{"paper":{"title":"CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CineMesh4D reconstructs personalized 4D whole-heart meshes directly from sparse multi-view 2D cine MRI.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ching-Hui Sia, Lei Li, Mark Y Chan, Xiaohan Yuan, Xiaoyue Liu","submitted_at":"2026-05-13T18:05:08Z","abstract_excerpt":"Accurate 3D+t whole-heart mesh reconstruction from cine MRI is a clinically crucial yet technically challenging task. The difficulty of this task arises from two coupled factors: inherently sparse sampling of 3D cardiac anatomy by 2D image slices and the tight coupling between cardiac shape and motion. Current cardiac image-to-mesh approaches typically reconstruct only a subset of cardiac chambers or a single phase of the cardiac cycle. In this work, we propose CineMesh4D, a novel end-to-end 4D (3D+t) pipeline that directly reconstructs patient-specific whole-heart mesh from multi-view 2D cine"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In quantitative and qualitative evaluations, CineMesh4D outperforms existing approaches in terms of reconstruction quality and motion consistency, providing a practical pathway for personalized real-time cardiac assessment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The differentiable rendering loss can reliably supervise accurate 3D+t whole-heart meshes from sparse multi-view 2D contours, and the dual-context temporal block sufficiently captures high-dimensional sequential cardiac patterns without additional constraints or data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CineMesh4D reconstructs personalized 4D whole-heart meshes directly from multi-view 2D cine MRI via cross-domain mapping with differentiable rendering and dual-context temporal blocks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CineMesh4D reconstructs personalized 4D whole-heart meshes directly from sparse multi-view 2D cine MRI.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1b4f88213d1ada93ce9a9ac9944744dd6180b168e59a0d69849b97b19eccf6b0"},"source":{"id":"2605.13994","kind":"arxiv","version":1},"verdict":{"id":"7cf010c4-dd0a-4a08-89fa-51731df3ee4c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:50:19.596786Z","strongest_claim":"In quantitative and qualitative evaluations, CineMesh4D outperforms existing approaches in terms of reconstruction quality and motion consistency, providing a practical pathway for personalized real-time cardiac assessment.","one_line_summary":"CineMesh4D reconstructs personalized 4D whole-heart meshes directly from multi-view 2D cine MRI via cross-domain mapping with differentiable rendering and dual-context temporal blocks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The differentiable rendering loss can reliably supervise accurate 3D+t whole-heart meshes from sparse multi-view 2D contours, and the dual-context temporal block sufficiently captures high-dimensional sequential cardiac patterns without additional constraints or data.","pith_extraction_headline":"CineMesh4D reconstructs personalized 4D whole-heart meshes directly from sparse multi-view 2D cine MRI."},"references":{"count":27,"sample":[{"doi":"","year":2021,"title":"Medical image analysis74, 102228 (2021)","work_id":"6f053aae-4d93-484d-acdc-2ba94bdb774e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","work_id":"e41754ed-2b84-4cd3-9f06-da2b7fa811fb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"In: Interna- tional Conference on Functional Imaging and Modeling of the Heart","work_id":"8cae79c9-152e-497e-a858-77c53adfcdea","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Medical Image Analysis104, 103630 (2025)","work_id":"092a4cfb-ea75-4850-aa65-6de23bad8bf6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1912,"title":"arXiv preprint arXiv:1912.00367 (2019)","work_id":"fa7cfd7b-4d17-451d-b0ee-99aa55df9798","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":27,"snapshot_sha256":"271eebd83a003ae43fd782b2051e24d8641627fe32e072142c9b0e72949707f0","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5e8f615df47e0034c370c410b57c9176ab4a723bac4f564255ee5f7e80773c5f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}