Background <p>The reliable detection of small pulmonary nodules is crucial for the early detection of lung cancer and other nodular lung diseases. However, the radiologist’s sensitivity for the detection of small pulmonary lesions is limited. Therefore, there is a strong demand for the development of accurate computer-aided detection (CAD) tools in this context. Our objective is to determine the efficacy of CAD in detection and assessment of pulmonary nodules in computed tomography of the chest.</p> Results <p>In our study we included 60 patients with incidentally discovered pulmonary nodules. All patients had CT chest scan then moved to the work station for processing with CAD tools, comparing the results with the radiologists’ findings. The CAD system detected 1 to 3 lesions in most cases, with 36.7% of participants having 3 lesions. The difference between CAD and expert opinion was significant for 48.3% of cases, with a majority 51.7% showing no difference. CAD achieved 81.7% true positives (TP) and had a relatively low false negative (FN) rate (3.3%). CAD tended to overestimate the number of lesions in 20% of cases and underestimate in 28.3% of cases.</p> Conclusions <p>Computer-aided detection system and the junior radiologist performed well independently; their combined approach provided the most accurate and reliable lesion detection, closely matching expert opinions. This suggests that integrating CAD with radiologists’ assessments can improve diagnostic accuracy in clinical settings.</p>