Decourt Colin, Duong Luc
Bordeaux INP - ENSEIRB-MATMECA, 1 Avenue du Dr Albert Schweitzer, Talence, France.
Ecole de technologie superieure, Department of Software and IT Engineering, 1100 Notre-Dame W., Montreal, Canada.
Comput Biol Med. 2020 Aug;123:103884. doi: 10.1016/j.compbiomed.2020.103884. Epub 2020 Jun 29.
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.
磁共振成像（MRI）中左心室的分割对于评估心脏功能至关重要。我们提出了DT-GAN，一种用于在儿科MRI中识别左心室的生成对抗网络（GAN）分割方法。左心室的分割需要大量带注释的数据；生成此类数据可能既耗时又受观察者差异影响。此外，在临床环境中也可能难以完成。因此，在我们的GAN训练过程中，我们引入了半监督语义分割，以减少训练所需的图像数量，同时保持良好的分割精度。GAN生成器生成一个分割标签图，其判别器输出一个置信度图，该图给出了一个像素来自标签或生成器的概率。此外，我们基于距离变换和逐像素交叉熵提出了一种新的GAN损失函数公式。这种新的损失函数通过更倾向于对边界像素进行正确分类，而不是关注远离解剖结构边界的像素，从而实现了对边界像素更好的分割。使用50%的带注释数据，我们提出的方法在内膜分割方面实现了平均豪斯多夫距离为2.16毫米±0.42毫米（U-Net为2.28毫米±0.21毫米），骰子系数为0.88±0.08（U-Net为0.91±0.12）。对于外膜分割，我们实现了平均豪斯多夫距离为2.23毫米±0.35毫米（U-Net为2.34毫米±0.39毫米），骰子系数为0.93毫米±0.04毫米（U-Net为0.89±0.09）。对于心肌分割，我们实现了平均豪斯多夫距离为2.98毫米±0.43毫米（U-Net为3.04毫米±0.27毫米），骰子系数为0.79毫米±0.10毫米（U-Net为0.74±0.04）。这种新模型对于心脏MRI的自动分析以及基于有限数量的训练数据进行大规模MRI读数研究可能非常有用。
