Abstract:
We propose a universal neural network architecture for single-stage multi-class polygonal model generation of anatomical structures from three-dimensional medical images. The key component of the architecture is a trainable affine module that dynamically positions and scales the seed surfaces of anatomical structures. This eliminates the need for manual template preparation and reduces the number of self-intersections in the resulting meshes. The effectiveness of the proposed approach has been confirmed on the CHAOS and MMWHS datasets. On CHAOS, an average Dice score of 0.958 was achieved with a ASSD of 1.399 mm, and self-intersections were observed in only 2 out of 20 generated surfaces. On MMWHS, the average Dice score across heart structures is approximately 0.9, and the proportion of self-intersecting edges is comparable to or lower than the best available methods. Overall, the results demonstrate an accuracy level comparable to modern standards while producing meshes with significantly cleaner topology. Ablation analysis also confirmed the importance of the affine module for generating topologically correct polygonal models.
