Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural Network
This work addresses the need for automated diagnostic tools in clinical settings where medical resources are scarce, offering a solution for stroke diagnosis, though it appears incremental in its approach.
The authors tackled automated segmentation of ischemic stroke lesions from multimodal MR images using a deep learning method, achieving a mean dice coefficient of 0.645 and a mean false negative lesion count of 1.515, which is close to human doctor performance.
The patient with ischemic stroke can benefit most from the earliest possible definitive diagnosis. While the high quality medical resources are quite scarce across the globe, an automated diagnostic tool is expected in analyzing the magnetic resonance (MR) images to provide reference in clinical diagnosis. In this paper, we propose a deep learning method to automatically segment ischemic stroke lesions from multi-modal MR images. By using atrous convolution and global convolution network, our proposed residual-structured fully convolutional network (Res-FCN) is able to capture features from large receptive fields. The network architecture is validated on a large dataset of 212 clinically acquired multi-modal MR images, which is shown to achieve a mean dice coefficient of 0.645 with a mean number of false negative lesions of 1.515. The false negatives can reach a value that close to a common medical image doctor, making it exceptive for a real clinical application.