基于深度学习的计算机辅助诊断系统在区分肺结节的良恶性方面是否优于放射科医生传统的双人读片？
Does a Deep Learning-Based Computer-Assisted Diagnosis System Outperform Conventional Double Reading by Radiologists in Distinguishing Benign and Malignant Lung Nodules?
作者信息
Liu Zhou, Li Li, Li Tianran, Luo Douqiang, Wang Xiaoliang, Luo Dehong
机构信息
Department of Radiology, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Shenzhen, China.
Department of Radiology, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China.
出版信息
Front Oncol. 2020 Oct 9;10:545862. doi: 10.3389/fonc.2020.545862. eCollection 2020.
BACKGROUND
In differentiating indeterminate pulmonary nodules, multiple studies indicated the superiority of deep learning-based computer-assisted diagnosis system (DL-CADx) over conventional double reading by radiologists, which needs external validation. Therefore, our aim was to externally validate the performance of a commercial DL-CADx in differentiating benign and malignant lung nodules.
METHODS
In this retrospective study, 233 patients with 261 pathologically confirmed lung nodules were enrolled. Double reading was used to rate each nodule using a four-scale malignancy score system, including unlikely (0-25%), malignancy cannot be completely excluded (25-50%), highly likely (50-75%), and considered as malignant (75-100%), with any disagreement resolved through discussion. DL-CADx automatically rated each nodule with a malignancy likelihood ranging from 0 to 100%, which was then quadrichotomized accordingly. Intraclass correlation coefficient (ICC) was used to evaluate the agreement in malignancy risk rating between DL-CADx and double reading, with ICC value of <0.5, 0.5 to 0.75, 0.75 to 0.9, and >0.9 indicating poor, moderate, good, and perfect agreement, respectively. With malignancy likelihood >50% as cut-off value for malignancy and pathological results as gold standard, sensitivity, specificity, and accuracy were calculated for double reading and DL-CADx, separately.
RESULTS
Among the 261 nodules, 247 nodules were successfully detected by DL-CADx with detection rate of 94.7%. Regarding malignancy rating, DL-CADx was in moderate agreement with double reading (ICC = 0.555, 95% CI 0.424 to 0.655). DL-CADx misdiagnosed 40 true malignant nodules as benign nodules and 30 true benign nodules as malignant nodules with sensitivity, specificity, and accuracy of 79.2, 45.5, and 71.7%, respectively. In contrast, double reading achieved better performance with 16 true malignant nodules misdiagnosed as benign nodules and 26 true benign nodules as malignant nodules with sensitivity, specificity, and accuracy of 91.7, 52.7, and 83.0%, respectively.
CONCLUSION
Compared with double reading, DL-CADx we used still shows inferior performance in differentiating malignant and benign nodules.
背景
在鉴别不确定的肺结节时，多项研究表明基于深度学习的计算机辅助诊断系统（DL-CADx）优于放射科医生的传统双重读片法，但这需要外部验证。因此，我们的目的是对一款商用DL-CADx在鉴别肺结节良恶性方面的性能进行外部验证。
方法
在这项回顾性研究中，纳入了233例有261个经病理证实的肺结节的患者。采用双重读片法，使用四级恶性肿瘤评分系统对每个结节进行评分，包括不太可能（0-25%）、不能完全排除恶性（25-50%）、很可能（50-75%）和被认为是恶性（75-100%），任何分歧通过讨论解决。DL-CADx自动对每个结节进行恶性可能性评分，范围为0至100%，然后据此进行四分法分类。组内相关系数（ICC）用于评估DL-CADx与双重读片法在恶性风险评级方面的一致性，ICC值<0.5、0.5至0.75、0.75至0.9和>0.9分别表示一致性差、中等、良好和完美。以恶性可能性>50%作为恶性的截断值，以病理结果作为金标准，分别计算双重读片法和DL-CADx的敏感性、特异性和准确性。
结果
在261个结节中，DL-CADx成功检测出247个结节，检测率为94.7%。关于恶性评级，DL-CADx与双重读片法一致性中等（ICC = 0.555，95%CI 0.424至0.655）。DL-CADx将40个真恶性结节误诊为良性结节，30个真良性结节误诊为恶性结节，敏感性、特异性和准确性分别为79.2%、45.5%和71.7%。相比之下，双重读片法表现更好，16个真恶性结节误诊为良性结节，26个真良性结节误诊为恶性结节，敏感性、特异性和准确性分别为91.7%、52.7%和83.0%。
结论
与双重读片法相比，我们使用的DL-CADx在鉴别恶性和良性结节方面仍表现较差。
Zotero 插件