DSA-Net : A Novel Approach for Brain Tumor Segmentation
DOI:
https://doi.org/10.17010/ijcs/2025/v10/i2/175107Keywords:
Attention
, Deep learning, dice, MRI, segmentation.Paper Submission Date
, February 2, 2025, Paper sent back for Revision, February 15, Paper Acceptance Date, March 20, Paper Published Online, April 5, 2025.Abstract
A brain tumor develops due to an abnormal proliferation of cells within the brain tissue. Early detection is crucial for patient safety, and Magnetic Resonance Imaging (MRI) scans are commonly used for diagnosing brain tumors. However, due to the diverse shapes and locations of tumors in the brain, accurate segmentation of tumors in MRI images remains a challenge for physicians. The variability in tumor appearance, often influenced by factors such as edema, necrosis, and surrounding healthy tissues, makes precise delineation difficult. Precise segmentation is essential for identifying the tumor and providing appropriate treatment. It allows clinicians to measure the tumor’s size and progression over time, enabling personalized treatment adjustments based on the individual patient’s response. This study introduces a novel deep learning technique called Depthwise Separable Attention Network (DSA-Net) for automatic tumor segmentation. The proposed DSA-Net model demonstrates a significantly higher Dice coefficient compared to existing models, indicating its effectiveness in brain tumor segmentation.
Downloads
Published
How to Cite
Issue
Section
References
P. K. Mandal, R. Mahajan, and I. D. Dinov, “Structural brain atlases: Design rationale and applications in normal and pathological cohorts,†J. Alzheimer's Disease, vol. 31, no. s3, pp. S169–S188, Sep. 2012.
J. B. Colby, L. Soderberg, C. Lebel, I. D. Dinov, P. M. Thompson, and R. Sowell, “Along-tract statistics allow for enhanced tractography analysis,†Neuroimage, vol. 59, no. 4, pp. 3227–3242, Feb. 2012, doi: 10.1016/j.neuroimage.2011.11.004.
Y. Tang, C. Hojatkashani, I. D. Dinov, B. Sun, L. Fan, X. Lin, H. Qi, X. Hua, S. Liu, and A. W. Toga, “The construction of a Chinese MRI brain atlas: A morphometric comparison study between Chinese and Caucasian cohorts,†NeuroImage, vol. 51, no. 1, pp. 33–41, May 2010, doi: 10.1016/j.neuroimage.2010.01.111.
M. A. Ottom, “Convolutional neural network for diagnosing skin cancer,†Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 7, pp. 333–338, 2019.
I. D. Dinov, Data Science and Predictive Analytics, Cham, Switzerland: Springer, 2018.
I. D. Dinov and M. V. Velev, Data Science: Time Complexity Inferential Uncertainty and Spacekime Analytics, Berlin, Germany: Walter de Gruyter, 2021.
M. A. B. Ahmad, Mining Health Data for Breast Cancer Diagnosis Using Machine Learning, Canberra, ACT, Australia: Univ. of Canberra, 2013.
M. A. Ottom and K. M. Nahar, “Computer aided diagnosis for chronic kidney disease using data mining,†Int. J. Cyber-Security Digital Forensics, vol. 8, no. 3, pp. 188–193, 2019, doi: 10.17781/P002607.
Y. Al-Issa, M. A. Ottom and A. Tamrawi, “eHealth cloud security challenges: A survey,†J. Healthcare Eng., vol. 2019, pp. 1–15, Sep. 2019, doi: 10.1155/2019/7516035.
T. Kapur, J. Egger, J. Jayender, M. Toews, and W. M. Wells, “Registration and segmentation for image-guided therapy,†in F. Jolesz (eds) Intraoperative Imaging Image-Guided Therapy, New York, NY, USA: Springer, 2014, pp. 79–91, doi: 10.1007/978-1-4614-7657-3_5.
O. Hiwaki, “Novel technique for noninvasive detection of localized dynamic brain signals by using transcranial static magnetic fields,†IEEE J. Transl. Eng. Health Med., vol. 9, pp. 1-6, 2021.
M. A. Ottom, H. A. Rahman, and I. D. Dinov, “Znet: Deep Learning approach for 2D MRI brain tumor segmentation,†IEEE J. Translational Eng. Health Medicine, vol. 10, pp. 1–8, 2022, Art no. 1800508, doi: 10.1109/jtehm.2022.3176737.
P. Zheng, X. Zhu, and W. Guo, “Brain tumour segmentation based on an improved U-Net,†BMC Medical Imaging, vol. 22, no. 1, Art. no. 199, Nov. 2022, doi: 10.1186/s12880-022-00931-1.
G. Wang, W. Li, S. Ourselin, and T. Vercauteren, “Automatic brain tumor segmentation based on cascaded convolutional neural networks with uncertainty estimation,†Frontiers Computational Neuroscience, vol. 13, Aug. 2019, doi: 10.3389/fncom.2019.00056.
A. Myronenko, “3D MRI brain tumor segmentation using autoencoder regularization,†Nov. 2018, doi: 10.48550/arXiv.1810.11654.
J. Cheng Dataset. [Online]. Available: 10.6084/m9.figshare.1512427.v8.
Brain Tumor Segmentation Dataset [Online]. Available: https://www.kaggle.com/datasets/nikhilroxtomar/brain-tumor-segmentation/data
