Self-Supervised Adversarial Learning with a Limited Dataset for Electronic Cleansing in Computed Tomographic Colonography: A Preliminary Feasibility Study.
Self-Supervised Adversarial Learning with a Limited Dataset for Electronic Cleansing in Computed Tomographic Colonography: A Preliminary Feasibility Study.
复制标题
DOI：
10.3390/cancers14174125
复制
发表时间：
2022-08-26
期刊：
影响因子：
5.2
通讯作者：
Yoshida, Hiroyuki
中科院分区：
文献类型：
--
作者：
Tachibana, Rie;Nappi, Janne J.;Hironaka, Toru;Yoshida, Hiroyuki
关键词：
电子清洁 (EC) 用于在 CT 结肠成像 (CTC) 图像上对结肠进行虚拟清洁，以进行结直肠癌筛查。然而，目前的EC方法精度有限，传统深度学习在CTC中的应用有限。我们评估了使用自监督对抗性学习在有限数据集上以亚体素精度执行 EC 的可行性。 3D 生成对抗网络经过预训练，可在拟人化结肠模型的 CTC 数据集上执行 EC，并使用自监督学习方案针对每个输入案例进行微调。在对 18 个临床 CTC 病例进行虚拟 3D 飞行检查时，该方法的虚拟清洁视觉感知质量优于商业 EC 软件。我们的结果表明，所提出的自我监督方案是解决结直肠癌筛查 CTC 中 EC 剩余技术问题的潜在有效方法。现有的计算机断层结肠成像 (CTC) 电子清洗 (EC) 方法通常基于图像分割，这限制了其对底层体素的准确性。由于可用于训练的 CTC 数据集的限制，传统深度学习在 EC 中的用途有限。本研究的目的是评估使用新颖的自监督对抗性学习方案在有限的训练数据集上以亚体素精度执行 EC 的技术可行性。三维 (3D) 生成对抗网络 (3D GAN) 经过预训练，可在拟人体模的 CTC 数据集上执行 EC。然后使用自监督方案对 3D GAN 进行微调以适应每个输入情况。 3D GAN 的架构通过模型研究进行了优化。在对 18 个临床 CTC 病例进行虚拟 3D 飞行检查时，所得到的 3D GAN 虚拟清洁的视觉感知质量优于商业 EC 软件。因此，所提出的自监督 3D GAN 可以训练在没有亚体素精度图像注释的小数据集上执行 EC，是解决 CTC 中 EC 剩余技术问题的潜在有效方法。
Electronic cleansing (EC) is used for performing a virtual cleansing of the colon on CT colonography (CTC) images for colorectal cancer screening. However, current EC methods have limited accuracy, and traditional deep learning is of limited use in CTC. We evaluated the feasibility of using self-supervised adversarial learning to perform EC on a limited dataset with subvoxel accuracy. A 3D generative adversarial network was pre-trained to perform EC on the CTC datasets of an anthropomorphic colon phantom, and it was fine-tuned to each input case by use of a self-supervised learning scheme. The visually perceived quality of the virtual cleansing by this method compared favorably to that of commercial EC software on the virtual 3D fly-through examinations of 18 clinical CTC cases. Our results indicate that the proposed self-supervised scheme is a potentially effective approach for addressing the remaining technical problems of EC in CTC for colorectal cancer screening. Existing electronic cleansing (EC) methods for computed tomographic colonography (CTC) are generally based on image segmentation, which limits their accuracy to that of the underlying voxels. Because of the limitations of the available CTC datasets for training, traditional deep learning is of limited use in EC. The purpose of this study was to evaluate the technical feasibility of using a novel self-supervised adversarial learning scheme to perform EC with a limited training dataset with subvoxel accuracy. A three-dimensional (3D) generative adversarial network (3D GAN) was pre-trained to perform EC on CTC datasets of an anthropomorphic phantom. The 3D GAN was then fine-tuned to each input case by use of the self-supervised scheme. The architecture of the 3D GAN was optimized by use of a phantom study. The visually perceived quality of the virtual cleansing by the resulting 3D GAN compared favorably to that of commercial EC software on the virtual 3D fly-through examinations of 18 clinical CTC cases. Thus, the proposed self-supervised 3D GAN, which can be trained to perform EC on a small dataset without image annotations with subvoxel accuracy, is a potentially effective approach for addressing the remaining technical problems of EC in CTC.
登录
查看更多内容
影响因子：
2.7
作者：
Chunhapongpipat K;Boonklurb R;Chaopathomkul B;Sirisup S;Lipikorn R
通讯作者：
Lipikorn R
影响因子：
3.8
作者：
Cai, Wenli;Zalis, Michael E.;Yoshida, Hiroyuki
通讯作者：
Yoshida, Hiroyuki
影响因子：
3.3
作者：
Neri, Emanuela;Lefere, Philippe;Bartolozzi, Carlo
通讯作者：
Bartolozzi, Carlo
影响因子：
3.8
作者：
Wang S;Li L;Cohen H;Mankes S;Chen JJ;Liang Z
通讯作者：
Liang Z
影响因子：
5
作者：
Pickhardt, Perry J.
通讯作者：
Pickhardt, Perry J.