深度学习神经网络融合模型与人工观察在肺结节检测与分类中的比较
研究纳入158例患者的158个肺结节(81良性、77恶性),由两名放射科医师和一个人工智能平台按Lung-RADS分类分析,比较恶性风险诊断性能。观察者1、观察者2和AI的AUC分别为0.917±0.023、0.870±0.033和0.790±0.037,融合AI算法性能略低于观察者,可能用于辅助角色,尤其对经验不足的放射科医师。
要点
- 融合AI算法对肺结节恶性风险的评估性能略低于放射科医师(AUC 0.790 vs 0.917和0.870)。
- 18个(11.3%)结节未被AI检测和分析。
- 观察者间在结节定位、大小和Lung-RADS分类上几乎完全一致(κ 0.984、0.978、0.924)。
核心结论
- 融合AI算法在估计恶性风险方面的性能略低于观察者。
- 融合AI算法可能应用于辅助角色,尤其对经验不足的放射科医师。
研究设计与样本
- 研究人群包括158例患者的158个结节,其中81个良性、77个恶性,恶性或良性由一名放射科医师基于病理评估和/或随访影像确定。
- 两名放射科医师和一个人工智能平台基于Lung-RADS分类分析结节,两名观察者还记录结节的大小、位置和形态特征。
- 计算观察者和AI的组内相关系数,并进行ROC曲线分析以确定诊断性能。
关键影像表现/征象
- 恶性与良性结节在结节大小、毛刺征存在和脂肪存在方面有显著差异(三项p均<0.001)。
- 18个(11.3%)结节未被AI检测和分析。
诊断标准与关键数值
- 观察者1、观察者2和AI在恶性概率ROC分析中的AUC分别为0.917±0.023、0.870±0.033和0.790±0.037。
- 观察者在定位、结节大小和Lung-RADS分类上几乎完全一致,κ(95%CI)分别为0.984(0.961-1.000)、0.978(0.970-0.984)和0.924(0.878-0.970)。
临床应用与阅片要点
- 融合AI算法可能用于辅助放射科医师解读肺结节鉴别,尤其对经验不足的放射科医师。
局限性
- 18个(11.3%)结节未被AI检测和分析。
- 融合AI算法性能略低于观察者。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: To compare the diagnostic performance of a newly developed artificial intelligence (AI) algorithm derived from the fusion of convolution neural networks (CNN) versus human observers in the estimation of malignancy risk in pulmonary nodules.
METHODS: The study population consists of 158 nodules from 158 patients. All nodules (81 benign and 77 malignant) were determined to be malignant or benign by a radiologist based on pathologic assessment and/or follow-up imaging. Two radiologists and an AI platform analyzed the nodules based on the Lung-RADS classification. The two observers also noted the size, location, and morphologic features of the nodules. An intraclass correlation coefficient was calculated for both observers and the AI; ROC curve analysis was performed to determine diagnostic performances.
RESULTS: Nodule size, presence of spiculation, and presence of fat were significantly different between the malignant and benign nodules (p < 0.001, for all three). Eighteen (11.3%) nodules were not detected and analyzed by the AI. Observer 1, observer 2, and the AI had an AUC of 0.917 ± 0.023, 0.870 ± 0.033, and 0.790 ± 0.037 in the ROC analysis of malignity probability, respectively. The observers were in almost perfect agreement for localization, nodule size, and lung-RADS classification [κ (95% CI)=0.984 (0.961-1.000), 0.978 (0.970-0.984), and 0.924 (0.878-0.970), respectively].
CONCLUSION: The performance of the fusion AI algorithm in estimating the risk of malignancy was slightly lower than the performance of the observers. Fusion AI algorithms might be applied in an assisting role, especially for inexperienced radiologists.
ADVANCES IN KNOWLEDGE: In this study, we proposed a fusion model using four state-of-art object detectors for lung nodule detection and discrimination. The use of fusion of deep learning neural networks might be used in a supportive role for radiologists when interpreting lung nodule discrimination.
引用
- Gürsoy Çoruh A, Yenigün B, Uzun Ç, et al. A comparison of the fusion model of deep learning neural networks with human observation for lung nodule detection and classification. Br J Radiol. 2021. PMID: 34111976. doi:10.1259/bjr.20210222
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。