Facilitating deep learning through preprocessing of optical coherence tomography images

While deep learning has delivered promising results in the field of ophthalmology, the hurdle to complete a deep learning study is high. In this study, we aim to facilitate small scale model trainings by exploring the role of preprocessing to reduce computational burden and accelerate learning. A sm...

Full description

Saved in:
Bibliographic Details
Published in:BMC ophthalmology 2023-04, Vol.23 (1), p.158-158, Article 158
Main Authors: Li, Anfei, Winebrake, James P, Kovacs, Kyle
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial Intelligence
Computer applications
Datasets
Deep Learning
Diabetes mellitus
Edema
Humans
Machine learning
Ophthalmology
Optical coherence tomography
Preprocessing
Retina
Study and teaching
Tomography
Tomography, Optical Coherence - methods
Vascularization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:While deep learning has delivered promising results in the field of ophthalmology, the hurdle to complete a deep learning study is high. In this study, we aim to facilitate small scale model trainings by exploring the role of preprocessing to reduce computational burden and accelerate learning. A small subset of a previously published dataset containing optical coherence tomography images of choroidal neovascularization, drusen, diabetic macula edema, and normal macula was modified using Fourier transformation and bandpass filter, producing high frequency images, original images, and low frequency images. Each set of images was trained with the same model, and their performances were compared. Compared to that with the original image dataset, the model trained with the high frequency image dataset achieved an improved final performance and reached maximum performance much earlier (in fewer epochs). The model trained with low frequency images did not achieve a meaningful performance. Appropriate preprocessing of training images can accelerate the training process and can potentially facilitate modeling using artificial intelligence when limited by sample size or computational power.
ISSN:1471-2415
1471-2415
DOI:10.1186/s12886-023-02916-2