Skip to main content
Erschienen in:

27.11.2021 | Original Article—Physics & Engineering

Displacement detection with sub-pixel accuracy and high spatial resolution using deep learning

verfasst von: Mariko Yamamoto, Shin Yoshizawa

Erschienen in: Journal of Medical Ultrasonics | Ausgabe 1/2022

Einloggen, um Zugang zu erhalten

Abstract

Purpose

The purpose of this study was to detect two dimensional and sub-pixel displacement with high spatial resolution using an ultrasonic diagnostic apparatus. Conventional displacement detection methods assume neighborhood uniformity and cannot achieve both high spatial resolution and sub-pixel displacement detection.

Methods

A deep-learning network that utilizes ultrasound images and output displacement distribution was developed. The network structure was constructed by modifying FlowNet2, a widely used network for optical flow estimation, and a training dataset was developed using ultrasound image simulation. Detection accuracy and spatial resolution were evaluated via simulated ultrasound images, and the clinical usefulness was evaluated with ultrasound images of the liver exposed to high-intensity-focused ultrasound (HIFU). These results were compared to the Lucas–Kanade method, a conventional sub-pixel displacement detection method.

Results

For a displacement within ± 40 µm (± 0.6 pixels), a pixel size of 67 µm, and signal noise of 1%, the accuracy was above 0.5 µm and 0.2 µm, the precision was above 0.4 µm and 0.3 µm, and the spatial resolution was 1.1 mm and 0.8 mm for the lateral and axial displacements, respectively. These improvements were also observed in the experimental data. Visualization of the lateral displacement distribution, which determines the edge of the treated lesion using HIFU, was also realized.

Conclusion

Two-dimensional and sub-pixel displacement detection with high spatial resolution was realized using a deep-learning methodology. The proposed method enabled the monitoring of small and local tissue deformations induced by HIFU exposure.
Literatur
1.
Zurück zum Zitat Szabo T. Diagnostic ultrasound imaging: inside out. Cambridge: Academic Press; 2013. Szabo T. Diagnostic ultrasound imaging: inside out. Cambridge: Academic Press; 2013.
2.
Zurück zum Zitat Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. Proceedings of imaging understanding workshop. 1981;121–30 Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. Proceedings of imaging understanding workshop. 1981;121–30
5.
Zurück zum Zitat Kanai H, Sato M, Chubachi N, et al. Transcutaneous measurement and spectrum analysis of heart wall vibrations. IEEE Trans Ultrason Ferroelectr Freq Control. 1996;43:791–810.CrossRef Kanai H, Sato M, Chubachi N, et al. Transcutaneous measurement and spectrum analysis of heart wall vibrations. IEEE Trans Ultrason Ferroelectr Freq Control. 1996;43:791–810.CrossRef
6.
Zurück zum Zitat Shiina T, Nitta N, Bamber JC, et al. Real time tissue elasticity imaging using the combined autocorrelation method. J Med Ultrason. 2002;29:119–28.CrossRef Shiina T, Nitta N, Bamber JC, et al. Real time tissue elasticity imaging using the combined autocorrelation method. J Med Ultrason. 2002;29:119–28.CrossRef
7.
Zurück zum Zitat Goodfellow I, Gengio Y, Courville A. Deep learning. Cambridge: The MIT Press; 2016. Goodfellow I, Gengio Y, Courville A. Deep learning. Cambridge: The MIT Press; 2016.
8.
Zurück zum Zitat Evan E, Faraz K, Grenier T, Garcia D, et al. A pilot study on convolutional neural networks for motion estimation from ultrasound images. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67:2565–73.CrossRef Evan E, Faraz K, Grenier T, Garcia D, et al. A pilot study on convolutional neural networks for motion estimation from ultrasound images. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67:2565–73.CrossRef
10.
Zurück zum Zitat Tehrani AKZ, Rivaz H. Displacement estimation in ultrasound elastography using pyramidal convolutional neural network. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67:2629–39.CrossRefPubMed Tehrani AKZ, Rivaz H. Displacement estimation in ultrasound elastography using pyramidal convolutional neural network. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67:2629–39.CrossRefPubMed
14.
Zurück zum Zitat Wu S, Gao Z, Lui J et al. Direct reconstruction of ultrasound elastography using an end-to-end deep neural network. International conference on medical image computing and computer assisted intervention (MICCAI). 2018;374–82 Wu S, Gao Z, Lui J et al. Direct reconstruction of ultrasound elastography using an end-to-end deep neural network. International conference on medical image computing and computer assisted intervention (MICCAI). 2018;374–82
17.
Zurück zum Zitat Jensen JA. Field: a program for simulating ultrasound systems. The 10th Nordic-Baltic conference on biomedical imaging published in medical and biological engineering and computing. 1996;34:351–3 Jensen JA. Field: a program for simulating ultrasound systems. The 10th Nordic-Baltic conference on biomedical imaging published in medical and biological engineering and computing. 1996;34:351–3
18.
19.
Zurück zum Zitat Yamamoto M, Yoshizawa S. Analysis of tissue displacement induced by high-intensity focused ultrasound exposure for coagulation monitoring. Jpn J Appl Phys. 2021;60:040903.CrossRef Yamamoto M, Yoshizawa S. Analysis of tissue displacement induced by high-intensity focused ultrasound exposure for coagulation monitoring. Jpn J Appl Phys. 2021;60:040903.CrossRef
20.
Zurück zum Zitat Montaldo G, Tanter M, Bercoff J, et al. Coherent plane-wave compounding for very high frame rate ultrasonography and transient elastography. IEEE Trans Ultrason Ferroelectr Freq Control. 2009;56:489–506.CrossRefPubMed Montaldo G, Tanter M, Bercoff J, et al. Coherent plane-wave compounding for very high frame rate ultrasonography and transient elastography. IEEE Trans Ultrason Ferroelectr Freq Control. 2009;56:489–506.CrossRefPubMed
21.
Zurück zum Zitat Sasaki S, Takagi R, Matsuura K, et al. Feasibility of real-time treatment feedback using novel filter for eliminating therapeutic ultrasound noise with high-speed ultrasonic imaging in ultrasound-guided high-intensity focused ultrasound treatment. Jpn J Appl Phys. 2014;53:07KF10.CrossRef Sasaki S, Takagi R, Matsuura K, et al. Feasibility of real-time treatment feedback using novel filter for eliminating therapeutic ultrasound noise with high-speed ultrasonic imaging in ultrasound-guided high-intensity focused ultrasound treatment. Jpn J Appl Phys. 2014;53:07KF10.CrossRef
23.
Zurück zum Zitat Luo J, Chen CW, et al. Artifact reduction in low bit rate DCT-based image compression. IEEE Trans Image Proc. 1996;9:1363–8. Luo J, Chen CW, et al. Artifact reduction in low bit rate DCT-based image compression. IEEE Trans Image Proc. 1996;9:1363–8.
Metadaten
Titel
Displacement detection with sub-pixel accuracy and high spatial resolution using deep learning
verfasst von
Mariko Yamamoto
Shin Yoshizawa
Publikationsdatum
27.11.2021
Verlag
Springer Nature Singapore
Erschienen in
Journal of Medical Ultrasonics / Ausgabe 1/2022
Print ISSN: 1346-4523
Elektronische ISSN: 1613-2254
DOI
https://doi.org/10.1007/s10396-021-01162-7

Neu im Fachgebiet Radiologie

Ab sofort gelten die neuen Verordnungsausnahmen für Lipidsenker

Freie Fahrt für Lipidsenker? Das nicht, doch mit niedrigerem Schwellenwert fürs Infarktrisiko und neuen Indikationen hat der G-BA die Verordnungs-Handbremse ein gutes Stück weit gelockert.

Abdominale CT bei Kindern: 40% mit Zufallsbefunden

Wird bei Kindern mit stumpfem Trauma eine CT des Bauchraums veranlasst, sind in rund 40% der Fälle Auffälligkeiten zu sehen, die nichts mit dem Trauma zu tun haben. Die allerwenigsten davon sind klinisch relevant.

Genügt die biparametrische MRT für die Prostatadiagnostik?

Die multiparametrische Magnetresonanztomografie hat einen festen Platz im Screening auf klinisch signifikante Prostatakarzinome. Ob auch ein biparametrisches Vorgehen ausreicht, ist in einer Metaanalyse untersucht worden.

Höhere Trefferquoten bei Brustkrebsscreening dank KI?

Künstliche Intelligenz unterstützt bei der Auswertung von Mammografie-Screenings und senkt somit den Arbeitsaufwand für Radiologen. Wie wirken sich diese Technologien auf die Trefferquote und die Falsch-positiv-Rate aus? Das hat jetzt eine Studie aus Schweden untersucht.

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.