ABSTRACT
AIM: To evaluate primary and secondary pathologies of interest using an artificial intelligence (AI) platform, AI-Rad Companion, on low-dose computed tomography (CT) series from integrated positron-emission tomography (PET)/CT to detect CT findings that might be overlooked. MATERIALS AND METHODS: One hundred and eighty-nine sequential patients who had undergone PET/CT were included. Images were evaluated using an ensemble of convolutional neural networks (AI-Rad Companion, Siemens Healthineers, Erlangen, Germany). The primary outcome was detection of pulmonary nodules for which the accuracy, identity, and intra-rater reliability was calculated. For secondary outcomes (binary detection of coronary artery calcium, aortic ectasia, vertebral height loss), accuracy and diagnostic performance were calculated. RESULTS: The overall per-nodule accuracy for detection of lung nodules was 0.847. The overall sensitivity and specificity for detection of lung nodules was 0.915 and 0.781. The overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia, and vertebral height loss was 0.979, 0.966, and 0.840, respectively. The sensitivity and specificity for coronary artery calcium was 0.989 and 0.969. The sensitivity and specificity for aortic ectasia was 0.806 and 1. CONCLUSION: The neural network ensemble accurately assessed the number of pulmonary nodules and presence of coronary artery calcium and aortic ectasia on low-dose CT series of PET/CT. The neural network was highly specific for the diagnosis of vertebral height loss, but not sensitive. The use of the AI ensemble can help radiologists and nuclear medicine physicians to catch CT findings that might be overlooked.
Subject(s)
Lung Neoplasms , Multiple Pulmonary Nodules , Solitary Pulmonary Nodule , Humans , Positron Emission Tomography Computed Tomography/methods , Artificial Intelligence , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/pathology , Calcium , Reproducibility of Results , Dilatation, Pathologic , Incidental Findings , Multiple Pulmonary Nodules/pathology , Neural Networks, Computer , Solitary Pulmonary Nodule/diagnostic imaging , Solitary Pulmonary Nodule/pathologyABSTRACT
BACKGROUND: Posterior circulation of brain is important because of vital organs' blood supply provided by them. In this study, we evaluate the relationship of posterior circulation measurements with age, gender and side by using computed tomography angiography (CTA) images. MATERIALS AND METHODS: A total 199 brain CTA examinations were retrospectively analysed for all posterior circulation arteries (vertebral artery, basilar artery, posterior cerebral artery [PCA], superior cerebellar artery [SCA], anterior inferior cerebellar artery, and posterior inferior cerebellar artery [PICA]) to compare the difference based on age, gender and side. RESULTS: There is no correlation between age and the mean diameters of all vessels (p > 0.05). The mean diameter of left vertebral artery was higher than right vertebral artery in all genders (p = 0.004 for males and p < 0.001 for females). The mean diameter of left SCA and PICA were higher than right SCA and PICA in females (p = 0.032 and p = 0.027, respectively). The mean diameters of basilar, left PCA, left SCA, left vertebral, right PCA, right SCA, right PICA and right vertebral artery were higher in males and that differences were statistically significant (p < 0.001, p = 0.002, p = 0.006, p = 0.004, p = 0.001, p = 0.003, p = 0.002, and p = 0.006, respectively). CONCLUSIONS: The posterior circulation vessel diameter is not affected by aging. The mean diameters of basilar artery, both PCAs, both SCAs, right PICA, both vertebral arteries were higher in males. The mean diameter of left vertebral artery is higher than that of right vertebral artery in all genders.
