Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, Nara, Japan.
Department of Orthopaedic Medical Engineering, Osaka University Graduate School of Medicine, Suita, Osaka, Japan.
Int J Comput Assist Radiol Surg. 2021 Nov;16(11):1855-1864. doi: 10.1007/s11548-021-02345-w. Epub 2021 Mar 17.
In quantitative computed tomography (CT), manual selection of the intensity calibration phantom's region of interest is necessary for calculating density (mg/cm) from the radiodensity values (Hounsfield units: HU). However, as this manual process requires effort and time, the purposes of this study were to develop a system that applies a convolutional neural network (CNN) to automatically segment intensity calibration phantom regions in CT images and to test the system in a large cohort to evaluate its robustness.
This cross-sectional, retrospective study included 1040 cases (520 each from two institutions) in which an intensity calibration phantom (B-MAS200, Kyoto Kagaku, Kyoto, Japan) was used. A training dataset was created by manually segmenting the phantom regions for 40 cases (20 cases for each institution). The CNN model's segmentation accuracy was assessed with the Dice coefficient, and the average symmetric surface distance was assessed through fourfold cross-validation. Further, absolute difference of HU was compared between manually and automatically segmented regions. The system was tested on the remaining 1000 cases. For each institution, linear regression was applied to calculate the correlation coefficients between HU and phantom density.
The source code and the model used for phantom segmentation can be accessed at https://github.com/keisuke-uemura/CT-Intensity-Calibration-Phantom-Segmentation . The median Dice coefficient was 0.977, and the median average symmetric surface distance was 0.116 mm. The median absolute difference of the segmented regions between manual and automated segmentation was 0.114 HU. For the test cases, the median correlation coefficients were 0.9998 and 0.999 for the two institutions, with a minimum value of 0.9863.
The proposed CNN model successfully segmented the calibration phantom regions in CT images with excellent accuracy.
在定量计算机断层扫描（CT）中，需要手动选择强度校准体模的感兴趣区域，以便从放射密度值（Hounsfield 单位：HU）计算密度（mg/cm）。然而，由于这个手动过程需要付出努力和时间，因此本研究的目的是开发一种应用卷积神经网络（CNN）自动分割 CT 图像中强度校准体模区域的系统，并在大样本中测试该系统，以评估其鲁棒性。
本研究为回顾性、横断面研究，共纳入 1040 例病例（分别来自 2 家机构各 520 例），这些病例均使用强度校准体模（日本京都 Kagaku 公司的 B-MAS200）。通过手动分割 40 例（每个机构各 20 例）体模区域创建训练数据集。使用 Dice 系数评估 CNN 模型的分割准确性，通过四重交叉验证评估平均对称面距离。进一步比较手动和自动分割区域的 HU 绝对值差异。该系统在其余 1000 例病例中进行了测试。对于每个机构，应用线性回归计算 HU 与体模密度之间的相关系数。
可在 https://github.com/keisuke-uemura/CT-Intensity-Calibration-Phantom-Segmentation 访问用于体模分割的源代码和模型。中位 Dice 系数为 0.977，中位平均对称面距离为 0.116mm。手动和自动分割区域之间的 HU 中位数绝对差值为 0.114HU。对于测试病例，两个机构的中位相关系数分别为 0.9998 和 0.999，最小值为 0.9863。
所提出的 CNN 模型成功地分割了 CT 图像中的校准体模区域，具有出色的准确性。
