Ischemic Stroke Lesion Segmentation Using Adversarial Learning

TL;DR

This paper introduces an adversarial learning-based segmentation model for ischemic stroke lesions using multi-modal CT data, improving accuracy over baseline methods.

Contribution

The study develops a novel adversarial segmentation framework combining U-Net and FCN discriminator for ischemic stroke lesion detection.

Findings

Achieved 42.10% dice accuracy on training data

Achieved 39% dice accuracy on testing data

Demonstrated effectiveness of adversarial learning in medical image segmentation

Abstract

Ischemic stroke occurs through a blockage of clogged blood vessels supplying blood to the brain. Segmentation of the stroke lesion is vital to improve diagnosis, outcome assessment and treatment planning. In this work, we propose a segmentation model with adversarial learning for ischemic lesion segmentation. We adopt U-Net with skip connection and dropout as segmentation baseline network and a fully connected network (FCN) as discriminator network. Discriminator network consists of 5 convolution layers followed by leaky-ReLU and an upsampling layer to rescale the output to the size of the input map. Training a segmentation network along with an adversarial network can detect and correct higher order inconsistencies between the segmentation maps produced by ground-truth and the Segmentor. We exploit three modalities (CT, DPWI, CBF) of acute computed tomography (CT) perfusion data provided in ISLES 2018 (Ischemic Stroke Lesion Segmentation) for ischemic lesion segmentation. Our model has achieved dice accuracy of 42.10% with the cross-validation of training and 39% with the testing data.