Gadolinium-enhanced magnetic resonance imaging (MRI) is widely used to detect recurrent nasal tumours. A specifically designed two-layer Hopfield neural network, called the spatiotemporal Hopfield neural cube (SHNC), is presented, to be used for detecting recurrent nasal papilloma. Differing from conventional, two-dimensional Hopfield neural networks, the SHNC extends the one-layer, two-dimensional Hopfield network in the original image plane into a two-layer, three-dimensional (3D) Hopfield network with pixel classification implemented in its third dimension. With extended 3D architecture, the network is able to use each pixel's spatial information in a pixel labelling procedure. Because the SHNC takes pixel spatial information into consideration, the effects of tiny detail or noise are removed. As a result, the drawback of disconnected fractions can be avoided. Furthermore, owing to the incorporation of competitive learning rules to update neuron states, to avoid the problem of having to satisfy strong constraints, the convergence of the network was improved. In addition, a more accurate signal-time curve, the relative intensity change (RIC), was adopted to represent the gadolinium-enhanced MRI temporal information, and the RIC curves of recurrent nasal papilloma were incorporated into the SHNC. The experimental results showed that the SHNC could obtain a more appropriate, precise position of recurrent nasal papilloma than the k-means, principal components analysis (PCA) or Eigenimage-filtering methods. The average sensitivity and specificity of the 26 cases were 0.9998 and 0.9961, respectively. These values demonstrate the effectiveness of the proposed technique.