Developing New Fully Connected Layers for Convolutional Neural Networks with Hyperparameter Optimization for Improved Multi-Label Image Classification

Author:

Katona Tamás12ORCID,Tóth Gábor3ORCID,Petró Mátyás4ORCID,Harangi Balázs2ORCID

Affiliation:

1. Doctoral School of Informatics, University of Debrecen, 4032 Debrecen, Hungary

2. Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, 4028 Debrecen, Hungary

3. Department of Laboratory Medicine, Faculty of Medicine, University of Debrecen, 4032 Debrecen, Hungary

4. Department of Radiology, Medical Imaging Insitute, Faculty of Medicine, University of Debrecen, 4032 Debrecen, Hungary

Abstract

Chest X-ray evaluation is challenging due to its high demand and the complexity of diagnoses. In this study, we propose an optimized deep learning model for the multi-label classification of chest X-ray images. We leverage pretrained convolutional neural networks (CNNs) such as VGG16, ResNet 50, and DenseNet 121, modifying their output layers and fine-tuning the models. We employ a novel optimization strategy using the Hyperband algorithm to efficiently search the hyperparameter space while adjusting the fully connected layers of the CNNs. The effectiveness of our approach is evaluated on the basis of the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metric. Our proposed methodology could assist in automated chest radiograph interpretation, offering a valuable tool that can be used by clinicians in the future.

Funder

National Research, Development and Innovation Fund of Hungary

Publisher

MDPI AG

Reference41 articles.

1. Viral pneumonia;Ruuskanen;Lancet,2011

2. The US radiologist workforce: An analysis of temporal and geographic variation by using large national datasets;Rosenkrantz;Radiology,2016

3. Diagnostic radiology in Liberia: A country report;Ali;J. Glob. Radiol.,2015

4. X-ray use in chest imaging in emergency department on the basis of cost and effectiveness;Fatihoglu;Acad. Radiol.,2016

5. Pneumothorax;Noppen;Respiration,2008

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