Deng Yihong, Chen Yuan, Xie Lihua, Wang Liansheng, Zhan Juan
Department of Pulmonary and Critical Care Medicine, the Third Xiangya Hospital, Central South University, Changsha, Hunan, China.
Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China.
Front Oncol. 2022 Oct 27;12:1001840. doi: 10.3389/fonc.2022.1001840. eCollection 2022.
The incidence and mortality of lung cancer ranks first in China. Bronchoscopy is one of the most common diagnostic methods for lung cancer. In recent years, image recognition technology(IRT) has been more and more widely studied and applied in the medical field. We developed a diagnostic model of lung cancer under bronchoscopy based on deep learning method and tried to classify pathological types.
A total of 2238 lesion images were collected retrospectively from 666 cases of lung cancer diagnosed by pathology in the bronchoscopy center of the Third Xiangya Hospital from Oct.01 2017 to Dec.31 2020 and 152 benign cases from Jun.01 2015 to Dec.31 2020. The benign and malignant images were divided into training, verification and test set according to 7:1:2 respectively. The model was trained and tested based on deep learning method. We also tried to classify different pathological types of lung cancer using the model. Furthermore, 9 clinicians with different experience were invited to diagnose the same test images and the results were compared with the model.
The diagnostic model took a total of 30s to diagnose 467 test images. The overall accuracy, sensitivity, specificity and area under curve (AUC) of the model to differentiate benign and malignant lesions were 0.951, 0.978, 0.833 and 0.940, which were equivalent to the judgment results of 2 doctors in the senior group and higher than those of other doctors. In the classification of squamous cell carcinoma (SCC) and adenocarcinoma (AC), the overall accuracy was 0.745, including 0.790 for SCC, 0.667 for AC and AUC was 0.728.
The performance of our diagnostic model to distinguish benign and malignant lesions in bronchoscopy is roughly the same as that of experienced clinicians and the efficiency is much higher than manually. Our study verifies the possibility of applying IRT in diagnosis of lung cancer during white light bronchoscopy.
肺癌的发病率和死亡率在中国位居首位。支气管镜检查是肺癌最常见的诊断方法之一。近年来，图像识别技术（IRT）在医学领域得到了越来越广泛的研究和应用。我们基于深度学习方法开发了一种支气管镜下肺癌诊断模型，并尝试对病理类型进行分类。
回顾性收集了2017年10月1日至2020年12月31日在中南大学湘雅三医院支气管镜中心经病理确诊的666例肺癌患者的2238张病变图像，以及2015年6月1日至2020年12月31日的152例良性病例。将良性和恶性图像分别按照7:1:2的比例分为训练集、验证集和测试集。基于深度学习方法对模型进行训练和测试。我们还尝试使用该模型对不同病理类型的肺癌进行分类。此外，邀请9名经验不同的临床医生对相同的测试图像进行诊断，并将结果与模型进行比较。
诊断模型诊断467张测试图像共耗时30秒。该模型鉴别良性和恶性病变的总体准确率、灵敏度、特异度和曲线下面积（AUC）分别为0.951、0.978、0.833和0.940，相当于高级组2名医生的判断结果，高于其他医生。在鳞状细胞癌（SCC）和腺癌（AC）的分类中，总体准确率为0.745，其中SCC为0.790，AC为0.667，AUC为0.728。
我们的诊断模型在支气管镜检查中鉴别良性和恶性病变的性能与经验丰富的临床医生大致相同，且效率远高于人工诊断。我们的研究验证了IRT在白光支气管镜检查中应用于肺癌诊断的可能性。
