Brain Tumor Segmentation and Survival Prediction using Automatic Hard mining in 3D CNN Architecture

TL;DR

This paper presents a 3D CNN architecture with hard mining for improved glioma segmentation from MRI, achieving higher dice scores and using machine learning for survival prediction, validated on BraTS datasets.

Contribution

Introduces a novel 3D CNN with dense connectivity and hard mining for glioma segmentation, enhancing accuracy and survival prediction performance.

Findings

Achieved dice scores of 0.775, 0.815, and 0.85 on test data for different tumor regions.

Increased DSC for tumor core and active tumor by approximately 7% with hard mining.

Survival prediction accuracy of around 45% on validation and test datasets.

Abstract

We utilize 3-D fully convolutional neural networks (CNN) to segment gliomas and its constituents from multimodal Magnetic Resonance Images (MRI). The architecture uses dense connectivity patterns to reduce the number of weights and residual connections and is initialized with weights obtained from training this model with BraTS 2018 dataset. Hard mining is done during training to train for the difficult cases of segmentation tasks by increasing the dice similarity coefficient (DSC) threshold to choose the hard cases as epoch increases. On the BraTS2020 validation data (n = 125), this architecture achieved a tumor core, whole tumor, and active tumor dice of 0.744, 0.876, 0.714,respectively. On the test dataset, we get an increment in DSC of tumor core and active tumor by approximately 7%. In terms of DSC, our network performances on the BraTS 2020 test data are 0.775, 0.815, and 0.85 for enhancing tumor, tumor core, and whole tumor, respectively. Overall survival of a subject is determined using conventional machine learning from rediomics features obtained using a generated segmentation mask. Our approach has achieved 0.448 and 0.452 as the accuracy on the validation and test dataset.