Lesion classification in mammograms using convolutional neural networks and transfer learning

ABSTRACT

Convolutional neural networks (CNNs) have recently been successfully used in the medical field to detect and classify pathologies in different imaging modalities, including in mammography. One disadvantage of CNNs is the need for large training datasets, which are particularly difficult to obtain in the medical domain. One way to solve this problem is using a transfer learning approach, in which a CNN, previously pre-trained with a large amount of labelled non-medical data, is subsequently fine-tuned using a smaller dataset of medical data. In this paper, we use such a transfer learning approach, which is applied to three different networks that were pre-trained using the Imagenet dataset. We investigate how the performance of these pre-trained CNNs to classify lesions in mammograms is affected by the use, or not, of normalised images during the fine-tuning stage. We also assess the performance of a support vector machine fed with features extracted from the CNN and the combined use of handcrafted features to complement the CNN-extracted features. The obtained results are encouraging.

KEYWORDS:

• Mammographic image
• convolutional neural network
• transfer learning
• support vector machine
• breast cancer
• lesion classification

Acknowledgements

This work was supported by National Funding from the FCT – Fundação para a Ciência e a Tecnologia, through the UID/EEA/50008/2013 Project. The database used in this work was a courtesy of MA Guevara and coauthors, Breast Cancer Digital Repository Consortium.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the FCT – Fundação para a Ciência e a Tecnologia, through the UID/EEA/50008/2013 Project.