© 2015, American College of Rheumatology. Objective To identify patterns of coexisting lesions seen on magnetic resonance imaging (MRI) in knees that are free of radiographic osteoarthritis (OA) and to examine the relationship of these MRI-detected lesions to incident OA. Methods Study subjects were individuals enrolled in the Multicenter Osteoarthritis Study, a prospective cohort study. In each subject, 1 knee in which radiographic OA was absent in both the tibiofemoral and patellofemoral joints at baseline was selected for study, with followup for 84 months. We used a novel approach, latent class analysis, to group the constellation of MRI lesions in each joint, i.e., cartilage damage, bone marrow lesion, meniscal tear, meniscal extrusion, synovitis, and effusion, into a manageable number of subgroups. The association of these subgroups with incident radiographic OA in the same joint was assessed using logistic regression. Results Among 885 eligible knees (203 with incident disease in the tibiofemoral joint, 64 with incident disease in the patellofemoral joint), 4 latent subgroups in the tibiofemoral joint were identified (described briefly as minimal lesions, mild lesions, moderate lesions [but limited meniscal lesions], and severe lesions). The odds ratios of incident tibiofemoral joint OA in the latter 3 subgroups (compared to the knees with minimal lesions as the referent) were 5.6, 1.8, and 5.0, respectively. A similar set of 4 subgroups in the patellofemoral joint was identified, except that the fourth subgroup had limited meniscal lesions. The odds ratios of incident disease in the patellofemoral joint were 3.8, 5.1, and 13.7 in the subgroups with mild lesions, moderate lesions, and severe lesions, respectively. Conclusion Different patterns of coexisting MRI lesions, which have different implications with regard to risk of knee OA, were identified. Meniscal damage seemed to play a different role in the development of incident disease in tibiofemoral versus patellofemoral joints.