A Novel Fusion Model of Hand-Crafted Features With Deep Convolutional Neural Networks for Classification of Several Chest Diseases Using X-Ray Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F23%3A10252812" target="_blank" >RIV/61989100:27240/23:10252812 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10103528" target="_blank" >https://ieeexplore.ieee.org/document/10103528</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ACCESS.2023.3267492" target="_blank" >10.1109/ACCESS.2023.3267492</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Novel Fusion Model of Hand-Crafted Features With Deep Convolutional Neural Networks for Classification of Several Chest Diseases Using X-Ray Images

Popis výsledku v původním jazyce

The results of recent research suggest that radiological images include important information related several chest diseases. As a result, the use of deep learning to assist in the automated diagnosis of chest diseases may prove useful as a diagnostic tool in the future. In this study, we propose a novel fusion model of hand-crafted features with deep convolutional neural networks (DCNNs) for classifying ten different chest diseases using chest X-rays. The method that has been suggested is split down into three distinct parts. The first step involves utilizing the Info-MGAN network to perform segmentation on the raw CXR data to construct lung images. In the second step, the segmented lung images are fed into a novel pipeline that extracts discriminatory features by using hand-crafted techniques such as SURF and ORB, and then these extracted features are fused to the trained DCNNs. At last, various machine learning models have been used as the last layer of the DCNN models for the classification of chest diseases. Comparison is made between the performance of various proposed architectures for classification, all of which integrate DCNNs, key point extraction methods, and machine learning models. The robustness of the model was further confirmed by statistical analyses of the datasets using McNemar&apos;s and ANOVA tests respectively.

Název v anglickém jazyce

A Novel Fusion Model of Hand-Crafted Features With Deep Convolutional Neural Networks for Classification of Several Chest Diseases Using X-Ray Images

Popis výsledku anglicky

The results of recent research suggest that radiological images include important information related several chest diseases. As a result, the use of deep learning to assist in the automated diagnosis of chest diseases may prove useful as a diagnostic tool in the future. In this study, we propose a novel fusion model of hand-crafted features with deep convolutional neural networks (DCNNs) for classifying ten different chest diseases using chest X-rays. The method that has been suggested is split down into three distinct parts. The first step involves utilizing the Info-MGAN network to perform segmentation on the raw CXR data to construct lung images. In the second step, the segmented lung images are fed into a novel pipeline that extracts discriminatory features by using hand-crafted techniques such as SURF and ORB, and then these extracted features are fused to the trained DCNNs. At last, various machine learning models have been used as the last layer of the DCNN models for the classification of chest diseases. Comparison is made between the performance of various proposed architectures for classification, all of which integrate DCNNs, key point extraction methods, and machine learning models. The robustness of the model was further confirmed by statistical analyses of the datasets using McNemar&apos;s and ANOVA tests respectively.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Access

ISSN

2169-3536

e-ISSN

2169-3536

Svazek periodika

11

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

26

Strana od-do

39243-39268

Kód UT WoS článku

000979908800001

EID výsledku v databázi Scopus

2-s2.0-85153493471