Implementing a non-local means method to CTA data of aortic dissection
It is necessary to conserve important information, like edges, details, and textures, in CT aortic dissection images, as this helps the radiologist examine and diagnose the disease. Hence, a less noisy image is required to support medical experts in performing better diagnoses. In this work, the non...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Diponegoro University
2021-07-01
|
Series: | Jurnal Teknologi dan Sistem Komputer |
Subjects: | |
Online Access: | https://jtsiskom.undip.ac.id/index.php/jtsiskom/article/view/14125 |
_version_ | 1797285493200650240 |
---|---|
author | Maya Fitria Cosmin Adrian Morariu Josef Pauli Ramzi Adriman |
author_facet | Maya Fitria Cosmin Adrian Morariu Josef Pauli Ramzi Adriman |
author_sort | Maya Fitria |
collection | DOAJ |
description | It is necessary to conserve important information, like edges, details, and textures, in CT aortic dissection images, as this helps the radiologist examine and diagnose the disease. Hence, a less noisy image is required to support medical experts in performing better diagnoses. In this work, the non-local means (NLM) method is conducted to minimize the noise in CT images of aortic dissection patients as a preprocessing step to produce accurate aortic segmentation results. The method is implemented in an existing segmentation system using six different kernel functions, and the evaluation is done by assessing DSC, precision, and recall of segmentation results. Furthermore, the visual quality of denoised images is also taken into account to be determined. Besides, a comparative analysis between NLM and other denoising methods is done in this experiment. The results showed that NLM yields encouraging segmentation results, even though the visualization of denoised images is unacceptable. Applying the NLM algorithm with the flat function provides the highest DSC, precision, and recall values of 0.937101, 0.954835, and 0.920517 consecutively. |
first_indexed | 2024-03-07T18:03:57Z |
format | Article |
id | doaj.art-c50b6ecf11484405b4cb6b78b7260b77 |
institution | Directory Open Access Journal |
issn | 2338-0403 |
language | English |
last_indexed | 2024-03-07T18:03:57Z |
publishDate | 2021-07-01 |
publisher | Diponegoro University |
record_format | Article |
series | Jurnal Teknologi dan Sistem Komputer |
spelling | doaj.art-c50b6ecf11484405b4cb6b78b7260b772024-03-02T10:06:18ZengDiponegoro UniversityJurnal Teknologi dan Sistem Komputer2338-04032021-07-019317417910.14710/jtsiskom.2021.1412512869Implementing a non-local means method to CTA data of aortic dissectionMaya Fitria0Cosmin Adrian Morariu1Josef Pauli2https://orcid.org/0000-0003-0363-6410Ramzi Adriman3https://orcid.org/0000-0002-2301-3627Department of Electrical and Computer Engineering, Universitas Syiah Kuala. Jl. Tgk. Syech Abdur Rauf No. 7 Kopelma Darussalam, Banda Aceh 23111, IndonesiaDepartment of Intelligent System, Faculty of Engineering, University of Duisburg-Essen. Bismarckstrasse 90, Building BC, 4. Floor, Duisburg 47057, GermanyDepartment of Intelligent System, Faculty of Engineering, University of Duisburg-Essen. Bismarckstrasse 90, Building BC, 4. Floor, Duisburg 47057, GermanyDepartment of Electrical and Computer Engineering, Universitas Syiah Kuala. Jl. Tgk. Syech Abdur Rauf No. 7 Kopelma Darussalam, Banda Aceh 23111, IndonesiaIt is necessary to conserve important information, like edges, details, and textures, in CT aortic dissection images, as this helps the radiologist examine and diagnose the disease. Hence, a less noisy image is required to support medical experts in performing better diagnoses. In this work, the non-local means (NLM) method is conducted to minimize the noise in CT images of aortic dissection patients as a preprocessing step to produce accurate aortic segmentation results. The method is implemented in an existing segmentation system using six different kernel functions, and the evaluation is done by assessing DSC, precision, and recall of segmentation results. Furthermore, the visual quality of denoised images is also taken into account to be determined. Besides, a comparative analysis between NLM and other denoising methods is done in this experiment. The results showed that NLM yields encouraging segmentation results, even though the visualization of denoised images is unacceptable. Applying the NLM algorithm with the flat function provides the highest DSC, precision, and recall values of 0.937101, 0.954835, and 0.920517 consecutively.https://jtsiskom.undip.ac.id/index.php/jtsiskom/article/view/14125aortic dissectionnoise reductionnon-local means, ct image, denoising method |
spellingShingle | Maya Fitria Cosmin Adrian Morariu Josef Pauli Ramzi Adriman Implementing a non-local means method to CTA data of aortic dissection Jurnal Teknologi dan Sistem Komputer aortic dissection noise reduction non-local means, ct image, denoising method |
title | Implementing a non-local means method to CTA data of aortic dissection |
title_full | Implementing a non-local means method to CTA data of aortic dissection |
title_fullStr | Implementing a non-local means method to CTA data of aortic dissection |
title_full_unstemmed | Implementing a non-local means method to CTA data of aortic dissection |
title_short | Implementing a non-local means method to CTA data of aortic dissection |
title_sort | implementing a non local means method to cta data of aortic dissection |
topic | aortic dissection noise reduction non-local means, ct image, denoising method |
url | https://jtsiskom.undip.ac.id/index.php/jtsiskom/article/view/14125 |
work_keys_str_mv | AT mayafitria implementinganonlocalmeansmethodtoctadataofaorticdissection AT cosminadrianmorariu implementinganonlocalmeansmethodtoctadataofaorticdissection AT josefpauli implementinganonlocalmeansmethodtoctadataofaorticdissection AT ramziadriman implementinganonlocalmeansmethodtoctadataofaorticdissection |