Metraipolis › archive › dc_7aa98b9834a3
A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video Segmentation — arXiv:2609.08043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08043
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:59:23.541Z
- SHA-256 of the archived text
11a7752f5dafa563106ad4fc7ebdc3fd21aa1678c29c12141b26a99b6114c021- Stable URL of this page
https://metraipolis.com/documento/dc_7aa98b9834a3
How to cite
A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video Segmentation — arXiv:2609.08043 — arXiv (en), https://arxiv.org/abs/2609.08043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7aa98b9834a3 (Metraipolis archive dc_7aa98b9834a3, sha256 11a7752f5dafa563106ad4fc7ebdc3fd21aa1678c29c12141b26a99b6114c021)
BibTeX
@misc{dc7aa98b9834a3,
title = {A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video Segmentation — arXiv:2609.08043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7aa98b9834a3; sha256 11a7752f5dafa563106ad4fc7ebdc3fd21aa1678c29c12141b26a99b6114c021},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning has achieved state-of-the-art performance in echocardiographic video segmentation, with an increasing number of models incorporating temporal information. However, quantitative evaluation of temporal explainability remains largely unexplored. We propose a quantitative framework for evaluating Grad-CAM explanations using four complementary metrics measuring temporal consistency, saliency motion, anatomical overlap, and temporal overlap. Using EchoNet-Dynamic, we compare a baseline 2D U-Net with ConvLSTM U-Net models trained across multiple temporal strides. While segmentation performance remained comparable across all models, intermediate ConvLSTM explanations exhibited substantially lower saliency consistency and greater centroid motion than final prediction explanations. Temporal Bottleneck explanations were significantly more stable than Encoder Bottleneck explanations across all strides, while final ConvLSTM Decoder3 explanations were broadly comparable to those of the 2D U-Net. Importantly, conventional frame-wise explanation metrics cannot determine whether variation in intermediate explanations reflects meaningful temporal feature evolution or explanation instability. These findings establish a preliminary quantitative framework for temporal explainability and motivate temporal-aware XAI methods that explicitly account for evolving representations in medical video models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.08043 — 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 2026-10-16T13:39:43.247Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).