Digital mammographic tumor classification using transfer learning from deep convolutional neural networks

Benjamin Q. Huynh; Hui Li; Maryellen L. Giger

doi:10.1117/1.JMI.3.3.034501

Abstract

Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve (AUC)=0.81]. Further, the performance of ensemble classifiers based on both types was significantly better than that of either classifier type alone (AUC=0.86 versus 0.81, p=0.022). We conclude that transfer learning can improve current CADx methods while also providing standalone classifiers without large datasets, facilitating machine-learning methods in radiomics and precision medicine.

Citation Download Citation

Benjamin Q. Huynh, Benjamin Q. Huynh, Hui Li, Hui Li, Maryellen L. Giger, Maryellen L. Giger, } "Digital mammographic tumor classification using transfer learning from deep convolutional neural networks," Journal of Medical Imaging 3(3), 034501 (22 August 2016). https://doi.org/10.1117/1.JMI.3.3.034501 . Submission:

ACCESS THE FULL ARTICLE

PERSONAL SIGN IN
Full access may be available with your subscription

Email or Username Forgot your username?

Password Forgot your password?

Show

Remember Email/Username on this computer

Remember Password

No SPIE account? Create an account
or Institutional Sign In via Shibboleth

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $20.00

Non-members: $25.00 ADD TO CART

Show All Keywords

Keywords/Phrases

Search In:

Publication Years