Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging: A systematic review and meta-analysis

Anthony V. Nguyen, Elizabeth Blears, Evan Ross, Rishi Rajiv Lall, Juan Ortega-Barnett

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

OBJECTIVE Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common intracranial pathologies encountered by neurosurgeons. They often may have similar radiological findings, making diagnosis difficult without surgical biopsy; however, management is quite different between these two entities. Recently, predictive analytics, including machine learning (ML), have garnered attention for their potential to aid in the diagnostic assessment of a variety of pathologies. Several ML algorithms have recently been designed to differentiate GBM from PCNSL radiologically with a high sensitivity and specificity. The objective of this systematic review and meta-analysis was to evaluate the implementation of ML algorithms in differentiating GBM and PCNSL. METHODS The authors performed a systematic review of the literature using PubMed in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML and brain tumors. These studies were further narrowed down to focus on works published between January 2008 and May 2018 addressing the use of ML in training models to distinguish between GBM and PCNSL on radiological imaging. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS Eight studies were identified addressing use of ML in training classifiers to distinguish between GBM and PCNSL on radiological imaging. ML performed well with the lowest reported AUC being 0.878. In studies in which ML was directly compared with radiologists, ML performed better than or as well as the radiologists. However, when ML was applied to an external data set, it performed more poorly. CONCLUSIONS Few studies have applied ML to solve the problem of differentiating GBM from PCNSL using imaging alone. Of the currently published studies, ML algorithms have demonstrated promising results and certainly have the potential to aid radiologists with difficult cases, which could expedite the neurosurgical decision-making process. It is likely that ML algorithms will help to optimize neurosurgical patient outcomes as well as the cost-effectiveness of neurosurgical care if the problem of overfitting can be overcome.

Original languageEnglish (US)
Article numberE5
JournalNeurosurgical Focus
Volume45
Issue number5
DOIs
StatePublished - Nov 1 2018

Fingerprint

Glioblastoma
Meta-Analysis
Lymphoma
Central Nervous System
Machine Learning
Area Under Curve
Pathology
Sensitivity and Specificity
PubMed
ROC Curve
Brain Neoplasms
Cost-Benefit Analysis
Decision Making
Guidelines

Keywords

  • Glioblastoma
  • Machine learning
  • Predictive analytics
  • Primary central nervous system lymphoma
  • Radiological diagnosis

ASJC Scopus subject areas

  • Surgery
  • Clinical Neurology

Cite this

Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging : A systematic review and meta-analysis. / Nguyen, Anthony V.; Blears, Elizabeth; Ross, Evan; Lall, Rishi Rajiv; Ortega-Barnett, Juan.

In: Neurosurgical Focus, Vol. 45, No. 5, E5, 01.11.2018.

Research output: Contribution to journalArticle

@article{05dd1847db57426ab908d787460def6b,
title = "Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging: A systematic review and meta-analysis",
abstract = "OBJECTIVE Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common intracranial pathologies encountered by neurosurgeons. They often may have similar radiological findings, making diagnosis difficult without surgical biopsy; however, management is quite different between these two entities. Recently, predictive analytics, including machine learning (ML), have garnered attention for their potential to aid in the diagnostic assessment of a variety of pathologies. Several ML algorithms have recently been designed to differentiate GBM from PCNSL radiologically with a high sensitivity and specificity. The objective of this systematic review and meta-analysis was to evaluate the implementation of ML algorithms in differentiating GBM and PCNSL. METHODS The authors performed a systematic review of the literature using PubMed in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML and brain tumors. These studies were further narrowed down to focus on works published between January 2008 and May 2018 addressing the use of ML in training models to distinguish between GBM and PCNSL on radiological imaging. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS Eight studies were identified addressing use of ML in training classifiers to distinguish between GBM and PCNSL on radiological imaging. ML performed well with the lowest reported AUC being 0.878. In studies in which ML was directly compared with radiologists, ML performed better than or as well as the radiologists. However, when ML was applied to an external data set, it performed more poorly. CONCLUSIONS Few studies have applied ML to solve the problem of differentiating GBM from PCNSL using imaging alone. Of the currently published studies, ML algorithms have demonstrated promising results and certainly have the potential to aid radiologists with difficult cases, which could expedite the neurosurgical decision-making process. It is likely that ML algorithms will help to optimize neurosurgical patient outcomes as well as the cost-effectiveness of neurosurgical care if the problem of overfitting can be overcome.",
keywords = "Glioblastoma, Machine learning, Predictive analytics, Primary central nervous system lymphoma, Radiological diagnosis",
author = "Nguyen, {Anthony V.} and Elizabeth Blears and Evan Ross and Lall, {Rishi Rajiv} and Juan Ortega-Barnett",
year = "2018",
month = "11",
day = "1",
doi = "10.3171/2018.8.FOCUS18325",
language = "English (US)",
volume = "45",
journal = "Neurosurgical Focus",
issn = "1092-0684",
publisher = "American Association of Neurological Surgeons",
number = "5",

}

TY - JOUR

T1 - Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging

T2 - A systematic review and meta-analysis

AU - Nguyen, Anthony V.

AU - Blears, Elizabeth

AU - Ross, Evan

AU - Lall, Rishi Rajiv

AU - Ortega-Barnett, Juan

PY - 2018/11/1

Y1 - 2018/11/1

N2 - OBJECTIVE Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common intracranial pathologies encountered by neurosurgeons. They often may have similar radiological findings, making diagnosis difficult without surgical biopsy; however, management is quite different between these two entities. Recently, predictive analytics, including machine learning (ML), have garnered attention for their potential to aid in the diagnostic assessment of a variety of pathologies. Several ML algorithms have recently been designed to differentiate GBM from PCNSL radiologically with a high sensitivity and specificity. The objective of this systematic review and meta-analysis was to evaluate the implementation of ML algorithms in differentiating GBM and PCNSL. METHODS The authors performed a systematic review of the literature using PubMed in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML and brain tumors. These studies were further narrowed down to focus on works published between January 2008 and May 2018 addressing the use of ML in training models to distinguish between GBM and PCNSL on radiological imaging. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS Eight studies were identified addressing use of ML in training classifiers to distinguish between GBM and PCNSL on radiological imaging. ML performed well with the lowest reported AUC being 0.878. In studies in which ML was directly compared with radiologists, ML performed better than or as well as the radiologists. However, when ML was applied to an external data set, it performed more poorly. CONCLUSIONS Few studies have applied ML to solve the problem of differentiating GBM from PCNSL using imaging alone. Of the currently published studies, ML algorithms have demonstrated promising results and certainly have the potential to aid radiologists with difficult cases, which could expedite the neurosurgical decision-making process. It is likely that ML algorithms will help to optimize neurosurgical patient outcomes as well as the cost-effectiveness of neurosurgical care if the problem of overfitting can be overcome.

AB - OBJECTIVE Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common intracranial pathologies encountered by neurosurgeons. They often may have similar radiological findings, making diagnosis difficult without surgical biopsy; however, management is quite different between these two entities. Recently, predictive analytics, including machine learning (ML), have garnered attention for their potential to aid in the diagnostic assessment of a variety of pathologies. Several ML algorithms have recently been designed to differentiate GBM from PCNSL radiologically with a high sensitivity and specificity. The objective of this systematic review and meta-analysis was to evaluate the implementation of ML algorithms in differentiating GBM and PCNSL. METHODS The authors performed a systematic review of the literature using PubMed in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML and brain tumors. These studies were further narrowed down to focus on works published between January 2008 and May 2018 addressing the use of ML in training models to distinguish between GBM and PCNSL on radiological imaging. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS Eight studies were identified addressing use of ML in training classifiers to distinguish between GBM and PCNSL on radiological imaging. ML performed well with the lowest reported AUC being 0.878. In studies in which ML was directly compared with radiologists, ML performed better than or as well as the radiologists. However, when ML was applied to an external data set, it performed more poorly. CONCLUSIONS Few studies have applied ML to solve the problem of differentiating GBM from PCNSL using imaging alone. Of the currently published studies, ML algorithms have demonstrated promising results and certainly have the potential to aid radiologists with difficult cases, which could expedite the neurosurgical decision-making process. It is likely that ML algorithms will help to optimize neurosurgical patient outcomes as well as the cost-effectiveness of neurosurgical care if the problem of overfitting can be overcome.

KW - Glioblastoma

KW - Machine learning

KW - Predictive analytics

KW - Primary central nervous system lymphoma

KW - Radiological diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85055906581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055906581&partnerID=8YFLogxK

U2 - 10.3171/2018.8.FOCUS18325

DO - 10.3171/2018.8.FOCUS18325

M3 - Article

C2 - 30453459

AN - SCOPUS:85055906581

VL - 45

JO - Neurosurgical Focus

JF - Neurosurgical Focus

SN - 1092-0684

IS - 5

M1 - E5

ER -