Skip to main content
Journal cover image

Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ.

Publication ,  Journal Article
Zhu, Z; Harowicz, M; Zhang, J; Saha, A; Grimm, LJ; Hwang, ES; Mazurowski, MA
Published in: Comput Biol Med
December 2019

PURPOSE: To determine whether deep learning-based algorithms applied to breast MR images can aid in the prediction of occult invasive disease following the diagnosis of ductal carcinoma in situ (DCIS) by core needle biopsy. MATERIALS AND METHODS: Our study is retrospective. The data was collected from 2000 to 2014. In this institutional review board-approved study, we analyzed dynamic contrast-enhanced fat-saturated T1-weighted MRI sequences from 131 patients with a core needle biopsy-confirmed diagnosis of DCIS. We explored two different deep learning approaches to predict whether there was an occult invasive component in the analyzed tumors that was ultimately identified at surgical excision. In the first approach, we adopted the transfer learning strategy. Specifically, we used the pre-trained GoogleNet. In the second approach, we used a pre-trained network to extract deep features, and a support vector machine (SVM) that utilizes these features to predict the upstaging of DCIS. We used nested 10-fold cross validation and the area under the ROC curve (AUC) to estimate the performance of the predictive models. RESULTS: The best classification performance was obtained using the deep features approach with GoogleNet model pre-trained on ImageNet as the feature extractor and a polynomial kernel SVM used as the classifier (AUC = 0.70, 95% CI: 0.58-0.79). For the transfer learning based approach, the highest AUC obtained was 0.68 (95% CI: 0.57-0.77). CONCLUSIONS: Convolutional neural networks might be used to identify occult invasive disease in patients diagnosed with DCIS by core needle biopsy.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Comput Biol Med

DOI

EISSN

1879-0534

Publication Date

December 2019

Volume

115

Start / End Page

103498

Location

United States

Related Subject Headings

  • Support Vector Machine
  • Retrospective Studies
  • Predictive Value of Tests
  • Middle Aged
  • Magnetic Resonance Imaging
  • Humans
  • Female
  • Deep Learning
  • Carcinoma, Ductal, Breast
  • Breast Neoplasms
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhu, Z., Harowicz, M., Zhang, J., Saha, A., Grimm, L. J., Hwang, E. S., & Mazurowski, M. A. (2019). Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ. Comput Biol Med, 115, 103498. https://doi.org/10.1016/j.compbiomed.2019.103498
Zhu, Zhe, Michael Harowicz, Jun Zhang, Ashirbani Saha, Lars J. Grimm, E Shelley Hwang, and Maciej A. Mazurowski. “Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ.Comput Biol Med 115 (December 2019): 103498. https://doi.org/10.1016/j.compbiomed.2019.103498.
Zhu Z, Harowicz M, Zhang J, Saha A, Grimm LJ, Hwang ES, et al. Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ. Comput Biol Med. 2019 Dec;115:103498.
Zhu, Zhe, et al. “Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ.Comput Biol Med, vol. 115, Dec. 2019, p. 103498. Pubmed, doi:10.1016/j.compbiomed.2019.103498.
Zhu Z, Harowicz M, Zhang J, Saha A, Grimm LJ, Hwang ES, Mazurowski MA. Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ. Comput Biol Med. 2019 Dec;115:103498.
Journal cover image

Published In

Comput Biol Med

DOI

EISSN

1879-0534

Publication Date

December 2019

Volume

115

Start / End Page

103498

Location

United States

Related Subject Headings

  • Support Vector Machine
  • Retrospective Studies
  • Predictive Value of Tests
  • Middle Aged
  • Magnetic Resonance Imaging
  • Humans
  • Female
  • Deep Learning
  • Carcinoma, Ductal, Breast
  • Breast Neoplasms