Year: 2024
Type: article
Abstract: Glioma is an abnormal, irregularly shaped cell growth in the brain. Diagnosing glioma often relies on magnetic resonance imaging (MRI), which requires precise segmentation of the tumor for effective analysis. Convolutional Neural Networks (CNN), such as U-Net, is widely used in medical image processing, particularly for image segmentation tasks. However, CNNs have the limitation in effectively learning spatial relationships within images. To address this, Capsule Networks (CapsNet) is introduced, utilizing capsule dynamic routing to better capture spatial hierarchies. This paper aims to investigate the performance of SegCaps, a segmentation model based on Capsule Networks, for brain glioma segmentation in MRI images, compared to the CNN-based U-Net model. Both models were tested on the BraTS2018 glioma dataset, which includes 374 MRI images of brain tumors across four modalities (T1, T1c, T2, FLAIR). The performance of SegCaps and U-Net was evaluated using two key segmentation metrics: Dice coefficient and Jaccard index. The results show that SegCaps outperformed U-Net with a Dice coefficient of 87.96% compared to U-Nets 85.56%, demonstrating a 2.4% improvement. Additionally, SegCaps required fewer parameters than the U-Net model, highlighting its efficiency. In conclusion, SegCaps can be considered as a promising alternative for glioma segmentation in MRI images. Future work could focus on refining the SegCaps model to enhance its performance while reducing computational costs.
Authors: Yasmin Farisya Norazlan, Siti Salasiah Mokri, Nurul Fatihah Ali, Ashrani Aizuddin Abd Rahni, Aqilah Baseri Huddin, Noraishikin Zulkarnain, Ahmad Abid Hakimi Md Salleh, Nor Aziyatul Izni
Institutions: National University of Malaysia, Universiti Teknologi MARA
Language: English
Subfield: Neurology
Field: Neuroscience
Domain: Life Sciences
Open Access status: hybrid
OpenAlex ID: W4403606659