Skip to main content
Journal cover image

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set.

Publication ,  Journal Article
Cain, EH; Saha, A; Harowicz, MR; Marks, JR; Marcom, PK; Mazurowski, MA
Published in: Breast Cancer Res Treat
January 2019

PURPOSE: To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients. METHODS: Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient's pre-treatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple-negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated. RESULTS: Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (0.707, 95% CI 0.582-0.833, p < 0.002). CONCLUSIONS: The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Breast Cancer Res Treat

DOI

EISSN

1573-7217

Publication Date

January 2019

Volume

173

Issue

2

Start / End Page

455 / 463

Location

Netherlands

Related Subject Headings

  • Triple Negative Breast Neoplasms
  • Treatment Outcome
  • Retrospective Studies
  • Receptor, erbB-2
  • Receptor, ErbB-2
  • ROC Curve
  • Oncology & Carcinogenesis
  • Neoplasm Staging
  • Neoadjuvant Therapy
  • Middle Aged
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Cain, E. H., Saha, A., Harowicz, M. R., Marks, J. R., Marcom, P. K., & Mazurowski, M. A. (2019). Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat, 173(2), 455–463. https://doi.org/10.1007/s10549-018-4990-9
Cain, Elizabeth Hope, Ashirbani Saha, Michael R. Harowicz, Jeffrey R. Marks, P Kelly Marcom, and Maciej A. Mazurowski. “Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set.Breast Cancer Res Treat 173, no. 2 (January 2019): 455–63. https://doi.org/10.1007/s10549-018-4990-9.
Cain, Elizabeth Hope, et al. “Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set.Breast Cancer Res Treat, vol. 173, no. 2, Jan. 2019, pp. 455–63. Pubmed, doi:10.1007/s10549-018-4990-9.
Journal cover image

Published In

Breast Cancer Res Treat

DOI

EISSN

1573-7217

Publication Date

January 2019

Volume

173

Issue

2

Start / End Page

455 / 463

Location

Netherlands

Related Subject Headings

  • Triple Negative Breast Neoplasms
  • Treatment Outcome
  • Retrospective Studies
  • Receptor, erbB-2
  • Receptor, ErbB-2
  • ROC Curve
  • Oncology & Carcinogenesis
  • Neoplasm Staging
  • Neoadjuvant Therapy
  • Middle Aged