Guangdong Lung Cancer Institute, Guangdong Provincial Key Laboratory of Translational Medicine in Lung Cancer, Guangdong Provincial People's Hospital & Guangdong Academy of Medical Sciences, Guangzhou, People's Republic of China.
Tencent Youtu Lab, Shanghai, People's Republic of China.
Oncologist. 2019 Sep;24(9):1159-1165. doi: 10.1634/theoncologist.2018-0908. Epub 2019 Apr 17.
Computed tomography (CT) is essential for pulmonary nodule detection in diagnosing lung cancer. As deep learning algorithms have recently been regarded as a promising technique in medical fields, we attempt to integrate a well-trained deep learning algorithm to detect and classify pulmonary nodules derived from clinical CT images.
Open-source data sets and multicenter data sets have been used in this study. A three-dimensional convolutional neural network (CNN) was designed to detect pulmonary nodules and classify them into malignant or benign diseases based on pathologically and laboratory proven results.
The sensitivity and specificity of this well-trained model were found to be 84.4% (95% confidence interval [CI], 80.5%-88.3%) and 83.0% (95% CI, 79.5%-86.5%), respectively. Subgroup analysis of smaller nodules (<10 mm) have demonstrated remarkable sensitivity and specificity, similar to that of larger nodules (10-30 mm). Additional model validation was implemented by comparing manual assessments done by different ranks of doctors with those performed by three-dimensional CNN. The results show that the performance of the CNN model was superior to manual assessment.
Under the companion diagnostics, the three-dimensional CNN with a deep learning algorithm may assist radiologists in the future by providing accurate and timely information for diagnosing pulmonary nodules in regular clinical practices.
The three-dimensional convolutional neural network described in this article demonstrated both high sensitivity and high specificity in classifying pulmonary nodules regardless of diameters as well as superiority compared with manual assessment. Although it still warrants further improvement and validation in larger screening cohorts, its clinical application could definitely facilitate and assist doctors in clinical practice.
计算机断层扫描（CT）在诊断肺癌时对肺结节的检测至关重要。由于深度学习算法最近被认为是医学领域有前途的技术，我们尝试整合经过良好训练的深度学习算法，以从临床 CT 图像中检测和分类肺结节。
本研究使用了开源数据集和多中心数据集。设计了一个三维卷积神经网络（CNN），根据病理和实验室证实的结果，检测肺结节并将其分类为恶性或良性疾病。
该经过良好训练的模型的敏感性和特异性分别为 84.4%（95%置信区间[CI]，80.5%-88.3%）和 83.0%（95% CI，79.5%-86.5%）。对较小结节（<10mm）的亚组分析显示出了类似较大结节（10-30mm）的显著敏感性和特异性。通过比较不同级别医生的手动评估与三维 CNN 的评估，对该模型进行了额外的验证。结果表明，CNN 模型的性能优于手动评估。
在伴随诊断的情况下，基于深度学习算法的三维 CNN 可能在未来通过为常规临床实践中的肺结节诊断提供准确和及时的信息，为放射科医生提供帮助。
本文描述的三维卷积神经网络在分类肺结节时，无论结节直径大小，均表现出较高的敏感性和特异性，并且优于手动评估。虽然它仍需要在更大的筛查队列中进一步改进和验证，但它的临床应用肯定可以促进和协助医生在临床实践中的工作。
