Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images.

Autor: Dunnhofer M; Machine Learning and Perception Lab, Department of Mathematics, Computer Science and Physics, University of Udine, via delle Scienze 206, Udine 33100, Italy. Electronic address: dunnhofer.matteo@spes.uniud.it., Antico M; School of Chemistry, Physics and Mechanical Engineering, Queensland University of Technology, Brisbane, Queensland, Australia; Institute of Health Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: maria.antico@hdr.qut.edu.au., Sasazawa F; School of Chemistry, Physics and Mechanical Engineering, Queensland University of Technology, Brisbane, Queensland, Australia; Institute of Health Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia; Department of Orthopaedic Surgery, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan. Electronic address: sasazawa230@gmail.com., Takeda Y; Department of Orthopaedic Surgery, Hyogo College of Medicine, Nishinomiya, Hyogo, Japan. Electronic address: yu.takeda@qut.edu.au., Camps S; Faculty of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands; Oncology Solutions Department, Philips Research, Eindhoven, The Netherlands. Electronic address: saskiacamps@gmail.com., Martinel N; Machine Learning and Perception Lab, Department of Mathematics, Computer Science and Physics, University of Udine, via delle Scienze 206, Udine 33100, Italy. Electronic address: niki.martinel@uniud.it., Micheloni C; Machine Learning and Perception Lab, Department of Mathematics, Computer Science and Physics, University of Udine, via delle Scienze 206, Udine 33100, Italy. Electronic address: christian.micheloni@uniud.it., Carneiro G; Australian Institute for Machine Learning, School of Computer Science, The University of Adelaide, Adelaide, Australia. Electronic address: gustavo.carneiro@adelaide.edu.au., Fontanarosa D; Institute of Health Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia; School of Clinical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: d3.fontanarosa@qut.edu.au.
Jazyk: angličtina
Zdroj: Medical image analysis [Med Image Anal] 2020 Feb; Vol. 60, pp. 101631. Date of Electronic Publication: 2019 Dec 23.
DOI: 10.1016/j.media.2019.101631
Abstrakt: The tracking of the knee femoral condyle cartilage during ultrasound-guided minimally invasive procedures is important to avoid damaging this structure during such interventions. In this study, we propose a new deep learning method to track, accurately and efficiently, the femoral condyle cartilage in ultrasound sequences, which were acquired under several clinical conditions, mimicking realistic surgical setups. Our solution, that we name Siam-U-Net, requires minimal user initialization and combines a deep learning segmentation method with a siamese framework for tracking the cartilage in temporal and spatio-temporal sequences of 2D ultrasound images. Through extensive performance validation given by the Dice Similarity Coefficient, we demonstrate that our algorithm is able to track the femoral condyle cartilage with an accuracy which is comparable to experienced surgeons. It is additionally shown that the proposed method outperforms state-of-the-art segmentation models and trackers in the localization of the cartilage. We claim that the proposed solution has the potential for ultrasound guidance in minimally invasive knee procedures.
(Crown Copyright © 2019. Published by Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: