It has been recognized that dual-time FDG-PET imaging can facilitate the differentiation of malignancy from benign lesions for cancer diagnosis. However, dual-time imaging protocols with retention index (RI) as a criteria in the classification are usually defined empirically, which might lead to the low accuracy in differentiation. Recently, a new quantitative index (QI) has been proposed to improve diagnostic efficacy. In this paper, we propose a novel framework to derive generalized optimal QI and its associated optimal ranges of imaging protocol to further improve the performance of dual-time FDG-PET imaging in lung cancer diagnosis.