Three-dimensional medical image analysis method and system for identification of vertebral fractures

The present invention provides a machine-based learning method to estimate a probability of bone fractures in a 3D image, more specifically vertebral fractures. The method and system utilizing such method utilize a data-driven computational model to learn 3D image features for classifying vertebra fractures, that producing two or more sets of 3D voxels, wherein each of the sets corresponds to the entire said 3D image, and wherein each of the sets consists of voxels of equal dimensions, the two or more sets of 3D voxels including a set of first voxels of a first size and a set of second voxels of a second size, said second size different to said first size; and generating a voxels classification output by assigning to said voxels one or more class probabilities of a voxel to contain a fracture by classifying each of said voxels in each set in the context of the surrounding voxels.