Impact of dose reduction and iterative reconstruction algorithm on the detectability of pulmonary nodules by artificial intelligence

• Published in: Diagnostic and interventional imaging Vol. 103; no. 5; pp. 273 - 280
• Main Authors: Schwyzer, Moritz, Messerli, Michael, Eberhard, Matthias, Skawran, Stephan, Martini, Katharina, Frauenfelder, Thomas
• Format: Journal Article
• Language: English
• Published: France Elsevier Masson SAS 01.05.2022
• Subjects: Algorithms; Artificial Intelligence; Dose reduction; Drug Tapering; Early Detection of Cancer; Humans; Iterative reconstruction algorithm; Lung Neoplasms - diagnostic imaging; Lung nodule; Multiple Pulmonary Nodules - diagnostic imaging; Nodule detection; Phantoms, Imaging; Radiation Dosage; Radiographic Image Interpretation, Computer-Assisted - methods; Radiology; Tomography, X-Ray Computed - methods; PACS; CI; CNR; DLP; Nodule detection; kV; HU; ROI; Dose reduction; CT; mSv; Iterative reconstruction algorithm; Lung nodule; Artificial intelligence; mAs; ADMIRE; Kilovolt; advanced modeled iterative reconstruction; Computed tomography; Region of interest; Dose length product; Contrast to noise ratio; Millisievert; Hounsfield unit; Picture archiving and communication system; Confidence interval; Milliampere seconds
• ISSN: 2211-5684; 2211-5684
• DOI: 10.1016/j.diii.2021.12.002

•The performance of pulmonary nodule detection by artificial intelligence software is impacted by dose reduction and reconstruction settings.•Chest CT with lower image noise seem to have greater sensitivity and fewer false positive findings compared to reconstruction settings with high image noise when using fully automatic nodule detection software.•When using fully automatic nodule detection software at reduced radiation dose levels, increasing strength levels of iterative reconstruction might improve sensitivity and reduce false positive findings. The purpose of this study was to assess whether the performances of an automated software for lung nodule detection with computed tomography (CT) are affected by radiation dose and the use of iterative reconstruction algorithm. A chest phantom (Multipurpose Chest Phantom N1; Kyoto Kagaku Co. Ltd, Kyoto, Japan) with 15 pulmonary nodules was scanned with a total of five CT protocol settings with up to 20-fold dose reduction. All CT examinations were reconstructed with iterative reconstruction algorithms ADMIRE 3 and ADMIRE 5 and were then analyzed for the presence of pulmonary nodules with a fully automated computer aided detection software system (InferReadTM CT Lung, Infervision), which is based on deep neural networks. The sensitivity of fully automated pulmonary nodule detection for ground-glass nodules at standard dose CT was greater (70.0%; 14/20; 95% CI: 51.6-88.4%) than at 10-fold and 20-fold dose reduction (30.0%; 6/20; 95% CI: 0.0%-62.5%). There were less false positive findings when ADMIRE 5 reconstruction was used (4.0 ± 2.8 [SD]; range: 2–6) instead of ADMIRE 3 reconstruction (25.0 ± 15.6 [SD]; range: 14–36). There was no difference in the sensitivity of detection of solid and subsolid nodules between standard dose (100%; 95% CI: 100–100%) and 10- and 20-fold reduced dose CT (92.5%; 95% CI: 83.8–100.0%). Image noise was significantly greater with ADMIRE 3 (81 ± 2 [SD] [range: 79–84]; 104 ± 3 [SD] [range: 101–107]; 114 ± 5 [SD] [range: 110–119]; 193 ± 10 [SD] [range: 183-203]; 220 ± 16 [SD] [range: 210–238]) compared to ADMIRE 5 (44 ± 2 [SD] [range: 42–46]; 60 ± 2 [SD] [range: 57–61]; 66 ± 1 [SD] [range: 65–67]; 103 ± 4 [SD] [range: 98–106]; 110 ± 1 [SD] [range: 109–111]), respectively in each of the five CT protocols. This phantom study suggests that dose reduction and iterative reconstruction settings have an impact on detectability of pulmonary nodules by artificial intelligence software and we therefore encourage adaption of dose levels and reconstruction methods prior to widespread implementation of fully automatic nodule detection software for lung cancer screening purposes.