Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, Shaanxi 710071, People's Republic of China. Department of Radiation Oncology, University of California-Los Angeles, Los Angeles, CA 90095, United States of America.
Phys Med Biol. 2020 Jul 13;65(13):135011. doi: 10.1088/1361-6560/ab9b57.
Automated multi-organ segmentation on abdominal CT images may replace or complement manual segmentation for clinical applications including image-guided radiation therapy. However, the accuracy of auto-segmentation is challenged by low image contrast, large spatial and inter-patient anatomical variations. In this study, we propose an end-to-end segmentation network, termed self-paced DenseNet, for improved multi-organ segmentation performance, especially for the difficult-to-segment organs. Specifically, a learning-based attention mechanism and dense connection block are seamlessly integrated into the proposed self-paced DenseNet to improve the learning capability and efficiency of the backbone network. To heavily focus on the organs showing low soft-tissue contrast and motion artifacts, a boundary condition is utilized to constrain the network optimization. Additionally, to ease the large learning pace discrepancies of individual organs, a task-wise self-paced-learning strategy is employed to adaptively control the learning paces of individual organs. The proposed self-paced DenseNet was trained and evaluated on a public abdominal CT data set consisting of 90 subjects with manually labeled ground truths of eight organs (including spleen, left kidney, esophagus, gallbladder, stomach, liver, pancreas, and duodenum). For quantitative evaluation, the Dice similarity coefficient (DSC) and average surface distance (ASD) were calculated. An average DSC of 84.46% and ASD of 1.82 mm were achieved on the eight organs, which outperforms the state-of-the-art segmentation methods 2.96% on DSC under the same experimental configuration. Moreover, the proposed segmentation method shows notable improvements on the duodenum and gallbladder, obtaining an average DSC of 69.26% and 80.94% and ASD of 2.14 mm and 2.24 mm, respectively. The results are markedly superior to the average DSC of 63.12% and 76.35% and average ASD of 3.87 mm and 4.33 mm using the vanilla DenseNet, respectively, for the two organs. We demonstrated the effectiveness of the proposed self-paced DenseNet to automatically segment abdominal organs with low boundary conspicuity. The self-paced DenseNet achieved consistently superior segmentation performance on eight abdominal organs with varying segmentation difficulties. The demonstrated computational efficiency (<2 s/CT) makes it well-suited for online applications.
基于 CT 图像的自动多器官分割可能会替代或补充临床应用中的手动分割，包括图像引导的放射治疗。然而，自动分割的准确性受到图像对比度低、空间和患者间解剖结构差异大的挑战。在这项研究中，我们提出了一种端到端分割网络，称为自步密集网络，以提高多器官分割性能，特别是对于难以分割的器官。具体来说，基于学习的注意力机制和密集连接块被无缝集成到所提出的自步密集网络中，以提高骨干网络的学习能力和效率。为了重点关注软组织对比度低和运动伪影的器官，利用边界条件来约束网络的优化。此外，为了缓解各个器官的学习步伐差异较大的问题，采用任务式自步学习策略来自适应地控制各个器官的学习步伐。所提出的自步密集网络在一个包含 90 名受试者的公共腹部 CT 数据集上进行了训练和评估，这些受试者的 8 个器官（包括脾脏、左肾、食管、胆囊、胃、肝、胰腺和十二指肠）均有手动标记的地面真实值。为了进行定量评估，计算了 Dice 相似系数（DSC）和平均表面距离（ASD）。在八个器官上，分别获得了 84.46%的平均 DSC 和 1.82mm 的平均 ASD，在相同的实验配置下，比最先进的分割方法高出 2.96%的 DSC。此外，所提出的分割方法在十二指肠和胆囊上取得了显著的改进，分别获得了 69.26%和 80.94%的平均 DSC 和 2.14mm 和 2.24mm 的平均 ASD，明显优于这两个器官使用普通密集网络时的平均 DSC 63.12%和 76.35%以及平均 ASD 3.87mm 和 4.33mm。我们证明了所提出的自步密集网络在自动分割低边界显著性的腹部器官方面的有效性。自步密集网络在具有不同分割难度的八个腹部器官上均取得了一致的优越分割性能。所展示的计算效率（<2s/CT）使其非常适合在线应用。
