两种不同人工智能（AI）方法评估腕骨骨龄与标准 Greulich 和 Pyle 方法的比较。
Performance of two different artificial intelligence (AI) methods for assessing carpal bone age compared to the standard Greulich and Pyle method.
机构信息
Dipartimento di Diagnostica per Immagini Policlinico, Università degli Studi di Palermo, Via del Vespro 127, 90127, Palermo, Italy.
UOC Radiologia Pediatrica Dipartimento di Diagnostica per Immagini e Interventistica, ARNAS, Ospedali Civico, Di Cristina Benfratelli, Palermo, Italy.
出版信息
Radiol Med. 2024 Oct;129(10):1507-1512. doi: 10.1007/s11547-024-01871-2. Epub 2024 Aug 20.
PURPOSE
Evaluate the agreement between bone age assessments conducted by two distinct machine learning system and standard Greulich and Pyle method.
MATERIALS AND METHODS
Carpal radiographs of 225 patients (mean age 8 years and 10 months, SD = 3 years and 1 month) were retrospectively analysed at two separate institutions (October 2018 and May 2022) by both expert radiologists and radiologists in training as well as by two distinct AI software programmes, 16-bit AI and BoneXpert® in a blinded manner.
RESULTS
The bone age range estimated by the 16-bit AI system in our sample varied between 1 year and 1 month and 15 years and 8 months (mean bone age 9 years and 5 months SD = 3 years and 3 months). BoneXpert® estimated bone age ranged between 8 months and 15 years and 7 months (mean bone age 8 years and 11 months SD = 3 years and 3 months). The average bone age estimated by the Greulich and Pyle method was between 11 months and 14 years, 9 months (mean bone age 8 years and 4 months SD = 3 years and 3 months). Radiologists' assessments using the Greulich and Pyle method were significantly correlated (Pearson's r > 0.80, p < 0.001). There was no statistical difference between BoneXpert® and 16-bit AI (mean difference = - 0.19, 95%CI = (- 0.45; 0.08)), and the agreement between two measurements varies between - 3.45 (95%CI = (- 3.95; - 3.03) and 3.07 (95%CI - 3.03; 3.57).
CONCLUSIONS
Both AI methods and GP provide correlated results, although the measurements made by AI were closer to each other compared to the GP method.
目的
评估两种不同机器学习系统与标准 Greulich 和 Pyle 方法的骨龄评估之间的一致性。
材料与方法
回顾性分析了 225 例患者（平均年龄 8 岁 10 个月，标准差 3 岁 1 个月）的腕骨 X 线片，这些患者分别于 2018 年 10 月和 2022 年 5 月在两个不同的机构（October 2018 and May 2022）由专家放射科医生和放射科医生培训生以及两种不同的人工智能软件程序 16 位 AI 和 BoneXpert® 进行盲法分析。
结果
在我们的样本中，16 位 AI 系统估计的骨龄范围为 1 年 1 个月至 15 年 8 个月（平均骨龄 9 岁 5 个月，标准差 3 岁 3 个月）。BoneXpert® 估计的骨龄范围为 8 个月至 15 年 7 个月（平均骨龄 8 岁 11 个月，标准差 3 岁 3 个月）。Greulich 和 Pyle 方法估计的平均骨龄在 11 个月至 14 岁之间，为 9 个月（平均骨龄 8 岁 4 个月，标准差 3 岁 3 个月）。放射科医生使用 Greulich 和 Pyle 方法评估的骨龄明显相关（Pearson's r>0.80，p<0.001）。BoneXpert® 和 16 位 AI 之间没有统计学差异（平均差异=-0.19，95%CI=-0.45；0.08），两次测量之间的一致性在-3.45（95%CI=-3.95；-3.03）至 3.07（95%CI=-3.03；3.57）之间。
结论
两种人工智能方法和 GP 提供了相关的结果，尽管人工智能方法的测量值彼此之间更接近。
Zotero 插件