To assess axial involvement on MRI in early peripheral spondyloarthritis (pSpA) and to evaluate whether axial inflammation predicts relapse on treatment withdrawal.Fifty-six patients with early, active, newly diagnosed pSpA underwent MRI of the sacroiliac joints (SIJs) and spine prior to golimumab initiation. At sustained clinical remission of pSpA, treatment was withdrawn and a second MRI was performed. Bone marrow oedema (BME) was scored by three readers according to the Spondyloarthritis Research Consortium of Canada (SPARCC) method. Scores were compared with an axial spondyloarthritis cohort (Belgian Arthritis and Spondylitis cohort). Structural lesions were assessed using a similar method. Furthermore, fulfilment of the Assessment of Spondyloarthritis International Society (ASAS) definition of a positive MRI for sacroiliitis was assessed. Spinal images were evaluated for BME and structural lesions using the Canada-Denmark MRI spine scoring system by two readers.Thirty-six per cent showed SIJ BME at baseline, all fulfilling the ASAS definition of sacroiliitis. No association with back pain was found. Twenty-one per cent displayed SIJ structural lesions. Spinal BME was limited: the median inflammation scores were low and no patients had ≥5 inflammatory corner lesions. On clinical remission, a significant decrease in SIJ SPARCC scores was detected. On clinical remission, no significant differences in SIJ SPARCC scores were noted between patients relapsing and those maintaining remission after treatment discontinuation.In patients with early pSpA, a surprisingly high prevalence of sacroiliitis on MRI was observed; SPARCC scores decreased significantly on tumour necrosis factor inhibition. Residual inflammation on MRI was not predictive of relapse of peripheral manifestations. No relevant inflammatory spinal involvement was detected. Collectively, our findings suggest a higher inflammatory burden in patients with early pSpA than anticipated.