A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer
Breast Cancer (BC) is the most common cancer among women worldwide and is characterized by intra- and inter-tumor heterogeneity that strongly contributes towards its poor prognosis. The Estrogen Receptor (ER), Progesterone Receptor (PR), Human Epidermal Growth Factor Receptor 2 (HER2), and Ki67 anti...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/3/1552 |
_version_ | 1797623198335893504 |
---|---|
author | Valentina Brancato Nadia Brancati Giusy Esposito Massimo La Rosa Carlo Cavaliere Ciro Allarà Valeria Romeo Giuseppe De Pietro Marco Salvatore Marco Aiello Mara Sangiovanni |
author_facet | Valentina Brancato Nadia Brancati Giusy Esposito Massimo La Rosa Carlo Cavaliere Ciro Allarà Valeria Romeo Giuseppe De Pietro Marco Salvatore Marco Aiello Mara Sangiovanni |
author_sort | Valentina Brancato |
collection | DOAJ |
description | Breast Cancer (BC) is the most common cancer among women worldwide and is characterized by intra- and inter-tumor heterogeneity that strongly contributes towards its poor prognosis. The Estrogen Receptor (ER), Progesterone Receptor (PR), Human Epidermal Growth Factor Receptor 2 (HER2), and Ki67 antigen are the most examined markers depicting BC heterogeneity and have been shown to have a strong impact on BC prognosis. Radiomics can noninvasively predict BC heterogeneity through the quantitative evaluation of medical images, such as Magnetic Resonance Imaging (MRI), which has become increasingly important in the detection and characterization of BC. However, the lack of comprehensive BC datasets in terms of molecular outcomes and MRI modalities, and the absence of a general methodology to build and compare feature selection approaches and predictive models, limit the routine use of radiomics in the BC clinical practice. In this work, a new radiomic approach based on a two-step feature selection process was proposed to build predictors for ER, PR, HER2, and Ki67 markers. An in-house dataset was used, containing 92 multiparametric MRIs of patients with histologically proven BC and all four relevant biomarkers available. Thousands of radiomic features were extracted from post-contrast and subtracted Dynamic Contrast-Enanched (DCE) MRI images, Apparent Diffusion Coefficient (ADC) maps, and T2-weighted (T2) images. The two-step feature selection approach was used to identify significant radiomic features properly and then to build the final prediction models. They showed remarkable results in terms of F1-score for all the biomarkers: 84%, 63%, 90%, and 72% for ER, HER2, Ki67, and PR, respectively. When possible, the models were validated on the TCGA/TCIA Breast Cancer dataset, returning promising results (F1-score = 88% for the ER+/ER− classification task). The developed approach efficiently characterized BC heterogeneity according to the examined molecular biomarkers. |
first_indexed | 2024-03-11T09:25:20Z |
format | Article |
id | doaj.art-7bd35a217a00448c9e30945189c90550 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T09:25:20Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-7bd35a217a00448c9e30945189c905502023-11-16T18:02:44ZengMDPI AGSensors1424-82202023-01-01233155210.3390/s23031552A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast CancerValentina Brancato0Nadia Brancati1Giusy Esposito2Massimo La Rosa3Carlo Cavaliere4Ciro Allarà5Valeria Romeo6Giuseppe De Pietro7Marco Salvatore8Marco Aiello9Mara Sangiovanni10IRCCS SYNLAB SDN, Istituto di Ricerca Diagnostica e Nucleare, Via E. Gianturco 113, 80143 Naples, ItalyInstitute for High Performance Computing and Networking, National Research Council of Italy (ICAR-CNR), Via P. Castellino 111, 80131 Naples, ItalyBio Check Up S.r.l., Via Riviera di Chiaia 9a, 80122 Naples, ItalyInstitute for High Performance Computing and Networking, National Research Council of Italy (ICAR-CNR), Via P. Castellino 111, 80131 Naples, ItalyIRCCS SYNLAB SDN, Istituto di Ricerca Diagnostica e Nucleare, Via E. Gianturco 113, 80143 Naples, ItalyBio Check Up S.r.l., Via Riviera di Chiaia 9a, 80122 Naples, ItalyDepartment of Advanced Biomedical Sciences, University of Naples Federico II, 80131 Naples, ItalyInstitute for High Performance Computing and Networking, National Research Council of Italy (ICAR-CNR), Via P. Castellino 111, 80131 Naples, ItalyIRCCS SYNLAB SDN, Istituto di Ricerca Diagnostica e Nucleare, Via E. Gianturco 113, 80143 Naples, ItalyIRCCS SYNLAB SDN, Istituto di Ricerca Diagnostica e Nucleare, Via E. Gianturco 113, 80143 Naples, ItalyInstitute for High Performance Computing and Networking, National Research Council of Italy (ICAR-CNR), Via P. Castellino 111, 80131 Naples, ItalyBreast Cancer (BC) is the most common cancer among women worldwide and is characterized by intra- and inter-tumor heterogeneity that strongly contributes towards its poor prognosis. The Estrogen Receptor (ER), Progesterone Receptor (PR), Human Epidermal Growth Factor Receptor 2 (HER2), and Ki67 antigen are the most examined markers depicting BC heterogeneity and have been shown to have a strong impact on BC prognosis. Radiomics can noninvasively predict BC heterogeneity through the quantitative evaluation of medical images, such as Magnetic Resonance Imaging (MRI), which has become increasingly important in the detection and characterization of BC. However, the lack of comprehensive BC datasets in terms of molecular outcomes and MRI modalities, and the absence of a general methodology to build and compare feature selection approaches and predictive models, limit the routine use of radiomics in the BC clinical practice. In this work, a new radiomic approach based on a two-step feature selection process was proposed to build predictors for ER, PR, HER2, and Ki67 markers. An in-house dataset was used, containing 92 multiparametric MRIs of patients with histologically proven BC and all four relevant biomarkers available. Thousands of radiomic features were extracted from post-contrast and subtracted Dynamic Contrast-Enanched (DCE) MRI images, Apparent Diffusion Coefficient (ADC) maps, and T2-weighted (T2) images. The two-step feature selection approach was used to identify significant radiomic features properly and then to build the final prediction models. They showed remarkable results in terms of F1-score for all the biomarkers: 84%, 63%, 90%, and 72% for ER, HER2, Ki67, and PR, respectively. When possible, the models were validated on the TCGA/TCIA Breast Cancer dataset, returning promising results (F1-score = 88% for the ER+/ER− classification task). The developed approach efficiently characterized BC heterogeneity according to the examined molecular biomarkers.https://www.mdpi.com/1424-8220/23/3/1552radiomicsBreast Cancermachine learningfeature selection |
spellingShingle | Valentina Brancato Nadia Brancati Giusy Esposito Massimo La Rosa Carlo Cavaliere Ciro Allarà Valeria Romeo Giuseppe De Pietro Marco Salvatore Marco Aiello Mara Sangiovanni A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer Sensors radiomics Breast Cancer machine learning feature selection |
title | A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer |
title_full | A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer |
title_fullStr | A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer |
title_full_unstemmed | A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer |
title_short | A Two-Step Feature Selection Radiomic Approach to Predict Molecular Outcomes in Breast Cancer |
title_sort | two step feature selection radiomic approach to predict molecular outcomes in breast cancer |
topic | radiomics Breast Cancer machine learning feature selection |
url | https://www.mdpi.com/1424-8220/23/3/1552 |
work_keys_str_mv | AT valentinabrancato atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT nadiabrancati atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT giusyesposito atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT massimolarosa atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT carlocavaliere atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT ciroallara atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT valeriaromeo atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT giuseppedepietro atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT marcosalvatore atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT marcoaiello atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT marasangiovanni atwostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT valentinabrancato twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT nadiabrancati twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT giusyesposito twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT massimolarosa twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT carlocavaliere twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT ciroallara twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT valeriaromeo twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT giuseppedepietro twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT marcosalvatore twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT marcoaiello twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer AT marasangiovanni twostepfeatureselectionradiomicapproachtopredictmolecularoutcomesinbreastcancer |