Park Junghoan, Joo Ijin, Jeon Sun Kyung, Kim Jong-Min, Park Sang Joon, Yoon Soon Ho
Seoul National University, Seoul, Republic of Korea.
Seoul National University Hospital, Seoul, Republic of Korea.
Abdom Radiol (NY). 2025 Mar;50(3):1448-1456. doi: 10.1007/s00261-024-04581-5. Epub 2024 Sep 19.
To develop fully-automated abdominal organ segmentation algorithms from non-enhanced abdominal CT and low-dose chest CT and assess their feasibility for automated CT volumetry and 3D radiomics analysis of abdominal solid organs.
Fully-automated nnU-Net-based models were developed to segment the liver, spleen, and both kidneys in non-enhanced abdominal CT, and the liver and spleen in low-dose chest CT. 105 abdominal CTs and 60 low-dose chest CTs were used for model development, and 55 abdominal CTs and 10 low-dose chest CTs for external testing. The segmentation performance for each organ was assessed using the Dice similarity coefficients, with manual segmentation results serving as the ground truth. Agreements between ground-truth measurements and model estimates of organ volume and 3D radiomics features were assessed using the Bland-Altman analysis and intraclass correlation coefficients (ICC).
The models accurately segmented the liver, spleen, right kidney, and left kidney in abdominal CT and the liver and spleen in low-dose chest CT, showing mean Dice similarity coefficients in the external dataset of 0.968, 0.960, 0.952, and 0.958, respectively, in abdominal CT, and 0.969 and 0.960, respectively, in low-dose chest CT. The model-estimated and ground truth volumes of these organs exhibited mean differences between - 0.7% and 2.2%, with excellent agreements. The automatically extracted mean and median Hounsfield units (ICCs, 0.970-0.999 and 0.994-0.999, respectively), uniformity (ICCs, 0.985-0.998), entropy (ICCs, 0.931-0.993), elongation (ICCs, 0.978-0.992), and flatness (ICCs, 0.973-0.997) showed excellent agreement with ground truth measurements for each organ; however, skewness (ICCs, 0.210-0.831), kurtosis (ICCs, 0.053-0.933), and sphericity (ICCs, 0.368-0.819) displayed relatively low and inconsistent agreement.
Our nnU-Net-based models accurately segmented abdominal solid organs in non-enhanced abdominal and low-dose chest CT, enabling reliable automated measurements of organ volume and specific 3D radiomics features.
开发基于非增强腹部CT和低剂量胸部CT的全自动腹部器官分割算法，并评估其在腹部实体器官自动CT容积测量和三维放射组学分析中的可行性。
开发基于nnU-Net的全自动模型，用于在非增强腹部CT中分割肝脏、脾脏和双肾，以及在低剂量胸部CT中分割肝脏和脾脏。105例腹部CT和60例低剂量胸部CT用于模型开发，55例腹部CT和10例低剂量胸部CT用于外部测试。使用Dice相似系数评估每个器官的分割性能，以手动分割结果作为参考标准。使用Bland-Altman分析和组内相关系数（ICC）评估参考标准测量值与模型估计的器官体积和三维放射组学特征之间的一致性。
模型在腹部CT中准确分割了肝脏、脾脏、右肾和左肾，在低剂量胸部CT中准确分割了肝脏和脾脏，在腹部CT外部数据集中的平均Dice相似系数分别为0.968、0.960、0.952和0.958，在低剂量胸部CT中分别为0.969和0.960。这些器官的模型估计体积与参考标准体积之间的平均差异在-0.7%至2.2%之间，一致性良好。自动提取的平均和中位数Hounsfield单位（ICC分别为0.970 - 0.999和0.994 - 0.999）、均匀性（ICC为0.985 - 0.998）、熵（ICC为0.931 - 0.993）、伸长率（ICC为0.978 - 0.992）和平坦度（ICC为0.973 - 0.997）与每个器官的参考标准测量值显示出良好的一致性；然而，偏度（ICC为0.210 - 0.831）、峰度（ICC为0.053 - 0.933）和球形度（ICC为0.368 - 0.819）的一致性相对较低且不一致。
我们基于nnU-Net的模型在非增强腹部和低剂量胸部CT中准确分割了腹部实体器官，能够可靠地自动测量器官体积和特定的三维放射组学特征。
