AI summaryⓘ
The authors developed a new kind of neural network called Anatomy-Informed Neural Networks (AINN) that uses knowledge about anatomy to avoid impossible predictions and improve learning when data is limited. They applied this to a medical case involving how blood vessels change shape when a wire is inserted, which is important for surgeries inside arteries. Their method combines physical and anatomical rules directly into the model and uses 2D X-ray images to train a 3D prediction of vessel behavior. They have tested parts of the model, but it hasn't been fully validated yet, and no actual neural network training has been done at this stage. Future work will apply this approach to real CT scans to see if it helps make better predictions with less data.
Anatomy-Informed Neural NetworksAortoiliac treeCosserat rod theoryLie group SE(3)Wasserstein-2 distanceEndovascular navigationAngiogramElastic energy minimizationPhysics-informed neural networksOptimal transport
Abstract
Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduce Anatomy-Informed Neural Networks (AINN), in which soft anatomic priors enter as penalty terms in the loss (e.g., a branching penalty that treats a renal transplant artery off the iliac instead of the aorta as unexpected rather than impossible), in direct analogy to a physics-informed neural network, and hard anatomic priors (e.g., continuity of the vessel) are built into the architecture and state representation, making such invalid predictions impossible by construction wherever the prior admits architectural enforcement. We develop it on a clinical test case with limited data: how the aortoiliac tree deforms when a stiff wire is introduced endoluminally. This is important to contemporary aortic surgery and will matter to autonomous endovascular navigation. We lift the vessel centerline and the wire path from R^3 to curves of frames in the Lie group SE(3), and couple a Cosserat-rod wire to a tortuosity-modulated, anatomically anchored vessel through a unilateral lumen-contact inequality. The prediction is a constrained minimizer of the coupled elastic energy, with contact forces as its Lagrange multipliers. Supervision is a Wasserstein-2 optimal-transport loss between the predicted projection through the C-arm geometry and the observed angiogram, so a 2D angiogram can train a 3D prediction. The kinematics, loss and projection are verified against known ground truth; the mechanics solver only against its own optimality conditions, and predicted displacement is not yet mesh-converged. Here, no network is trained. Future work will transfer this in silico model to real CT scans and test whether it improves predictive accuracy and reduces the training data required.