Automatic Segmentation and Overall Survival Prediction in Gliomas using\n Fully Convolutional Neural Network and Texture Analysis

2017/12/06 by Varghese Alex, Alex, Varghese, Mohammed Safwan +3
Medicine · Neuroscience · #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Glioma Diagnosis and Treatment #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.1712.02066

openalex publication_date 2017/12/06 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28

Abstract

In this paper, we use a fully convolutional neural network (FCNN) for the\nsegmentation of gliomas from Magnetic Resonance Images (MRI). A fully\nautomatic, voxel based classification was achieved by training a 23 layer deep\nFCNN on 2-D slices extracted from patient volumes. The network was trained on\nslices extracted from 130 patients and validated on 50 patients. For the task\nof survival prediction, texture and shape based features were extracted from T1\npost contrast volume to train an XGBoost regressor. On BraTS 2017 validation\nset, the proposed scheme achieved a mean whole tumor, tumor core and active\ndice score of 0.83, 0.69 and 0.69 respectively and an accuracy of 52% for the\noverall survival prediction.\n

Related

• Glioma Prognosis: Segmentation of the Tumor and Survival Prediction using Shape, Geometric and Clinical Information
• Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction
• Brain Tumor Segmentation and Survival Prediction using Automatic Hard\n mining in 3D CNN Architecture
• Domain Knowledge Based Brain Tumor Segmentation and Overall Survival Prediction
• Brain MRI study for glioma segmentation using convolutional neural networks and original post-processing techniques with low computational demand