Hostname: page-component-cd9895bd7-p9bg8 Total loading time: 0 Render date: 2024-12-24T03:20:10.601Z Has data issue: false hasContentIssue false

P.115 Diagnostic performance of machine learning based MR algorithm vs conventional MR images for predicting the likelihood of brain tumors

Published online by Cambridge University Press:  24 June 2022

S Chatterjee
Affiliation:
(Lucknow)
R Alkhaldi
Affiliation:
(Dublin)*
P Yaadav
Affiliation:
(Latur)
D Bethineedi
Affiliation:
(Visakhapatnam)
A Shreya
Affiliation:
(Bengaluru)
N Bankole
Affiliation:
(Rabat)
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Background: MRI forms an imperative part of the diagnostic and treatment protocol for primary brain tumors and metastasis. Though conventional T1W MRI forms the basis for diagnosis at present, it faces several limitations. Machine learning (ML) algorithms require less expertise and provide better diagnostic accuracy. Methods: A systematic review of PubMed, Google Scholar, and Cochrane databases along with registries through 1980-2021 was done. Original articles in English evaluating Conventional MRI or ML algorithms. Data was extracted by 2 reviewers and meta-analysis was performed using bivariate regression model. Results: The study protocol was registered under PROSPERO. Twelve studies with 1247 participants were included for systematic analysis and three studies for meta-analysis. ML algorithms had better aggregate sensitivity and specificity (80%, 83.14%) than Conventional MRI (81.84%, 74.78%).The pooled sensitivity, specificity, DOR for the studies were 0.926 (95% CI, 0.840-0.926), 0.991 (95% CI, 0.955-0.998) and 1446.946 (312.634-6692.646) with AUC=0.904 under HSROC. On subgroup analysis, MRS and Random Forest Model had highest sensitivity and specificity (100%,100%;100%,100%), DSC MRI and Deep Neural Network had highest AUC (0.98,0.986). Conclusions: ML algorithm has superior diagnostic performance and faster diagnostic capability once trained than conventional imaging for brain tumors. It has immense potential to be the standard of care in the future.

Type
Poster Presentations
Copyright
© The Author(s), 2022. Published by Cambridge University Press on behalf of Canadian Neurological Sciences Federation