Entropy-based deep neural network training optimization for optical coherence tomography imaging

This paper presents an optimization technique for the number of training epochs needed for deep learning models. The proposed method eliminates the need for separate validation data and significantly decreases training epochs. Using a four-class Optical Coherence Tomography (OCT) image dataset encom...

Full description

Saved in:
Bibliographic Details
Main Authors: Karri Karthik, Manjunatha Mahadevappa
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Applied Artificial Intelligence
Online Access:https://www.tandfonline.com/doi/10.1080/08839514.2024.2355760
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846119936804519936
author Karri Karthik
Manjunatha Mahadevappa
author_facet Karri Karthik
Manjunatha Mahadevappa
author_sort Karri Karthik
collection DOAJ
description This paper presents an optimization technique for the number of training epochs needed for deep learning models. The proposed method eliminates the need for separate validation data and significantly decreases training epochs. Using a four-class Optical Coherence Tomography (OCT) image dataset encompassing Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), Drusen, and Normal retina categories, we evaluated twelve architectures. These include general-purpose models (Alexnet, VGG11, VGG13, VGG16, VGG19, ResNet-18, ResNet-34, and ResNet-50) and OCT image-specific models (RetiNet, AOCT-NET, DeepOCT, and Octnet). The proposed technique reduced training epochs ranging from 4.35% to 58.27% for all architectures except Alexnet. Although the overall increase in accuracy ranges from 0.28% to 12.6%, with some architectures experiencing minor improvements, this is seen as acceptable considering the substantial reduction in training time. By achieving higher accuracy with fewer training epochs and eliminating the need for separate validation data, our methodology streamlines early stopping significantly. Statistical evaluations via Shapiro-Wilk and Kruskal-Wallis tests further affirm these results, showcasing the potential of this novel technique for efficient deep learning practices in scenarios constrained by time or computational resources.
format Article
id doaj-art-9cbb1b8daa0c4018a45b7bba09db2f8d
institution Kabale University
issn 0883-9514
1087-6545
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Applied Artificial Intelligence
spelling doaj-art-9cbb1b8daa0c4018a45b7bba09db2f8d2024-12-16T16:13:01ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2355760Entropy-based deep neural network training optimization for optical coherence tomography imagingKarri Karthik0Manjunatha Mahadevappa1School of Medical Science and Technology, Indian Institute of Technology Kharagpur, Kharagpur, IndiaSchool of Medical Science and Technology, Indian Institute of Technology Kharagpur, Kharagpur, IndiaThis paper presents an optimization technique for the number of training epochs needed for deep learning models. The proposed method eliminates the need for separate validation data and significantly decreases training epochs. Using a four-class Optical Coherence Tomography (OCT) image dataset encompassing Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), Drusen, and Normal retina categories, we evaluated twelve architectures. These include general-purpose models (Alexnet, VGG11, VGG13, VGG16, VGG19, ResNet-18, ResNet-34, and ResNet-50) and OCT image-specific models (RetiNet, AOCT-NET, DeepOCT, and Octnet). The proposed technique reduced training epochs ranging from 4.35% to 58.27% for all architectures except Alexnet. Although the overall increase in accuracy ranges from 0.28% to 12.6%, with some architectures experiencing minor improvements, this is seen as acceptable considering the substantial reduction in training time. By achieving higher accuracy with fewer training epochs and eliminating the need for separate validation data, our methodology streamlines early stopping significantly. Statistical evaluations via Shapiro-Wilk and Kruskal-Wallis tests further affirm these results, showcasing the potential of this novel technique for efficient deep learning practices in scenarios constrained by time or computational resources.https://www.tandfonline.com/doi/10.1080/08839514.2024.2355760
spellingShingle Karri Karthik
Manjunatha Mahadevappa
Entropy-based deep neural network training optimization for optical coherence tomography imaging
Applied Artificial Intelligence
title Entropy-based deep neural network training optimization for optical coherence tomography imaging
title_full Entropy-based deep neural network training optimization for optical coherence tomography imaging
title_fullStr Entropy-based deep neural network training optimization for optical coherence tomography imaging
title_full_unstemmed Entropy-based deep neural network training optimization for optical coherence tomography imaging
title_short Entropy-based deep neural network training optimization for optical coherence tomography imaging
title_sort entropy based deep neural network training optimization for optical coherence tomography imaging
url https://www.tandfonline.com/doi/10.1080/08839514.2024.2355760
work_keys_str_mv AT karrikarthik entropybaseddeepneuralnetworktrainingoptimizationforopticalcoherencetomographyimaging
AT manjunathamahadevappa entropybaseddeepneuralnetworktrainingoptimizationforopticalcoherencetomographyimaging