Prediction of Overall Survival of Brain Tumor Patients

TL;DR

This paper presents a method for segmenting brain tumors and predicting patient survival using features from MRI images, achieving competitive accuracy with fewer features than existing methods.

Contribution

It introduces a tumor segmentation and survival prediction approach that uses fewer features and achieves higher accuracy than current state-of-the-art methods.

Findings

Surpasses previous methods in survival prediction accuracy.

Uses fewer features while maintaining high performance.

Achieves 59% accuracy overall, 67% with resection status.

Abstract

Automated brain tumor segmentation plays an important role in the diagnosis and prognosis of the patient. In addition, features from the tumorous brain help in predicting patients overall survival. The main focus of this paper is to segment tumor from BRATS 2018 benchmark dataset and use age, shape and volumetric features to predict overall survival of patients. The random forest classifier achieves overall survival accuracy of 59% on the test dataset and 67% on the dataset with resection status as gross total resection. The proposed approach uses fewer features but achieves better accuracy than state of the art methods.