Publication: Convolution method to enhance angiogram images
| datacite.subject.fos | oecd::Engineering and technology::Electrical engineering, Electronic engineering, Information engineering | |
| dc.contributor.author | Kadir, Nur Iffah Nasuha | |
| dc.date.accessioned | 2024-02-22T04:49:16Z | |
| dc.date.available | 2024-02-22T04:49:16Z | |
| dc.date.issued | 2021-07-01 | |
| dc.description.abstract | X-ray angiography is a standard method for CAD. Coronary angiography is a procedure that uses a special dye which is a contrast material and x-rays to see how blood flows through the arteries in the heart. However, the produced images are low quality images and not always of adequate quality for visual examination. Some unavoidable imaging problems, such as noise, low contrast, motion artifacts caused by heart beating and respiration, integration effects of the catheter, and also the surrounding tissues make the processing of these images more difficult. Therefore, image enhancement is needed to improve image visions while preserving the details of the image structures to get a better interpretation and appropriate clinical decision. This paper aims to employ a pixel-based technique to improve the contrast of the image. The convolution operation is proposed to enhance the angiography image to detect blood vessels in the angiogram images. Pixel-based contrast enhancement methods which are HE, AHE, and CLAHE were compared to convolution operation to get a better-quality image. The quality of the image is evaluated based on the MSE and SSIM values of the image. The evaluation from the qualitative and quantitative analysis shows that AHE is found to be the most suitable method to improve the contrast of the angiogram images with better quality than other methods. | |
| dc.identifier.uri | https://erepo.usm.my/handle/123456789/18429 | |
| dc.language.iso | en | |
| dc.title | Convolution method to enhance angiogram images | |
| dc.type | Resource Types::text::report | |
| dspace.entity.type | Publication | |
| oairecerif.author.affiliation | Universiti Sains Malaysia |