The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University, School of Medicine, 601N. Caroline Street, Baltimore, MD 21287, USA.
Department of Computer Science, Johns Hopkins University, School of Arts and Sciences, Baltimore, MD 21218, USA.
Diagn Interv Imaging. 2020 Jan;101(1):35-44. doi: 10.1016/j.diii.2019.05.008. Epub 2019 Jul 26.
The purpose of this study was to report procedures developed to annotate abdominal computed tomography (CT) images from subjects without pancreatic disease that will be used as the input for deep convolutional neural networks (DNN) for development of deep learning algorithms for automatic recognition of a normal pancreas.
Dual-phase contrast-enhanced volumetric CT acquired from 2005 to 2009 from potential kidney donors were retrospectively assessed. Four trained human annotators manually and sequentially annotated 22 structures in each datasets, then expert radiologists confirmed the annotation. For efficient annotation and data management, a commercial software package that supports three-dimensional segmentation was used.
A total of 1150 dual-phase CT datasets from 575 subjects were annotated. There were 229 men and 346 women (mean age: 45±12years; range: 18-79years). The mean intra-observer intra-subject dual-phase CT volume difference of all annotated structures was 4.27mL (7.65%). The deep network prediction for multi-organ segmentation showed high fidelity with 89.4% and 1.29mm in terms of mean Dice similarity coefficients and mean surface distances, respectively.
A reliable data collection/annotation process for abdominal structures was developed. This process can be used to generate large datasets appropriate for deep learning.
本研究旨在报告为开发用于自动识别正常胰腺的深度学习算法而针对无胰腺疾病受试者的腹部计算机断层扫描（CT）图像进行注释所开发的程序。
回顾性评估了 2005 年至 2009 年期间潜在肾供体的双期增强容积 CT。四名经过培训的人类注释员手动且顺序地对每个数据集的 22 个结构进行注释，然后由专家放射科医生确认注释。为了实现高效注释和数据管理，使用了支持三维分割的商业软件包。
共对 575 名受试者的 1150 个双期 CT 数据集进行了注释。其中 229 名男性和 346 名女性（平均年龄：45±12 岁；范围：18-79 岁）。所有注释结构的观察者内双期 CT 体积差异的平均值为 4.27mL（7.65%）。多器官分割的深度网络预测具有很高的保真度，平均 Dice 相似系数和平均表面距离分别为 89.4%和 1.29mm。
开发了一种可靠的腹部结构数据采集/注释流程。该流程可用于生成适用于深度学习的大型数据集。
