Notification: Our email services are now fully restored after a brief, temporary outage caused by a denial-of-service (DoS) attack. If you sent an email on Dec 6 and haven't received a response, please resend your email.
CFP last date
20 December 2024
Reseach Article

Automatic Identification of Extremely Tiny Brain Hemorrhages in Susceptibility Weighted Images using Convolutional Neural Network

by Sahereh Obeidavi
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 185 - Number 43
Year of Publication: 2023
Authors: Sahereh Obeidavi
10.5120/ijca2023923244

Sahereh Obeidavi . Automatic Identification of Extremely Tiny Brain Hemorrhages in Susceptibility Weighted Images using Convolutional Neural Network. International Journal of Computer Applications. 185, 43 ( Nov 2023), 43-48. DOI=10.5120/ijca2023923244

@article{ 10.5120/ijca2023923244,
author = { Sahereh Obeidavi },
title = { Automatic Identification of Extremely Tiny Brain Hemorrhages in Susceptibility Weighted Images using Convolutional Neural Network },
journal = { International Journal of Computer Applications },
issue_date = { Nov 2023 },
volume = { 185 },
number = { 43 },
month = { Nov },
year = { 2023 },
issn = { 0975-8887 },
pages = { 43-48 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume185/number43/32979-2023923244/ },
doi = { 10.5120/ijca2023923244 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T01:28:33.932998+05:30
%A Sahereh Obeidavi
%T Automatic Identification of Extremely Tiny Brain Hemorrhages in Susceptibility Weighted Images using Convolutional Neural Network
%J International Journal of Computer Applications
%@ 0975-8887
%V 185
%N 43
%P 43-48
%D 2023
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Ischemic stroke is an acute cerebrovascular disease that causes long-term disability and even death. Acute lesions that occur in most stroke patients can be eliminated with careful diagnosis and treatment. The presence of acute lesions in a majority of stroke cases necessitates precise diagnosis and treatment for elimination. Despite the sensitivity of MRI imaging to these lesions, accurately gauging their location and volume manually poses challenges for physicians. The manual examination of numerous MRI-generated cross-sections is time-consuming and susceptible to human error. Consequently, the consensus among medical practitioners is that automated segmentation procedures for ischemic stroke lesions can significantly expedite the commencement of treatment. Various methods have been developed to attain this objective, with deep neural networks emerging as notably effective, producing outcomes that are both superior and more precise. Within the realm of deep learning algorithms, the U-Net algorithm has gained popularity in recent years for its accurate response, high precision, rapid processing and learning capabilities, and its independence from large datasets for learning. The U-Net algorithm has become a favored choice for identifying and segmenting image components in the processing of medical images. The proposed segmentation framework comprises two distinct networks: the U-Net convolutional neural network serves as the primary structure of the model, while the Inception convolutional neural network is integrated into each layer of the U-Net network. Incorporating the Inception network within the U-Net network has notably enhanced segmentation accuracy. This report focuses on elucidating the algorithm's intricacies, encompassing its architectures, pre-processing techniques, data pre-preparation, and post-processing methods. The structural aspects of the algorithm, particularly its convolutional network, are explored in depth. Additionally, the optimal configuration for the algorithm's parameters and super parameters is investigated to enhance and achieve peak accuracy in the segmentation of stroke-related images.

References
  1. Wu, Y. and Chen, T. (2016). An up-to-date review on cerebral microbleeds. Journal of Stroke and Cerebrovas-cular Diseases, 25(6):1301–1306.
  2. Charidimou, A., Krishnan, A., Werring, D. J., and Rolf J¨ager, H. (2013). Cerebral microbleeds: a guide to detection and clinical relevance in different disease settings. Neuroradiology, 55:655–674.
  3. Shams, S., Martola, J., Cavallin, L., Granberg, T., Shams, M., Aspelin, P., Wahlund, L., and Kristoffersen-Wiberg, M. (2015). Swi or t2*: which mri sequence to use in the detection of cerebral microbleeds? The karolinska imaging dementia study. American Journal of Neuroradiology, 36(6):1089–1095.
  4. De Bresser, J., Brundel, M., Conijn, M., Van Dillen, J., Geerlings, M., Viergever, M., Luijten, P., and Biessels, G. (2013). Visual cerebral microbleed detection on 7t mr imaging: reliability and effects of image processing. American Journal of Neuroradiology, 34(6):E61–E64.
  5. Barnes, S. R., Haacke, E. M., Ayaz, M., Boikov, A. S., Kirsch, W., and Kido, D. (2011). Semiautomated detection of cerebral microbleeds in magnetic resonance images. Magnetic resonance imaging, 29(6):844–852.
  6. Fazlollahi, A., Meriaudeau, F., Villemagne, V. L., Rowe, C. C., Yates, P., Salvado, O., and Bourgeat, P. (2014). Efficient machine learning framework for computer-aided detection of cerebral microbleeds using the radon transform. In 2014 IEEE 11th international symposium on biomedical imaging (ISBI), pages 113–116. IEEE.
  7. Dou, Q., Chen, H., Yu, L., Shi, L., Wang, D., Mok, V.C., and Heng, P. A. (2015). Automatic cerebral microbleeds detection from mr images via independent subspace analysis based hierarchical features. In 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pages 7933–7936. IEEE
  8. Wang, S., Jiang, Y., Hou, X., Cheng, H., and Du, S. (2017). Cerebral micro-bleed detection based on the convolution neural network with rank based average pooling. IEEE Access, 5:16576–16583.
  9. Hong, J., Wang, S.-H., Cheng, H., and Liu, J. (2020). Classification of cerebral microbleeds based on fully-optimized convolutional neural network. Multimedia Tools and Applications, 79:15151–15169.
  10. Hong, J., Cheng, H., Zhang, Y.-D., and Liu, J. (2019). Detecting cerebral microbleeds with transfer learning. Machine Vision and Applications, 30:1123–1133.
  11. Q Dou, Q., Chen, H., Yu, L., Zhao, L., Qin, J., Wang, D., Mok, V. C., Shi, L., and Heng, P.-A. (2016). Automatic detection of cerebral microbleeds from mr images via 3d convolutional neural networks. IEEE transactions on medical imaging, 35(5):1182–1195.
  12. Zhang, Y.-D., Hou, X.-X., Chen, Y., Chen, H., Yang, M., Yang, J., and Wang, S.-H. (2018). Voxelwise detection of cerebral microbleed in cadasil patients by leaky rectified linear unit and early stopping. Multimedia Tools and Applications, 77:21825–21845.
Index Terms

Computer Science
Information Sciences

Keywords

Machine Learning Convolutional Neural Network Brain Hemorrhages Stroke Classification.