Scalability and others functionalities such as the Region of Interest encoding become essential properties of an efficient image coding scheme. Within the framework of lossless compression techniques, S+P and CALIC represent the state-of-the-art. The proposed Interleaved S+P algorithm outperforms these method while providing the desired properties. Based on the LAR (Locally Adaptive Resolution) method, an original pyramidal decomposition combined with a DPCM scheme is elaborated. This solution uses the S-transform in such a manner that a refined prediction context is available for each estimation steps. The image coding is done in two main steps, so that the first one supplies a LAR low-resolution image of good visual quality, and the second one allows a lossless reconstruction. The method exploits an implicit context modelling, intrinsic property of our content-based quad-tree like representation.