Saved in:
Bibliographic Details
Main Authors: Zhang, Qikang, Lei, Yingjie, Zheng, Zihao, Chen, Ziyang, Xie, Zhonghao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.02341
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913678005108736
author Zhang, Qikang
Lei, Yingjie
Zheng, Zihao
Chen, Ziyang
Xie, Zhonghao
author_facet Zhang, Qikang
Lei, Yingjie
Zheng, Zihao
Chen, Ziyang
Xie, Zhonghao
contents 4D medical image interpolation is essential for improving temporal resolution and diagnostic precision in clinical applications. Previous works ignore the problem of distribution shifts, resulting in poor generalization under different distribution. A natural solution would be to adapt the model to a new test distribution, but this cannot be done if the test input comes without a ground truth label. In this paper, we propose a novel test time training framework which uses self-supervision to adapt the model to a new distribution without requiring any labels. Indeed, before performing frame interpolation on each test video, the model is trained on the same instance using a self-supervised task, such as rotation prediction or image reconstruction. We conduct experiments on two publicly available 4D medical image interpolation datasets, Cardiac and 4D-Lung. The experimental results show that the proposed method achieves significant performance across various evaluation metrics on both datasets. It achieves higher peak signal-to-noise ratio values, 33.73dB on Cardiac and 34.02dB on 4D-Lung. Our method not only advances 4D medical image interpolation but also provides a template for domain adaptation in other fields such as image segmentation and image registration.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02341
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test Time Training for 4D Medical Image Interpolation
Zhang, Qikang
Lei, Yingjie
Zheng, Zihao
Chen, Ziyang
Xie, Zhonghao
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
4D medical image interpolation is essential for improving temporal resolution and diagnostic precision in clinical applications. Previous works ignore the problem of distribution shifts, resulting in poor generalization under different distribution. A natural solution would be to adapt the model to a new test distribution, but this cannot be done if the test input comes without a ground truth label. In this paper, we propose a novel test time training framework which uses self-supervision to adapt the model to a new distribution without requiring any labels. Indeed, before performing frame interpolation on each test video, the model is trained on the same instance using a self-supervised task, such as rotation prediction or image reconstruction. We conduct experiments on two publicly available 4D medical image interpolation datasets, Cardiac and 4D-Lung. The experimental results show that the proposed method achieves significant performance across various evaluation metrics on both datasets. It achieves higher peak signal-to-noise ratio values, 33.73dB on Cardiac and 34.02dB on 4D-Lung. Our method not only advances 4D medical image interpolation but also provides a template for domain adaptation in other fields such as image segmentation and image registration.
title Test Time Training for 4D Medical Image Interpolation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.02341