CardioComposer: Flexible and Compositional Anatomical Structure Generation with Disentangled Geometric Guidance
This work addresses a domain-specific problem for clinical research and medical device design by enabling more flexible and realistic anatomical generation.
The paper tackled the trade-off between controllability and anatomical realism in generative models of 3D anatomy by proposing a programmable framework using disentangled geometric guidance, resulting in independent control over size, shape, position, and composition of anatomical structures.
Generative models of 3D anatomy, when integrated with biophysical simulators, enable the study of structure-function relationships for clinical research and medical device design. However, current models face a trade-off between controllability and anatomical realism. We propose a programmable and compositional framework for guiding unconditional diffusion models of human anatomy using interpretable ellipsoidal primitives embedded in 3D space. Our method involves the selection of certain tissues within multi-tissue segmentation maps, upon which we apply geometric moment losses to guide the reverse diffusion process. This framework supports the independent control over size, shape, and position, as well as the composition of multi-component constraints during inference.