Realization of medical image data transfer learning based on MATLAB

Objective To discuss how to implement the application of medical image data on transfer learning based on MATLAB.Methods Taking MIMIC-CXR for example, 500 X-ray images of positive and the same number negative pleural effusion were randomly selected as the total data set, and the MATLAB software tran...

Full description

Saved in:
Bibliographic Details
Main Authors: HUANG Xiaxuan, HUANG Tao, YUAN Shiqi, HE Ningxia, WU Wentao, LYU Jun
Format: Article
Language:zho
Published: Editorial Office of New Medicine 2022-02-01
Series:Yixue xinzhi zazhi
Subjects:
Online Access:https://yxxz.whuznhmedj.com/storage/attach/2202/1B178EKI7YanhAKNIsONfaBgJzYjRbIFmI48yoyd.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119993673383936
author HUANG Xiaxuan
HUANG Tao
YUAN Shiqi
HE Ningxia
WU Wentao
LYU Jun
author_facet HUANG Xiaxuan
HUANG Tao
YUAN Shiqi
HE Ningxia
WU Wentao
LYU Jun
author_sort HUANG Xiaxuan
collection DOAJ
description Objective To discuss how to implement the application of medical image data on transfer learning based on MATLAB.Methods Taking MIMIC-CXR for example, 500 X-ray images of positive and the same number negative pleural effusion were randomly selected as the total data set, and the MATLAB software transfer learning method based on the ResNet network model was used for multiple training, calculating the AUC value to evaluate the accuracy of the model training for pleural effusion image classification.Results The pleural effusion imaging test set and training set used in this study were evenly distributed. Some training models had an accuracy rate of 80%, and the loss rate dropped to below 20%. The highest accuracy rate in training with 250 iterations was up to 100%, which took about 2 minutes and 38 seconds. Based on the prediction results of image data transfer learning obtained in this model training, the highest AUC value was 93.53%.Conclusion The transfer learning method of the ResNet network model can realize the effective combination and enhance-ment of model construction and medical imaging data training, and the model has good predictive performance, which provides a certain basis for clinicians in the early diagnosis of pleural effusion.
format Article
id doaj-art-8f3cfb250a9d4ca8b3bd9016f0261287
institution OA Journals
issn 1004-5511
language zho
publishDate 2022-02-01
publisher Editorial Office of New Medicine
record_format Article
series Yixue xinzhi zazhi
spelling doaj-art-8f3cfb250a9d4ca8b3bd9016f02612872025-08-20T02:35:30ZzhoEditorial Office of New MedicineYixue xinzhi zazhi1004-55112022-02-01321333910.12173/j.issn.1004-5511.2021090186300Realization of medical image data transfer learning based on MATLABHUANG XiaxuanHUANG TaoYUAN ShiqiHE NingxiaWU WentaoLYU JunObjective To discuss how to implement the application of medical image data on transfer learning based on MATLAB.Methods Taking MIMIC-CXR for example, 500 X-ray images of positive and the same number negative pleural effusion were randomly selected as the total data set, and the MATLAB software transfer learning method based on the ResNet network model was used for multiple training, calculating the AUC value to evaluate the accuracy of the model training for pleural effusion image classification.Results The pleural effusion imaging test set and training set used in this study were evenly distributed. Some training models had an accuracy rate of 80%, and the loss rate dropped to below 20%. The highest accuracy rate in training with 250 iterations was up to 100%, which took about 2 minutes and 38 seconds. Based on the prediction results of image data transfer learning obtained in this model training, the highest AUC value was 93.53%.Conclusion The transfer learning method of the ResNet network model can realize the effective combination and enhance-ment of model construction and medical imaging data training, and the model has good predictive performance, which provides a certain basis for clinicians in the early diagnosis of pleural effusion.https://yxxz.whuznhmedj.com/storage/attach/2202/1B178EKI7YanhAKNIsONfaBgJzYjRbIFmI48yoyd.pdfmatlab transfer learning image classification pleural effusion
spellingShingle HUANG Xiaxuan
HUANG Tao
YUAN Shiqi
HE Ningxia
WU Wentao
LYU Jun
Realization of medical image data transfer learning based on MATLAB
Yixue xinzhi zazhi
matlab
transfer learning
image classification
pleural effusion
title Realization of medical image data transfer learning based on MATLAB
title_full Realization of medical image data transfer learning based on MATLAB
title_fullStr Realization of medical image data transfer learning based on MATLAB
title_full_unstemmed Realization of medical image data transfer learning based on MATLAB
title_short Realization of medical image data transfer learning based on MATLAB
title_sort realization of medical image data transfer learning based on matlab
topic matlab
transfer learning
image classification
pleural effusion
url https://yxxz.whuznhmedj.com/storage/attach/2202/1B178EKI7YanhAKNIsONfaBgJzYjRbIFmI48yoyd.pdf
work_keys_str_mv AT huangxiaxuan realizationofmedicalimagedatatransferlearningbasedonmatlab
AT huangtao realizationofmedicalimagedatatransferlearningbasedonmatlab
AT yuanshiqi realizationofmedicalimagedatatransferlearningbasedonmatlab
AT heningxia realizationofmedicalimagedatatransferlearningbasedonmatlab
AT wuwentao realizationofmedicalimagedatatransferlearningbasedonmatlab
AT lyujun realizationofmedicalimagedatatransferlearningbasedonmatlab