Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach.
<h4>Purpose</h4>Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve th...
Guardado en:
Autores principales: | , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Public Library of Science (PLoS)
2014
|
Materias: | |
Acceso en línea: | https://doaj.org/article/b7e79f159f5e4a8390fce9a4bcdf7eb3 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:b7e79f159f5e4a8390fce9a4bcdf7eb3 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:b7e79f159f5e4a8390fce9a4bcdf7eb32021-11-18T08:34:34ZDiagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach.1932-620310.1371/journal.pone.0087387https://doaj.org/article/b7e79f159f5e4a8390fce9a4bcdf7eb32014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24498092/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Purpose</h4>Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported.<h4>Materials and methods</h4>The study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination.<h4>Results</h4>Seven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively.<h4>Conclusion</h4>Multi-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions.Hongmin CaiYanxia PengCaiwen OuMinsheng ChenLi LiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 1, p e87387 (2014) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Hongmin Cai Yanxia Peng Caiwen Ou Minsheng Chen Li Li Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach. |
description |
<h4>Purpose</h4>Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported.<h4>Materials and methods</h4>The study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination.<h4>Results</h4>Seven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively.<h4>Conclusion</h4>Multi-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions. |
format |
article |
author |
Hongmin Cai Yanxia Peng Caiwen Ou Minsheng Chen Li Li |
author_facet |
Hongmin Cai Yanxia Peng Caiwen Ou Minsheng Chen Li Li |
author_sort |
Hongmin Cai |
title |
Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach. |
title_short |
Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach. |
title_full |
Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach. |
title_fullStr |
Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach. |
title_full_unstemmed |
Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach. |
title_sort |
diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted mr: a machine learning approach. |
publisher |
Public Library of Science (PLoS) |
publishDate |
2014 |
url |
https://doaj.org/article/b7e79f159f5e4a8390fce9a4bcdf7eb3 |
work_keys_str_mv |
AT hongmincai diagnosisofbreastmassesfromdynamiccontrastenhancedanddiffusionweightedmramachinelearningapproach AT yanxiapeng diagnosisofbreastmassesfromdynamiccontrastenhancedanddiffusionweightedmramachinelearningapproach AT caiwenou diagnosisofbreastmassesfromdynamiccontrastenhancedanddiffusionweightedmramachinelearningapproach AT minshengchen diagnosisofbreastmassesfromdynamiccontrastenhancedanddiffusionweightedmramachinelearningapproach AT lili diagnosisofbreastmassesfromdynamiccontrastenhancedanddiffusionweightedmramachinelearningapproach |
_version_ |
1718421643587485696 |