The Gap in the Thickness: Estimating Effectiveness of Pulmonary Nodule Detection in Thick- and Thin-Section CT Images with 3D Deep Neural Networks. (February 2023)

• Record Type: Journal Article
• Authors: Guo, Quan; Wang, Chengdi; Guo, Jixiang; Bai, Hongli; Xu, Xiuyuan; Yang, Lan; Wang, Jianyong; Chen, Nan; Wang, Zihuai; Gan, Yuncui; Liu, Lunxu; Li, Weimin; Yi, Zhang
• Is Part Of: Computer methods and programs in biomedicine. Volume 229(2023)
• Publication Date: 2023-02
• Subjects: Lung Nodule -- Computed Tomography -- Neural Networks; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107290
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A 3D convolutional neural network model has been developed to detect pulmonary nodule in either thick or thin section LDCT. A set of CT scans have been annotated for pulmonary nodules in an efficient three-level protocol, correct and improve the annotation with trained neural networks proposal. A performance gap between the thick and thin scans for pulmonary nodule detection by experienced pulmonary experts, regarding both false negative and false positive has been observed. Neural network models, achieving competitive detection performance, can help reduce false negative and trade off the false negative for sensitivity. A combination of the human and trained Neural network models is a promising way to achieve fast and accurate diagnose, even with thick scan setting, which is efficiency in screening, has cheap price, and has lower radiation dose Abstract: Background and Objectives. There is a noticeable gap in diagnostic evidence strength between the thick and thin scans of Low-Dose CT (LDCT) for pulmonary nodule detection. When the thin scans are needed is unknown, especially when aided with an artificial intelligence nodule detection system. Methods. A case study is conducted with a set of 1, 000 pulmonary nodule screening LDCT scans with both thick (5.0mm), and thin (1.0mm) section scans available. Pulmonary nodule detection is performed by human and artificial intelligence models for nodule detection developed using 3D convolutional neural networks (CNNs). The intra-sample consistency is evaluated with thick and thin scans, for both clinical doctor and NN (neural network) models. Free receiver operating characteristic (FROC) is used to measure the accuracy of humans and NNs. Results. Trained NNs outperform humans with small nodules < 6.0mm, which is a good complement to human ability. For nodules > 6.0mm, human and NNs perform similarly while human takes a fractional advantage. By allowing a few more FPs, a significant sensitivity improvement can be achieved with NNs. Conclusions. There is a performance gap between the thick and thin scans for pulmonary nodule detection regarding both false negatives and false positives. NNs can help reduce false negatives when the nodules are small and trade off the false negatives for sensitivity. A combination of human and trained NNs is a promising way to achieve a fast and accurate diagnosis.