Semi-supervised generative adversarial networks for the segmentation of the left ventricle in pediatric MRI

Segmentation of the left ventricle in magnetic resonance imaging (MRI) is important for assessing cardiac function. We present DT-GAN, a generative adversarial network (GAN) segmentation approach for the identification of the left ventricle in pediatric MRI. Segmentation of the left ventricle requires a large amount of annotated data; generating such data can be time-consuming and subject to observer variability. Additionally, it can be difficult to accomplish in a clinical setting. During the training of our GAN, we therefore introduce a semi-supervised semantic segmentation to reduce the number of images required for training, while maintaining a good segmentation accuracy. The GAN generator produces a segmentation label map and its discriminator outputs a confidence map, which gives the probability of a pixel coming from the label or from the generator. Moreover, we propose a new formulation of the GAN loss function based on distance transform and pixel-wise cross-entropy. This new loss function provides a better segmentation of boundary pixels, by favoring the correct classification of those pixels rather than focusing on pixels that are farther away from the boundary between anatomical structures. Our proposed method achieves a mean Hausdorff distance of 2.16 mm +/- 0.42 mm (2.28 mm +/- 0.21 mm for U-Net) and a Dice score of 0.88 +/- 0.08 (0.91 +/- 0.12 for U-Net) for the endocardium segmentation, using 50% of the annotated data. For the epicardium segmentation, we achieve a mean Hausdorff distance of 2.23 mm +/- 0.35 mm (2.34 mm +/- 0.39 mm for U-Net) and a Dice score of 0.93 mm +/- 0.04 mm (0.89 +/- 0.09 for U-Net). For the myocardium segmentation, we achieve a mean Hausdorff distance of 2.98 mm +/- 0.43 mm (3.04 mm +/- 0.27 mm for U-Net) and a Dice score of 0.79 mm +/- 0.10 mm (0.74 +/- 0.04 for U-Net). This new model could be very useful for the automatic analysis of cardiac MRI and for conducting large-scale studies based on MRI readings, with a limited amount of training data.