Michiel Schaap

We introduce a novel framework for learning vector representations of tree-structured geometric data focusing on 3D vascular networks. Our approach employs two sequentially trained Transformer-based autoencoders. In the first stage, the Vessel Autoencoder captures continuous geometric details of individual vessel segments by learning embeddings from sampled points along each curve. In the second stage, the Vessel Tree Autoencoder encodes the topology of the vascular network as a single vector representation, leveraging the segment-level embeddings from the first model. A recursive decoding process ensures that the reconstructed topology is a valid tree structure. Compared to 3D convolutional models, this proposed approach substantially lowers GPU memory requirements, facilitating large-scale training. Experimental results on a 2D synthetic tree dataset and a 3D coronary artery dataset demonstrate superior reconstruction fidelity, accurate topology preservation, and realistic interpolations in latent space. Our scalable framework, named VeTTA, offers precise, flexible, and topologically consistent modeling of anatomical tree structures in medical imaging.

Virtual interventions enable the physics-based simulation of device deployment within coronary arteries. This framework allows for counterfactual reasoning by deploying the same device in different arterial anatomies. However, current methods to create such counterfactual arteries face a trade-off between controllability and realism. In this study, we investigate how Latent Diffusion Models (LDMs) can custom synthesize coronary anatomy for virtual intervention studies based on mid-level anatomic constraints such as topological validity, local morphological shape, and global skeletal structure. We also extend diffusion model guidance strategies to the context of morpho-skeletal conditioning and propose a novel guidance method for continuous attributes that adaptively updates the negative guiding condition throughout sampling. Our framework enables the generation and editing of coronary anatomy in a controllable manner, allowing device designers to derive mechanistic insights regarding anatomic variation and simulated device deployment.

Coronary computed tomography angiography provides non-invasive assessment of coronary stenosis severity and flow impairment. Automated artificial intelligence (AI) analysis may assist in precise quantification and characterization of coronary atherosclerosis, enabling patient-specific risk determination and management strategies. This multicentre international study compared an automated deep learning-based method for segmenting coronary atherosclerosis in coronary computed tomography angiography (CCTA) against the reference standard of intravascular ultrasound (IVUS). The study included clinically stable patients with known coronary artery disease from 15 centres in the USA and Japan. An AI-enabled plaque analysis was utilized to quantify and characterize total plaque (TPV), vessel, lumen, calcified plaque (CP), non-calcified plaque (NCP), and low-attenuation plaque (LAP) volumes derived from CCTA and compared with IVUS measurements in a blinded, core laboratory-adjudicated fashion. In 237 patients, 432 lesions were assessed; mean lesion length was 24.5 mm, and mean IVUS-TPV was 186.0 mm³. AI-enabled plaque analysis on CCTA showed strong correlation and high accuracy when compared with IVUS; correlation coefficient, slope, and Y intercept for TPV were 0.91, 0.99, and 1.87, respectively; for CP volume 0.91, 1.05, and 5.32, respectively; and for NCP volume 0.87, 0.98, and 15.24, respectively. Bland–Altman analysis demonstrated strong agreement with little bias for these measurements. AI-enabled CCTA quantification and characterization of atherosclerosis demonstrated strong agreement with IVUS reference standard measurements. This tool may prove effective for accurate evaluation of coronary atherosclerotic burden and cardiovascular risk assessment. Matching cross-sectional, longitudinal, and 3D views of IVUS and CCTA show correlating presence of calcified and non-calcified plaque between the two imaging modalities. The table highlights plaque volume correlations for total plaque (TPV), calcified plaque (CP), and non-calcified plaque (NCP) on a per-lesion basis (n = 432). In the cross-sectional and longitudinal view, blue-coloured areas are calcified plaque and yellow-coloured areas are non-calcified plaque. In the 3D view, blue-coloured area is calcified plaque and yellow translucent-coloured area is non-calcified plaque.

Objective: In this paper, we propose an algorithm for the generation of a patient-specific cardiac vascular network starting from segmented epicardial vessels down to the arterioles. Method: We extend a tree generation method based on satisfaction of functional principles, named Constrained Constructive Optimization (CCO), to account for multiple, competing vascular trees. The algorithm simulates angiogenesis under vascular volume minimization with flow-related and geometrical constraints adapting the simultaneous tree growths to patient priors. The generated trees fill the entire left ventricle myocardium up to the arterioles. Results: From actual vascular tree models segmented from CT images, we generated networks with 6000 terminal segments for 6 patients. These networks contain between 33 and 62 synthetic trees. All vascular models match morphometry properties previously described. Conclusion and significance: Image-based models derived from CT angiography are being used clinically to simulate blood flow in the coronary arteries of individual patients to aid in the diagnosis of disease and planning treatments. However, image resolution limits vessel segmentation to larger epicardial arteries. The generated model can be used to simulate blood flow and derived quantities from the aorta into the myocardium. This is an important step for diagnosis an treatment planning of coronary artery disease.

Studying joint kinematics is of interest to improve prosthesis design and to characterize postoperative motion. State of the art techniques register bones segmented from prior computed tomography or magnetic resonance scans with X-ray fluoroscopic sequences. Elimination of the prior 3D acquisition could potentially lower costs and radiation dose. Therefore, we propose to substitute the segmented bone surface with a statistical shape model based estimate. A dedicated dynamic reconstruction and tracking algorithm was developed estimating the shape based on all frames, and pose per frame. The algorithm minimizes the difference between the projected bone contour and image edges. To increase robustness, we employ a dynamic prior, image features, and prior knowledge about bone edge appearances. This enables tracking and reconstruction from a single initial pose per sequence. We evaluated our method on the distal femur using eight biplane fluoroscopic drop-landing sequences. The proposed dynamic prior and features increased the convergence rate of the reconstruction from 71% to 91%, using a convergence limit of 3 mm. The achieved root mean square point-to-surface accuracy at the converged frames was 1.48 ± 0.41 mm.The resulting tracking precision was 1-1.5 mm, with the largest errors occurring in the rotation around the femoral shaft (about 2.5° precision).