Forgery Detection in Medical Images: A Case of Covid-19 using Convolutional Neural Network
Volume 18, Issue 1, 2024
Download| Author(s): |
Samar Abbas Mangi Institue of Compuer Science, Shah Abdul Latif University Khairpur, mangisamar@gmail.com Samina Rajper Institue of Compuer Science, Shah Abdul Latif University Khairpur, samina.rajper@salu.edu.pk Noor Ahmed Shaikh Institue of Compuer Science, Shah Abdul Latif University Khairpur, noor.shaikh@salu.edu.pk |
|---|---|
| Abstract | Detecting medical data tampering has emerged as a major challenge in the processing of medical data that is secure-aware. Recently, there has been a growth in the illegal practice of misrepresenting healthy persons in medical records as Covid-19 sufferers. This poses a threat to the integrity of the data, making forgery detection critical. Convolutional neural networks (CNNs) have proven to be effective in detecting anomalies in manipulated data by identifying distortion or tampering in the original data. In order to check the noise pattern in the data, this research uses a CNN-based error level analysis (ELA) approach to detect COVID-19 medical data forgeries. Through the use of data splicing forgery, sigmoid, and ReLU phenomenon methods, the suggested improved ELA method is assessed. Various types of forgeries are applied to COVID-19 data, and the proposed CNN model is then used to detect data tampering, achieving an accuracy of approximately 92%. Clinicians and the AI community are both interested in deploying artificial neural networks in early COVID-19 patient screening for speedy diagnosis as a result of this. |
| Keywords | CNN, covid-19, Machine Learning, forgery detection |
| Year | 2024 |
| Volume | 18 |
| Issue | 1 |
| Type | Research paper, manuscript, article |
| Journal Name | Journal of Information & Communication Technology | Publisher Name | ILMA University | Jel Classification | - | DOI | - | ISSN no (E, Electronic) | 2075-7239 | ISSN no (P, Print) | 2415-0169 | Country | Pakistan | City | Karachi | Institution Type | University | Journal Type | Open Access | Manuscript Processing | Blind Peer Reviewed | Format | Paper Link | https://jict.ilmauniversity.edu.pk/journal/jict/18.1/8.pdf | Page |