DCGANs for Realistic Breast Mass Augmentation in X-ray Mammography

TL;DR

This paper demonstrates that using DCGANs to generate realistic breast mass images and applying flipping augmentation can significantly improve lesion detection accuracy in imbalanced mammography datasets.

Contribution

It introduces a method to synthesize diverse, realistic breast mass images using DCGANs to enhance deep learning performance in medical image classification.

Findings

DCGAN-generated images improve F1 score by up to 0.09.

Synthetic images with flipping outperform traditional augmentation.

DCGANs produce diverse, photo-realistic breast mass patches.

Abstract

Early detection of breast cancer has a major contribution to curability, and using mammographic images, this can be achieved non-invasively. Supervised deep learning, the dominant CADe tool currently, has played a great role in object detection in computer vision, but it suffers from a limiting property: the need of a large amount of labelled data. This becomes stricter when it comes to medical datasets which require high-cost and time-consuming annotations. Furthermore, medical datasets are usually imbalanced, a condition that often hinders classifiers performance. The aim of this paper is to learn the distribution of the minority class to synthesise new samples in order to improve lesion detection in mammography. Deep Convolutional Generative Adversarial Networks (DCGANs) can efficiently generate breast masses. They are trained on increasing-size subsets of one mammographic dataset and used to generate diverse and realistic breast masses. The effect of including the generated images and/or applying horizontal and vertical flipping is tested in an environment where a 1:10 imbalanced dataset of masses and normal tissue patches is classified by a fully-convolutional network. A maximum of ~ 0:09 improvement of F1 score is reported by using DCGANs along with flipping augmentation over using the original images. We show that DCGANs can be used for synthesising photo-realistic breast mass patches with considerable diversity. It is demonstrated that appending synthetic images in this environment, along with flipping, outperforms the traditional augmentation method of flipping solely, offering faster improvements as a function of the training set size.