Conditional Generative Adversarial and Convolutional Networks for X-ray Breast Mass Segmentation and Shape Classification

TL;DR

This paper introduces a conditional GAN-based method for accurate breast mass segmentation in mammography, achieving high accuracy even with limited data, and a CNN for tumor shape classification with 72% accuracy.

Contribution

The paper presents a novel cGAN approach for breast mass segmentation and a CNN for tumor shape classification, outperforming existing methods.

Findings

Segmentation accuracy with Dice coefficient >94% and Jaccard index >89%.

Effective shape classification with approximately 72% accuracy.

Method performs well on public and private datasets.

Abstract

This paper proposes a novel approach based on conditional Generative Adversarial Networks (cGAN) for breast mass segmentation in mammography. We hypothesized that the cGAN structure is well-suited to accurately outline the mass area, especially when the training data is limited. The generative network learns intrinsic features of tumors while the adversarial network enforces segmentations to be similar to the ground truth. Experiments performed on dozens of malignant tumors extracted from the public DDSM dataset and from our in-house private dataset confirm our hypothesis with very high Dice coefficient and Jaccard index (>94% and >89%, respectively) outperforming the scores obtained by other state-of-the-art approaches. Furthermore, in order to detect portray significant morphological features of the segmented tumor, a specific Convolutional Neural Network (CNN) have also been designed for classifying the segmented tumor areas into four types (irregular, lobular, oval and round), which provides an overall accuracy about 72% with the DDSM dataset.