Hybrid-CSR: Coupling Explicit and Implicit Reconstruction of Cortical Surface

We present Hybrid-CSR, a geometric deep-learning model that combines explicit and implicit shape representations for cortical surface reconstruction. Specifically, Hybrid- CSR begins with explicit deformations of template meshes to obtain coarsely recon- structed cortical surfaces, based on which the oriented point clouds are estimated for the subsequent differentiable poisson surface reconstruction. By doing so, our method unifies explicit (oriented point clouds) and implicit (indicator function) cortical sur- face reconstruction. Compared to explicit representation-based methods, our hybrid ap- proach is more friendly to capture detailed structures, and when compared with implicit representation-based methods, our method can be topology aware because of end-to-end training with a mesh-based deformation module. In order to address topology defects, we propose a new topology correction pipeline that relies on optimization-based diffeo- morphic surface registration. Experimental results on three brain datasets show that our approach surpasses existing implicit and explicit cortical surface reconstruction methods in numeric metrics in terms of accuracy, regularity, and consistency. Our code will be publicly released when published. © 2024. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.