Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images

Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of...

Full description

Saved in:
Bibliographic Details
Published in:Diagnostics (Basel) Vol. 11; no. 12; p. 2183
Main Authors: Thambawita, Vajira, Strümke, Inga, Hicks, Steven A., Halvorsen, Pål, Parasa, Sravanthi, Riegler, Michael A.
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 24.11.2021
MDPI
Subjects:
Automation
Classification
convolutional neural networks
Datasets
Deep learning
endoscopic images
Endoscopy
Experiments
image resolution
Neural networks
Performance evaluation
endoscopic images
image resolution
convolutional neural networks
ISSN:2075-4418, 2075-4418
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Consultant Covidien LP; Medical advisory board-Fujifilm.
Board member of Augere Medical.
ISSN:2075-4418
2075-4418
DOI:10.3390/diagnostics11122183