Nouvel Hôpital Civil, Institut Hospitalo-Universitaire de Strasbourg, 1 place de l'Hôpital, 67000, Strasbourg, France.
ICube UMR 7357, University of Strasbourg, CNRS, FMTS, 300 bd Sébastien Brant, 67412, Illkirch, France.
Int J Comput Assist Radiol Surg. 2019 Aug;14(8):1275-1284. doi: 10.1007/s11548-019-01989-z. Epub 2019 Apr 30.
We address the automatic segmentation of healthy and cancerous liver tissues (parenchyma, active and necrotic parts of hepatocellular carcinoma (HCC) tumor) on multiphase CT images using a deep learning approach.
We devise a cascaded convolutional neural network based on the U-Net architecture. Two strategies for dealing with multiphase information are compared: Single-phase images are concatenated in a multi-dimensional features map on the input layer, or output maps are computed independently for each phase before being merged to produce the final segmentation. Each network of the cascade is specialized in the segmentation of a specific tissue. The performances of these networks taken separately and of the cascaded architecture are assessed on both single-phase and on multiphase images.
In terms of Dice coefficients, the proposed method is on par with a state-of-the-art method designed for automatic MR image segmentation and outperforms previously used technique for interactive CT image segmentation. We validate the hypothesis that several cascaded specialized networks have a higher prediction accuracy than a single network addressing all tasks simultaneously. Although the portal venous phase alone seems to provide sufficient contrast for discriminating tumors from healthy parenchyma, the multiphase information brings significant improvement for the segmentation of cancerous tissues (active versus necrotic part).
The proposed cascaded multiphase architecture showed promising performances for the automatic segmentation of liver tissues, allowing to reliably estimate the necrosis rate, a valuable imaging biomarker of the clinical outcome.
我们使用深度学习方法解决多期 CT 图像上健康和癌性肝组织（实质、肝细胞癌（HCC）肿瘤的活动和坏死部分）的自动分割问题。
我们设计了一种基于 U-Net 架构的级联卷积神经网络。比较了两种处理多期信息的策略：单期图像在输入层的多维特征图中串联，或者为每个相位独立计算输出图，然后合并生成最终分割。级联中的每个网络都专门用于分割特定的组织。单独评估这些网络以及级联架构在单期和多期图像上的性能。
在 Dice 系数方面，该方法与专门用于自动 MR 图像分割的最新方法相当，优于以前用于交互式 CT 图像分割的技术。我们验证了这样一个假设，即几个级联的专用网络比同时处理所有任务的单个网络具有更高的预测准确性。尽管门静脉期似乎足以提供足够的对比度来区分肿瘤与健康实质，但多期信息对于癌性组织（活动与坏死部分）的分割有显著改善。
所提出的级联多期架构在肝脏组织的自动分割方面表现出有前景的性能，能够可靠地估计坏死率，这是临床结果的一个有价值的成像生物标志物。
