arXiv subjects

Ajay Manicka

Publications and source records attributed to Ajay Manicka.

3 recordsLinked to original sources

arXiv2025

Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models

We present Anatomica: an inference-time framework for generating multi-class anatomical voxel maps with localized geo-topological control. During generation, we use cuboidal control domains of varying dimensionality, location, and shape to slice out relevant substructures. These local substructures are used to compute differentiable penalty functions that steer the sample towards target constraints. We control geometric features such as size, shape, and position through voxel-wise moments, while topological features such as connected components, loops, and voids are enforced through persistent homology. Lastly, we implement Anatomica for latent diffusion models, where neural field decoders partially extract substructures, enabling the efficient control of anatomical properties. Anatomica applies flexibly across diverse anatomical systems, composing constraints to control complex structures over arbitrary dimensions and coordinate systems, thereby enabling the rational design of synthetic datasets for virtual trials or machine learning workflows.

cs.LG↗

arXiv2025

CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models

Generative models of 3D cardiovascular anatomy can synthesize informative structures for clinical research and medical device evaluation, but face a trade-off between geometric controllability and realism. We propose CardioComposer: a programmable, inference-time framework for generating multi-class anatomical label maps from interpretable ellipsoidal primitives. These primitives represent geometric attributes such as the size, shape, and position of discrete substructures. We specifically develop differentiable measurement functions based on voxel-wise geometric moments, enabling loss-based gradient guidance during diffusion model sampling. We demonstrate that these losses can constrain individual geometric attributes in a disentangled manner and provide compositional control over multiple substructures. Finally, we show that our method is compatible with a broad range of anatomical systems containing non-convex substructures, spanning cardiac, vascular, and skeletal organs. We release our code at https://github.com/kkadry/CardioComposer.

eess.IV↗

arXiv2022

Automated Routing of Droplets for DNA Storage on a Digital Microfluidics Platform

Technologies for sequencing (reading) and synthesizing (writing) DNA have progressed on a Moore's law-like trajectory over the last three decades. This has motivated the idea of using DNA for data storage. Theoretically, DNA-based storage systems could out-compete all existing forms of archival storage. However, a large gap exists between what is theoretically possible in terms of read and write speeds and what has been practically demonstrated with DNA. This paper introduces a novel approach to DNA storage, with automated assembly on a digital microfluidic biochip. This technology offers unprecedented parallelism in DNA assembly using a dual library of "symbols" and "linkers". An algorithmic solution is discussed for the problem of managing droplet traffic on the device, with prioritized three-dimensional "A*" routing. An overview is given of the software that was developed for routing a large number of droplets in parallel on the device, minimizing congestion and maximizing throughput.

cs.ET↗