Automatic Segmentation and Overall Survival Prediction in Gliomas using Fully Convolutional Neural Network and Texture Analysis
This work addresses the problem of automating glioma analysis for medical imaging, but it is incremental as it combines existing methods (FCNN and XGBoost) on a known dataset.
The paper tackled automatic segmentation of gliomas from MRI using a fully convolutional neural network and predicted overall survival with texture analysis, achieving mean dice scores of 0.83, 0.69, and 0.69 for tumor regions and 52% accuracy in survival prediction.
In this paper, we use a fully convolutional neural network (FCNN) for the segmentation of gliomas from Magnetic Resonance Images (MRI). A fully automatic, voxel based classification was achieved by training a 23 layer deep FCNN on 2-D slices extracted from patient volumes. The network was trained on slices extracted from 130 patients and validated on 50 patients. For the task of survival prediction, texture and shape based features were extracted from T1 post contrast volume to train an XGBoost regressor. On BraTS 2017 validation set, the proposed scheme achieved a mean whole tumor, tumor core and active dice score of 0.83, 0.69 and 0.69 respectively and an accuracy of 52% for the overall survival prediction.