A Quantitative Assessment of Pre-Operative MRI Reports in Glioma Patients: Report Metrics and IDH Prediction Ability.

Hang Cao,Robert K Fulbright,Jennifer Moliterno,E Zeynep Erson-Omay,Murat Günel

doi:10.3389/fonc.2020.600327

Hang Cao, Robert K Fulbright + Show 3 more

Open Access

https://doi.org/10.3389/fonc.2020.600327

Copy DOI

Abstract

ObjectivesTo measure the metrics of glioma pre-operative MRI reports and build IDH prediction models.MethodsPre-operative MRI reports of 144 glioma patients in a single institution were collected retrospectively. Words were transformed to lowercase letters. White spaces, punctuations, and stop words were removed. Stemming was performed. A word cloud method applied to processed text matrix visualized language behavior. Spearman’s rank correlation assessed the correlation between the subjective descriptions of the enhancement pattern. The T1-contrast images associated with enhancement descriptions were selected. The keywords associated with IDH status were evaluated by χ2 value ranking. Random forest, k-nearest neighbors and Support Vector Machine algorithms were used to train models based on report features and age. All statistical analysis used two-tailed test with significance at p <.05.ResultsLonger word counts occurred in reports of older patients, higher grade gliomas, and wild type IDH gliomas. We identified 30 glioma enhancement descriptions, eight of which were commonly used: peripheral, heterogeneous, irregular, nodular, thick, rim, large, and ring. Five of eight patterns were correlated. IDH mutant tumors were characterized by words related to normal, symmetric or negative findings. IDH wild type tumors were characterized words by related to pathological MR findings like enhancement, necrosis and FLAIR foci. An integrated KNN model based on report features and age demonstrated high-performance (AUC: 0.89, 95% CI: 0.88–0.90).ConclusionReport length depended on age, glioma grade, and IDH status. Description of glioma enhancement was varied. Report descriptions differed for IDH wild and mutant gliomas. Report features can be used to predict glioma IDH status.

Highlights

The pre-operative MRI scan of patients with glioma plays both a critical role in aiding diagnosis (1), the surgical approach, and in serving as a baseline reference for future management
Differences were found in age, initial histology reading, WHO grade, O6-methylguanine-DNA methyl-transferase (MGMT) status between Isocitrate dehydrogenase (IDH) mutant and wild type groups (P
IDH wild type tumors were in older patients and were more commonly Grade IV tumors

Summary

Introduction

The pre-operative MRI scan of patients with glioma plays both a critical role in aiding diagnosis (1), the surgical approach, and in serving as a baseline reference for future management. Through advanced MR imaging method and radiomics analysis, the pre-operative genotype (3), immune phenotype (4), and prognosis prediction (5) become possible. These findings based on image data greatly expand the clinician’s vision on glioma pathogenesis and treatment strategies. The value and properties of another very important part of the pre-operative MRI data, the radiology report, have not been so well appreciated. The qualitative and quantitative comments contained in MRI report remain the major point of reference for many diagnostic and treatment decisions. The general properties of disease-specific reports have not been established using quantitative analyses designed to analyze natural language. The reports as unchangeable medical record could better reflect real-world judgement and largely diminish the possible retrospective bias

Objectives

Methods

Results

Conclusion