A cascade and heterogeneous neural network for CT pulmonary nodule detection and its evaluation on both phantom and patient data. (June 2021)

• Record Type: Journal Article
• Authors: Xiao, Yi; Wang, Xiang; Li, Qingchu; Fan, Rongrong; Chen, Rutan; Shao, Ying; Chen, Yanbo; Gao, Yaozong; Liu, Aie; Chen, Lei; Liu, Shiyuan
• Is Part Of: Computerized medical imaging and graphics. Volume 90(2021)
• Publication Date: 2021-06
• Subjects: Computed tomography (CT) -- Lung nodule detection -- Phantom -- Deep learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2021.101889
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: Proposed a fully automated nodule detector using cascade and heterogeneous CNNs, which achieved a sensitivity of 0.881 on 1215 testing CT images. Evaluated the performance of nodule detection for different dose, resolution, and reconstruction methods using CT volumes from 828 phantom and 110 patients, respectively. The results recommend reconstruction methods "iDose4-STD" and "iDose4-YA" for thin- and thick-slice, respectively. Abstract: Screening of pulmonary nodules in computed tomography (CT) is crucial for early diagnosis and treatment of lung cancer. Although computer-aided diagnosis (CAD) systems have been designed to assist radiologists to detect nodules, fully automated detection is still challenging due to variations in nodule size, shape, and density. In this paper, we first propose a fully automated nodule detection method using a cascade and heterogeneous neural network trained on chest CT images of 12155 patients, then evaluate the performance by using phantom (828 CT images) and clinical datasets (2640 CT images) scanned with different imaging parameters. The nodule detection network employs two feature pyramid networks (FPNs) and a classification network (BasicNet). The first FPN is trained to achieve high sensitivity for nodule detection, and the second FPN refines the candidates for false positive reduction (FPR). Then, a BasicNet is combined with the second FPR to classify the candidates into either nodules or non-nodules for the final refinement. This study investigates the performance of nodule detection of solid and ground-glass nodules in phantom and patient data scanned with different imaging parameters. The results show that the detection of the solid nodules is robust to imaging parameters, and for GGO detection, reconstruction methods "iDose4-YA" and "STD-YA" achieve better performance. For thin-slice images, higher performance is achieved across different nodule sizes with reconstruction method "iDose4-STD". For 5 mm slice thickness, the best choice is the reconstruction method "iDose4-YA" for larger nodules (>5 mm). Overall, the reconstruction method "iDose4-YA" is suggested to achieve the best balanced results for both solid and GGO nodules.