Conditional Adversarial Network for Semantic Segmentation of Brain Tumor

TL;DR

This paper introduces a novel conditional adversarial network architecture for brain tumor segmentation in MRI images, improving accuracy by leveraging adversarial training to distinguish between ground truth and predicted segmentation maps.

Contribution

It proposes an end-to-end trainable cGAN-based model for brain tumor segmentation and survival prediction, demonstrating superior performance on the BraTS 2017 dataset.

Findings

Achieved a DICE score of 0.68 for whole tumor segmentation

Demonstrated high sensitivity and specificity in validation

Outperformed existing methods on BraTS 2017 data

Abstract

Automated medical image analysis has a significant value in diagnosis and treatment of lesions. Brain tumors segmentation has a special importance and difficulty due to the difference in appearances and shapes of the different tumor regions in magnetic resonance images. Additionally, the data sets are heterogeneous and usually limited in size in comparison with the computer vision problems. The recently proposed adversarial training has shown promising results in generative image modeling. In this paper, we propose a novel end-to-end trainable architecture for brain tumor semantic segmentation through conditional adversarial training. We exploit conditional Generative Adversarial Network (cGAN) and train a semantic segmentation Convolution Neural Network (CNN) along with an adversarial network that discriminates segmentation maps coming from the ground truth or from the segmentation network for BraTS 2017 segmentation task[15, 4, 2, 3]. We also propose an end-to-end trainable CNN for survival day prediction based on deep learning techniques for BraTS 2017 prediction task [15, 4, 2, 3]. The experimental results demonstrate the superior ability of the proposed approach for both tasks. The proposed model achieves on validation data a DICE score, Sensitivity and Specificity respectively 0.68, 0.99 and 0.98 for the whole tumor, regarding online judgment system.