Pathological changes in optical coherence tomography (OCT) B-scan images complicate the automatic detection of retinal layer boundaries. This study proposes a sequential anatomical surface detection algorithm for extracting the complete retinal layer from pathological OCT images. After speckle noise reduction, the internal limiting membrane (ILM), retinal pigment epithelium (RPE), and lower RPE/BM boundary are sequentially localized according to their anatomical and reflectivity characteristics. The detected surfaces are refined using a local minimum-cost path, and the retinal mask is then generated by fully preserving the region between the ILM and BM boundaries. This approach reduces the risk of losing pathological structures during segmentation, including intraretinal cysts, CNV-related abnormalities, and drusen. The proposed algorithm does not require supervised training and enables the formation of a retinal region of interest for subsequent automated analysis.
| Mualliflar | Юсупов, О.Р., Шамсиева, Х.Г. |
|---|---|
| Jurnal | Рақамли технологияларнинг назарий ва амалий масалалари |
| Nashr sanasi | 2026-08-02 |
| Jild | 9 |
| Son | 3 |
| Betlar | 82-89 |
| Til | Rus |
| DOI | 10.62132/ijdt.v9i3.403 |
DOI: 10.62132/ijdt.v9i3.403 · Maqolaning asl sahifasi
оптическая когерентная томография, патологические B-сканы, сегментация слоя сетчатки, определение анатомических поверхностей, подавление спекл-шума, динамическое программирование, ретинальная область интереса, optical coherence tomography, pathological B-scans, retinal layer segmentation, anatomical surface detection, speckle noise reduction, dynamic programming, retinal region of interest
Trade discounts are among the fastest-acting profit levers available to a distributor of fast-moving consumer goods (FMCG). A distributor typically receives a limited discount budget from the manufacturer and must…
This article investigates the identification of factors influencing the prediction of urbanization levels, using the Samarkand region as a case study. The study analyzed 131 indicators (spanning 2000–2024) encompassing…
The growing volume of big data in modern information technologies necessitates the development of efficient parallel algorithms in cloud computing environments. Existing systems such as Hadoop and Spark face challenges…
This paper presents a comprehensive review of existing methods and approaches for Sound Event Detection (SED) in environmental acoustic monitoring. The theoretical foundations of SED, acoustic feature extraction…
This article analyzes the role of Big Data technologies and Data Mining methods in modern medicine, emphasizing their importance in diagnostics, treatment, disease prediction, and medical data management. It also…
Phishing remains one of the most persistent cybersecurity threats, and URLs are often the earliest observable indicator of an attack. Although existing phishing URL detection methods achieve high accuracy using lexical…
This article proposes an IoT-based automatic system for smart homes that is designed for early fire detection and prevention. The system is built on an Arduino Uno platform and continuously monitors the environment…
Cardiovascular diseases are one of the leading causes of death worldwide, and their early detection is one of the urgent tasks of modern medicine. In recent years, machine learning algorithms have been widely used to…
Maternal mortality in Uzbekistan remains marked by substantial regional heterogeneity: differences between the capital region and several peripheral areas reach three- to fourfold levels, highlighting the need for more…
This article analyzes the medical diagnosis process from a data perspective and describes an approach to formally representing a mixed-type feature space describing a patient's condition. The formation of medical data…
Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar