Deducting abnormalities in chest X-rays using Gabor filters and deep neural network (DNN)
Chest X-rays are widely used as a diagnostic tool to detect respiratory diseases. The complexity of the texture and structures shown in the resulting images can make their interpretation difficult. A more accurate interpretation would help diagnose respiratory diseases earlier, resulting in more eff...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2024
|
| Online Access: | http://journalarticle.ukm.my/25736/ http://journalarticle.ukm.my/25736/1/16.pdf |
| Summary: | Chest X-rays are widely used as a diagnostic tool to detect respiratory diseases. The complexity of the texture and structures shown in the resulting images can make their interpretation difficult. A more accurate interpretation would help diagnose respiratory diseases earlier, resulting in more effective and timely treatment. In this research, the author proposes a new method for detecting abnormalities in chest X-ray images using Gabor filters and artificial intelligence (AI). Gabor filters are a type of filter that can be used to extract texture features from images. These features can then be used to train a deep neural network (DNN) to detect abnormalities in chest X-rays. The method demonstrates the effectiveness of its approach on a dataset of chest X-rays from the National Institutes of Health (NIH) Chest X-ray Dataset. The method achieved an accuracy of 79% in detecting abnormalities, suggesting that this novel method has the potential to help detect respiratory diseases early and, ultimately, improve the lives of the millions afflicted by such diseases. |
|---|