Optical Coherence Tomography in Myocardial Infarction Management: Enhancing Precision in Percutaneous Coronary Intervention

Journal of Clinical Medicine, Год журнала: 2024, Номер 13(19), С. 5791 - 5791

Опубликована: Сен. 28, 2024

In acute myocardial infarction (AMI), the urgency of coronary revascularization through percutaneous intervention (PCI) is paramount, offering notable advantages over pharmacologic treatment. However, persistent risk adverse events, including recurrent AMI and heart failure post-revascularization, underscores necessity for enhanced strategies in managing artery disease. Traditional angiography, while widely employed, presents significant limitations by providing only two-dimensional representations complex three-dimensional vascular structures, hampering accurate assessment plaque characteristics stenosis severity. Intravascular imaging, specifically optical coherence tomography (OCT), significantly addresses these with superior spatial resolution compared to intravascular ultrasound (IVUS). Within context AMI, OCT serves dual purposes: as a diagnostic tool accurately identify culprit lesions ambiguous cases guide optimizing PCI procedures. Its capacity differentiate between various mechanisms syndrome, such rupture spontaneous dissection, enhances its potential. Furthermore, facilitates precise lesion preparation, optimal stent sizing, confirms deployment efficacy. Recent meta-analyses indicate that OCT-guided markedly improves safety efficacy revascularization, subsequently decreasing risks mortality complications. This review emphasizes critical role refining patient-specific therapeutic approaches, aligning principles precision medicine enhance clinical outcomes individuals experiencing AMI.

Язык: Английский

---

The potential of artificial intelligence reading label system on the training of ophthalmologists in retinal diseases, a multicenter bimodal multi-disease study

BMC Medical Education, Год журнала: 2025, Номер 25(1)

Опубликована: Апрель 8, 2025

Язык: Английский

---

Advances in OCT Angiography

Translational Vision Science & Technology, Год журнала: 2025, Номер 14(3), С. 6 - 6

Опубликована: Март 7, 2025

Optical coherence tomography angiography (OCTA) is a signal processing and scan acquisition approach that enables OCT devices to clearly identify vascular tissue down the capillary scale. As originally proposed, OCTA included several important limitations, including small fields of view relative allied imaging modalities presence confounding artifacts. New approaches, both hardware software, are solving these problems can now produce high-quality angiograms from throughout retina choroid. Image analysis tools have also improved, enabling data be quantified at high precision used diagnose disease using deep learning models. This review highlights advances trends in technology, focusing on work produced since 2020.

Язык: Английский

---

Classification of OCT Images of the Human Eye Using Mobile Devices

Applied Sciences, Год журнала: 2025, Номер 15(6), С. 2937 - 2937

Опубликована: Март 8, 2025

The aim of this study was to develop a mobile application for Android devices dedicated the classification pathological changes in human eye optical coherence tomography (OCT) B-scans. process is conducted using convolutional neural networks (CNNs). Six models were trained during study: simple network with three layers, VGG16, InceptionV3, Xception, Joint Attention Network + MobileNetV2 and OpticNet-71. All these converted TensorFlow Lite format implement them into application. For purpose, best parameters chosen, taking accuracy, precision, recall, F1-score confusion matrix consideration. designed OCT images developed Kotlin programming language within Studio integrated development environment. With application, can be performed on an image chosen from user’s files or acquired photo-taking function. results are displayed networks, along respective times each associated undergoing task. has been tested various smartphones. testing phase included evaluation score considering factors such as acquisition method, i.e., camera gallery.

Язык: Английский

---

Automatic Segmentation and Statistical Analysis of the Foveal Avascular Zone

Technologies, Год журнала: 2024, Номер 12(12), С. 235 - 235

Опубликована: Ноя. 21, 2024

This study facilitates the extraction of foveal avascular zone (FAZ) metrics from optical coherence tomography angiography (OCTA) images, offering valuable clinical insights and enabling detailed statistical analysis FAZ size shape across three patient groups: healthy, type II diabetes mellitus both (DM) high blood pressure (HBP). Additionally, it evaluates performance four deep learning (DL) models—U-Net, U-Net with DenseNet121, MobileNetV2 VGG16—in automating segmentation FAZ. Manual images by ophthalmological clinicians was performed initially, data augmentation used to enhance dataset for robust model training evaluation. Consequently, original set 103 full retina OCTA extended 672 cases, including 42 normal patients, 357 DM 273 patients HBP. Among models, DenseNet outperformed others, achieving highest accuracy, Intersection over Union (IoU), Dice coefficient all groups. research is distinct in its focus on inclusion hypertension diabetes, an area that less studied existing literature.

Язык: Английский

---

Prediction of fellow eye neovascularization in type 3 macular neovascularization (Retinal angiomatous proliferation) using deep learning

PLoS ONE, Год журнала: 2024, Номер 19(10), С. e0310097 - e0310097

Опубликована: Окт. 30, 2024

Purpose To establish a deep learning artificial intelligence model to predict the risk of long-term fellow eye neovascularization in unilateral type 3 macular (MNV). Methods This retrospective study included 217 patients (199 training/validation AI and 18 testing set) with diagnosis MNV. The purpose was within 24 months after initial diagnosis. data used train baseline fundus image horizontal/vertical cross-hair scan optical coherence tomography images eye. neural network this for AI-learning based on visual geometry group modification. precision, recall, accuracy, area under curve values receiver operating characteristics (AUCROC) were calculated model. accuracy an experienced (examiner 1) less 2) human examiner also evaluated. Results incidence over 28.6% set 38.9% (P = 0.361). In model, precision 0.562, recall 0.714, 0.667, AUCROC 0.675. sensitivity, specificity, 0.429, 0.727, 0.611, respectively, 1, 0.143, 0.636, 0.444, 2. Conclusions is first focusing clinical course While our exhibited comparable that examiners, overall not high. may partly be result relatively small number training, suggesting need future multi-center studies improve

Язык: Английский

---

Evaluating deep learning models for classifying OCT images with limited data and noisy labels

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Дек. 5, 2024

The use of deep learning for OCT image classification could enhance the diagnosis and monitoring retinal diseases. However, challenges like variability in abnormalities, noise, artifacts images limit its clinical use. Our study aimed to evaluate performance various (DL) architectures classifying pathologies versus healthy cases based on images, under data scarcity label noise. We examined five DL architectures: ResNet18, ResNet34, ResNet50, VGG16, InceptionV3. Fine-tuning pre-trained models was conducted 5526 reduced subsets down 21 scarcity. fine-tuned with noise levels 10%, 15%, 20% evaluated. All achieved high accuracy (> 90%) training sets 345 or more images. InceptionV3 highest (99%) when trained entire set. decreased increased as sample size decreased. Label significantly affected model accuracy. Compensating labeling errors requires approximately 4, 9, 14 times set reach correctly labeled results showed that can accurately classify controls. findings highlight while mislabeling impact analysis, this be effectively mitigated by increasing size. By addressing errors, our research aims improve real-world application disease management.

Язык: Английский

---

Novel Application of Non‐Invasive Methodological Approaches in Biomedical Sciences Towards Better Understanding of Marine Teleost Ocular Health and Disease

Journal of Fish Diseases, Год журнала: 2024, Номер unknown

Опубликована: Дек. 16, 2024

ABSTRACT Seafood is an important resource for global nutrition and food security, with both land marine aquaculture playing pivotal roles. High visual acuity key health survival of farmed, cultured, wild fish. Cleaner fish technology to control parasite infestation has become in highlights the importance efficacy cleaner species. New clinical diagnostic approaches towards understanding optimising could benefit aquacultured populations. Opportunities developing using advanced non‐invasive assessment diagnosis ocular wild, experimental are more rapidly realising how threats eye these animals might be better understood mitigated. Ophthalmoscopy can non‐invasively image anatomical aspects retinal anterior tissues been used mammalian biomedicine since turn 20th century. More now than ever, labour‐intensive post‐mortem analysis such as histology increasingly being replaced or supplemented by application various forms optical coherence tomography (OCT) imaging biomedicine. Advances availability other methodological three‐dimensional printing computer science make instrument customisation affordable adaptable. This review article will outline ophthalmoscopy, OCT, methodologies applied teleost species describe some future opportunities that technological advances afford advancing disease general.

Язык: Английский

---

Impact of Histogram Equalization on the Classification of Retina Lesions from OCT B-Scans

Electronics, Год журнала: 2024, Номер 13(24), С. 4996 - 4996

Опубликована: Дек. 19, 2024

Deep learning solutions can be used to classify pathological changes of the human retina visualized in OCT images. Available datasets that train neural network models include images (B-scans) classes with selected and healthy retina. These often require correction due improper acquisition or intensity variations related type device. This article provides a detailed assessment impact preprocessing on classification efficiency. The histograms were examined and, depending histogram distribution, incorrect image fragments removed. At same time, equalization using standard method Contrast-Limited Adaptive Histogram Equalization (CLAHE) was analyzed. most extensive dataset Labeled Optical Coherence Tomography (LOCT) for experimental studies. assessed different architectures various parameters, assuming equal size. Comprehensive studies have shown removing unnecessary white parts from input combined CLAHE improves accuracy up as much 4.75% architecture optimizer type.

Язык: Английский

---

Implications of myopia in diagnosis and screening of open angle glaucoma

Current Opinion in Ophthalmology, Год журнала: 2024, Номер unknown

Опубликована: Дек. 19, 2024

Rapid increase in the prevalence of myopia has been documented worldwide. Myopia, especially high myopia, is not only an important risk factor for having open angle glaucoma (OAG), but also a strong linking with progression OAG. Since myopic axial length (AXL) elongation associated nonglaucomatous optic nerve head (ONH) and visual field abnormalities, poses challenge differential diagnosis This review provides overview literature studying relationships between AXL-elongation prognosis OAG, functional structural changes eye.

Язык: Английский

---