Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images

Abstract Deep learning is being employed in disease detection and classification based on medical images for clinical decision making. It typically requires large amounts of labelled data; however, the sample size of such medical image datasets is generally small. This study proposes a novel trainin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guangzhou An, Masahiro Akiba, Kazuko Omodaka, Toru Nakazawa, Hideo Yokota
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/e6d1ea699766437d95c7d3f7de66dd3d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e6d1ea699766437d95c7d3f7de66dd3d
record_format	dspace
spelling	oai:doaj.org-article:e6d1ea699766437d95c7d3f7de66dd3d2021-12-02T15:53:43ZHierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images10.1038/s41598-021-83503-72045-2322https://doaj.org/article/e6d1ea699766437d95c7d3f7de66dd3d2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83503-7https://doaj.org/toc/2045-2322Abstract Deep learning is being employed in disease detection and classification based on medical images for clinical decision making. It typically requires large amounts of labelled data; however, the sample size of such medical image datasets is generally small. This study proposes a novel training framework for building deep learning models of disease detection and classification with small datasets. Our approach is based on a hierarchical classification method where the healthy/disease information from the first model is effectively utilized to build subsequent models for classifying the disease into its sub-types via a transfer learning method. To improve accuracy, multiple input datasets were used, and a stacking ensembled method was employed for final classification. To demonstrate the method’s performance, a labelled dataset extracted from volumetric ophthalmic optical coherence tomography data for 156 healthy and 798 glaucoma eyes was used, in which glaucoma eyes were further labelled into four sub-types. The average weighted accuracy and Cohen’s kappa for three randomized test datasets were 0.839 and 0.809, respectively. Our approach outperformed the flat classification method by 9.7% using smaller training datasets. The results suggest that the framework can perform accurate classification with a small number of medical images.Guangzhou AnMasahiro AkibaKazuko OmodakaToru NakazawaHideo YokotaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Guangzhou An Masahiro Akiba Kazuko Omodaka Toru Nakazawa Hideo Yokota Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
description	Abstract Deep learning is being employed in disease detection and classification based on medical images for clinical decision making. It typically requires large amounts of labelled data; however, the sample size of such medical image datasets is generally small. This study proposes a novel training framework for building deep learning models of disease detection and classification with small datasets. Our approach is based on a hierarchical classification method where the healthy/disease information from the first model is effectively utilized to build subsequent models for classifying the disease into its sub-types via a transfer learning method. To improve accuracy, multiple input datasets were used, and a stacking ensembled method was employed for final classification. To demonstrate the method’s performance, a labelled dataset extracted from volumetric ophthalmic optical coherence tomography data for 156 healthy and 798 glaucoma eyes was used, in which glaucoma eyes were further labelled into four sub-types. The average weighted accuracy and Cohen’s kappa for three randomized test datasets were 0.839 and 0.809, respectively. Our approach outperformed the flat classification method by 9.7% using smaller training datasets. The results suggest that the framework can perform accurate classification with a small number of medical images.
format	article
author	Guangzhou An Masahiro Akiba Kazuko Omodaka Toru Nakazawa Hideo Yokota
author_facet	Guangzhou An Masahiro Akiba Kazuko Omodaka Toru Nakazawa Hideo Yokota
author_sort	Guangzhou An
title	Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
title_short	Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
title_full	Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
title_fullStr	Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
title_full_unstemmed	Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
title_sort	hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e6d1ea699766437d95c7d3f7de66dd3d
work_keys_str_mv	AT guangzhouan hierarchicaldeeplearningmodelsusingtransferlearningfordiseasedetectionandclassificationbasedonsmallnumberofmedicalimages AT masahiroakiba hierarchicaldeeplearningmodelsusingtransferlearningfordiseasedetectionandclassificationbasedonsmallnumberofmedicalimages AT kazukoomodaka hierarchicaldeeplearningmodelsusingtransferlearningfordiseasedetectionandclassificationbasedonsmallnumberofmedicalimages AT torunakazawa hierarchicaldeeplearningmodelsusingtransferlearningfordiseasedetectionandclassificationbasedonsmallnumberofmedicalimages AT hideoyokota hierarchicaldeeplearningmodelsusingtransferlearningfordiseasedetectionandclassificationbasedonsmallnumberofmedicalimages
_version_	1718385544868659200

Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images

Ejemplares similares