Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction
Objective. The image reconstruction of ultrasound computed tomography is computationally expensive with conventional iterative methods. The fully learned direct deep learning reconstruction is promising to speed up image reconstruction significantly. However, for direct reconstruction from measureme...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
27 January 2023
|
| In: |
Physics in medicine and biology
Year: 2023, Jahrgang: 68, Heft: 3, Pages: 1-16 |
| ISSN: | 1361-6560 |
| DOI: | 10.1088/1361-6560/acaeed |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1088/1361-6560/acaeed Verlag, lizenzpflichtig, Volltext: https://dx.doi.org/10.1088/1361-6560/acaeed 
|
| Verfasserangaben: | Wenzhao Zhao, Yuling Fan, Hongjian Wang, Hartmut Gemmeke, Koen W.A. van Dongen, Torsten Hopp and Jürgen Hesser |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1887974482 | ||
| 003 | DE-627 | ||
| 005 | 20240703173637.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240507s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6560/acaeed |2 doi | |
| 035 | |a (DE-627)1887974482 | ||
| 035 | |a (DE-599)KXP1887974482 | ||
| 035 | |a (OCoLC)1443675564 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Zhao, Wenzhao |d 1990- |e VerfasserIn |0 (DE-588)1304109860 |0 (DE-627)186034769X |4 aut | |
| 245 | 1 | 0 | |a Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction |c Wenzhao Zhao, Yuling Fan, Hongjian Wang, Hartmut Gemmeke, Koen W.A. van Dongen, Torsten Hopp and Jürgen Hesser |
| 264 | 1 | |c 27 January 2023 | |
| 300 | |b Illustrationen | ||
| 300 | |a 16 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 07.05.2024 | ||
| 520 | |a Objective. The image reconstruction of ultrasound computed tomography is computationally expensive with conventional iterative methods. The fully learned direct deep learning reconstruction is promising to speed up image reconstruction significantly. However, for direct reconstruction from measurement data, due to the lack of real labeled data, the neural network is usually trained on a simulation dataset and shows poor performance on real data because of the simulation-to-real gap. Approach. To improve the simulation-to-real generalization of neural networks, a series of strategies are developed including a Fourier-transform-integrated neural network, measurement-domain data augmentation methods, and a self-supervised-learning-based patch-wise preprocessing neural network. Our strategies are evaluated on both the simulation dataset and real measurement datasets from two different prototype machines. Main results. The experimental results show that our deep learning methods help to improve the neural networks’ robustness against noise and the generalizability to real measurement data. Significance. Our methods prove that it is possible for neural networks to achieve superior performance to traditional iterative reconstruction algorithms in imaging quality and allow for real-time 2D-image reconstruction. This study helps pave the path for the application of deep learning methods to practical ultrasound tomography image reconstruction based on simulation datasets. | ||
| 700 | 1 | |a Fan, Yuling |d 1993- |e VerfasserIn |0 (DE-588)132853720X |0 (DE-627)1887975748 |4 aut | |
| 700 | 1 | |a Wang, Hongjian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Gemmeke, Hartmut |e VerfasserIn |4 aut | |
| 700 | 1 | |a Dongen, Koen W. A. van |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hopp, Torsten |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hesser, Jürgen |d 1964- |e VerfasserIn |0 (DE-588)1020647353 |0 (DE-627)691291071 |0 (DE-576)361513739 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Physics in medicine and biology |d Bristol : IOP Publ., 1956 |g 68(2023), 3, Seite 1-16 |h Online-Ressource |w (DE-627)269016163 |w (DE-600)1473501-5 |w (DE-576)088704130 |x 1361-6560 |7 nnas |a Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction |
| 773 | 1 | 8 | |g volume:68 |g year:2023 |g number:3 |g pages:1-16 |g extent:16 |a Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction |
| 856 | 4 | 0 | |u https://doi.org/10.1088/1361-6560/acaeed |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1088/1361-6560/acaeed |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20240507 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 1020647353 |a Hesser, Jürgen |m 1020647353:Hesser, Jürgen |d 60000 |d 65200 |e 60000PH1020647353 |e 65200PH1020647353 |k 0/60000/ |k 1/60000/65200/ |p 7 |y j | ||
| 998 | |g 132853720X |a Fan, Yuling |m 132853720X:Fan, Yuling |d 60000 |d 63000 |e 60000PF132853720X |e 63000PF132853720X |k 0/60000/ |k 1/60000/63000/ |p 2 | ||
| 998 | |g 1304109860 |a Zhao, Wenzhao |m 1304109860:Zhao, Wenzhao |d 60000 |d 63000 |e 60000PZ1304109860 |e 63000PZ1304109860 |k 0/60000/ |k 1/60000/63000/ |p 1 |x j | ||
| 999 | |a KXP-PPN1887974482 |e 4521118828 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"title":[{"title_sort":"Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction","title":"Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction"}],"note":["Gesehen am 07.05.2024"],"origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"27 January 2023"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"person":[{"role":"aut","given":"Wenzhao","display":"Zhao, Wenzhao","family":"Zhao"},{"given":"Yuling","role":"aut","display":"Fan, Yuling","family":"Fan"},{"family":"Wang","display":"Wang, Hongjian","given":"Hongjian","role":"aut"},{"given":"Hartmut","role":"aut","display":"Gemmeke, Hartmut","family":"Gemmeke"},{"family":"Dongen","display":"Dongen, Koen W. A. van","given":"Koen W. A. van","role":"aut"},{"role":"aut","given":"Torsten","display":"Hopp, Torsten","family":"Hopp"},{"family":"Hesser","display":"Hesser, Jürgen","role":"aut","given":"Jürgen"}],"relHost":[{"part":{"issue":"3","year":"2023","text":"68(2023), 3, Seite 1-16","pages":"1-16","extent":"16","volume":"68"},"note":["Gesehen am 28.01.2019","Fortsetzung der Druck-Ausgabe"],"origin":[{"dateIssuedDisp":"1956-","publisherPlace":"Bristol","publisher":"IOP Publ.","dateIssuedKey":"1956"}],"title":[{"title_sort":"Physics in medicine and biology","subtitle":"an official journal of the Institute of Physics and Engineering in Medicine","title":"Physics in medicine and biology"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"disp":"Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstructionPhysics in medicine and biology","id":{"issn":["1361-6560"],"eki":["269016163"],"zdb":["1473501-5"]},"physDesc":[{"extent":"Online-Ressource"}],"recId":"269016163","pubHistory":["1.1956 -"]}],"id":{"eki":["1887974482"],"doi":["10.1088/1361-6560/acaeed"]},"name":{"displayForm":["Wenzhao Zhao, Yuling Fan, Hongjian Wang, Hartmut Gemmeke, Koen W.A. van Dongen, Torsten Hopp and Jürgen Hesser"]},"physDesc":[{"noteIll":"Illustrationen","extent":"16 S."}],"recId":"1887974482"} | ||
| SRT | |a ZHAOWENZHASIMULATION2720 | ||