CSNet: A new DeepNet framework for ischemic stroke lesion segmentation

• Published in: Computer methods and programs in biomedicine 2020-09, Vol.193, p.105524-105524, Article 105524
• Main Authors: Kumar, Amish, Upadhyay, Neha, Ghosal, Palash, Chowdhury, Tamal, Das, Dipayan, Mukherjee, Amritendu, Nandi, Debashis
• Format: Article
• Language: English
• Subjects: Brain Ischemia - diagnostic imaging; Brain stroke; Convolutional network; Humans; Image Processing, Computer-Assisted; Ischemic Stroke; Lesion segmentation; Magnetic Resonance Imaging; MRI; Stroke - diagnostic imaging
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2020.105524

•A deep learning-based hybrid training strategy is designed to perform the task of Ischemic Stroke lesion segmentation.•The architecture combines U-Net and Fractal-Net into one training scheme and employs the concept of a cascaded architecture.•The accuracy of the model is enhanced by removing the redundant parts from the segmenter's input.•A voting mechanism has been made use of to further improve the segmentation accuracy.•The experimental results demonstrate the superiority of the presented method on the ISLES benchmark dataset. Background and objectives: Acute stroke lesion segmentation is of paramount importance as it can aid medical personnel to render a quicker diagnosis and administer consequent treatment. Automation of this task is technically exacting due to the variegated appearance of lesions and their dynamic development, medical discrepancies, unavailability of datasets, and the requirement of several MRI modalities for imaging. In this paper, we propose a composite deep learning model primarily based on the self-similar fractal networks and the U-Net model for performing acute stroke diagnosis tasks automatically to assist as well as expedite the decision-making process of medical practitioners. Methods: We put forth a new deep learning architecture, the Classifier-Segmenter network (CSNet), involving a hybrid training strategy with a self-similar (fractal) U-Net model, explicitly designed to perform the task of segmentation. In fractal networks, the underlying design strategy is based on the repetitive generation of self-similar fractals in place of residual connections. The U-Net model exploits both spatial as well as semantic information along with parameter sharing for a faster and efficient training process. In this new architecture, we exploit the benefits of both by combining them into one hybrid training scheme and developing the concept of a cascaded architecture, which further enhances the model’s accuracy by removing redundant parts from the Segmenter’s input. Lastly, a voting mechanism has been employed to further enhance the overall segmentation accuracy. Results: The performance of the proposed architecture has been scrutinized against the existing state-of-the-art deep learning architectures applied to various biomedical image processing tasks by submission on the publicly accessible web platform provided by the MICCAI Ischemic Stroke Lesion Segmentation (ISLES) challenge. The experimental results demonstrate the superiority o