Hardie Russell C, Trout Andrew T, Dillman Jonathan R, Narayanan Barath N, Tanimoto Aki A
Department of Electrical and Computer Engineering, University of Dayton, 300 College Park, Dayton, OH 45469.
Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH.
AJR Am J Roentgenol. 2025 Jan;224(1):e2431972. doi: 10.2214/AJR.24.31972. Epub 2024 Oct 9.
When lung nodule computer-aided detection (CAD) systems are applied for pediatric CT, performance may be degraded on low-dose scans due to increased image noise. The purpose of this study was to conduct an intraindividual comparison of the performance for lung nodule detection of two CAD systems trained using adult data between low-dose and standard-dose pediatric chest CT scans. This retrospective study included 73 patients (32 female participants, 41 male participants; mean age, 14.7 years; age range, 4-20 years) who underwent both clinical standard-dose and investigational low-dose chest CT examinations during the same encounter from November 30, 2018, to August 31, 2020, as part of an earlier prospective study. Fellowship-trained pediatric radiologists annotated lung nodules to serve as the reference standard. Both CT scans were processed using two publicly available lung nodule CAD systems previously trained using adult data: FlyerScan (github.com/rhardie1/FlyerScanCT) and Medical Open Network for Artificial Intelligence (MONAI; github.com/Project-MONAI/model-zoo/releases). The sensitivities of the two CAD systems for nodules measuring 3-30 mm ( = 247) were calculated when operating at a fixed frequency of two false-positives per scan. FlyerScan exhibited detection sensitivities of 76.9% (190/247; 95% CI, 73.3-80.8%) on standard-dose scans and 66.8% (165/247; 95% CI, 62.6-71.5%) on low-dose scans. MONAI exhibited detection sensitivities of 67.6% (167/247; 95% CI, 61.5-72.1%) on standard-dose scans and 62.3% (154/247; 95% CI, 56.1-66.5%) on low-dose scans. The number of detected nodules for standard-dose versus low-dose scans for 3-mm nodules was 33 versus 24 (FlyerScan) and 16 versus 13 (MONAI), 4-mm nodules was 46 versus 42 (FlyerScan) and 39 versus 30 (MONAI), 5-mm nodules was 38 versus 33 (FlyerScan) and 32 versus 31 (MONAI), and 6-mm nodules was 27 versus 20 (FlyerScan) and 24 versus 24 (MONAI). For nodules measuring 7 mm or larger, detection did not show a consistent pattern between standard-dose and low-dose scans for either system. Two lung nodule CAD systems showed decreased sensitivity on low-dose versus standard-dose pediatric CT scans obtained in the same patients. The reduced detection at low dose was overall more pronounced for nodules measuring less than 5 mm. Caution is needed when using low-dose CT protocols in combination with CAD systems to help detect small lung nodules in pediatric patients.
当将肺结节计算机辅助检测（CAD）系统应用于儿科CT时，由于图像噪声增加，低剂量扫描时其性能可能会下降。本研究的目的是对两个使用成人数据训练的CAD系统在低剂量和标准剂量儿科胸部CT扫描中检测肺结节的性能进行个体内比较。这项回顾性研究纳入了73例患者（32例女性参与者，41例男性参与者；平均年龄14.7岁；年龄范围4至20岁），他们在2018年11月30日至2020年8月31日的同一次检查中接受了临床标准剂量和研究性低剂量胸部CT检查，这是一项早期前瞻性研究的一部分。经过专科培训的儿科放射科医生对肺结节进行标注，作为参考标准。两种CT扫描均使用两个先前使用成人数据训练的公开可用的肺结节CAD系统进行处理：FlyerScan（github.com/rhardie1/FlyerScanCT）和医学人工智能开放网络（MONAI；github.com/Project-MONAI/model-zoo/releases）。当以每次扫描两个假阳性的固定频率运行时，计算了两个CAD系统对直径为3至30毫米（n = 247）结节的敏感度。FlyerScan在标准剂量扫描中的检测敏感度为76.9%（190/247；95%置信区间，73.3 - 80.8%），在低剂量扫描中的检测敏感度为66.8%（16s/247；95%置信区间，62.6 - 71.5%）。MONAI在标准剂量扫描中的检测敏感度为67.6%（167/247；95%置信区间，61.5 - 72.1%），在低剂量扫描中的检测敏感度为62.3%（154/247；95%置信区间，56.1 - 66.5%）。3毫米结节的标准剂量扫描与低剂量扫描检测到的结节数量，FlyerScan分别为33个和24个，MONAI分别为16个和13个；4毫米结节分别为46个和42个，MONAI分别为39个和30个；5毫米结节分别为38个和33个，MONAI分别为32个和31个；6毫米结节分别为27个和20个，MONAI分别为24个和24个。对于直径7毫米及以上的结节，两个系统在标准剂量和低剂量扫描之间均未显示出一致的模式。与在同一患者中获得的标准剂量儿科CT扫描相比，两个肺结节CAD系统在低剂量扫描时敏感度降低。对于直径小于5毫米的结节，低剂量时检测能力的下降总体上更为明显。在将低剂量CT方案与CAD系统联合用于帮助检测儿科患者的小肺结节时需要谨慎。
