Recent advances in technology, including widespread availability of multidetector computed tomographic (MDCT) scanners associated with an abundance of new information obtained especially from low-dose CT (LDCT) lung cancer screening programs, have increased our understanding of the varieties of small peripheral lung nodules encountered in daily clinical practice, in particular, the importance and prevalence of non-calcified pulmonary nodule (NCPN). The determination of the etiology of such a nodule is usually important to direct the appropriate therapy (e.g., observation, biopsy, or resection). Sometimes it is difficult or impractical to obtain tissue and thus establish a definitive diagnosis. In such cases, it may be helpful to know the likelihood that such a nodule represents a benign lesion, metastasis, or primary bronchogenic carcinoma.
　　The high frequency of NCPN <10mm incidentally detected on a MDCT of the chest raises the question of how clinicians and radiologists should deal with these nodules. Unfortunately, the low specificity of CT necessitates the follow-up of a large number of small (<10 mm) pulmonary nodules that ultimately turn out to be benign, and there are few data regarding the benefit of long-term follow-up of subcentimeter NCPNs. Data pertaining to the natural history of these nodules will have important implications for cost benefit analysis in any future LDCT screening programs. This lecture sought to investigate the clinical relevance of small (10 mm or less) incidental pulmonary nodules and to determine the spectrum of malignant tumours in such patients. This lecture also sought to determine the characteristics associated with malignancy and to develop a statistical model to guide the clinician as to choice of patients for diagnostic biopsy.
　　While the imaging technology has proven effective, numerous research efforts have explored use of another up-and-coming technology — artificial intelligence (AI). AI is one of the hottest topics radiologic meeting. Many studies have demonstrated the great potential of AI to supplement small nodule and lung cancer detection, the scientific lecture is looking outward to define the next evolution of the technology. This technology may further improve nodule detection, classification and sizing, while also reducing false-positive rates. The lecture will explore the potential of AI to aid radiologists in assessing lung nodule detection and diagnosis in CT scans.