Department of Radiology, Seoul National University Hospital, Seoul, Korea.
Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.
Korean J Radiol. 2023 Apr;24(4):294-304. doi: 10.3348/kjr.2022.0588. Epub 2023 Mar 7.
OBJECTIVE: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. MATERIALS AND METHODS: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired -test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. RESULTS: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). CONCLUSION: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.
目的：我们旨在研究基于深度学习的 CT 图像转换的图像标准化是否会提高基于深度学习的自动肝脏分割在各种重建方法中的性能。
材料与方法：我们收集了使用各种重建方法（包括滤波反投影、迭代重建、最佳对比以及 40、60 和 80keV 的单能量图像）获得的腹部增强双能 CT。开发了一种基于深度学习的图像转换算法，以使用 142 次 CT 检查（128 次用于训练，14 次用于调整）对 CT 图像进行标准化。来自 42 名患者的另外 43 次 CT 检查（平均年龄 10.1 岁）被用作测试数据。使用商业软件程序（MEDIP PRO v2.0.0.0，MEDICALIP Co. Ltd.）基于 2D U-NET 创建肝脏分割掩模和肝体积。原始 80keV 图像用作地面实况。我们使用配对 t 检验比较图像标准化前后肝脏体积相对于地面真实体积的 Dice 相似系数（DSC）和差异比的分割性能。一致性相关系数（CCC）用于评估分割的肝体积与地面真实体积之间的一致性。
结果：原始 CT 图像显示出可变且较差的分割性能。标准化图像的肝脏分割 DSC 明显高于原始图像（DSC[原始，5.40%-91.27%]与[标准化，93.16%-96.74%]，均 < 0.001）。肝脏体积的差异比也在图像转换后显著降低（原始，9.84%-91.37%与标准化，1.99%-4.41%）。在所有协议中，图像转换后 CCC 均提高（原始，-0.006-0.964 与标准化，0.990-0.998）。
结论：基于深度学习的 CT 图像标准化可以提高使用各种方法重建的 CT 图像的自动肝脏分割性能。基于深度学习的 CT 图像转换有可能提高分割网络的泛化能力。
Math Biosci Eng. 2022-9-23
Bioengineering (Basel). 2024-11-30
Oral Radiol. 2025-1
Radiol Artif Intell. 2022-5-4
Radiol Artif Intell. 2021-11-10
Radiol Artif Intell. 2021-10-6
Radiographics. 2021
J Big Data. 2021
Zotero 插件
