journal of magnetic resonance imaging : JMRI.

[33]  N. Pavlidis,et al.  Advances in the management of brain metastases from cancer of unknown primary. , 2019, Future oncology.

[34]  J. Titano,et al.  Machine learning for semi-automated classification of glioblastoma, brain metastasis and central nervous system lymphoma using magnetic resonance advanced imaging. , 2019, Annals of translational medicine.

[35]  A. Averbuch,et al.  Application of MR morphologic, diffusion tensor, and perfusion imaging in the classification of brain tumors using machine learning scheme , 2019, Neuroradiology.

[36]  Axel Wismüller,et al.  Investigating a quantitative radiomics approach for brain tumor classification , 2019, Medical Imaging.

[37]  C. Langlotz,et al.  Deep Learning in Neuroradiology , 2018, American Journal of Neuroradiology.

[38]  Lior Rokach,et al.  Ensemble learning: A survey , 2018, WIREs Data Mining Knowl. Discov..

[39]  Oleg S. Pianykh,et al.  Current Applications and Future Impact of Machine Learning in Radiology. , 2018, Radiology.

[40]  C. Suh,et al.  Diffusion-Weighted Imaging and Diffusion Tensor Imaging for Differentiating High-Grade Glioma from Solitary Brain Metastasis: A Systematic Review and Meta-Analysis , 2018, American Journal of Neuroradiology.

[41]  Srini Tridandapani,et al.  Deep Learning in Radiology. , 2018, Academic radiology.

[42]  Eudocia Q Lee,et al.  Incidence and prognosis of patients with brain metastases at diagnosis of systemic malignancy: a population-based study , 2017, Neuro-oncology.

[43]  Chuan Zhou,et al.  Deep Learning in Medical Image Analysis. , 2017, Advances in experimental medicine and biology.

[44]  Soonmee Cha,et al.  Metastasis in Adult Brain Tumors. , 2016, Neuroimaging clinics of North America.

[45]  Vinod Kumar,et al.  A package-SFERCB-"Segmentation, feature extraction, reduction and classification analysis by both SVM and ANN for brain tumors" , 2016, Appl. Soft Comput..

[46]  Anand D. Sarwate,et al.  COINSTAC: A Privacy Enabled Model and Prototype for Leveraging and Processing Decentralized Brain Imaging Data , 2016, Front. Neurosci..

[47]  F. Howe,et al.  Morphometric model for discrimination between glioblastoma multiforme and solitary metastasis using three‐dimensional shape analysis , 2016, Magnetic resonance in medicine.

[48]  Ponnuthurai N. Suganthan,et al.  Ensemble Classification and Regression-Recent Developments, Applications and Future Directions [Review Article] , 2016, IEEE Computational Intelligence Magazine.

[49]  Evangelia E. Tsolaki,et al.  Fast spectroscopic multiple analysis (FASMA) for brain tumor classification: a clinical decision support system utilizing multi-parametric 3T MR data , 2015, International Journal of Computer Assisted Radiology and Surgery.

[50]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[51]  Luís Torgo,et al.  A Survey of Predictive Modelling under Imbalanced Distributions , 2015, ArXiv.

[52]  G. Collins,et al.  Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement , 2015, BMJ : British Medical Journal.

[53]  Gary S Collins,et al.  Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): Explanation and Elaboration , 2015, Annals of Internal Medicine.

[54]  F. Howe,et al.  Discrimination between glioblastoma multiforme and solitary metastasis using morphological features derived from the p:q tensor decomposition of diffusion tensor imaging , 2014, NMR in biomedicine.

[55]  K. Fountas,et al.  Investigating brain tumor differentiation with diffusion and perfusion metrics at 3T MRI using pattern recognition techniques. , 2013, Magnetic resonance imaging.

[56]  Evangelia E. Tsolaki,et al.  Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data , 2013, International Journal of Computer Assisted Radiology and Surgery.

[57]  Christos Davatzikos,et al.  Investigating machine learning techniques for MRI-based classification of brain neoplasms , 2011, International Journal of Computer Assisted Radiology and Surgery.

[58]  A Heerschap,et al.  Discrimination between Metastasis and Glioblastoma Multiforme Based on Morphometric Analysis of MR Images , 2010, American Journal of Neuroradiology.

[59]  Christos Davatzikos,et al.  Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme , 2009, Magnetic resonance in medicine.

[60]  K. Yamashita,et al.  Performance Evaluation of Radiologists with Artificial Neural Network for Differential Diagnosis of Intra-Axial Cerebral Tumors on MR Images , 2008, American Journal of Neuroradiology.

[61]  William Stafford Noble,et al.  Support vector machine , 2013 .

[62]  B. Erickson,et al.  Pattern of T2 hypointensity associated with ring-enhancing brain lesions can help to differentiate pathology , 2006, Neuroradiology.

[63]  D. Altman,et al.  Measuring inconsistency in meta-analyses , 2003, BMJ : British Medical Journal.

[64]  G. Johnson,et al.  Peritumoral diffusion tensor imaging of high-grade gliomas and metastatic brain tumors. , 2003, AJNR. American journal of neuroradiology.

[65]  Steff Lewis,et al.  Forest plots: trying to see the wood and the trees , 2001, BMJ : British Medical Journal.

[66]  Y Maruyama,et al.  A randomized trial of surgery in the treatment of single metastases to the brain. , 1990, The New England journal of medicine.

[67]  Siti Mariyam Shamsuddin,et al.  Handling Imbalanced Ratio for Class Imbalance Problem Using SMOTE , 2019, Proceedings of the Third International Conference on Computing, Mathematics and Statistics (iCMS2017).

[68]  Jill S Barnholtz-Sloan,et al.  Epidemiology of gliomas. , 2015, Cancer treatment and research.

[69]  J. Barnholtz-Sloan,et al.  CBTRUS statistical report: Primary brain and central nervous system tumors diagnosed in the United States in 2006-2010. , 2013, Neuro-oncology.

[70]  George C. Kagadis,et al.  Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features , 2008, Comput. Methods Programs Biomed..