A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images

Recently, research has been conducted to assist in the processing and analysis of histopathological images using machine learning algorithms. In this study, we established machine learning-based algorithms to detect photothrombotic lesions in histological images of photothrombosis-induced rabbit bra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sang Hee Jo, Yoonhee Kim, Yoon Bum Lee, Sung Suk Oh, Jong-ryul Choi
Formato:	article
Lenguaje:	EN
Publicado:	World Scientific Publishing 2021
Materias:	machine learning histopathological images photothrombotic lesion rabbit brain binary classification logistic regression multi-layer neural networks Technology T Optics. Light QC350-467
Acceso en línea:	https://doaj.org/article/5027b08b23ad499191895fd9a03de34c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5027b08b23ad499191895fd9a03de34c
record_format	dspace
spelling	oai:doaj.org-article:5027b08b23ad499191895fd9a03de34c2021-11-23T13:04:53ZA comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images1793-54581793-720510.1142/S1793545821500188https://doaj.org/article/5027b08b23ad499191895fd9a03de34c2021-11-01T00:00:00Zhttp://www.worldscientific.com/doi/epdf/10.1142/S1793545821500188https://doaj.org/toc/1793-5458https://doaj.org/toc/1793-7205Recently, research has been conducted to assist in the processing and analysis of histopathological images using machine learning algorithms. In this study, we established machine learning-based algorithms to detect photothrombotic lesions in histological images of photothrombosis-induced rabbit brains. Six machine learning-based algorithms for binary classification were applied, and the accuracies were compared to classify normal tissues and photothrombotic lesions. The lesion classification model consisting of a 3-layered neural network with a rectified linear unit (ReLU) activation function, Xavier initialization, and Adam optimization using datasets with a unit size of 128×128 pixels yielded the highest accuracy (0.975). In the validation using the tested histological images, it was confirmed that the model could identify regions where brain damage occurred due to photochemical ischemic stroke. Through the development of machine learning-based photothrombotic lesion classification models and performance comparisons, we confirmed that machine learning algorithms have the potential to be utilized in histopathology and various medical diagnostic techniques.Sang Hee JoYoonhee KimYoon Bum LeeSung Suk OhJong-ryul ChoiWorld Scientific Publishingarticlemachine learninghistopathological imagesphotothrombotic lesionrabbit brainbinary classificationlogistic regressionmulti-layer neural networksTechnologyTOptics. LightQC350-467ENJournal of Innovative Optical Health Sciences, Vol 14, Iss 6, Pp 2150018-1-2150018-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning histopathological images photothrombotic lesion rabbit brain binary classification logistic regression multi-layer neural networks Technology T Optics. Light QC350-467
spellingShingle	machine learning histopathological images photothrombotic lesion rabbit brain binary classification logistic regression multi-layer neural networks Technology T Optics. Light QC350-467 Sang Hee Jo Yoonhee Kim Yoon Bum Lee Sung Suk Oh Jong-ryul Choi A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
description	Recently, research has been conducted to assist in the processing and analysis of histopathological images using machine learning algorithms. In this study, we established machine learning-based algorithms to detect photothrombotic lesions in histological images of photothrombosis-induced rabbit brains. Six machine learning-based algorithms for binary classification were applied, and the accuracies were compared to classify normal tissues and photothrombotic lesions. The lesion classification model consisting of a 3-layered neural network with a rectified linear unit (ReLU) activation function, Xavier initialization, and Adam optimization using datasets with a unit size of 128×128 pixels yielded the highest accuracy (0.975). In the validation using the tested histological images, it was confirmed that the model could identify regions where brain damage occurred due to photochemical ischemic stroke. Through the development of machine learning-based photothrombotic lesion classification models and performance comparisons, we confirmed that machine learning algorithms have the potential to be utilized in histopathology and various medical diagnostic techniques.
format	article
author	Sang Hee Jo Yoonhee Kim Yoon Bum Lee Sung Suk Oh Jong-ryul Choi
author_facet	Sang Hee Jo Yoonhee Kim Yoon Bum Lee Sung Suk Oh Jong-ryul Choi
author_sort	Sang Hee Jo
title	A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
title_short	A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
title_full	A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
title_fullStr	A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
title_full_unstemmed	A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
title_sort	comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images
publisher	World Scientific Publishing
publishDate	2021
url	https://doaj.org/article/5027b08b23ad499191895fd9a03de34c
work_keys_str_mv	AT sangheejo acomparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT yoonheekim acomparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT yoonbumlee acomparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT sungsukoh acomparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT jongryulchoi acomparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT sangheejo comparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT yoonheekim comparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT yoonbumlee comparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT sungsukoh comparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages AT jongryulchoi comparativestudyonmachinelearningbasedclassificationtofindphotothromboticlesioninhistologicalrabbitbrainimages
_version_	1718416701367779328

A comparative study on machine learning-based classification to find photothrombotic lesion in histological rabbit brain images

Ejemplares similares