{"ID":2859733,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04553","arxiv_id":"2510.04553","title":"Fast Witness Persistence for MRI Volumes via Hybrid Landmarking","abstract":"We introduce a scalable witness-based persistent homology pipeline for full-brain MRI volumes that couples density-aware landmark selection with a GPU-ready witness filtration. Candidates are scored by a hybrid metric that balances geometric coverage against inverse kernel density, yielding landmark sets that shrink mean pairwise distances by 30-60% over random or density-only baselines while preserving topological features. Benchmarks on BrainWeb, IXI, and synthetic manifolds execute in under ten seconds on a single NVIDIA RTX 4090 GPU, avoiding the combinatorial blow-up of Cech, Vietoris-Rips, and alpha filtrations. The package is distributed on PyPI as whale-tda (installable via pip); source and issues are hosted at https://github.com/jorgeLRW/whale. The release also exposes a fast preset (mri_deep_dive_fast) for exploratory sweeps, and ships with reproducibility-focused scripts and artifacts for drop-in use in medical imaging workflows.","short_abstract":"We introduce a scalable witness-based persistent homology pipeline for full-brain MRI volumes that couples density-aware landmark selection with a GPU-ready witness filtration. Candidates are scored by a hybrid metric that balances geometric coverage against inverse kernel density, yielding landmark sets that shrink me...","url_abs":"https://arxiv.org/abs/2510.04553","url_pdf":"https://arxiv.org/pdf/2510.04553v1","authors":"[\"Jorge Leonardo Ruiz Williams\"]","published":"2025-10-06T07:34:21Z","proceeding":"cs.CG","tasks":"[\"cs.CG\",\"cs.CV\",\"cs.LG\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":608661,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2859733,"paper_url":"https://arxiv.org/abs/2510.04553","paper_title":"Fast Witness Persistence for MRI Volumes via Hybrid Landmarking","repo_url":"https://github.com/jorgeLRW/whale","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}