Background: Non-small-cell carcinoma (NCSLC) is the most common type of early lung cancer. Early detection of NSCLC is still a diagnostic challenge. Current clinical management of patients with pulmonary nodule is inefficient and may lead to misclassification, thus increasing healthcare expenses. Further, a few previous studies showed liquid biopsy and artificial intelligence (AI) platform on computed tomography (CT) imaging contributes to early NSCLC detection. Still, there is something lacking in a precise and authorized lung nodule classifier to minimize discomfort of patients. This study aims to evaluate the possibility and effectiveness of combining circulating genetically abnormal cells (CACs) with an AI platform on CT imaging to improve the diagnostic route for NSCLC. Methods: A prospective cohort of 101 in-patients was enrolled from Sep. 1, 2020 to Jan. 15, 2021, with non-calcified pulmonary nodules, ranging from 0.5 to 3 cm in diameter, indicated by CT. The participants' pulmonary nodules will be assessed by two evaluation tools: CAC detection on full blood and AI platform on CT imaging. The diagnostic performances of the two tools were evaluated in a blinded validation study respectively and combined in an open-label retrospective analysis. Results: 68 of enrolled patients were confirmed as NSCLC by pathology. The diagnostic performance of CACs for NSCLC detection was 80.9% for sensitivity and 87.3% for positive predictive value (PPV) while overall accuracy reaches 79.2%. AI platform showed a slight disadvantage as 78.6% for PPV and 73.5% for accuracy. 9 false-negative patients on CAC results could be reversed with a combination of AI platform on CT imaging, while sensitivity rises to 94.1%. However, of 33 benign nodules patients, 8 wrong diagnoses by CAC detection could decrease to 2 when combined with the results from the AI platform, which may avoid unnecessary biopsies. Conclusions: Coupling CAC with an AI platform on CT imaging could be a useful strategy to improve the diagnostic route for NSCLC and avoid unnecessary biopsies.