Machine Learning Tools for Image-Based Glioma Grading and the Quality of Their Reporting: Challenges and Opportunities

Abstract

Technological innovation has enabled the development of machine learning (ML) tools that aim to improve the practice of radiologists. In the last decade, ML applications to neuro-oncology have expanded significantly, with the pre-operative prediction of glioma grade using medical imaging as a specific area of interest. We introduce the subject of ML models for glioma grade prediction by remarking upon the models reported in the literature as well as by describing their characteristic developmental workflow and widely used classifier algorithms. The challenges facing these models—including data sources, external validation, and glioma grade classification methods —are highlighted. We also discuss the quality of how these models are reported, explore the present and future of reporting guidelines and risk of bias tools, and provide suggestions for the reporting of prospective works. Finally, this review offers insights into next steps that the field of ML glioma grade prediction can take to facilitate clinical implementation.

Performance of deep learning algorithms to distinguish high-grade glioma from low-grade glioma: A systematic review and meta-analysis

“…Up to now, previous systematic reviews and meta-analyses on AI applied to glioma focused on the following topics: prediction of AI on the molecular classification of glioma, 57 , 58 , 59 prediction the prognosis, 60 differential diagnosis between glioma and other brain tumors, 61 , 62 glioma image segmentation, 63 and grading of glioma. 64 , 65 , 66 As for the grading of glioma, two studies pointed out the current obstacles of AI deployment, 64 , 65 and one study conducted a meta-analysis on machine learning (ML) of grading. 66 However, though DL showed sufficient superiority in other cancers, such as cervical cancer and breast cancer, 67 it still remained vacant in grading glioma.…”

“…Moreover, DL automatically extracts image features while ML mainly relies on images whose features have been extracted before, usually by clinicians or other experts. 64 This trait of DL makes it strongly hinge on the quality of images. In our study, only 16 of 33 studies excluded poor-quality images before processing.…”

“…Another limitation is that in glioma classification, we failed to incorporate molecular information, which is becoming increasingly important, since it marks a more refined classification of patients and is critical for clinical treatment choice and prognosis. 64 In addition, the QUADAS-2 assessment was not tailored for AI-based studies, which resulted in risk of bias and applicability concerns.…”

Machine-Learning-Based Radiomics for Classifying Glioma Grade from Magnetic Resonance Images of the Brain

“…The development of radiomics, which extracts data from pictures by translating them into features measuring tumor characteristics, has accelerated the use of ML approaches to imaging, including radiomics-based analysis of brain tumors [ 21 ] In a study by Cho et al, five radiomics feature characteristics for glioma grading and three classifiers demonstrated an average AUC of 0.94 for training groups and 0.90 for test groups [ 22 ]. In several studies, the ML-based approach predicted glioma grades and expression levels of multiple pathologic biomarkers with good accuracy and stability [ 23 ].…”

CSF-Glioma: A Causal Segmentation Framework for Accurate Grading and Subregion Identification of Gliomas

“…Glioma grading is a crucial aspect of diagnosing and treating brain tumors. Accurate grading provides essential information about tumor aggressiveness and helps guide treatment decisions for patients [ 1 , 2 ]. Deep learning models have shown impressive performance in glioma grading by utilizing medical image data [ 3 , 4 ].…”