Although [(18)F]fluorothymidine positron emission tomography (FLT-PET) permits estimation of tumor thymidine kinase-1 expression, and thus, cell proliferation, high physiological uptake of tracer in liver tissue can limit its utility. We evaluated FLT-PET combined with a temporal-intensity information-based voxel-clustering approach termed kinetic spatial filtering (FLT-PET(KSF)) for detecting drug response in liver metastases. FLT-PET and computed tomography data were collected from patients with confirmed breast or colorectal liver metastases before, and two weeks after the first cycle of chemotherapy. Changes in tumor FLT-PET and FLT-PET(KSF) variables were determined. Visual distinction between tumor and normal liver was seen in FLT-PET(KSF) images. Of the 33 metastases from 20 patients studied, 26 were visible after kinetic filtering. The net irreversible retention of the tracer (Ki; from unfiltered data) in the tumor, correlated strongly with tracer uptake when the imaging variable was an unfiltered average or maximal standardized uptake value, 60 min post-injection (SUV(60,av): r = 0.9, SUV(60,max): r = 0.7; p < 0.0001 for both) and occurrence of high intensity voxels derived from FLT-PET(KSF) (r = 0.7, p < 0.0001). Overall, a significant reduction in the imaging variables was seen in responders compared to non-responders; however, the two week time point selected for imaging was too early to allow prediction of long term clinical benefit from chemotherapy. FLT-PET and FLT-PET(KSF) detected changes in proliferation in liver metastases.