Cargando…

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

SIMPLE SUMMARY: Tumor angiogenesis and heterogeneity are associated with poor prognosis for breast cancer. Advances in computer technology have made it possible to noninvasively quantify tumor angiogenesis and heterogeneity appearing in imaging data. We investigated whether low-dose CT could be used...

Descripción completa

Detalles Bibliográficos
Autores principales: Park, Hyun-Soo, Lee, Kwang-sig, Seo, Bo-Kyoung, Kim, Eun-Sil, Cho, Kyu-Ran, Woo, Ok-Hee, Song, Sung-Eun, Lee, Ji-Young, Cha, Jaehyung
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8656976/
https://www.ncbi.nlm.nih.gov/pubmed/34885124
http://dx.doi.org/10.3390/cancers13236013
_version_ 1784612404433256448
author Park, Hyun-Soo
Lee, Kwang-sig
Seo, Bo-Kyoung
Kim, Eun-Sil
Cho, Kyu-Ran
Woo, Ok-Hee
Song, Sung-Eun
Lee, Ji-Young
Cha, Jaehyung
author_facet Park, Hyun-Soo
Lee, Kwang-sig
Seo, Bo-Kyoung
Kim, Eun-Sil
Cho, Kyu-Ran
Woo, Ok-Hee
Song, Sung-Eun
Lee, Ji-Young
Cha, Jaehyung
author_sort Park, Hyun-Soo
collection PubMed
description SIMPLE SUMMARY: Tumor angiogenesis and heterogeneity are associated with poor prognosis for breast cancer. Advances in computer technology have made it possible to noninvasively quantify tumor angiogenesis and heterogeneity appearing in imaging data. We investigated whether low-dose CT could be used as a method for functional oncology imaging to assess tumor heterogeneity and angiogenesis in breast cancer and to predict noninvasively histological biomarkers and molecular subtypes of breast cancer. Low-dose breast CT has advantages in terms of radiation safety and patient convenience. Our study produced promising results for the use of machine learning with low-dose breast CT to identify histological prognostic factors including hormone receptor and human epidermal growth factor receptor 2 status, grade, and molecular subtype in patients with invasive breast cancer. Machine learning that integrates texture and perfusion features of breast cancer with low-dose CT can provide valuable information for the realization of precision medicine. ABSTRACT: This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01–1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients.
format Online
Article
Text
id pubmed-8656976
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86569762021-12-10 Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients Park, Hyun-Soo Lee, Kwang-sig Seo, Bo-Kyoung Kim, Eun-Sil Cho, Kyu-Ran Woo, Ok-Hee Song, Sung-Eun Lee, Ji-Young Cha, Jaehyung Cancers (Basel) Article SIMPLE SUMMARY: Tumor angiogenesis and heterogeneity are associated with poor prognosis for breast cancer. Advances in computer technology have made it possible to noninvasively quantify tumor angiogenesis and heterogeneity appearing in imaging data. We investigated whether low-dose CT could be used as a method for functional oncology imaging to assess tumor heterogeneity and angiogenesis in breast cancer and to predict noninvasively histological biomarkers and molecular subtypes of breast cancer. Low-dose breast CT has advantages in terms of radiation safety and patient convenience. Our study produced promising results for the use of machine learning with low-dose breast CT to identify histological prognostic factors including hormone receptor and human epidermal growth factor receptor 2 status, grade, and molecular subtype in patients with invasive breast cancer. Machine learning that integrates texture and perfusion features of breast cancer with low-dose CT can provide valuable information for the realization of precision medicine. ABSTRACT: This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01–1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients. MDPI 2021-11-29 /pmc/articles/PMC8656976/ /pubmed/34885124 http://dx.doi.org/10.3390/cancers13236013 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. 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
Park, Hyun-Soo
Lee, Kwang-sig
Seo, Bo-Kyoung
Kim, Eun-Sil
Cho, Kyu-Ran
Woo, Ok-Hee
Song, Sung-Eun
Lee, Ji-Young
Cha, Jaehyung
Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients
title Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients
title_full Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients
title_fullStr Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients
title_full_unstemmed Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients
title_short Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients
title_sort machine learning models that integrate tumor texture and perfusion characteristics using low-dose breast computed tomography are promising for predicting histological biomarkers and treatment failure in breast cancer patients
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8656976/
https://www.ncbi.nlm.nih.gov/pubmed/34885124
http://dx.doi.org/10.3390/cancers13236013
work_keys_str_mv AT parkhyunsoo machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT leekwangsig machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT seobokyoung machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT kimeunsil machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT chokyuran machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT woookhee machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT songsungeun machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT leejiyoung machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients
AT chajaehyung machinelearningmodelsthatintegratetumortextureandperfusioncharacteristicsusinglowdosebreastcomputedtomographyarepromisingforpredictinghistologicalbiomarkersandtreatmentfailureinbreastcancerpatients