Deep Transfer Learning for Automatic Prediction of Hemorrhagic Stroke on CT Images
Article
Rao, B. Nageswara, Mohanty, Sudhansu, Sen, Kamal, Acharya, U. Rajendra, Cheong, Kang Hao and Sabut, Sukanta. 2022. "Deep Transfer Learning for Automatic Prediction of Hemorrhagic Stroke on CT Images." Computational and Mathematical Methods in Medicine. 2022. https://doi.org/10.1155/2022/3560507
Article Title | Deep Transfer Learning for Automatic Prediction of Hemorrhagic Stroke on CT Images |
---|---|
ERA Journal ID | 44832 |
Article Category | Article |
Authors | Rao, B. Nageswara, Mohanty, Sudhansu, Sen, Kamal, Acharya, U. Rajendra, Cheong, Kang Hao and Sabut, Sukanta |
Journal Title | Computational and Mathematical Methods in Medicine |
Journal Citation | 2022 |
Article Number | 3560507 |
Number of Pages | 10 |
Year | 2022 |
Publisher | Hindawi Publishing Corporation |
Place of Publication | United Kingdom |
ISSN | 1748-670X |
1748-6718 | |
Digital Object Identifier (DOI) | https://doi.org/10.1155/2022/3560507 |
Web Address (URL) | https://www.hindawi.com/journals/cmmm/2022/3560507/ |
Abstract | Intracerebral hemorrhage (ICH) is the most common type of hemorrhagic stroke which occurs due to ruptures of weakened blood vessel in brain tissue. It is a serious medical emergency issues that needs immediate treatment. Large numbers of noncontrast-computed tomography (NCCT) brain images are analyzed manually by radiologists to diagnose the hemorrhagic stroke, which is a difficult and time-consuming process. In this study, we propose an automated transfer deep learning method that combines ResNet-50 and dense layer for accurate prediction of intracranial hemorrhage on NCCT brain images. A total of 1164 NCCT brain images were collected from 62 patients with hemorrhagic stroke from Kalinga Institute of Medical Science, Bhubaneswar and used for evaluating the model. The proposed model takes individual CT images as input and classifies them as hemorrhagic or normal. This deep transfer learning approach reached 99.6% accuracy, 99.7% specificity, and 99.4% sensitivity which are better results than that of ResNet-50 only. It is evident that the deep transfer learning model has advantages for automatic diagnosis of hemorrhagic stroke and has the potential to be used as a clinical decision support tool to assist radiologists in stroke diagnosis. |
Keywords | Blood vessels; Deep Transfer Learning; Hemorrhagic Stroke; CT Images; Intracerebral hemorrhage |
ANZSRC Field of Research 2020 | 400306. Computational physiology |
Byline Affiliations | Kalinga Institute of Industrial Technology, India |
Kalinga Institute of Medical Science, India | |
Ngee Ann Polytechnic, Singapore | |
Singapore University of Social Sciences (SUSS), Singapore | |
Asia University, Taiwan | |
Singapore University of Technology and Design |
Permalink -
https://research.usq.edu.au/item/z1vzy/deep-transfer-learning-for-automatic-prediction-of-hemorrhagic-stroke-on-ct-images
Download files
81
total views23
total downloads1
views this month1
downloads this month