Glioma Prognosis: Segmentation of the Tumor and Survival Prediction using Shape, Geometric and Clinical Information

TL;DR

This paper presents a CNN-based method with hypercolumn and batch normalization for brain tumor segmentation from MRI, combined with feature extraction and neural network regression for survival prediction, achieving high accuracy on BraTS 2018 data.

Contribution

It introduces a novel CNN model with hypercolumn and batch normalization for improved tumor segmentation and integrates geometric, fractal, and histogram features for survival prediction.

Findings

Achieved over 89% dice score in tumor segmentation.

Predicted survival with approximately 67% accuracy.

Validated on BraTS 2018 dataset with strong results.

Abstract

Segmentation of brain tumor from magnetic resonance imaging (MRI) is a vital process to improve diagnosis, treatment planning and to study the difference between subjects with tumor and healthy subjects. In this paper, we exploit a convolutional neural network (CNN) with hypercolumn technique to segment tumor from healthy brain tissue. Hypercolumn is the concatenation of a set of vectors which form by extracting convolutional features from multiple layers. Proposed model integrates batch normalization (BN) approach with hypercolumn. BN layers help to alleviate the internal covariate shift during stochastic gradient descent (SGD) training by zero-mean and unit variance of each mini-batch. Survival Prediction is done by first extracting features(Geometric, Fractal, and Histogram) from the segmented brain tumor data. Then, the number of days of overall survival is predicted by implementing regression on the extracted features using an artificial neural network (ANN). Our model achieves a mean dice score of 89.78%, 82.53% and 76.54% for the whole tumor, tumor core and enhancing tumor respectively in segmentation task and 67.90% in overall survival prediction task with the validation set of BraTS 2018 challenge. It obtains a mean dice accuracy of 87.315%, 77.04% and 70.22% for the whole tumor, tumor core and enhancing tumor respectively in the segmentation task and a 46.80% in overall survival prediction task in the BraTS 2018 test data set.