A Novel Weighted Average 2D-CNN Ensemble for Intracranial Hemorrhage CT Image Classification
A Novel Weighted Average 2D-CNN Ensemble for Intracranial Hemorrhage CT Image Classification |
||
![]() |
![]() |
|
© 2024 by IJETT Journal | ||
Volume-72 Issue-7 |
||
Year of Publication : 2024 | ||
Author : Santwana Gudadhe, Anuradha Thakare |
||
DOI : 10.14445/22315381/IJETT-V72I7P126 |
How to Cite?
Santwana Gudadhe, Anuradha Thakare, "A Novel Weighted Average 2D-CNN Ensemble for Intracranial Hemorrhage CT Image Classification," International Journal of Engineering Trends and Technology, vol. 72, no. 7, pp. 247-255, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I7P126
Abstract
Rapid and precise diagnosis and treatment of brain hemorrhage is of the highest importance because of the serious danger it presents to human life. Depending on where and how the bleeding is occurring, several distinct kinds of brain hemorrhage can be distinguished. Five subtypes of hemorrhage are covered in the primary division: subdural, epidural, intraventricular, intraparenchymal, and subarachnoid. Intracranial hemorrhage Computed Tomography (CT) image classification using the proposed weighted average 2D-Convolution neural network model has been proposed for intracranial hemorrhage subtype CT image classification. Intracranial hemorrhage subtypes, Intracranial Hemorrhage (ICH), Subdural Hemorrhage (SAH), Epidural Hemorrhage (EDH), and normal subtypes are outlined in this article. Three separate neural network models using two-dimensional convolution were evaluated for the purpose of bleeding subtype classification. Finally, a new ensemble model for a weighted average 2D convolution neural network has been designed. The suggested ensemble model can distinguish between 4 types of hemorrhage. Applying the proposed model to the test dataset reveals a maximum accuracy of 95.86%. In terms of classification, the suggested model can achieve a respectable degree of precision.
Keywords
Intracranial hemorrhage, Convolution neural network, Weighted average 2D-convolution neural network ensemble model, Classification.
References
[1] Charlotte van Asch, “Imaging of Non-Traumatic Intracerebral and Intraventricular Haemorrhage,” Doctoral Thesis, Utrecht University, pp. 1-187, 2015.
[Google Scholar] [Publisher Link]
[2] Zhiwei Shao, Sheng Tu, and Anwen Shao, “Pathophysiological Mechanisms and Potential Therapeutic Targets in Intracerebral Hemorrhage,” Frontiers in Pharmacology, vol. 10, pp. 1-8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Xiyue Wang et al., “A Deep Learning Algorithm for Automatic Detection and Classification of Acute Intracranial Hemorrhages in Head CT Scans,” NeuroImage: Clinical, vol. 32, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Devika Rajashekar, and John W. Liang, Intracerebral Hemorrhage, Treasure Island (FL): StatPearls Publishing, 2024.
[Google Scholar] [Publisher Link]
[5] Mohammad R. Arbabshirani et al., “Advanced Machine Learning in Action: Identification of Intracranial Hemorrhage on Computed Tomography Scans of the Head with Clinical Workflow Integration,” NPJ Digital Medicine, vol. 1, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yu Liu et al., “Image Classification Based on Convolutional Neural Networks with Cross-Level Strategy,” Multimedia Tools and Applications, vol. 76, pp. 11065-11079, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Cristian Simionescu, and Adrian Iftene, “Deep Learning Research Directions in Medical Imaging,” Mathematics, vol. 10, no. 23, pp. 1-25, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Risheng Wang et al., “Medical Image Segmentation Using Deep Learning: A Survey,” IET Image Processing, vol. 16, no. 5, pp. 1243–1267, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ji Young Lee et al., “Detection and Classification of Intracranial Haemorrhage on CT Images Using a Novel Deep-Learning Algorithm,” Scientific Reports, vol. 10, pp. 1-7, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Mohamed Amine Mahjoubi et al., “Deep Learning for Cerebral Hemorrhage Detection and Classification in Head CT Scans Using CNN,” 2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology, Mohammedia, Morocco, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Praveen Kumaravel et al., “A Simplified Framework for the Detection of Intracranial Hemorrhage in CT Brain Images Using Deep Learning,” Current Medical Imaging, vol. 17, no. 10, pp. 1226-1236, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] José-Luis Solorio-Ramírez et al., “Brain Hemorrhage Classification in CT Scan Images Using Minimalist Machine Learning,” Diagnostics, vol. 11, no. 8, pp. 1-37, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mohammed Ammar et al., “Deep Learning Models for Intracranial Hemorrhage Recognition: A Comparative Study,” Procedia Computer Science, vol. 196, pp. 418-425, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Nipa Anjum, Abu Noman Md. Sakib, and Sk. Md. Masudul Ahsan, “Classification of Brain Hemorrhage Using Deep Learning from CT Scan Images,” Proceedings of International Conference on Information and Communication Technology for Development, Studies in Autonomic, Data-driven and Industrial Computing, pp. 181-193, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] C.S.S. Anupama et al., “Synergic Deep Learning Model–Based Automated Detection and Classification of Brain Intracranial Hemorrhage Images in Wearable Networks,” Personal and Ubiquitous Computing, vol. 26, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mia Daugaard Jørgensen et al., “Convolutional Neural Network Performance Compared to Radiologists in Detecting Intracranial Hemorrhage from Brain Computed Tomography: A Systematic Review and Meta-Analysis,” European Journal of Radiology, vol. 146, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Yu-Ruei Chen et al., “An Efficient Deep Neural Network for Automatic Classification of Acute Intracranial Hemorrhages in Brain CT Scans,” Computers in Biology and Medicine, vol. 176, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Brain CT Images with Intracranial Hemorrhage Masks, Kaggle, 2019. [Online]. Available: https://www.kaggle.com/datasets/vbookshelf/computed-tomography-ct-images
[19] Murtadha Hssayeni et al., “Computed Tomography Images for Intracranial Hemorrhage Detection and Segmentation, (Version 1.0.0),” PhysioNet, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Bnsreenu, Python_for_Microscopists, Github. [Online]. Available: https://github.com/bnsreenu/python_for_microscopists/blob/master/091_intro_to_transfer_learning_VGG16.py