Accurate colorectal tumor segmentation for CT scans based on the label assignment generative adversarial network
Accurate colorectal tumor segmentation for CT scans based on the label assignment generative adversarial network
复制标题
DOI：
10.1002/mp.13584
复制
发表时间：
2019-08-01
期刊：
影响因子：
3.8
通讯作者：
Li, Xueyan
中科院分区：
文献类型：
--
作者：
Liu, Xiaoming;Guo, Shuxu;Li, Xueyan
目的结直肠肿瘤分割是结直肠癌分析和诊断的重要步骤。这项任务非常耗时，因为它通常由放射科医生手动执行。本文提出了一种自动后处理模块来细化深度网络的分割。标签分配生成对抗网络（LAGAN）是从生成对抗网络（GAN）改进而来的，它为深度网络的输出分配标签。我们应用 LAGAN 在计算机断层扫描 (CT) 扫描中分割结直肠肿瘤，并探索深度网络不同组合的性能。材料和方法 共有 223 名结直肠癌 (CRC) 患者参加了该研究。结直肠肿瘤的 CT 扫描首先分别通过 FCN32 和 Unet 进行分割，输出概率图。然后，概率图通过LAGAN进行标记，最后得到二值分割结果。 LAGAN由生成模型和判别模型组成。生成模型利用深层网络的概率图来模拟基本事实的分布，而判别模型则试图区分生成和基本事实。通过竞争训练，LAGAN的生成模型可以实现概率图的标签分配。结果 LAGAN 将 FCN32 的 DSC 从 81.83% +/- 0.35% 增加到 90.82% +/- 0.36%。在基于 Unet 的分割中，LAGAN 将 DSC 从 86.67% +/- 0.70% 增加到 91.54% +/- 0.53%。细化单个 CT 切片大约需要 10 毫秒。结论 结果表明 LAGAN 是一个强大且灵活的模块，可用于细化各种深度网络的分割。与其他网络相比，LAGAN 可以实现结直肠肿瘤的理想分割精度。
Purpose Colorectal tumor segmentation is an important step in the analysis and diagnosis of colorectal cancer. This task is a time consuming one since it is often performed manually by radiologists. This paper presents an automatic postprocessing module to refine the segmentation of deep networks. The label assignment generative adversarial network (LAGAN) is improved from the generative adversarial network (GAN) and assigns labels to the outputs of deep networks. We apply the LAGAN to segment colorectal tumors in computed tomography (CT) scans and explore the performances of different combinations of deep networks. Material and methods A total of 223 patients with colorectal cancer (CRC) are enrolled in the study. The CT scans of the colorectal tumors are first segmented by FCN32 and Unet separately, which output probabilistic maps. Then, the probabilistic maps are labeled by the LAGAN and finally, the binary segmentation results are obtained. The LAGAN consists of a generating model and a discriminating model. The generating model utilizes the probabilistic maps from deep networks to imitate the distribution of the ground truths, and the discriminating model attempts to distinguish generations and ground truths. Through competitive training, the generating model of the LAGAN can realize label assignments for the probabilistic maps. Results The LAGAN increases the DSC of FCN32 from 81.83% +/- 0.35% to 90.82% +/- 0.36%. In the Unet-based segmentation, the LAGAN increases the DSC from 86.67% +/- 0.70% to 91.54% +/- 0.53%. It takes approximately 10 ms to refine a single CT slice. Conclusions The results demonstrate that the LAGAN is a robust and flexible module, which can be used to refine the segmentation of diverse deep networks. Compared with other networks, the LAGAN can achieve desirable segmented accuracy for colorectal tumors.