深度学习CT图像标准化提升肝脏分割泛化性能
本研究收集腹部增强双能CT,采用多种重建方法(滤波反投影、迭代重建、最佳对比、40/60/80 keV单能图像),开发深度学习图像转换算法进行标准化,测试集43例(平均年龄10.1岁)。标准化后肝脏分割Dice相似系数显著提高(原始5.40%-91.27% vs. 标准化93.16%-96.74%,所有P<0.001),肝脏体积差异比降低(原始9.84%-91.37% vs. 标准化1.99%-4.41%),一致性相关系数改善(原始-0.006-0.964 vs. 标准化0.990-0.998)。结论:深度学习CT图像标准化可改善多种重建方法下的自动肝脏分割性能,有望提高分割网络的泛化能力。
要点
- 不同重建方法下原始CT图像肝脏分割性能差异大且较差。
- 深度学习图像标准化后各重建协议分割DSC均显著提高。
- 标准化后肝脏体积差异比降低,与参考体积一致性提高。
核心结论
- 基于深度学习的CT图像标准化可提高多种重建方法下自动肝脏分割的性能,并可能提升分割网络的泛化能力。
研究设计与样本
- 研究为实验性方法开发与验证,使用腹部增强双能CT,重建方法包括滤波反投影、迭代重建、最佳对比及40、60、80 keV单能图像。
- 训练集142例(128例训练、14例调优),测试集43例来自42例患者(平均年龄10.1岁)。
- 使用基于2D U-NET的商业软件(MEDIP PRO v2.0.0.0)生成肝脏分割掩模及体积,以原始80 keV图像作为参考标准。
- 采用配对t检验比较标准化前后Dice相似系数和肝脏体积差异比,使用一致性相关系数评估体积一致性。
诊断标准与关键数值
- 标准化后肝脏分割Dice相似系数为93.16%-96.74%,显著高于原始图像的5.40%-91.27%(所有P<0.001)。
- 标准化后肝脏体积差异比为1.99%-4.41%,原始图像为9.84%-91.37%。
- 标准化后一致性相关系数为0.990-0.998,原始图像为-0.006-0.964。
临床应用与阅片要点
- 在应用深度学习肝脏分割工具时,可考虑先对CT图像进行标准化转换以减小重建方法差异的影响。
- 阅片或定量分析时需注意不同重建方法可能导致自动分割性能波动,标准化有助于提高体积测量一致性。
局限性
- 测试集样本量较小(43例),且平均年龄10.1岁,可能限制结论的普遍性。
- 参考标准为原始80 keV图像,而非手动分割金标准。
- 研究为单中心设计,未在外部数据验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
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 t-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 P < 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.
引用
- Lee, Hong, Cho, et al. Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation. Korean J Radiol. 2023. PMID: 36907592. doi:10.3348/kjr.2022.0588
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。