Arvyandita, Talitha Bertha (2026) A Comparative Multi Method Study For Cardiac Ultrasound Image Enhancement Using Retinex Based. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
21081010253.-cover.pdf Download (564kB) |
|
|
Text (Bab 1)
21081010253.-bab1.pdf Download (517kB) |
|
|
Text (Bab 2)
21081010253.-bab2.pdf Restricted to Repository staff only until 24 July 2029. Download (1MB) | Request a copy |
|
|
Text (Bab 3)
21081010253.-bab3.pdf Restricted to Repository staff only until 24 July 2029. Download (1MB) | Request a copy |
|
|
Text (Bab 4)
21081010253.-bab4.pdf Restricted to Repository staff only until 24 July 2029. Download (1MB) | Request a copy |
|
|
Text (Bab 5)
21081010253.-bab5.pdf Download (343kB) |
|
|
Text (Daftar Pustaka)
21081010253.-daftarpustaka.pdf Download (347kB) |
Abstract
Cardiovascular disease is the leading cause of death worldwide, making accurate diagnosis essential. Cardiac ultrasound (echocardiography) is a commonly used imaging modality, yet its images often suffer from low visual quality due to speckle noise, poor contrast, and uneven illumination. This study conducts a multi-method comparative analysis for cardiac ultrasound image enhancement using Retinex-based methods, namely Single Scale Retinex (SSR), Multi Scale Retinex (MSR), and Multi Scale Retinex with Color Restoration (MSRCR), combined with Bilateral Filter and Median Filter preprocessing, together with Contrast Limited Adaptive Histogram Equalization (CLAHE) as a non-Retinex comparison method. The cardiac ultrasound dataset was obtained from the Unity Public Portal, focusing on the parasternal long axis (PLAX) view. Six enhancement combinations (K1–K6) together with CLAHE were evaluated quantitatively using PSNR, SSIM, Entropy, and CII metrics. The results show that Retinex-based methods excel in Entropy (average 7.07) and CII (average 1.22), which are most relevant to the enhancement objective, whereas CLAHE excels in PSNR (24.32 dB) and SSIM (0.5383). Based on the aggregate score of the four metrics, stability, and the percentage of images with CII greater than 1, the K1 combination (Bilateral Filter + SSR) was determined to be the most optimal, achieving the lowest aggregate score (2.50), the highest Entropy (7.3040), and a CII > 1 percentage of 95.95%. This combination enhances contrast smoothly and evenly without introducing artifacts that interfere with clinical interpretation, making it the most suitable for cardiac ultrasound image enhancement. Keywords: cardiac ultrasound, echocardiography, image enhancement, Retinex, SSR, MSR, MSRCR, CLAHE.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76.6 Computer Programming Q Science > QA Mathematics > QA76.87 Neural computers |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Talitha Bertha Arvyandita | ||||||||||||
| Date Deposited: | 24 Jul 2026 06:51 | ||||||||||||
| Last Modified: | 24 Jul 2026 08:09 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/57984 |
Actions (login required)
![]() |
View Item |
