An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images

The field of explainable artificial intelligence (XAI) aims to build explainable and interpretable machine learning (or deep learning) methods without sacrificing prediction performance. Convolutional neural networks (CNNs) have been successful in making predictions, especially in image classificati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shaw-Hwa Lo, Yiqiao Yin
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	explainable artificial intelligence convolutional neural networks deep learning Chest X-ray Image I-score Industrial engineering. Management engineering T55.4-60.8 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/53ec9eee07714ac8a782832afb013df0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:53ec9eee07714ac8a782832afb013df0
record_format	dspace
spelling	oai:doaj.org-article:53ec9eee07714ac8a782832afb013df02021-11-25T16:13:23ZAn Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images10.3390/a141103371999-4893https://doaj.org/article/53ec9eee07714ac8a782832afb013df02021-11-01T00:00:00Zhttps://www.mdpi.com/1999-4893/14/11/337https://doaj.org/toc/1999-4893The field of explainable artificial intelligence (XAI) aims to build explainable and interpretable machine learning (or deep learning) methods without sacrificing prediction performance. Convolutional neural networks (CNNs) have been successful in making predictions, especially in image classification. These popular and well-documented successes use extremely deep CNNs such as VGG16, DenseNet121, and Xception. However, these well-known deep learning models use tens of millions of parameters based on a large number of pretrained filters that have been repurposed from previous data sets. Among these identified filters, a large portion contain no information yet remain as input features. Thus far, there is no effective method to omit these noisy features from a data set, and their existence negatively impacts prediction performance. In this paper, a novel interaction-based convolutional neural network (ICNN) is introduced that does not make assumptions about the relevance of local information. Instead, a model-free influence score (I-score) is proposed to directly extract the influential information from images to form important variable modules. This innovative technique replaces all pretrained filters found by trial-and-error with explainable, influential, and predictive variable sets (modules) determined by the I-score. In other words, future researchers need not rely on pretrained filters; the suggested algorithm identifies only the variables or pixels with high I-score values that are extremely predictive and important. The proposed method and algorithm were tested on real-world data set and a state-of-the-art prediction performance of 99.8% was achieved without sacrificing the explanatory power of the model. This proposed design can efficiently screen patients infected by COVID-19 before human diagnosis and can be a benchmark for addressing future XAI problems in large-scale data sets.Shaw-Hwa LoYiqiao YinMDPI AGarticleexplainable artificial intelligenceconvolutional neural networksdeep learningChest X-ray ImageI-scoreIndustrial engineering. Management engineeringT55.4-60.8Electronic computers. Computer scienceQA75.5-76.95ENAlgorithms, Vol 14, Iss 337, p 337 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	explainable artificial intelligence convolutional neural networks deep learning Chest X-ray Image I-score Industrial engineering. Management engineering T55.4-60.8 Electronic computers. Computer science QA75.5-76.95
spellingShingle	explainable artificial intelligence convolutional neural networks deep learning Chest X-ray Image I-score Industrial engineering. Management engineering T55.4-60.8 Electronic computers. Computer science QA75.5-76.95 Shaw-Hwa Lo Yiqiao Yin An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images
description	The field of explainable artificial intelligence (XAI) aims to build explainable and interpretable machine learning (or deep learning) methods without sacrificing prediction performance. Convolutional neural networks (CNNs) have been successful in making predictions, especially in image classification. These popular and well-documented successes use extremely deep CNNs such as VGG16, DenseNet121, and Xception. However, these well-known deep learning models use tens of millions of parameters based on a large number of pretrained filters that have been repurposed from previous data sets. Among these identified filters, a large portion contain no information yet remain as input features. Thus far, there is no effective method to omit these noisy features from a data set, and their existence negatively impacts prediction performance. In this paper, a novel interaction-based convolutional neural network (ICNN) is introduced that does not make assumptions about the relevance of local information. Instead, a model-free influence score (I-score) is proposed to directly extract the influential information from images to form important variable modules. This innovative technique replaces all pretrained filters found by trial-and-error with explainable, influential, and predictive variable sets (modules) determined by the I-score. In other words, future researchers need not rely on pretrained filters; the suggested algorithm identifies only the variables or pixels with high I-score values that are extremely predictive and important. The proposed method and algorithm were tested on real-world data set and a state-of-the-art prediction performance of 99.8% was achieved without sacrificing the explanatory power of the model. This proposed design can efficiently screen patients infected by COVID-19 before human diagnosis and can be a benchmark for addressing future XAI problems in large-scale data sets.
format	article
author	Shaw-Hwa Lo Yiqiao Yin
author_facet	Shaw-Hwa Lo Yiqiao Yin
author_sort	Shaw-Hwa Lo
title	An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images
title_short	An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images
title_full	An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images
title_fullStr	An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images
title_full_unstemmed	An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images
title_sort	interaction-based convolutional neural network (icnn) toward a better understanding of covid-19 x-ray images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/53ec9eee07714ac8a782832afb013df0
work_keys_str_mv	AT shawhwalo aninteractionbasedconvolutionalneuralnetworkicnntowardabetterunderstandingofcovid19xrayimages AT yiqiaoyin aninteractionbasedconvolutionalneuralnetworkicnntowardabetterunderstandingofcovid19xrayimages AT shawhwalo interactionbasedconvolutionalneuralnetworkicnntowardabetterunderstandingofcovid19xrayimages AT yiqiaoyin interactionbasedconvolutionalneuralnetworkicnntowardabetterunderstandingofcovid19xrayimages
_version_	1718413256171716608

An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images

Ejemplares similares