Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification

The rising global incidence of chronic kidney disease necessitates the development of image categorization of renal glomeruli. COVID-19 has been shown to enter the glomerulus, a tissue structure in the kidney. This study observes the differences between focal-segmental, normal and sclerotic renal gl...

Full description

Bibliographic Details
Main Authors: Hsi-Chieh Lee, Ahmad Fauzan Aqil
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/12/3/1040
_version_ 1827661790873387008
author Hsi-Chieh Lee
Ahmad Fauzan Aqil
author_facet Hsi-Chieh Lee
Ahmad Fauzan Aqil
author_sort Hsi-Chieh Lee
collection DOAJ
description The rising global incidence of chronic kidney disease necessitates the development of image categorization of renal glomeruli. COVID-19 has been shown to enter the glomerulus, a tissue structure in the kidney. This study observes the differences between focal-segmental, normal and sclerotic renal glomerular tissue diseases. The splitting and combining of allied and multivariate models was accomplished utilizing a combined technique using existing models. In this study, model combinations are created by using a high-accuracy accuracy-based model to improve other models. This research exhibits excellent accuracy and consistent classification results on the ResNet101V2 combination using a mix of transfer learning methods, with the combined model on ResNet101V2 showing an accuracy of up to 97 percent with an F1-score of 0.97, compared to other models. However, this study discovered that the anticipated time required was higher than the model employed in general, which was mitigated by the usage of high-performance computing in this study.
first_indexed 2024-03-10T00:16:07Z
format Article
id doaj.art-99cee985d5b04a6482aa04309af41ef1
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-10T00:16:07Z
publishDate 2022-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-99cee985d5b04a6482aa04309af41ef12023-11-23T15:50:53ZengMDPI AGApplied Sciences2076-34172022-01-01123104010.3390/app12031040Combination of Transfer Learning Methods for Kidney Glomeruli Image ClassificationHsi-Chieh Lee0Ahmad Fauzan Aqil1Department of Computer Science and Information Engineering, National Quemoy University, Kinmen 89250, TaiwanDepartment of Computer Science and Information Engineering, National Quemoy University, Kinmen 89250, TaiwanThe rising global incidence of chronic kidney disease necessitates the development of image categorization of renal glomeruli. COVID-19 has been shown to enter the glomerulus, a tissue structure in the kidney. This study observes the differences between focal-segmental, normal and sclerotic renal glomerular tissue diseases. The splitting and combining of allied and multivariate models was accomplished utilizing a combined technique using existing models. In this study, model combinations are created by using a high-accuracy accuracy-based model to improve other models. This research exhibits excellent accuracy and consistent classification results on the ResNet101V2 combination using a mix of transfer learning methods, with the combined model on ResNet101V2 showing an accuracy of up to 97 percent with an F1-score of 0.97, compared to other models. However, this study discovered that the anticipated time required was higher than the model employed in general, which was mitigated by the usage of high-performance computing in this study.https://www.mdpi.com/2076-3417/12/3/1040combined classification modeldeep transfer learningfocal-segmentalkidney diseasekidney glomerulimedical image
spellingShingle Hsi-Chieh Lee
Ahmad Fauzan Aqil
Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification
Applied Sciences
combined classification model
deep transfer learning
focal-segmental
kidney disease
kidney glomeruli
medical image
title Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification
title_full Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification
title_fullStr Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification
title_full_unstemmed Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification
title_short Combination of Transfer Learning Methods for Kidney Glomeruli Image Classification
title_sort combination of transfer learning methods for kidney glomeruli image classification
topic combined classification model
deep transfer learning
focal-segmental
kidney disease
kidney glomeruli
medical image
url https://www.mdpi.com/2076-3417/12/3/1040
work_keys_str_mv AT hsichiehlee combinationoftransferlearningmethodsforkidneyglomeruliimageclassification
AT ahmadfauzanaqil combinationoftransferlearningmethodsforkidneyglomeruliimageclassification