Metraipolis › archive › dc_94f48e577dfc

Spatiotemporal Distillation via Recurrent Bottlenecks for Aortic Tracking — arXiv:2608.23879

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.23879
License (as archived): CC0-1.0
Archived: 2026-10-18T06:36:38.417Z
SHA-256 of the archived text: 721d277f514526f060a1797d5707b68d29e20a1acd9a472e6af931581f0b4c51
Stable URL of this page: https://metraipolis.com/documento/dc_94f48e577dfc

How to cite

Spatiotemporal Distillation via Recurrent Bottlenecks for Aortic Tracking — arXiv:2608.23879 — arXiv (en), https://arxiv.org/abs/2608.23879 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_94f48e577dfc (Metraipolis archive dc_94f48e577dfc, sha256 721d277f514526f060a1797d5707b68d29e20a1acd9a472e6af931581f0b4c51)

BibTeX

@misc{dc94f48e577dfc,
  title = {Spatiotemporal Distillation via Recurrent Bottlenecks for Aortic Tracking — arXiv:2608.23879},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23879},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_94f48e577dfc; sha256 721d277f514526f060a1797d5707b68d29e20a1acd9a472e6af931581f0b4c51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23879. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cardiac cine-MRI serves as a direct visual indicator of cardiovascular hemodynamics by capturing the continuous wall motion of the aorta. Quantifying these dynamic structural changes across the cardiac cycle is essential for measuring aortic distensibility, a primary marker of arterial stiffness. However, standard 2D segmentation networks focus on each frame independently. Consequently, when rapid systolic flow temporarily obscures the aorta's boundaries, this lack of continuous context results in frame-to-frame tracking dropouts and boundary inconsistencies. Spatiotemporal ($2\text{D}+t$) networks can enforce temporal consistency across the sequence but suffer from a scarcity of expert annotations. To address this, we present a semi-supervised spatiotemporal ($2\text{D}$ to $2\text{D}+t$) knowledge distillation framework exploiting the cardiac cycle. The framework distills a spatial teacher's expertise into a spatiotemporal student network by executing a dynamic latent interception, pairing a recurrent spatiotemporal bottleneck with a residual spatial bypass. Our model selection strategy applies a baseline validation threshold ($\text{DSC} \ge 0.50$) prior to selecting the epoch that maximizes anatomical consistency. This strategy enables the spatiotemporal student model to achieve superior surface tracking accuracy ($\text{NSD@1mm} = 92.3\% \pm 0.2\%$) and high structural reliability ($\text{Frac}_{2\text{CC}} = 99.2\% \pm 0.6\%$), reducing population-wide structural anomalies by over 56\% compared to a 2D nnU-Net baseline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.23879 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:28:52.325Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).