InfoMotion: A Graph-Based Approach to Video Dataset Distillation for Echocardiography

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhe, Reynaud, Hadrien, Gomez, Alberto, Kainz, Bernhard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917143835049984
author Li, Zhe
Reynaud, Hadrien
Gomez, Alberto
Kainz, Bernhard
author_facet Li, Zhe
Reynaud, Hadrien
Gomez, Alberto
Kainz, Bernhard
contents Echocardiography plays a critical role in the diagnosis and monitoring of cardiovascular diseases as a non-invasive real-time assessment of cardiac structure and function. However, the growing scale of echocardiographic video data presents significant challenges in terms of storage, computation, and model training efficiency. Dataset distillation offers a promising solution by synthesizing a compact, informative subset of data that retains the key clinical features of the original dataset. In this work, we propose a novel approach for distilling a compact synthetic echocardiographic video dataset. Our method leverages motion feature extraction to capture temporal dynamics, followed by class-wise graph construction and representative sample selection using the Infomap algorithm. This enables us to select a diverse and informative subset of synthetic videos that preserves the essential characteristics of the original dataset. We evaluate our approach on the EchoNet-Dynamic datasets and achieve a test accuracy of \(69.38\%\) using only \(25\) synthetic videos. These results demonstrate the effectiveness and scalability of our method for medical video dataset distillation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09422
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InfoMotion: A Graph-Based Approach to Video Dataset Distillation for Echocardiography
Li, Zhe
Reynaud, Hadrien
Gomez, Alberto
Kainz, Bernhard
Computer Vision and Pattern Recognition
Echocardiography plays a critical role in the diagnosis and monitoring of cardiovascular diseases as a non-invasive real-time assessment of cardiac structure and function. However, the growing scale of echocardiographic video data presents significant challenges in terms of storage, computation, and model training efficiency. Dataset distillation offers a promising solution by synthesizing a compact, informative subset of data that retains the key clinical features of the original dataset. In this work, we propose a novel approach for distilling a compact synthetic echocardiographic video dataset. Our method leverages motion feature extraction to capture temporal dynamics, followed by class-wise graph construction and representative sample selection using the Infomap algorithm. This enables us to select a diverse and informative subset of synthetic videos that preserves the essential characteristics of the original dataset. We evaluate our approach on the EchoNet-Dynamic datasets and achieve a test accuracy of \(69.38\%\) using only \(25\) synthetic videos. These results demonstrate the effectiveness and scalability of our method for medical video dataset distillation.
title InfoMotion: A Graph-Based Approach to Video Dataset Distillation for Echocardiography
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.09422