Purpose: The purpose of this study was to explore the use of fluorescein angiography (FA) images in a convolutional neural network (CNN) in the management of retinopathy of prematurity (ROP).
Methods: The dataset involved a total of 835 FA images of 149 eyes (90 patients), where each eye was associated with a binary outcome (57 "untreated" eyes and 92 "treated"; 308 "untreated" images, 527 "treated"). The resolution of the images was 1600 and 1200 px in 20% of cases, whereas the remaining 80% had a resolution of 640 and 480 px. All the images were resized to 640 and 480 px before training and no other preprocessing was applied. A CNN with four convolutional layers was trained on 90% of the images ( = 752) randomly chosen. The accuracy of the prediction was assessed on the remaining 10% of images ( = 83). Keras version 2.2.0 for R with Tensorflow backend version 1.11.0 was used for the analysis.
Results: The validation accuracy after 100 epochs was 0.88, whereas training accuracy was 0.97. The receiver operating characteristic (ROC) presented an area under the curve (AUC) of 0.91.
Conclusions: Our study showed, we believe for the first time, the applicability of artificial intelligence (CNN) technology in the ROP management driven by FA. Further studies are needed to exploit different fields of applications of this technology.
Translational Relevance: This algorithm is the basis for a system that could be applied to both ROP as well as experimental oxygen induced retinopathy.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7424905 | PMC |
| http://dx.doi.org/10.1167/tvst.9.2.37 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Efficient nonlinear function approximation in analog resistive crossbars for recurrent neural networks.
Nat Commun
January 2025
Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China.
Analog In-memory Computing (IMC) has demonstrated energy-efficient and low latency implementation of convolution and fully-connected layers in deep neural networks (DNN) by using physics for computing in parallel resistive memory arrays. However, recurrent neural networks (RNN) that are widely used for speech-recognition and natural language processing have tasted limited success with this approach. This can be attributed to the significant time and energy penalties incurred in implementing nonlinear activation functions that are abundant in such models.
View Article and Find Full Text PDFA hybrid deep learning air pollution prediction approach based on neighborhood selection and spatio-temporal attention.
Sci Rep
January 2025
School of Architecture and Urban Planning, Beijing University of Civil Engineering and Architecture, Beijing, 100055, China.
Air pollution is a critical global environmental issue, further exacerbated by rapid industrialization and urbanization. Accurate prediction of air pollutant concentrations is essential for effective pollution prevention and control measures. The complex nature of pollutant data is influenced by fluctuating meteorological conditions, diverse pollution sources, and propagation processes, underscores the crucial importance of the spatial and temporal feature extraction for accurately predicting air pollutant concentrations.
View Article and Find Full Text PDFOptimized sequential model for superior classification of plant disease.
Sci Rep
January 2025
D. Y. Patil Agriculture and Technical University, Talsande, Maharashtra, India.
Indian agriculture is vital sector in the country's economy, providing employment and sustenance to millions of farmers. However, Plant diseases are a serious risk to crop yields and farmers' livelihoods. Traditional plant disease diagnosis methods rely heavily on human expertise, which can lead to inaccuracies due to the invisible nature of early disease symptoms and the labor-intensive process, making them inefficient for large-scale agricultural management.
View Article and Find Full Text PDFEnhanced hybrid attention deep learning for avocado ripeness classification on resource constrained devices.
Sci Rep
January 2025
Faculty of Science and Technology, Suan Sunandha Rajabhat University, Bangkok, 10300, Thailand.
Attention mechanisms such as the Convolutional Block Attention Module (CBAM) can help emphasize and refine the most relevant feature maps such as color, texture, spots, and wrinkle variations for the avocado ripeness classification. However, the CBAM lacks global context awareness, which may prevent it from capturing long-range dependencies or global patterns such as relationships between distant regions in the image. Further, more complex neural networks can improve model performance but at the cost of increasing the number of layers and train parameters, which may not be suitable for resource constrained devices.
View Article and Find Full Text PDFImproving Nanoparticle Size Estimation from Scanning Transmission Electron Micrographs with a Multislice Surrogate Model.
Nano Lett
January 2025
Electron Microscopy Center, Empa - Swiss Federal Laboratories for Materials Science and Technology, Überlandstrasse 129, 8600 Dübendorf, Switzerland.
The computational cost of simulating scanning transmission electron microscopy (STEM) images limits the curation of large enough data sets to train accurate and robust machine learning networks for deep feature extraction from atomically resolved STEM images. For nanoparticle size estimation in particular, a diverse data set is essential due to the large variations in size, shape, crystallinity, orientation, and dynamical diffraction effects in experimental data. To address this, we train a 3D convolutional neural network to predict STEM images from voxelized atomic models, achieving a 100x speed-up compared to traditional multislice simulations while maintaining high image quality.
View Article and Find Full Text PDFWant 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!