Purpose: To determine if macular thickness maps (MTMs) are sufficient to guide management of eyes with exudative age-related macular degeneration (eAMD), we compared the ability to detect change using MTMs with the ability to detect change using the entire optical coherence tomography (OCT) scan in patients undergoing therapy.
Design: Retrospective, comparative diagnostic analysis.
Methods: Patients with eAMD were imaged using macula-centered 6 × 6-mm OCT scans (CIRRUS HD-OCT 5000; Zeiss). In each case, graders were asked to determine if there were changes that warranted a full clinical assessment after viewing 2 consecutive scans using one of 3 different imaging strategies: MTMs alone, individual foveal-centered B scans alone, or 5 macular B scans including the foveal-centered B scan. Graders were told the 2 scans were taken 2 weeks apart. The consensus ground truth was reached by the graders using a CIRRUS review station to evaluate all the information contained within the OCT scans.
Results: A total of 53 eyes were included in this study with 1385 imaging sessions. The Fleiss kappa was highest when graders were given MTMs alone compared with the ground truth. When the averages of all 5 graders were compared with the ground truth, the MTMs alone showed the highest level of agreement (90.05%, SD 0.78%) followed by the central B scans (87.87%, SD 1.59%) and the 5-B scan method (86.512%, SD 0.64%).
Conclusion: MTMs alone provide sufficient information to easily identify recurrent exudation in patients with eAMD, and these maps may be all that is needed for remote monitoring.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10808271 | PMC |
| http://dx.doi.org/10.1016/j.ajo.2023.07.014 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Frontal plane mechanical leg alignment estimation from knee x-rays using deep learning.
Osteoarthr Cartil Open
March 2025
Department for Health Sciences, Medicine and Research, University of Continuing Education Krems, Krems, Austria.
Objective: Lower limb malalignment can complicate symptoms and accelerate knee osteoarthritis (OA), necessitating consideration in study population selection. In this study, we develop and validate a deep learning model that classifies leg alignment as "normal" or "malaligned" from knee antero-posterior (AP)/postero-anterior (PA) radiographs alone, using an adjustable hip-knee-ankle (HKA) angle threshold.
Material And Methods: We utilized 8878 digital radiographs, including 6181 AP/PA full-leg x-rays (LLRs) and 2697 AP/PA knee x-rays (2292 with positioning frame, 405 without).
Phantom evaluation of feasibility and applicability of artificial intelligence based pulmonary nodule detection in chest radiographs.
Medicine (Baltimore)
November 2024
Department of Radiology, Kantonsspital Baden, affiliated Hospital for Research and Teaching of the Faculty of Medicine of the University of Zurich, Baden, Switzerland.
The aim of our study was to evaluate the specific performance of an artificial intelligence (AI) algorithm for lung nodule detection in chest radiography for a larger number of nodules of different sizes and densities using a standardized phantom approach. A total of 450 nodules with varying density (d1 to d3) and size (3, 5, 8, 10 and 12 mm) were inserted in a Lungman phantom at various locations. Radiographic images with varying projections were acquired and processed using the AI algorithm for nodule detection.
View Article and Find Full Text PDFAECuration: Automated event curation for spike sorting.
J Neural Eng
January 2025
Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213, UNITED STATES.
Spike sorting is a commonly used analysis method for identifying single-units and multi-units from extracellular recordings. The extracellular recordings contain a mixture of signal components, such as neural and non-neural events, possibly due to motion and breathing artifacts or electrical interference. Identifying single and multi-unit spikes using a simple threshold-crossing method may lead to uncertainty in differentiating the actual neural spikes from non-neural spikes.
View Article and Find Full Text PDFContinuous single-ended depth-of-interaction measurement using highly multiplexed signals and artificial neural networks.
Phys Med Biol
January 2025
Department of Nuclear Medicine, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03080, Korea (the Republic of).
This study aims to enhance positron emission tomography (PET) imaging systems by developing a continuous depth-of-interaction (DOI) measurement technique using a single-ended readout. Our primary focus is on reducing the number of readout channels in the scintillation detectors while maintaining accurate DOI estimations, using a high-pass filter-based signal multiplexing technique combined with artificial neural networks (ANNs). Approach: Instead of reading out all 64 signals from an 8×8 silicon photomultiplier array for DOI estimation, the proposed method technique reduces the signals into just four channels by applying high-pass filters with different time constants.
View Article and Find Full Text PDFMetastatic Lung Lesion Changes in Follow-up Chest CT: The Advantage of Deep Learning Simultaneous Analysis of Prior and Current Scans With SimU-Net.
J Thorac Imaging
September 2024
School of Computer Science and Engineering, The Hebrew University of Jerusalem.
Purpose: Radiological follow-up of oncology patients requires the detection of metastatic lung lesions and the quantitative analysis of their changes in longitudinal imaging studies. Our aim was to evaluate SimU-Net, a novel deep learning method for the automatic analysis of metastatic lung lesions and their temporal changes in pairs of chest CT scans.
Materials And Methods: SimU-Net is a simultaneous multichannel 3D U-Net model trained on pairs of registered prior and current scans of a patient.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!