Literature DB >> 36242701

Landmark tracking in 4D ultrasound using generalized representation learning.

Daniel Wulff1, Jannis Hagenah2, Floris Ernst3.   

Abstract

PURPOSE: In this study, we present and validate a novel concept for target tracking in 4D ultrasound. The key idea is to replace image patch similarity metrics by distances in a latent representation. For this, 3D ultrasound patches are mapped into a representation space using sliced-Wasserstein autoencoders.
METHODS: A novel target tracking method for 4D ultrasound is presented that performs tracking in a representation space instead of in images space. Sliced-Wasserstein autoencoders are trained in an unsupervised manner which are used to map 3D ultrasound patches into a representation space. The tracking procedure is based on a greedy algorithm approach and measuring distances between representation vectors to relocate the target . The proposed algorithm is validated on an in vivo data set of liver images. Furthermore, three different concepts for training the autoencoder are presented to provide cross-patient generalizability, aiming at minimal training time on data of the individual patient.
RESULTS: Eight annotated 4D ultrasound sequences are used to test the tracking method. Tracking could be performed in all sequences using all autoencoder training approaches. A mean tracking error of 3.23 mm could be achieved using generalized fine-tuned autoencoders. It is shown that using generalized autoencoders and fine-tuning them achieves better tracking results than training subject individual autoencoders.
CONCLUSION: It could be shown that distances between encoded image patches in a representation space can serve as a meaningful measure of the image patch similarity, even under realistic deformations of the anatomical structure. Based on that, we could validate the proposed tracking algorithm in an in vivo setting. Furthermore, our results indicate that using generalized autoencoders, fine-tuning on only a small number of patches from the individual patient provides promising results.
© 2022. The Author(s).

Entities:  

Keywords:  Greedy search; Radiotherapy; Representation space; Sliced-Wasserstein autoencoder

Year:  2022        PMID: 36242701     DOI: 10.1007/s11548-022-02768-z

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   3.421


  5 in total

Review 1.  Ultrasound guidance in minimally invasive robotic procedures.

Authors:  Maria Antico; Fumio Sasazawa; Liao Wu; Anjali Jaiprakash; Jonathan Roberts; Ross Crawford; Ajay K Pandey; Davide Fontanarosa
Journal:  Med Image Anal       Date:  2019-01-11       Impact factor: 8.545

2.  Tracking 3D ultrasound anatomical landmarks via three orthogonal plane-based scale discriminative correlation filter network.

Authors:  Yibin Huang; Jishuai He; Xu Wu; Xiaozhi Zhao; Jian Wu
Journal:  Med Phys       Date:  2021-04-03       Impact factor: 4.071

3.  Quantification of nonrigid liver deformation in radiofrequency ablation interventions using image registration.

Authors:  Ha Manh Luu; Adriaan Moelker; Stefan Klein; Wiro Niessen; Theo van Walsum
Journal:  Phys Med Biol       Date:  2018-08-29       Impact factor: 3.609

4.  Development of a robot-assisted ultrasound-guided radiation therapy (USgRT).

Authors:  Peter Karl Seitz; Beatrice Baumann; Wibke Johnen; Cord Lissek; Johanna Seidel; Rolf Bendl
Journal:  Int J Comput Assist Radiol Surg       Date:  2019-12-12       Impact factor: 2.924

5.  The 2014 liver ultrasound tracking benchmark.

Authors:  V De Luca; T Benz; S Kondo; L König; D Lübke; S Rothlübbers; O Somphone; S Allaire; M A Lediju Bell; D Y F Chung; A Cifor; C Grozea; M Günther; J Jenne; T Kipshagen; M Kowarschik; N Navab; J Rühaak; J Schwaab; C Tanner
Journal:  Phys Med Biol       Date:  2015-07-02       Impact factor: 3.609

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.