Dense Multi-path U-Net for Ischemic Stroke Lesion Segmentation in Multiple Image Modalities
This work addresses the challenge of accurately delineating ischemic stroke lesions for medical diagnosis and treatment, representing an incremental improvement over existing U-Net methods.
The paper tackled the problem of ischemic stroke lesion segmentation by proposing a novel U-Net-based architecture that processes multiple image modalities in separate paths with dense connections and dilated inception modules, achieving improved performance compared to several baselines and a state-of-the-art method (ERFNet) on a dataset of 93 stroke cases.
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.