Multi-parametric MRI-based radiomics models for predicting molecular subtype and androgen receptor expression in breast cancer
Open accessAbstract
Objective: To investigate whether radiomics features extracted from multi-parametric MRI combining machine learning approach can predict molecular subtype and androgen receptor (AR) expression of breast cancer in a non-invasive way. Materials and Methods: Patients diagnosed with clinical T2–4 stage breast cancer from March 2016 to July 2020 were retrospectively enrolled. The molecular subtypes and AR expression in pre-treatment biopsy specimens were assessed. A total of 4,198 radiomics features were extracted from the pre-biopsy multi-parametric MRI (including dynamic contrast-enhancement T1-weighted images, fat-suppressed T2-weighted images, and apparent diffusion coefficient map) of each patient. We applied several feature selection strategies including the least absolute shrinkage and selection operator (LASSO), and recursive feature elimination (RFE), the maximum relevance minimum redundancy (mRMR), Boruta and Pearson correlation analysis, to select the most optimal features. We then built 120 diagnostic models using distinct classification algorithms and feature sets divided by MRI sequences and selection strategies to predict molecular subtype and AR expression of breast cancer in the testing dataset of leave-one-out cross-validation (LOOCV). The performances of binary classification models were assessed via the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). And the performances of multiclass classification models were assessed via AUC, overall accuracy, precision, recall rate, and F1-score. Results: A total of 162 patients (mean age, 46.91 ± 10.08 years) were enrolled in this study; 30 were low-AR expression and 132 were high-AR expression. HR+/HER2− cancers were diagnosed in 56 cases (34.6%), HER2+ cancers in 81 cases (50.0%), and TNBC in 25 patients (15.4%). There was no significant difference in clinicopathologic characteristics between low-AR and high-AR groups (P > 0.05), except the menopausal status, ER, PR, HER2, and Ki-67 index (P = 0.043, <0.001, <0.001, 0.015, and 0.006, respectively). No significant difference in clinicopathologic characteristics was observed among three molecular subtypes except the AR status and Ki-67 (P = <0.001 and 0.012, respectively). The Multilayer Perceptron (MLP) showed the best performance in discriminating AR expression, with an AUC of 0.907 and an accuracy of 85.8% in the testing dataset. The highest performances were obtained for discriminating TNBC vs. non-TNBC (AUC: 0.965, accuracy: 92.6%), HER2+ vs. HER2− (AUC: 0.840, accuracy: 79.0%), and HR+/HER2− vs. others (AUC: 0.860, accuracy: 82.1%) using MLP as well. The micro-AUC of MLP multiclass classification model was 0.896, and the overall accuracy was 0.735. Conclusions: Multi-parametric MRI-based radiomics combining with machine learning approaches provide a promising method to predict the molecular subtype and AR expression of breast cancer non-invasively.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Huang et al. [99] achieved an AUC of 0.907 and an accuracy of 85.8% with a Multilayer Perceptron (MLP).
“| Huang et al. [99] | multi-parametric MRI | MRI | Private dataset | Multilayer Perceptron (MLP): 0.907 (AUC) and 85.8% (ACC) |”
From A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis (2024) · cites this paper as [99]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21660 · Cited by 108,699 · see citing works
PD-1 and PD-L1 Immune Checkpoint Blockade to Treat Breast Cancer
Hartkopf, A. D., Taran, F., Wallwiener, M., Walter, C. B., Krämer, B., Grischke, E., & Brucker, S. Y. (2016) · Breast Care · doi:10.1159/000453569 · Cited by 30,989 · see citing works
Nishimura, R., Osako, T., Nishiyama, Y., Tashima, R., Nakano, M., Fujisue, M., Toyozumi, Y., & Arima, N. (2013) · Oncology · doi:10.1159/000353099 · Cited by 13,239 · see citing works
Comprehensive molecular portraits of human breast tumours
The Cancer Genome Atlas Network (2012) · Nature · doi:10.1038/nature11412 · Cited by 12,129 · see citing works
Peng, H., Long, F., & Ding, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.159 · Cited by 10,614 · see citing works
Waks, A. G., & Winer, E. P. (2019) · JAMA · doi:10.1001/jama.2018.19323 · Cited by 4,913 · see citing works
Goldhirsch, A., Wood, W. C., Coates, A. S., Gelber, R. D., Thurlimann, B. J. K., & Senn, H.-J. (2011) · Annals of Oncology · doi:10.1093/annonc/mdr304 · Cited by 3,839 · see citing works
A comparison of random forest variable selection methods for classification prediction modeling
Speiser, J. L., Miller, M. E., Tooze, J., & Ip, E. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.05.028 · Cited by 1,561 · see citing works
Gucalp, A., Tolaney, S. M., Isakoff, S. J., Ingle, J. N., Liu, M., Carey, L., Blackwell, K., Rugo, H. S., Nabell, L. M., Forero, A., et al. (2013) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-12-3327 · Cited by 750 · see citing works
Quantitative Imaging in Cancer Evolution and Ecology
Gatenby, R. A., Grove, O., & Gillies, R. J. (2013) · Radiology · doi:10.1148/radiol.13122697 · Cited by 515 · see citing works
On behalf of the EUSOBI international Breast Diffusion-Weighted Imaging working group, Baltzer, P., Mann, R. M., et al. (2019) · European Radiology · doi:10.1007/s00330-019-06510-3 · Cited by 438 · see citing works
Dieci, M. V., Radosevic‐Robin, N., Fineberg, S., den Eynden, G. V., Ternès, N., Penault-Llorca, F. M., Pruneri, G., D’Alfonso, T. M., Demaria, S., Castañeda, C. A., et al. (2017) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2017.10.003 · Cited by 431 · see citing works
Vera-Badillo, F., Templeton, A. J., Gouveia, P. D., Díaz-Padilla, I., Bedard, P. L., Al-Mubarak, M., Šeruga, B., Tannock, I. F., Ocaña, A., & Amir, E. (2013) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djt319 · Cited by 370 · see citing works
Endocrine resistance in breast cancer – An overview and update
Clarke, R. C., Tyson, J. J., & Dixon, J. M. (2015) · Molecular and Cellular Endocrinology · doi:10.1016/j.mce.2015.09.035 · Cited by 356 · see citing works
The Biological Meaning of Radiomic Features
Tomaszewski, M. R., & Gillies, R. J. (2021) · Radiology · doi:10.1148/radiol.2021219005 · Cited by 327 · see citing works
New Strategies for Triple-Negative Breast Cancer—Deciphering the Heterogeneity
Mayer, I. A., Abramson, V. G., Lehmann, B. D., & Pietenpol, J. A. (2014) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-13-0583 · Cited by 320 · see citing works
Androgen receptor in triple negative breast cancer: A potential target for the targetless subtype
Gerratana, L., Basile, D., Buono, G., Placido, S. D., Giuliano, M., Minichillo, S., Coinu, A., Martorana, F., Santo, I. D., Mastro, L. D., et al. (2018) · Cancer Treatment Reviews · doi:10.1016/j.ctrv.2018.06.005 · Cited by 287 · see citing works
Breast Cancer Type Classification Using Machine Learning
Wu, J., & Hicks, C. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11020061 · Cited by 260 · see citing works
Mutant p53 in breast cancer: potential as a therapeutic target and biomarker
Duffy, M. J., Synnott, N. C., & Crown, J. P. (2018) · Breast Cancer Research and Treatment · doi:10.1007/s10549-018-4753-7 · Cited by 234 · see citing works
Trastuzumab in the Treatment of Breast Cancer
Maximiano, S., Magalhães, P., Guerreiro, M. P., & Morgado, M. (2016) · BioDrugs · doi:10.1007/s40259-016-0162-9 · Cited by 226 · see citing works
Youk, J. H., Son, E. J., Chung, J. I., Kim, J., & Kim, E. (2012) · European Radiology · doi:10.1007/s00330-012-2425-2 · Cited by 222 · see citing works
Ericsson, P. I. G., Stovgaard, E. S., Sua, L. F., Reisenbichler, E., Kos, Z., Carter, J. M., Michiels, S., Quesne, J. P. C. L., Nielsen, T. O., Lænkholm, A., et al. (2020) · The Journal of Pathology · doi:10.1002/path.5406 · Cited by 211 · see citing works
Diffusion MRI of the breast: Current status and future directions
Iima, M., Honda, M., Sigmund, E. E., Kishimoto, A. O., Kataoka, M., & Togashi, K. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26908 · Cited by 187 · see citing works
Bickelhaupt, S., Paech, D., Kickingereder, P., Steudle, F., Lederer, W., Daniel, H., GOETZ, M. A., Gählert, N., Tichy, D., Wiesenfarth, M., et al. (2017) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.25606 · Cited by 135 · see citing works
Ha, R. S., Mutasa, S., Karcich, J., Gupta, N., Sant, E. P. V., Nemer, J. S., Sun, M., Chang, P., Liu, M. Z., & Jambawalikar, S. (2019) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-019-00179-2 · Cited by 124 · see citing works
Lee, J. Y., Lee, K., Seo, B. K., Cho, K. R., Woo, O. H., Song, S. E., Kim, E., Lee, H. Y., Kim, J. S., & Cha, J. (2021) · European Radiology · doi:10.1007/s00330-021-08146-8 · Cited by 124 · see citing works
Yamamoto, S., Han, W., Kim, Y., Du, L., Jamshidi, N., Huang, D., Kim, J. H., & Kuo, M. (2015) · Radiology · doi:10.1148/radiol.15142698 · Cited by 120 · see citing works
Božović‐Spasojević, I., Zardavas, D., Brohée, S., Ameye, L., Fumagalli, D., Ades, F., de Azambuja, E., Barèche, Y., Piccart, M. J., Paesmans, M., et al. (2016) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-16-0979 · Cited by 117 · see citing works
Aleskandarany, M. A., Abduljabbar, R. F., Ashankyty, I., Elmouna, A., Jerjees, D. A., Ali, S., Buluwela, L., Diez, M., Caldas, C., Green, A. R., et al. (2016) · Breast Cancer Research and Treatment · doi:10.1007/s10549-016-3934-5 · Cited by 101 · see citing works
Jiang, M., Zhang, D., Tang, S.-C., Luo, X., Chuan, Z.-R., Lv, W., Jiang, F., Ni, X., Cui, X., & Dietrich, C. F. (2020) · European Radiology · doi:10.1007/s00330-020-07544-8 · Cited by 101 · see citing works
Androgen receptor signaling pathways as a target for breast cancer treatment
Pietri, E., Conteduca, V., Andreis, D., Massa, I., Melegari, E., Sarti, S., Cecconetto, L., Schirone, A., Bravaccini, S., Serra, P., et al. (2016) · Endocrine Related Cancer · doi:10.1530/erc-16-0190 · Cited by 97 · see citing works
Leithner, D., Mayerhoefer, M. E., Martinez, D. F., Jochelson, M. S., Morris, E. A., Thakur, S. B., & Pinker, K. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9061853 · Cited by 95 · see citing works
Forgia, D. L., Fanizzi, A., Campobasso, F., Bellotti, R., Didonna, V., Lorusso, V., Moschetta, M., Massafra, R., Tamborra, P., Tangaro, S., et al. (2020) · Diagnostics · doi:10.3390/diagnostics10090708 · Cited by 92 · see citing works
Xie, T., Zhao, Q., Fu, C., et al. (2018) · European Radiology · doi:10.1007/s00330-018-5804-5 · Cited by 89 · see citing works
Fan, M., Zhang, P., Wang, Y., et al. (2019) · European Radiology · doi:10.1007/s00330-018-5891-3 · Cited by 84 · see citing works
Chang, R., Chen, H., Chang, Y., Huang, C., Chen, J., & Lo, C. (2016) · Magnetic Resonance Imaging · doi:10.1016/j.mri.2016.03.001 · Cited by 83 · see citing works
Leithner, D., Bernard‐Davila, B., Martinez, D. F., et al. (2019) · Molecular Imaging and Biology · doi:10.1007/s11307-019-01383-w · Cited by 80 · see citing works
Fan, M., Hu, C., Zhang, P., et al. (2017) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.25921 · Cited by 78 · see citing works
Androgen Receptor Expression and Breast Cancer Survival: Results From the Nurses’ Health Studies
Kensler, K. H., Poole, E. M., Heng, Y. J., Collins, L. C., Glass, B., Beck, A. H., Hazra, A., ROSNER, B. A., Eliassen, A. H., Hankinson, S. E., et al. (2018) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djy173 · Cited by 66 · see citing works
Yamaguchi, K., Abé, H., Newstead, G. M., Egashira, R., Nakazono, T., Imaizumi, T., & Irié, H. (2014) · Breast Cancer · doi:10.1007/s12282-013-0512-0 · Cited by 63 · see citing works
Analysis of circulating tumor DNA in breast cancer as a diagnostic and prognostic biomarker
Rohanizadegan, M. (2018) · Cancer Genetics · doi:10.1016/j.cancergen.2018.02.002 · Cited by 54 · see citing works
Androgen receptor: A promising therapeutic target in breast cancer
Vasiliou, S. K., & Diamandis, E. P. (2019) · Critical Reviews in Clinical Laboratory Sciences · doi:10.1080/10408363.2019.1575643 · Cited by 52 · see citing works
Chaudhury, B., Zhou, M., Goldgof, D. B., Hall, L., Gatenby, R. A., Gillies, R. J., Patel, B., Weinfurtner, R. J., & Drukteinis, J. S. (2015) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.24921 · Cited by 51 · see citing works
Umutlu, L., Kirchner, J., Bruckmann, N. M., et al. (2021) · Cancers · doi:10.3390/cancers13122928 · Cited by 51 · see citing works
The prognostic value of androgen receptors in breast cancer subtypes
Kraby, M. R., Valla, M., Opdahl, S., et al. (2018) · Breast Cancer Research and Treatment · doi:10.1007/s10549-018-4904-x · Cited by 50 · see citing works
Chen, S.-J., Shu, Z.-Y., Li, Y., Chen, B., Tang, L., Mo, W.-J., Shao, G., & Shao, F. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2020.01410 · Cited by 46 · see citing works
Is there a correlation between 3T multiparametric MRI and molecular subtypes of breast cancer?
Montemezzi, S., Camera, L., Giri, M. G., et al. (2018) · European Journal of Radiology · doi:10.1016/j.ejrad.2018.09.024 · Cited by 43 · see citing works
Kato, F., Kudo, K., Yamashita, H., et al. (2015) · European Journal of Radiology · doi:10.1016/j.ejrad.2015.10.018 · Cited by 34 · see citing works
Ni, M., Zhou, X., Liu, J., Yu, H., Gao, Y., Zhang, X., & Li, Z. (2020) · BMC Cancer · doi:10.1186/s12885-020-07557-y · Cited by 34 · see citing works
Self-citationRadioproteomics in Breast Cancer: Prediction of Ki-67 Expression With MRI-based Radiomic Models
Kayadibi, Y., Koçak, B., Uçar, N., Akan, Y. N., Akbas, P., & Bektaş, S. (2021) · Academic Radiology · doi:10.1016/j.acra.2021.02.001 · Cited by 27 · see citing works
Classifying Breast Cancer Molecular Subtypes by Using Deep Clustering Approach
Rohani, N., & Eslahchi, C. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2020.553587 · Cited by 26 · see citing works
Influence of Androgen Receptor on the Prognosis of Breast Cancer
Hwang, K., Kim, Y. A., Kim, Y. A., et al. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9041083 · Cited by 24 · see citing works
Jahan, N., Jones, C., & Rahman, R. L. (2021) · Molecular and Cellular Endocrinology · doi:10.1016/j.mce.2021.111324 · Cited by 24 · see citing works
Witzel, I., Loibl, S., Wirtz, R. M., Fasching, P. A., Denkert, C., Weber, K. E., Lück, H., Huober, J., Karn, T., van Mackelenbergh, M., et al. (2019) · British Journal of Cancer · doi:10.1038/s41416-019-0630-3 · Cited by 23 · see citing works
Mansouri, H., Alcaraz, L. B., Mollévi, C., Mallavialle, A., Jacot, W., Boissière‐Michot, F., Simony-Lafontaine, J., Laurent‐Matha, V., Roger, P., Liaudet‐Coopman, E., et al. (2020) · Cancers · doi:10.3390/cancers12051244 · Cited by 23 · see citing works
Geady, C., Keller, H., Siddiqui, I. F. S., Bilkey, J., Dhani, N. C., & Jaffray, D. A. (2020) · Physica Medica · doi:10.1016/j.ejmp.2020.03.018 · Cited by 22 · see citing works
Heterogeneity analysis of MRI T2 maps for measurement of early tumor response to radiotherapy
Tomaszewski, M. R., Dominguez‐Viqueira, W., Ortiz, A. C., et al. (2020) · NMR in Biomedicine · doi:10.1002/nbm.4454 · Cited by 21 · see citing works
Akashi, M., Yamaguchi, R., Kusano, H., et al. (2020) · Breast Cancer Research and Treatment · doi:10.1007/s10549-020-05855-4 · Cited by 17 · see citing works
Leone, A. D., Fragomeni, S. M., Scardina, L., et al. (2021) · PubMed · doi:10.26355/eurrev_202102_25087 · Cited by 17 · see citing works
Targeted Treatment of Triple-Negative Breast Cancer
Young, J. A., & Tan, A. R. (2021) · The Cancer Journal · doi:10.1097/ppo.0000000000000495 · Cited by 15 · see citing works
Lehrer, M., Rao, A., Bhadra, A., Ravikumar, V., Chen, J. Y., Wintermark, M., Hwang, S. N., Holder, C. A., Huang, E. P., Fevrier-Sullivan, B., et al. (2017) · Oncoscience · doi:10.18632/oncoscience.353 · Cited by 9 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis
Xu, X., Li, J., Zhu, Z., Zhao, L., Wang, H., Song, C., Chen, Y., Zhao, Q., Yang, J., & Pei, Y. (2024) · Bioengineering · doi:10.3390/bioengineering11030219 · Cited by 242 · see citing works
- Authors
- Huang, Y., Wei, L., Hu, Y., Shao, N., Lin, Y., He, S., Shi, H., Zhang, X., & Lin, Y.
- Affiliations
- Sun Yat-sen University (CN)
- Corresponding author
- Zhang, Xiaoling
- Lin, Ying
- Venue
- Frontiers in Oncology
- Publisher
- Frontiers Media SA
- Published
- 2021-08-18
- Volume
- 11
- Pages
- 706733-706733
- ISSN
- 2234-943X (ISSN-L)
- PMC
- PMC8416497
- OpenAlex
- W3195423050
- Cited by
- 82
- References
- 62
- Citations by year
- 2026: 10 · 2025: 14 · 2024: 20 · 2023: 24 · 2022: 14
- FWCI
- 7.79
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Oncology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Sun Yat-sen University (2016007)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › MRI in cancer diagnosis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
- Keywords
- breast cancer, radiomics, multiparametric MRI, androgen receptor expression, molecular subtype prediction, triple-negative breast cancer, HER2-positive breast cancer, hormone receptor-positive breast cancer, apparent diffusion coefficient, dynamic contrast-enhanced MRI, feature selection, non-invasive prediction, Ki-67, Ki-67 proliferation index
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
