通过训练有素的技术人员为人工智能应用开发容积胰腺 CT 数据集：COVID-19 封控期间的一项研究。
Development of a volumetric pancreas segmentation CT dataset for AI applications through trained technologists: a study during the COVID 19 containment phase.
机构信息
Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA.
Department of Gastroenterology and Hepatology, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA.
出版信息
Abdom Radiol (NY). 2020 Dec;45(12):4302-4310. doi: 10.1007/s00261-020-02741-x. Epub 2020 Sep 16.
PURPOSE
To evaluate the performance of trained technologists vis-à-vis radiologists for volumetric pancreas segmentation and to assess the impact of supplementary training on their performance.
METHODS
In this IRB-approved study, 22 technologists were trained in pancreas segmentation on portal venous phase CT through radiologist-led interactive videoconferencing sessions based on an image-rich curriculum. Technologists segmented pancreas in 188 CTs using freehand tools on custom image-viewing software. Subsequent supplementary training included multimedia videos focused on common errors, which were followed by second batch of 159 segmentations. Two radiologists reviewed all cases and corrected inaccurate segmentations. Technologists' segmentations were compared against radiologists' segmentations using Dice-Sorenson coefficient (DSC), Jaccard coefficient (JC), and Bland-Altman analysis.
RESULTS
Corrections were made in 71 (38%) cases from first batch [26 (37%) oversegmentations and 45 (63%) undersegmentations] and in 77 (48%) cases from second batch [12 (16%) oversegmentations and 65 (84%) undersegmentations]. DSC, JC, false positive (FP), and false negative (FN) [mean (SD)] in first versus second batches were 0.63 (0.15) versus 0.63 (0.16), 0.48 (0.15) versus 0.48 (0.15), 0.29 (0.21) versus 0.21 (0.10), and 0.36 (0.20) versus 0.43 (0.19), respectively. Differences were not significant (p > 0.05). However, range of mean pancreatic volume difference reduced in the second batch [- 2.74 cc (min - 92.96 cc, max 87.47 cc) versus - 23.57 cc (min - 77.32, max 30.19)].
CONCLUSION
Trained technologists could perform volumetric pancreas segmentation with reasonable accuracy despite its complexity. Supplementary training further reduced range of volume difference in segmentations. Investment into training technologists could augment and accelerate development of body imaging datasets for AI applications.
目的
评估经过培训的技术人员与放射科医生在胰腺容积分割方面的表现，并评估补充培训对其表现的影响。
方法
在这项经机构审查委员会批准的研究中，22 名技术人员通过放射科医生主导的基于丰富图像课程的交互式视频会议，接受了门静脉期 CT 上胰腺分割的培训。技术人员使用徒手工具在定制的图像查看软件上对 188 例 CT 进行胰腺分割。随后的补充培训包括针对常见错误的多媒体视频，之后是第二批 159 次分割。两位放射科医生对所有病例进行了复查，并纠正了不准确的分割。使用 Dice-Sorensen 系数（DSC）、Jaccard 系数（JC）和 Bland-Altman 分析比较技术人员和放射科医生的分割结果。
结果
第一批病例中有 71 例（38%）需要纠正[26 例（37%）过度分割和 45 例（63%）欠分割]，第二批病例中有 77 例（48%）需要纠正[12 例（16%）过度分割和 65 例（84%）欠分割]。第一批和第二批的 DSC、JC、假阳性（FP）和假阴性（FN）[均值（标准差）]分别为 0.63（0.15）和 0.63（0.16）、0.48（0.15）和 0.48（0.15）、0.29（0.21）和 0.21（0.10）以及 0.36（0.20）和 0.43（0.19）。差异无统计学意义（p>0.05）。然而，第二批的平均胰腺体积差异范围缩小[-2.74 cc（最小值-92.96 cc，最大值 87.47 cc）与-23.57 cc（最小值-77.32，最大值 30.19）]。
结论
尽管胰腺容积分割较为复杂，但经过培训的技术人员仍能以合理的精度进行分割。补充培训进一步减少了分割中的体积差异范围。投资培训技术人员可以增强和加速人工智能应用体部成像数据集的发展。
Zotero 插件