Volumetric texture analysis is an import task in medical imaging domain and is widely used for characterizingtissues and tumors in medical volumes. Local binary pattern (LBP) based texture descriptors are quite success-ful for characterizing texture information in 2D images. Unfortunately, the number of binary patterns growsexponentially with number of bits in LBP. Hence its straightforward extension to 3D domain results in extremelylarge number of bit patterns that may not be relevant for subsequent tasks like classification. In this work wepresent an efficient extension of LBP for 3D data using decision tree. The leaves of this tree represent texturewords whose binary patterns are encoded using the path being followed from the root to reach the leaf. Oncetrained, this tree is used to create histogram in bag-of-words fashion that can be used as texture descriptor forwhole volumetric image. For training, each voxel is converted into a 3D LBP pattern and is assigned the labelof it's corresponding volumetric image. These patterns are used in supervised fashion to construct decision tree.The leaves of the corresponding tree are used as texture descriptor for downstream learning tasks. The proposedtexture descriptor achieved state of the art classification results on RFAI database 1. We further showed itsefficacy on MR knee protocol classification task where we obtained near perfect results. The proposed algorithmis extremely efficient, computing texture descriptor of typical MRI image in less than 100 milliseconds.
展开▼
