“…Motivated by the use of non‐local information in NL_R_FCM [5] and the constructions of factor in RSCFCM [6], we propose an NLSCHFCM algorithm for brain MR image segmentation by introducing a novel non‐local‐based factor where W i , n is the weighted parameter calculated by using (4). Therefore, we proposed an improved fuzzy clustering‐type objective function based on the novel factor NLF i , k In [27, 30], the bias field is reconstructed by using the liner combination of basis functions and can be written as where q l ∈ R , l = 1, …, L , are the combination coefficients. φ l is the orthogonal basis function and satisfies: , δ i , j = 1 for i = j and δ i , j = 0 for i ≠ j .…”