Manuscript title: Impact of vessel suppression AI on reading efficiency and nodule detection in CT chest.

BACKGROUND

Vessel suppression (VS) software enhances pulmonary nodule conspicuity by attenuating vascular and fissural structures, but real-world impact on clinical workflows remains uncertain.

METHODS

We retrospectively analyzed 8,835 chest CT examinations (January 2023-February 2024) interpreted at a single academic institution, comparing pre- and post-VS implementation. Reads by residents and faculty were assessed separately. Outcomes included interpretation time and pulmonary nodule detection, extracted using natural language processing with manual validation.

RESULTS

Among residents, mean read time decreased from 19.1 to 12.2 minutes (p<0.001), with improved detection of punctate nodules (13.0% vs 24.2%, p<0.001). Faculty showed reduced mean read time (6.6 vs 5.2 minutes, p<0.001) and modest improvement in punctate nodule detection (26.0% vs 29.5%, p=0.042).

CONCLUSION

VS improved reading efficiency for both trainees and faculty and substantially increased small-nodule detection among residents and attending radiologists. While the clinical significance of detecting sub-2 mm nodules remains uncertain, efficiency gains support the value of VS in high-volume and training environments. Further study is warranted to define downstream clinical impact and guide management of incidentally detected small nodules.