Adversarially Trained Convolutional Neural Networks for Semantic Segmentation of Ischaemic Stroke Lesion using Multisequence Magnetic Resonance Imaging

Abstract

Ischaemic stroke is a medical condition caused by occlusion of blood supply to the brain tissue thus forming a lesion. A lesion is zoned into a core associated with irreversible necrosis typically located at the center of the lesion, while reversible hypoxic changes in the outer regions of the lesion are termed as the penumbra. Early estimation of core and penumbra in ischaemic stroke is crucial for timely intervention with thrombolytic therapy to reverse the damage and restore normalcy. Multisequence magnetic resonance imaging (MRI) is commonly employed for clinical diagnosis. However, a sequence singly has not been found to be sufficiently able to differentiate between core and penumbra, while a combination of sequences is required to determine the extent of the damage. The challenge, however, is that with an increase in the number of sequences, it cognitively taxes the clinician to discover symptomatic biomarkers in these images. In this paper, we present a data-driven fully automated method for estimation of core and penumbra in ischaemic lesions using diffusion-weighted imaging (DWI) and perfusion-weighted imaging (PWI) sequence maps of MRI. The method employs recent developments in convolutional neural networks (CNN) for semantic segmentation in medical images. In the absence of availability of a large amount of labeled data, the CNN is trained using an adversarial approach employing cross-entropy as a segmentation loss along with losses aggregated from three discriminators of which two employ relativistic visual Turing test. This method is experimentally validated on the ISLES-2015 dataset through three-fold cross-validation to obtain with an average Dice score of 0.82 and 0.73 for segmentation of penumbra and core respectively.

A Review on Computer Aided Diagnosis of Acute Brain Stroke

“…Satish et al, presented an automatic method for identification of core and penumbra regions in ischemic lesions using DWI and perfusion-weighted imaging (PWI). In the absence of the availability of more labeled data, the CNN is trained adversarially (i.e., synthesizing images, applying a segmentation loss (cross-entropy)), with aggregated losses from three discriminators (two of which have the relativistic visual Turing test) [155]. Figure 9 shows the stages for lesion segmentation, identification, and classification of stroke regions for deep learning techniques.…”

A Review on Stroke Lesion Analysis in MRI Datasets

“…Sathish et al, [14] illustrated an adversarial learning methodology in deep learning for the semantic segmentation of the brain. Fully automated Convolutional neural network is used to estimate the core and penumbra using sequence maps in MRI.…”

Lung Segmentation and Nodule Detection in Computed Tomography Scan using a Convolutional Neural Network Trained Adversarially using Turing Test Loss

“…In each iteration of training, the discriminator is first trained to performs a Turing test to identify the ground truth (GT) and the segmentation map (Pred.) by presenting them together as the input to the network [12]. The concatenated input tensor of size 2 × 512 × 512 is shuffled along the depth to randomize the order of the two channels as shown in Fig.…”