Dense Multi-path U-Net for Ischemic Stroke Lesion Segmentation in Multiple Image Modalities

TL;DR

This paper introduces a novel multi-path, densely-connected U-Net architecture with dilated convolutions for improved ischemic stroke lesion segmentation across multiple imaging modalities, demonstrating superior performance over existing methods.

Contribution

The work presents a new multi-path, densely-connected U-Net with extended inception modules and dilated convolutions, enhancing lesion segmentation accuracy in multi-modal stroke imaging.

Findings

Achieved improved segmentation accuracy over baseline models.

Training time was approximately 5 hours on a TITAN XP GPU.

Segmentation speed ranged from 0.2 to 2 seconds per volume.

Abstract

Delineating infarcted tissue in ischemic stroke lesions is crucial to determine the extend of damage and optimal treatment for this life-threatening condition. However, this problem remains challenging due to high variability of ischemic strokes' location and shape. Recently, fully-convolutional neural networks (CNN), in particular those based on U-Net, have led to improved performances for this task. In this work, we propose a novel architecture that improves standard U-Net based methods in three important ways. First, instead of combining the available image modalities at the input, each of them is processed in a different path to better exploit their unique information. Moreover, the network is densely-connected (i.e., each layer is connected to all following layers), both within each path and across different paths, similar to HyperDenseNet. This gives our model the freedom to learn the scale at which modalities should be processed and combined. Finally, inspired by the Inception architecture, we improve standard U-Net modules by extending inception modules with two convolutional blocks with dilated convolutions of different scale. This helps handling the variability in lesion sizes. We split the 93 stroke datasets into training and validation sets containing 83 and 9 examples respectively. Our network was trained on a NVidia TITAN XP GPU with 16 GBs RAM, using ADAM as optimizer and a learning rate of 1$\times$10$^{-5}$ during 200 epochs. Training took around 5 hours and segmentation of a whole volume took between 0.2 and 2 seconds, as average. The performance on the test set obtained by our method is compared to several baselines, to demonstrate the effectiveness of our architecture, and to a state-of-art architecture that employs factorized dilated convolutions, i.e., ERFNet.