RSANet: Recurrent Slice-wise Attention Network for Multiple Sclerosis Lesion Segmentation
This addresses the time-consuming and operator-dependent manual lesion segmentation problem for multiple sclerosis diagnosis, representing an incremental improvement over existing deep learning methods.
The paper tackles automated segmentation of multiple sclerosis lesions in 3D MRI images by proposing RSANet, a recurrent slice-wise attention network that models images as slice sequences to capture long-range dependencies. Experiments on 43 patients show it outperforms state-of-the-art approaches.
Brain lesion volume measured on T2 weighted MRI images is a clinically important disease marker in multiple sclerosis (MS). Manual delineation of MS lesions is a time-consuming and highly operator-dependent task, which is influenced by lesion size, shape and conspicuity. Recently, automated lesion segmentation algorithms based on deep neural networks have been developed with promising results. In this paper, we propose a novel recurrent slice-wise attention network (RSANet), which models 3D MRI images as sequences of slices and captures long-range dependencies through a recurrent manner to utilize contextual information of MS lesions. Experiments on a dataset with 43 patients show that the proposed method outperforms the state-of-the-art approaches. Our implementation is available online at https://github.com/tinymilky/RSANet.