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

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 1,0 0 0 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 de-tection 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.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

A study was conducted on 1,000 LDCT scans for pulmonary nodule screening, comparing the performance of thick and thin scans. The study found that trained neural networks outperformed human doctors in detecting small nodules (<6.0mm), while human doctors had a slight advantage for larger nodules (>6.0mm). The combination of artificial intelligence and human doctors showed promise for achieving fast and accurate diagnosis.