Abstract
Lung cancer screening based on low-dose CT (LDCT) has now been widely applied because of its effectiveness and ease of performance. Radiologists who evaluate a large LDCT screening images face enormous challenges, including mechanical repetition and boring work, the easy omission of small nodules, lack of consistent criteria, etc. It requires an efficient method for helping radiologists improve nodule detection accuracy with efficiency and cost-effectiveness. Many novel deep neural network-based systems have demonstrated the potential for use in the proposed technique to detect lung nodules. However, the effectiveness of clinical practice has not been fully recognized or proven. Therefore, the aim of this study to develop and assess a deep learning (DL) algorithm in identifying pulmonary nodules (PNs) on LDCT and investigate the prevalence of the PNs in China. Radiologists and algorithm performance were assessed using the FROC score, ROC-AUC, and average time consumption. Agreement between the reference standard and the DL algorithm in detecting positive nodules was assessed per-study by Bland–Altman analysis. The Lung Nodule Analysis (LUNA) public database was used as the external test. The prevalence of NCPNs was investigated as well as other detailed information regarding the number of pulmonary nodules, their location, and characteristics, as interpreted by two radiologists.
Highlights
Lung cancer screening has been widely applied because of its effectiveness and ease of performance
The sensitivity of the deep learning (DL) model was more than 90% at a rate of 2 false positives (FPs) nodules identified per study (91% at 2 FPs/study), and the free-response receiver operating characteristic (FROC) score in the multi-centre validation set was 0.75
The sensitivity of the DL model was more than 93.4% at a rate of 0.8FP nodules identified per study (93.4% at 0.8FPs/study) on the Lung Nodule Analysis (LUNA) dataset, the FROC score for the LUNA data was 0.80, which was slightly better than the abovementioned score obtained in the multi-centre validation set
Summary
Lung cancer screening has been widely applied because of its effectiveness and ease of performance. AI detection of lung nodules has long been expected to be an effective assistant in daily clinical practice, especially for LDCT lung nodule screening. Many novel deep neural networkbased systems have demonstrated the potential for use in the proposed technique for helping radiologists improve nodule detection accuracy with efficiency and cost-effectiveness[13,14,15,16,17,18]. The aim of this study was to assess the performance and effectiveness of deep neural networks for lung nodule detection by comparing the diagnostic efficacy of this AI system with that of radiologists evaluating clinical LDCT cases, in addition, performed a large-scale analysis of lung LDCT screening in three medical centres, investigate the prevalence and characteristics of the NCPNs in Chinese population
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
