深度卷积网络骨抑制技术对孤立性肺结节诊断效能的研究

The clinical research of deep bone suppression imaging in solitary pulmonary nodules

目的评估新型骨抑制技术—深度卷积网络骨抑制成像(deep bone suppression imaging,deepBSI)对孤立性肺结节(solitary pulmonary nodule,SPN)的诊断效能,并与数字化X线片(digital radiograph,DR)、双能量减影技术(dual energy substraction,DES)进行对比分析。方法收集我院2016年12月~2017年9月拍摄标准胸部正位片247例(114例诊断SPN,133例无结节)。3位低年资及3位高年资医师按DR图像→DR+deepBSI图像→DR+DES图像的阅片顺序,分别在三组图像上标出结节可能位置并评分,进行Z检验,应用ROC曲线分析三种检查方法对SPN的诊断效能。结果6位医师,DR、deepBSI、DES三种检查方法诊断SPN的ROC曲线下面积分别约0.715、0.804、0.800,deepBSI、DES诊断效能均优于DR(P<0.05)。当结节与肋骨重叠面积>50%时,deepBSI、DES二种方法相比于DR诊断SPN的诊断效能越好。结论deepBSI、DES诊断效能均优于DR,有助于肺结节的检出,与肋骨重叠面积大的结节优势更显著,deepBSI、DES诊断敏感性及特异性始终相似。

Objective To evaluate a newly developed bone suppression methods-deep Bone Suppression Imaging(deepBSI)for detecting solitary pulmonary nodules(SPNs),comparing to digital radiograph(DR),and Dual-energy subtraction(DES).Methods A total of 247 patients were collected from Nan fang Hospital from 2016 to 2017,114 patients with SPNs and 133 patients without nodules.Three radiologists and three radiology residents marked suspicious-appearing nodules on the standard chest radiographs,deep BSI images and DES images in this study.The Z-test and receiver operating characteristic(ROC)was used for analyses.Results For all observers,the average area under the ROC curves(AUCs)was significantly improved from 0.715 with use of standard chest radiographs alone to 0.804 with standard plus deepBSI and to 0.800 with standard plus DES(both P<0.001).Conclusion Use of deepBSI imaging together with a standard radiograph can improve radiologists’accuracy for detection of SPNs on chest radiographs,especially for nodules with partial to complete overlapping with bones.The diagnostic performance of deepBSI and DES is similar,but DES with the requirement for special equipment and a certainly increase in radiation dose.