Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection

TL;DR

This paper introduces a neural network-based method for automatic segmentation of ischemic regions in stroke patients using multi-input parametric maps, achieving performance comparable to expert annotations.

Contribution

The paper presents a novel multi-input neural network with slow fusion and a focal Tversky loss for improved ischemic region segmentation in stroke imaging.

Findings

Dice coefficient of 0.81 for penumbra

Dice coefficient of 0.52 for core

Effective performance comparable to neuroradiologists

Abstract

Time is a fundamental factor during stroke treatments. A fast, automatic approach that segments the ischemic regions helps treatment decisions. In clinical use today, a set of color-coded parametric maps generated from computed tomography perfusion (CTP) images are investigated manually to decide a treatment plan. We propose an automatic method based on a neural network using a set of parametric maps to segment the two ischemic regions (core and penumbra) in patients affected by acute ischemic stroke. Our model is based on a convolution-deconvolution bottleneck structure with multi-input and slow fusion. A loss function based on the focal Tversky index addresses the data imbalance issue. The proposed architecture demonstrates effective performance and results comparable to the ground truth annotated by neuroradiologists. A Dice coefficient of 0.81 for penumbra and 0.52 for core over the large vessel occlusion test set is achieved. The full implementation is available at: https://git.io/JtFGb.