Simple low-cost approaches to semantic segmentation in radiation therapy planning for prostate cancer using deep learning with non-contrast planning CT images
Simple low-cost approaches to semantic segmentation in radiation therapy planning for prostate cancer using deep learning with non-contrast planning CT images
复制标题
DOI：
10.1016/j.ejmp.2020.09.004
复制
发表时间：
2020-10-01
影响因子：
3.4
通讯作者：
Shigematsu, Naoyuki
中科院分区：
文献类型：
--
作者：
Nemoto, Takafumi;Futakami, Natsumi;Shigematsu, Naoyuki
目的：深度学习在语义分割方面表现出很大的功效。然而，由于伦理问题的复杂性和单个机构可用的成像研究数量有限，因此在医学成像数据的收集、标记和管理方面存在困难。本研究旨在找到一种简单且低成本的方法来提高深度学习语义分割的准确性，用于前列腺癌的放射治疗。方法：总共有556例前列腺癌放射治疗的非增强CT图像使用二维U-Net进行了检查。最初，所有切片都用于输入数据。然后，我们切除了颅骨部分的切片，这些切片超出了膀胱和直肠的边缘。最后，将膀胱和直肠的地面真值标签作为通道添加到前列腺训练dataset.Results的输入中：在56例病例的测试数据集中，每个器官的最高平均骰子相似系数（DSC）分别为0.85 +/- 0.05，0.94 +/- 0.04和0.85 +/- 0.07，分别为前列腺，膀胱和直肠。从原始图像中去除颅骨切片显著增加了直肠的DSC，从0.83 +/- 0.09增加到0.85 +/- 0.07（p < 0.05）。将膀胱和直肠信息添加到前列腺训练中而不移除切片，将前列腺的DSC从0.79 +/- 0.05显著增加到0.85 +/- 0.05（p < 0.05）。结论：这些无成本的方法可能对新应用有用，其中可能包括更新的模型和数据集。它们可能适用于其他器官风险（OAR）和临床目标，如选择性淋巴结照射。
Purpose: Deep learning has shown great efficacy for semantic segmentation. However, there are difficulties in the collection, labeling and management of medical imaging data, because of ethical complications and the limited number of imaging studies available at a single facility.This study aimed to find a simple and low-cost method to increase the accuracy of deep learning semantic segmentation for radiation therapy of prostate cancer.Methods: In total, 556 cases with non-contrast CT images for prostate cancer radiation therapy were examined using a two-dimensional U-Net. Initially, all slices were used for the input data. Then, we removed slices of the cranial portions, which were beyond the margins of the bladder and rectum. Finally, the ground truth labels for the bladder and rectum were added as channels to the input for the prostate training dataset.Results: The highest mean dice similarity coefficients (DSCs) for each organ in the test dataset of 56 cases were 0.85 +/- 0.05, 0.94 +/- 0.04 and 0.85 +/- 0.07 for the prostate, bladder and rectum, respectively. Removal of the cranial slices from the original images significantly increased the DSC of the rectum from 0.83 +/- 0.09 to 0.85 +/- 0.07 (p < 0.05). Adding bladder and rectum information to prostate training without removing the slices significantly increased the DSC of the prostate from 0.79 +/- 0.05 to 0.85 +/- 0.05 (p < 0.05).Conclusions: These cost-free approaches may be useful for new applications, which may include updated models and datasets. They may be applicable to other organs at risk (OARs) and clinical targets such as elective nodal irradiation.