Ischemic stroke segmentation in multi-sequence MRI by symmetry determined superpixel based hierarchical clustering. (January 2020)

• Record Type: Journal Article
• Authors: Vupputuri, Anusha; Ashwal, Stephen; Tsao, Bryan; Ghosh, Nirmalya
• Is Part Of: Computers in biology and medicine. Volume 116(2020)
• Publication Date: 2020-01
• Subjects: Axial-symmetry -- Hierarchical clustering -- Ischemic stroke -- Multi-sequence MRI -- Superpixel; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2019.103536
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Automated estimation of ischemic stroke evolution across different brain anatomical regions has immense potential to revolutionize stroke treatment. Multi-sequence Magnetic Resonance Imaging (MRI) techniques provide information to characterize abnormal tissues based on their anatomy and physical properties. Asymmetry of the right and left hemispheres of the brain is an important cue for abnormality estimation but using it alone is susceptible to occasional error due to self-asymmetry of the brain. A precise estimate of the symmetry axis is therefore essential for accurate asymmetry identification, which holds the key to the proposed method. The proposed symmetry determined superpixel based hierarchical clustering (SSHC) method initially estimates the lesion from inter-hemispheric asymmetry. This asymmetry further determines the thresholding parameter for hierarchically clustering the superpixels leading to an automated and accurate lesion delineation. A multi-sequence MRI based pipeline also combines the estimations from individual sequences. SSHC is evaluated on different sequences of the Loma Linda University (LLU) dataset with 26 patients and the Ischemic Stroke Lesion Segmentation (ISLES′15) dataset with 28 patients. SSHC eliminates the need for manual determination of threshold for combining the superpixel clusters and is more reliable as it derives the information from the quick estimation of asymmetry. SSHC outperforms the state-of-the-art resulting in a high Dice similarity score of 0.704 ± 0.27 and a recall of 0.85 ± 0.01 which are 6 % and 35 % respectively higher than the challenge winning method. SSHC thus demonstrates a promising potential in the automated detection of (sub-)acute adult ischemic stroke. Graphical abstract: Image 1 Highlights: Automated delineation of ischemic injury in acute and sub-acute stroke. Superpixel based clustering of injury leveraged on asymmetry cue. Validation on two different datasets with mutisequence MRI data. Eliminates the need of high-end computations and training.