A Novel Dual Feature Extraction using Fine-Tuned ResNet with GWO and Deep Dense Neural Network for Multiple Lung Disease Classification

Author:

Kauhsik Baijnath1,khan yusera farooq1,Chadha Akshma1,Ashok Malvika1,Pant Pushpesh Gokul1

Affiliation:

1. SMVDU: Shri Mata Vaishno Devi University

Abstract

Abstract

Lung diseases are one of the primary causes of mortality worldwide. The majority of lung disorders are not discovered until they have progressed significantly. Therefore, the development of systems and methods that allow for immediate and earlier diagnosis will play a crucial role in the modern world. Computer Aided Diagnosis (CADx) systems presently performs this role and are being expanded. This study investigates the feasibility of employing methods for learning features from fine-tuned adaptive learning rate deep learning architectures to provide robust and comprehensive features on NIH Chest X-ray Dataset for three class (are Cardiomegaly, Emphysema, and Hernia) lung disease. A novel dual feature extraction using residual networks with nature inspired Gray Wolf Optimization (GWO) algorithm and Deep Dense Neural Network (ResNet-GWO-DD) is proposed in this study. Dual feature extraction is experimented using two fine-tuned ResNet-50 and ResNet-101 Transfer Learning (TL) architectures. The deep learned features were optimized using Grey Wolf Optimization (GWO). The global best optimal features extracted using GWO are combined for classification using Deep Dense Neural Network. The dual learning of deep features using ResNet-50 and ResNet-101 help the GWO to learn global best optimal features. These dual learning capabilities greatly enhance the performance of the proposed model and achieve significant accuracy while comparing the state-of-the-art methods. The performance of proposed method is further evaluated using three different optimizers such as Adam, stochastic gradient descent (SGD), and Continuous Coin Betting (COCOB). Deep features extracted using GWO and optimizer Adam has yielded maximum accuracy of 99.68%, 96.63% and 96.58% for Hernia, Emphysema, and Cardiomegaly respectively compared to SGD and COCOB.

Publisher

Research Square Platform LLC

Reference38 articles.

1. A multichannel EfficientNet deep learning-based stacking ensemble approach for lung disease detection using chest X-ray images;Ravi V;Cluster Comput,2023

2. Amin H, Siddiqui WJ (2021) Cardiomegaly. StatPearls [internet]. StatPearls Publishing

3. Emphysema: definition, imaging, and quantification;Thurlbeck WM;AJR Am J Roentgenol,1994

4. Lung hernia-a review;Weissberg D;AdvClinExp Med,2013

5. Etiologic classification of diffuse parenchymal (interstitial) lung diseases;Griese M;J Clin Med,2022

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3