Department of Radiology, The Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School, Nanjing 210008, PR China.
State Key Laboratory of Natural Medicines, China Pharmaceutical University, Nanjing, PR China; Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing 210009, PR China.
EBioMedicine. 2020 Apr;54:102724. doi: 10.1016/j.ebiom.2020.102724. Epub 2020 Apr 4.
Interstitial lung disease requires frequent re-examination, which directly causes excessive cumulative radiation exposure. To date, AI has not been applied to CT for enhancing clinical care; thus, we hypothesize AI may empower CT with intelligence to realize automatic and accurate pulmonary scanning, thus dramatically decrease medical radiation exposure without compromising patient care.
Facial boundary detection was realized by recognizing adjacent jaw position through training and testing a region proposal network (RPN) on 76,882 human faces using a preinstalled 2-dimensional camera; the lung-fields was then segmented by V-Net on another training set with 314 subjects and calculated the moving distance of the scanning couch based on a pre-generated calibration table. A multi-cohort study, including 1,186 patients was used for validation and radiation dose quantification under three clinical scenarios.
A U-HAPPY (United imaging Human Automatic Planbox for PulmonarY) scanning CT was designed. Error distance of RPN was 4·46±0·02 pixels with a success rate of 98·7% in training set and 2·23±0·10 pixels with 100% success rate in testing set. Average Dice's coefficient was 0·99 in training set and 0·96 in testing set. A calibration table with 1,344,000 matches was generated to support the linkage between camera and scanner. This real-time automation makes an accurate plan-box to cover exact location and area needed to scan, thus reducing amounts of radiation exposures significantly (all, P<0·001).
U-HAPPY CT designed for pulmonary imaging acquisition standardization is promising for reducing patient risk and optimizing public health expenditures.
The National Natural Science Foundation of China.
间质性肺病需要频繁复查，这直接导致了过度的累积辐射暴露。迄今为止，人工智能尚未应用于 CT 以增强临床护理；因此，我们假设人工智能可以为 CT 赋予智能，实现自动和准确的肺部扫描，从而在不影响患者护理的情况下显著降低医疗辐射暴露。
通过在安装的 2 维相机上使用区域提议网络 (RPN) 对 76882 个人脸进行训练和测试，实现了面部边界检测；然后通过 V-Net 在另一个包含 314 名受试者的训练集中分割肺野，并根据预生成的校准表计算扫描床的移动距离。一项包含 1186 名患者的多队列研究用于在三种临床情况下进行验证和辐射剂量量化。
设计了一款 U-HAPPY（联影肺部自动扫描计划盒）扫描 CT。RPN 的误差距离在训练集中为 4.46±0.02 像素，成功率为 98.7%；在测试集中为 2.23±0.10 像素，成功率为 100%。训练集和测试集的平均 Dice 系数分别为 0.99 和 0.96。生成了一个包含 1344000 次匹配的校准表，以支持相机和扫描仪之间的链接。这种实时自动化可以精确地规划出需要扫描的精确位置和区域，从而显著减少辐射暴露量（均，P<0.001）。
设计用于肺部成像采集标准化的 U-HAPPY CT 有望降低患者风险和优化公共卫生支出。
国家自然科学基金。
