Cargando…

Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics

Machine learning for medical imaging not only requires sufficient amounts of data for training and testing but also that the data be independent. It is common to see highly interdependent data whenever there are inherent correlations between observations. This is especially to be expected for sequen...

Descripción completa

Detalles Bibliográficos
Autores principales: Sultan, Laith R., Cary, Theodore W., Al-Hasani, Maryam, Karmacharya, Mrigendra B., Venkatesh, Santosh S., Assenmacher, Charles-Antoine, Radaelli, Enrico, Sehgal, Chandra M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9511699/
https://www.ncbi.nlm.nih.gov/pubmed/36168560
http://dx.doi.org/10.3390/ai3030043
_version_ 1784797696388759552
author Sultan, Laith R.
Cary, Theodore W.
Al-Hasani, Maryam
Karmacharya, Mrigendra B.
Venkatesh, Santosh S.
Assenmacher, Charles-Antoine
Radaelli, Enrico
Sehgal, Chandra M.
author_facet Sultan, Laith R.
Cary, Theodore W.
Al-Hasani, Maryam
Karmacharya, Mrigendra B.
Venkatesh, Santosh S.
Assenmacher, Charles-Antoine
Radaelli, Enrico
Sehgal, Chandra M.
author_sort Sultan, Laith R.
collection PubMed
description Machine learning for medical imaging not only requires sufficient amounts of data for training and testing but also that the data be independent. It is common to see highly interdependent data whenever there are inherent correlations between observations. This is especially to be expected for sequential imaging data taken from time series. In this study, we evaluate the use of statistical measures to test the independence of sequential ultrasound image data taken from the same case. A total of 1180 B-mode liver ultrasound images with 5903 regions of interests were analyzed. The ultrasound images were taken from two liver disease groups, fibrosis and steatosis, as well as normal cases. Computer-extracted texture features were then used to train a machine learning (ML) model for computer-aided diagnosis. The experiment resulted in high two-category diagnosis using logistic regression, with AUC of 0.928 and high performance of multicategory classification, using random forest ML, with AUC of 0.917. To evaluate the image region independence for machine learning, Jenson–Shannon (JS) divergence was used. JS distributions showed that images of normal liver were independent from each other, while the images from the two disease pathologies were not independent. To guarantee the generalizability of machine learning models, and to prevent data leakage, multiple frames of image data acquired of the same object should be tested for independence before machine learning. Such tests can be applied to real-world medical image problems to determine if images from the same subject can be used for training.
format Online
Article
Text
id pubmed-9511699
institution National Center for Biotechnology Information
language English
publishDate 2022
record_format MEDLINE/PubMed
spelling pubmed-95116992022-09-26 Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics Sultan, Laith R. Cary, Theodore W. Al-Hasani, Maryam Karmacharya, Mrigendra B. Venkatesh, Santosh S. Assenmacher, Charles-Antoine Radaelli, Enrico Sehgal, Chandra M. AI (Basel) Article Machine learning for medical imaging not only requires sufficient amounts of data for training and testing but also that the data be independent. It is common to see highly interdependent data whenever there are inherent correlations between observations. This is especially to be expected for sequential imaging data taken from time series. In this study, we evaluate the use of statistical measures to test the independence of sequential ultrasound image data taken from the same case. A total of 1180 B-mode liver ultrasound images with 5903 regions of interests were analyzed. The ultrasound images were taken from two liver disease groups, fibrosis and steatosis, as well as normal cases. Computer-extracted texture features were then used to train a machine learning (ML) model for computer-aided diagnosis. The experiment resulted in high two-category diagnosis using logistic regression, with AUC of 0.928 and high performance of multicategory classification, using random forest ML, with AUC of 0.917. To evaluate the image region independence for machine learning, Jenson–Shannon (JS) divergence was used. JS distributions showed that images of normal liver were independent from each other, while the images from the two disease pathologies were not independent. To guarantee the generalizability of machine learning models, and to prevent data leakage, multiple frames of image data acquired of the same object should be tested for independence before machine learning. Such tests can be applied to real-world medical image problems to determine if images from the same subject can be used for training. 2022-09 2022-09-01 /pmc/articles/PMC9511699/ /pubmed/36168560 http://dx.doi.org/10.3390/ai3030043 Text en https://creativecommons.org/licenses/by/4.0/This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sultan, Laith R.
Cary, Theodore W.
Al-Hasani, Maryam
Karmacharya, Mrigendra B.
Venkatesh, Santosh S.
Assenmacher, Charles-Antoine
Radaelli, Enrico
Sehgal, Chandra M.
Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics
title Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics
title_full Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics
title_fullStr Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics
title_full_unstemmed Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics
title_short Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics
title_sort can sequential images from the same object be used for training machine learning models? a case study for detecting liver disease by ultrasound radiomics
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9511699/
https://www.ncbi.nlm.nih.gov/pubmed/36168560
http://dx.doi.org/10.3390/ai3030043
work_keys_str_mv AT sultanlaithr cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT carytheodorew cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT alhasanimaryam cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT karmacharyamrigendrab cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT venkateshsantoshs cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT assenmachercharlesantoine cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT radaellienrico cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics
AT sehgalchandram cansequentialimagesfromthesameobjectbeusedfortrainingmachinelearningmodelsacasestudyfordetectingliverdiseasebyultrasoundradiomics