Accurate tissue segmentation in brain magnetic resonance image is of paramount importance for brain reconstruction and analysis. Supervoxels analysis enables relatively robust segmentation of brain tissues, by assigning the supervoxels to tissue clusters according to the inherent information of multiple features captured from the supervoxels. In this popular framework, difficulties are encountered in clustering imposed by the insufficient selection, deficient utilisation of features, and rough supervoxel boundaries due to the influence of noise. To address these aforementioned challenges, the authors propose a weighted feature fusion clustering segmentation method for dividing supervoxels into three tissues on the basis of a robust feature fused similarity matrix. To comprehensively capture the similarities of features among the supervoxels, we construct three complementary similarity matrices on the basis of multiple features from three aspects, that is, appearance, shape, and space location. Next, the authors propose a weighted similarity network fusion method to discriminatively fuse the three similarity matrices into one single matrix. This novel fusion process cannot only extract the common and complementary information of features, but also automatically adjust the weight of similarities according to its reliability. Finally, we achieve initial segmentation results by performing spectral clustering on the fused similarity matrix. To optimise the segmented boundaries affected by noise in the initial segmentation results, the authors construct a voxel-wise diffusion energy function by considering the intensity information of neighbouring voxels. Experiments on two public brain magnetic resonance image datasets demonstrate the robustness of the proposed approach.