Cargando…

Radiomic features from MRI distinguish myxomas from myxofibrosarcomas

BACKGROUND: Myxoid tumors pose diagnostic challenges for radiologists and pathologists. All myxoid tumors can be differentiated from each other using fluorescent in-situ hybridization (FISH) or immunohistochemical markers, except for myxomas and myxofibrosarcomas. Myxomas and myxofibrosarcomas are r...

Descripción completa

Detalles Bibliográficos
Autores principales: Martin-Carreras, Teresa, Li, Hongming, Cooper, Kumarasen, Fan, Yong, Sebro, Ronnie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6694512/
https://www.ncbi.nlm.nih.gov/pubmed/31416421
http://dx.doi.org/10.1186/s12880-019-0366-9
_version_ 1783443838340169728
author Martin-Carreras, Teresa
Li, Hongming
Cooper, Kumarasen
Fan, Yong
Sebro, Ronnie
author_facet Martin-Carreras, Teresa
Li, Hongming
Cooper, Kumarasen
Fan, Yong
Sebro, Ronnie
author_sort Martin-Carreras, Teresa
collection PubMed
description BACKGROUND: Myxoid tumors pose diagnostic challenges for radiologists and pathologists. All myxoid tumors can be differentiated from each other using fluorescent in-situ hybridization (FISH) or immunohistochemical markers, except for myxomas and myxofibrosarcomas. Myxomas and myxofibrosarcomas are rare tumors. Myxomas are benign and histologically bland, whereas myxofibrosarcomas are malignant and histologically heterogenous. Because of the histological heterogeneity, low grade myxofibrosarcomas may be mistaken for myxomas on core needle biopsies. We evaluated the performance of T1-weighted signal intensity (T1SI), tumor volume, and radiomic features extracted from magnetic resonance imaging (MRI) to differentiate myxomas from myxofibrosarcomas. METHODS: The MRIs of 56 patients (29 with myxomas, 27 with myxofibrosarcomas) were analyzed. We extracted 89 radiomic features. Random forests based classifiers using the T1SI, volume features, and radiomic features were used to differentiate myxomas from myxofibrosarcomas. The classifiers were validated using a leave-one-out cross-validation. The performances of the classifiers were then compared. RESULTS: Myxomas had lower normalized T1SI than myxofibrosaromas (p = 0.006) and the AUC using the T1SI was 0.713. However, the classification model using radiomic features had an AUC of 0.885 (accuracy = 0.839, sensitivity = 0.852, specificity = 0.828), and outperformed the classification models using T1SI (AUC = 0.713) and tumor volume (AUC = 0.838). The classification model using radiomic features was significantly better than the classifier using T1SI values (p = 0.039). CONCLUSIONS: Myxofibrosarcomas are on average higher in T1-weighted signal intensity than myxomas. Myxofibrosarcomas are larger and have shape differences compared to myxomas. Radiomic features performed best for differentiating myxomas from myxofibrosarcomas compared to T1-weighted signal intensity and tumor volume features. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s12880-019-0366-9) contains supplementary material, which is available to authorized users.
format Online
Article
Text
id pubmed-6694512
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-66945122019-08-19 Radiomic features from MRI distinguish myxomas from myxofibrosarcomas Martin-Carreras, Teresa Li, Hongming Cooper, Kumarasen Fan, Yong Sebro, Ronnie BMC Med Imaging Research Article BACKGROUND: Myxoid tumors pose diagnostic challenges for radiologists and pathologists. All myxoid tumors can be differentiated from each other using fluorescent in-situ hybridization (FISH) or immunohistochemical markers, except for myxomas and myxofibrosarcomas. Myxomas and myxofibrosarcomas are rare tumors. Myxomas are benign and histologically bland, whereas myxofibrosarcomas are malignant and histologically heterogenous. Because of the histological heterogeneity, low grade myxofibrosarcomas may be mistaken for myxomas on core needle biopsies. We evaluated the performance of T1-weighted signal intensity (T1SI), tumor volume, and radiomic features extracted from magnetic resonance imaging (MRI) to differentiate myxomas from myxofibrosarcomas. METHODS: The MRIs of 56 patients (29 with myxomas, 27 with myxofibrosarcomas) were analyzed. We extracted 89 radiomic features. Random forests based classifiers using the T1SI, volume features, and radiomic features were used to differentiate myxomas from myxofibrosarcomas. The classifiers were validated using a leave-one-out cross-validation. The performances of the classifiers were then compared. RESULTS: Myxomas had lower normalized T1SI than myxofibrosaromas (p = 0.006) and the AUC using the T1SI was 0.713. However, the classification model using radiomic features had an AUC of 0.885 (accuracy = 0.839, sensitivity = 0.852, specificity = 0.828), and outperformed the classification models using T1SI (AUC = 0.713) and tumor volume (AUC = 0.838). The classification model using radiomic features was significantly better than the classifier using T1SI values (p = 0.039). CONCLUSIONS: Myxofibrosarcomas are on average higher in T1-weighted signal intensity than myxomas. Myxofibrosarcomas are larger and have shape differences compared to myxomas. Radiomic features performed best for differentiating myxomas from myxofibrosarcomas compared to T1-weighted signal intensity and tumor volume features. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s12880-019-0366-9) contains supplementary material, which is available to authorized users. BioMed Central 2019-08-15 /pmc/articles/PMC6694512/ /pubmed/31416421 http://dx.doi.org/10.1186/s12880-019-0366-9 Text en © The Author(s). 2019 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.
spellingShingle Research Article
Martin-Carreras, Teresa
Li, Hongming
Cooper, Kumarasen
Fan, Yong
Sebro, Ronnie
Radiomic features from MRI distinguish myxomas from myxofibrosarcomas
title Radiomic features from MRI distinguish myxomas from myxofibrosarcomas
title_full Radiomic features from MRI distinguish myxomas from myxofibrosarcomas
title_fullStr Radiomic features from MRI distinguish myxomas from myxofibrosarcomas
title_full_unstemmed Radiomic features from MRI distinguish myxomas from myxofibrosarcomas
title_short Radiomic features from MRI distinguish myxomas from myxofibrosarcomas
title_sort radiomic features from mri distinguish myxomas from myxofibrosarcomas
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6694512/
https://www.ncbi.nlm.nih.gov/pubmed/31416421
http://dx.doi.org/10.1186/s12880-019-0366-9
work_keys_str_mv AT martincarrerasteresa radiomicfeaturesfrommridistinguishmyxomasfrommyxofibrosarcomas
AT lihongming radiomicfeaturesfrommridistinguishmyxomasfrommyxofibrosarcomas
AT cooperkumarasen radiomicfeaturesfrommridistinguishmyxomasfrommyxofibrosarcomas
AT fanyong radiomicfeaturesfrommridistinguishmyxomasfrommyxofibrosarcomas
AT sebroronnie radiomicfeaturesfrommridistinguishmyxomasfrommyxofibrosarcomas