Deep Learning Radiomics to Predict PTEN Mutation Status From Magnetic Resonance Imaging in Patients With Glioma.

Hongyu Chen,Fuhua Lin,Jian Zhou,Zhi-Cheng Li,Jinming Zhang,Xiaofei Lv,Yinsheng Chen

doi:10.3389/fonc.2021.734433

Abstract

ObjectivesPhosphatase and tensin homolog (PTEN) mutation is an indicator of poor prognosis of low-grade and high-grade glioma. This study built a reliable model from multi-parametric magnetic resonance imaging (MRI) for predicting the PTEN mutation status in patients with glioma.MethodsIn this study, a total of 244 patients with glioma were retrospectively collected from our center (n = 77) and The Cancer Imaging Archive (n = 167). All patients were randomly divided into a training set (n = 170) and a validation set (n = 74). Three models were built from preoperative MRI for predicting PTEN status, including a radiomics model, a convolutional neural network (CNN) model, and an integrated model based on both radiomics and CNN features. The performance of each model was evaluated by accuracy and the area under the receiver operating characteristic curve (AUC).ResultsThe CNN model achieved an AUC of 0.84 and an accuracy of 0.81, which performed better than did the radiomics model, with an AUC of 0.83 and an accuracy of 0.66. Combining radiomics with CNN will further benefit the predictive performance (accuracy = 0.86, AUC = 0.91).ConclusionsThe combination of both the CNN and radiomics features achieved significantly higher performance in predicting the mutation status of PTEN in patients with glioma than did the radiomics or the CNN model alone.

Highlights

Diffuse glioma is the most common primary brain tumor that mainly includes the World Health Organization (WHO) grades II, III, and IV
We investigated the benefits of combining both deep convolutional neural network (CNN) and radiomics features extracted from MRI
The Phosphatase and tensin homolog (PTEN) mutation data of the TCIA patients were obtained from The Cancer Genome Atlas (TCGA), which includes genomics data corresponding to TCIA patients

Summary

Introduction

Diffuse glioma is the most common primary brain tumor that mainly includes the World Health Organization (WHO) grades II, III (lower-grade glioma, LGG), and IV (glioblastoma, GBM). The WHO classification of central nervous system (CNS) tumors was updated in 2016 on the basis of the integrated diagnosis of molecular genetics [1]. Phosphatase and tensin homolog (PTEN) is a common tumor suppressor gene that regulates the proliferation, survival, and other cellular processes by opposing the activation of phosphoinositide 3-kinase (PI3K)/protein kinase B (AKT/PKB) [2]. The mutation status of PTEN is associated with poor prognosis [3, 4] and resistance to some treatments [5, 6] of multiple tumors, including glioma. The detection of PTEN status relies on genetic profiling approaches, requiring tumor tissue via surgical resection.

Objectives

Methods

Results

Conclusion