Computer aided diagnosis using Harris Hawks optimizer with deep learning for pneumonia detection on chest X-ray images

Pneumonia is an infectious disease which causes ulcers of the lungs and remains a significant reason for mortality among children and the elderly globally. An earlier analysis of pneumonia is vital to ensure cure treatment and upsurge survival rates. Chest X-ray (CXR) image is one of the most often...

Full description

Saved in:
Bibliographic Details
Published in:International journal of information technology (Singapore. Online) 2024-03, Vol.16 (3), p.1677-1683
Main Authors: Parthasarathy, V., Saravanan, S.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Imaging
Computer Science
Image Processing and Computer Vision
Machine Learning
Original Research
Pattern Recognition and Graphics
Software Engineering
Vision
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:Pneumonia is an infectious disease which causes ulcers of the lungs and remains a significant reason for mortality among children and the elderly globally. An earlier analysis of pneumonia is vital to ensure cure treatment and upsurge survival rates. Chest X-ray (CXR) image is one of the most often utilized approaches to diagnose pneumonia. However, the analysis of CXRs is a tedious process and is exposed to subjective variability. Many deep learning (DL) approaches for identifying pneumonia in CXR images are presented. Proposing effectual and great DL approaches for classifying and detecting pneumonia is the major goal of this work. This study presents a new Computer Aided Diagnosis using Harris Hawks Optimizer with Deep Learning (CAD-HHODL) method for Pneumonia Detection on CXR Images. The CAD-HHODL method investigates the CXR images for the recognition and classification of pneumonia. To obtain this, the CAD-HHODL method performs image pre-processing using a median filtering (MF) approach. For feature extraction, the residual network (ResNet50) model is used. Besides, the long short-term memory (LSTM) model can be utilized for the detection of pneumonia and its performance can be enriched by the use of the HHO model-based hyperparameter tuning process. The experimental results of the CAD-HHODL method are validated on the benchmark CXR database. The simulation values inferred the high performance of the CAD-HHODL method over other techniques.
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-023-01700-1