Conditional Generative Adversarial and Convolutional Networks for X-ray Breast Mass Segmentation and Shape Classification
This work addresses breast cancer diagnosis by improving segmentation and shape classification for medical imaging, but it is incremental as it builds on existing cGAN and CNN methods.
The paper tackled breast mass segmentation in mammography using a conditional Generative Adversarial Network (cGAN), achieving Dice coefficients >94% and Jaccard indices >89% on limited training data, and classified segmented tumors into four shape types with about 72% accuracy.
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.