Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Haojun, Li, Meng, Sun, Zhenguo, Jia, Ning, Sun, Yu, Luo, Shaqi, Song, Shiji, Huang, Gao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913436388032512
author Jiang, Haojun
Li, Meng
Sun, Zhenguo
Jia, Ning
Sun, Yu
Luo, Shaqi
Song, Shiji
Huang, Gao
author_facet Jiang, Haojun
Li, Meng
Sun, Zhenguo
Jia, Ning
Sun, Yu
Luo, Shaqi
Song, Shiji
Huang, Gao
contents The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images. Successful echocardiography requires a thorough understanding of the structures on the two-dimensional plane and the spatial relationships between planes in three-dimensional space. In this paper, we innovatively propose a large-scale self-supervised pre-training method to acquire a cardiac structure-aware world model. The core innovation lies in constructing a self-supervised task that requires structural inference by predicting masked structures on a 2D plane and imagining another plane based on pose transformation in 3D space. To support large-scale pre-training, we collected over 1.36 million echocardiograms from ten standard views, along with their 3D spatial poses. In the downstream probe guidance task, we demonstrate that our pre-trained model consistently reduces guidance errors across the ten most common standard views on the test set with 0.29 million samples from 74 routine clinical scans, indicating that structure-aware pre-training benefits the scanning.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19756
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train
Jiang, Haojun
Li, Meng
Sun, Zhenguo
Jia, Ning
Sun, Yu
Luo, Shaqi
Song, Shiji
Huang, Gao
Computer Vision and Pattern Recognition
Artificial Intelligence
The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images. Successful echocardiography requires a thorough understanding of the structures on the two-dimensional plane and the spatial relationships between planes in three-dimensional space. In this paper, we innovatively propose a large-scale self-supervised pre-training method to acquire a cardiac structure-aware world model. The core innovation lies in constructing a self-supervised task that requires structural inference by predicting masked structures on a 2D plane and imagining another plane based on pose transformation in 3D space. To support large-scale pre-training, we collected over 1.36 million echocardiograms from ten standard views, along with their 3D spatial poses. In the downstream probe guidance task, we demonstrate that our pre-trained model consistently reduces guidance errors across the ten most common standard views on the test set with 0.29 million samples from 74 routine clinical scans, indicating that structure-aware pre-training benefits the scanning.
title Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.19756