CT plays an important role in diagnosis of lung cancer, however has been limited by uncertain detection rate for early stage of non-small-cell lung cancer (NSCLC), particularly central tumors. Genetic analysis of sputum has proven to be useful in diagnosis of NSCLC. We proposed to evaluate efficacy of combing CT and genetic analysis of sputum for noninvasive diagnosis of stage I NSCLC. Genomic copy changes of a panel of lung cancer-related genes, HYAL2, FHIT, p16, and SP-A were analyzed by a mini-chip in sputum from 33 patients with stage I NSCLC and 49 cancer-free controls. The genetic and CT diagnoses were compared with surgical-pathologic stage. CT had higher sensitivity (85%) in detection of lung cancer compared with the mini-chip (70%) (p<0.05), while there was no significant difference in specificity between the two tests (89% vs. 92%, p=0.09). Similarly, CT showed considerably higher sensitivity (93%) in identifying peripheral tumors than did the mini-chip (64%) (p<0.05), whereas there was no difference in specificity between them (98% vs. 96%, p=0.28). However, in detecting central tumors, CT had lower specificity (90%) compared with the mini-chip (98%) (p<0.05), although its sensitivity (79%) was higher than that of the mini-chip (73%) (p=0.05). Combining both tests offered higher sensitivity (91%) than did any single one (85%, 70%, all <0.05), while still keeping 92% sensitivity. In particular, this combined approach yielded higher sensitivity, specificity, and accuracy for diagnosing central cancers compared with CT alone (all p<0.05). The integration of the genetic assay with CT led to improvements in noninvasive diagnosis of stage I NSCLCs, especially central tumors.