Artificial intelligence evaluation of simulated phantom lung nodules with different pre-adaptive iteration techniques

Abstract

Objective: To investigate the detection rate of pulmonary nodules and the accuracy of automated measurement in chest simulation phantom by artificial intelligent computer-aided detection of pulmonary nodules with different pre-adaptive iterative techniques (ASIR-V) in wide-spectrum CT scanning. Methods: Sixteen pulmonary nodules with different diameters, densities and shapes were placed in the chest simulation phantom from December 2017 to March 2018. The weight of ASIR-V was set at 0%, 20%, 30%, 40% and 50% respectively by using Revolution CT broadband energy spectrum scanning protocol. Spearman correlation analysis was used to analyze the dose volume CT dose index (CTDIvol) and dose length product (DLP) of each group. Scanning data were imported into Tuma Shenwei artificial pulmonary nodule analysis software to evaluate the nature of the detected nodules, and ICC was used to detect the differences among groups. Results: With the increase of ASIR-V weight, the effective dose of patients decreased gradually. CTDIvol of five groups of radiation dose volume CT dose index was 7.93, 7.24, 5.85, 5.15, 3.76 mGy,dose-length product DLP was 379, 346, 280, 246, 179 mGy·cm.There was a linear negative correlation between ASIR-V weights and CTDIvol as well as DLP, r value was-0.969, P<0.01.There was no significant difference in the detection rate of pulmonary nodules between AI and physicians (P>0.05). There was high intraclass correlation coefficients for the diameter, volume, CT value and malignant percentage of pulmonary nodules (ICCs:0.981-1.000). Conclusions: Radiation dose of unenhanced chest CT scan using wide detector spectral imaging decreased with the increasing of preset ASIR-V. Lung nodule detection rate and evaluation performance can be maintained well by using ASIR-V reconstructions at lower radiation dosage.