Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner
We aimed to investigate the association between the radiomic features of contrast-enhanced spectral mammography (CESM) images and a specific receptor pattern of breast neoplasms. In this single-center retrospective study, we selected patients with neoplastic breast lesions who underwent CESM before...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/23/15322 |
| _version_ | 1797463016251326464 |
|---|---|
| author | Luca Nicosia Anna Carla Bozzini Daniela Ballerini Simone Palma Filippo Pesapane Sara Raimondi Aurora Gaeta Federica Bellerba Daniela Origgi Paolo De Marco Giuseppe Castiglione Minischetti Claudia Sangalli Lorenza Meneghetti Giuseppe Curigliano Enrico Cassano |
| author_facet | Luca Nicosia Anna Carla Bozzini Daniela Ballerini Simone Palma Filippo Pesapane Sara Raimondi Aurora Gaeta Federica Bellerba Daniela Origgi Paolo De Marco Giuseppe Castiglione Minischetti Claudia Sangalli Lorenza Meneghetti Giuseppe Curigliano Enrico Cassano |
| author_sort | Luca Nicosia |
| collection | DOAJ |
| description | We aimed to investigate the association between the radiomic features of contrast-enhanced spectral mammography (CESM) images and a specific receptor pattern of breast neoplasms. In this single-center retrospective study, we selected patients with neoplastic breast lesions who underwent CESM before a biopsy and surgical assessment between January 2013 and February 2022. Radiomic analysis was performed on regions of interest selected from recombined CESM images. The association between the features and each evaluated endpoint (ER, PR, Ki-67, HER2+, triple negative, G2–G3 expressions) was investigated through univariate logistic regression. Among the significant and highly correlated radiomic features, we selected only the one most associated with the endpoint. From a group of 321 patients, we enrolled 205 malignant breast lesions. The median age at the exam was 50 years (interquartile range (IQR) 45–58). NGLDM_Contrast was the only feature that was positively associated with both ER and PR expression (<i>p</i>-values = 0.01). NGLDM_Coarseness was negatively associated with Ki-67 expression (<i>p</i>-value = 0.02). Five features SHAPE Volume(mL), SHAPE_Volume(vx), GLRLM_RLNU, NGLDM_Busyness and GLZLM_GLNU were all positively and significantly associated with HER2+; however, all of them were highly correlated. Radiomic features of CESM images could be helpful to predict particular molecular subtypes before a biopsy. |
| first_indexed | 2024-03-09T17:44:41Z |
| format | Article |
| id | doaj.art-97a1f25bebd942d18beed0a02e0b5c4c |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T17:44:41Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-97a1f25bebd942d18beed0a02e0b5c4c2023-11-24T11:17:04ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-12-0123231532210.3390/ijms232315322Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive MannerLuca Nicosia0Anna Carla Bozzini1Daniela Ballerini2Simone Palma3Filippo Pesapane4Sara Raimondi5Aurora Gaeta6Federica Bellerba7Daniela Origgi8Paolo De Marco9Giuseppe Castiglione Minischetti10Claudia Sangalli11Lorenza Meneghetti12Giuseppe Curigliano13Enrico Cassano14Breast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, ItalyBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, ItalyBreast Radiology, Fondazione IRCCS Istituto Nazionale dei Tumori, 20133 Milano, ItalyDepartment of Radiological and Hematological Sciences, Catholic University of the Sacred Heart, Largo Francesco Vito 1, 00168 Rome, ItalyBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, ItalyMolecular and Pharmaco-Epidemiology Unit, Department of Experimental Oncology, IEO IRCCS, 20139 Milan, ItalyMolecular and Pharmaco-Epidemiology Unit, Department of Experimental Oncology, IEO IRCCS, 20139 Milan, ItalyMolecular and Pharmaco-Epidemiology Unit, Department of Experimental Oncology, IEO IRCCS, 20139 Milan, ItalyMedical Physics Unit, IEO European Institute of Oncology IRCCS, Via Ripamonti 435, 20141 Milan, ItalyMedical Physics Unit, IEO European Institute of Oncology IRCCS, Via Ripamonti 435, 20141 Milan, ItalyMedical Physics Unit, IEO European Institute of Oncology IRCCS, Via Ripamonti 435, 20141 Milan, ItalyData Management, European Institute of Oncology IRCCS, 20141 Milan, ItalyBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, ItalyDepartment of Oncology and Hemato-Oncology, University of Milano, 20122 Milano, ItalyBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, ItalyWe aimed to investigate the association between the radiomic features of contrast-enhanced spectral mammography (CESM) images and a specific receptor pattern of breast neoplasms. In this single-center retrospective study, we selected patients with neoplastic breast lesions who underwent CESM before a biopsy and surgical assessment between January 2013 and February 2022. Radiomic analysis was performed on regions of interest selected from recombined CESM images. The association between the features and each evaluated endpoint (ER, PR, Ki-67, HER2+, triple negative, G2–G3 expressions) was investigated through univariate logistic regression. Among the significant and highly correlated radiomic features, we selected only the one most associated with the endpoint. From a group of 321 patients, we enrolled 205 malignant breast lesions. The median age at the exam was 50 years (interquartile range (IQR) 45–58). NGLDM_Contrast was the only feature that was positively associated with both ER and PR expression (<i>p</i>-values = 0.01). NGLDM_Coarseness was negatively associated with Ki-67 expression (<i>p</i>-value = 0.02). Five features SHAPE Volume(mL), SHAPE_Volume(vx), GLRLM_RLNU, NGLDM_Busyness and GLZLM_GLNU were all positively and significantly associated with HER2+; however, all of them were highly correlated. Radiomic features of CESM images could be helpful to predict particular molecular subtypes before a biopsy.https://www.mdpi.com/1422-0067/23/23/15322radiomicsCESMmolecular subtypesbreast cancer |
| spellingShingle | Luca Nicosia Anna Carla Bozzini Daniela Ballerini Simone Palma Filippo Pesapane Sara Raimondi Aurora Gaeta Federica Bellerba Daniela Origgi Paolo De Marco Giuseppe Castiglione Minischetti Claudia Sangalli Lorenza Meneghetti Giuseppe Curigliano Enrico Cassano Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner International Journal of Molecular Sciences radiomics CESM molecular subtypes breast cancer |
| title | Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner |
| title_full | Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner |
| title_fullStr | Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner |
| title_full_unstemmed | Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner |
| title_short | Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner |
| title_sort | radiomic features applied to contrast enhancement spectral mammography possibility to predict breast cancer molecular subtypes in a non invasive manner |
| topic | radiomics CESM molecular subtypes breast cancer |
| url | https://www.mdpi.com/1422-0067/23/23/15322 |
| work_keys_str_mv | AT lucanicosia radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT annacarlabozzini radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT danielaballerini radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT simonepalma radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT filippopesapane radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT sararaimondi radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT auroragaeta radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT federicabellerba radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT danielaoriggi radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT paolodemarco radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT giuseppecastiglioneminischetti radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT claudiasangalli radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT lorenzameneghetti radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT giuseppecurigliano radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner AT enricocassano radiomicfeaturesappliedtocontrastenhancementspectralmammographypossibilitytopredictbreastcancermolecularsubtypesinanoninvasivemanner |