TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

The application of artificial intelligence (AI) to various medical subfields has been a popular topic of research in recent years. In particular, deep learning has been widely used and has proven effective in many cases. Topological data analysis (TDA)—a rising field at the intersection of mathemati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chuan-Shen Hu, Austin Lawson, Jung-Sheng Chen, Yu-Min Chung, Clifford Smyth, Shih-Min Yang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning topological data analysis persistent homology persistence statistics persistence curves hybrid models Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/0e130dd218d24683878becb1f61b9846
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0e130dd218d24683878becb1f61b9846
record_format	dspace
spelling	oai:doaj.org-article:0e130dd218d24683878becb1f61b98462021-11-25T18:17:14ZTopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification10.3390/math92229242227-7390https://doaj.org/article/0e130dd218d24683878becb1f61b98462021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2924https://doaj.org/toc/2227-7390The application of artificial intelligence (AI) to various medical subfields has been a popular topic of research in recent years. In particular, deep learning has been widely used and has proven effective in many cases. Topological data analysis (TDA)—a rising field at the intersection of mathematics, statistics, and computer science—offers new insights into data. In this work, we develop a novel deep learning architecture that we call <i>TopoResNet</i> that integrates topological information into the residual neural network architecture. To demonstrate TopoResNet, we apply it to a skin lesion classification problem. We find that TopoResNet improves the accuracy and the stability of the training process.Chuan-Shen HuAustin LawsonJung-Sheng ChenYu-Min ChungClifford SmythShih-Min YangMDPI AGarticledeep learningtopological data analysispersistent homologypersistence statisticspersistence curveshybrid modelsMathematicsQA1-939ENMathematics, Vol 9, Iss 2924, p 2924 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning topological data analysis persistent homology persistence statistics persistence curves hybrid models Mathematics QA1-939
spellingShingle	deep learning topological data analysis persistent homology persistence statistics persistence curves hybrid models Mathematics QA1-939 Chuan-Shen Hu Austin Lawson Jung-Sheng Chen Yu-Min Chung Clifford Smyth Shih-Min Yang TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification
description	The application of artificial intelligence (AI) to various medical subfields has been a popular topic of research in recent years. In particular, deep learning has been widely used and has proven effective in many cases. Topological data analysis (TDA)—a rising field at the intersection of mathematics, statistics, and computer science—offers new insights into data. In this work, we develop a novel deep learning architecture that we call <i>TopoResNet</i> that integrates topological information into the residual neural network architecture. To demonstrate TopoResNet, we apply it to a skin lesion classification problem. We find that TopoResNet improves the accuracy and the stability of the training process.
format	article
author	Chuan-Shen Hu Austin Lawson Jung-Sheng Chen Yu-Min Chung Clifford Smyth Shih-Min Yang
author_facet	Chuan-Shen Hu Austin Lawson Jung-Sheng Chen Yu-Min Chung Clifford Smyth Shih-Min Yang
author_sort	Chuan-Shen Hu
title	TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification
title_short	TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification
title_full	TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification
title_fullStr	TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification
title_full_unstemmed	TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification
title_sort	toporesnet: a hybrid deep learning architecture and its application to skin lesion classification
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0e130dd218d24683878becb1f61b9846
work_keys_str_mv	AT chuanshenhu toporesnetahybriddeeplearningarchitectureanditsapplicationtoskinlesionclassification AT austinlawson toporesnetahybriddeeplearningarchitectureanditsapplicationtoskinlesionclassification AT jungshengchen toporesnetahybriddeeplearningarchitectureanditsapplicationtoskinlesionclassification AT yuminchung toporesnetahybriddeeplearningarchitectureanditsapplicationtoskinlesionclassification AT cliffordsmyth toporesnetahybriddeeplearningarchitectureanditsapplicationtoskinlesionclassification AT shihminyang toporesnetahybriddeeplearningarchitectureanditsapplicationtoskinlesionclassification
_version_	1718411363030663168

TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

Ejemplares similares