Photoacoustic image synthesis with generative adversarial networks

Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties with high spatial resolution. However, previous attempts to solve the optical inverse problem with supervised machine learning were hampered by the absence of labeled reference data. While this...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Schellenberg, Melanie (VerfasserIn) , Gröhl, Janek (VerfasserIn) , Dreher, Kris (VerfasserIn) , Nölke, Jan-Hinrich (VerfasserIn) , Holzwarth, Niklas (VerfasserIn) , Tizabi, Minu (VerfasserIn) , Seitel, Alexander (VerfasserIn) , Maier-Hein, Lena (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 13 September 2022
In: Photoacoustics
Year: 2022, Jahrgang: 28, Pages: 1-10
ISSN:2213-5979
DOI:10.1016/j.pacs.2022.100402
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.pacs.2022.100402
Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S2213597922000672
Volltext
Verfasserangaben:Melanie Schellenberg, Janek Gröhl, Kris K. Dreher, Jan-Hinrich Nölke, Niklas Holzwarth, Minu D. Tizabi, Alexander Seitel, Lena Maier-Hein

MARC

LEADER 00000caa a2200000 c 4500
001 1832518582
003 DE-627
005 20251202095016.0
007 cr uuu---uuuuu
008 230126s2022 xx |||||o 00| ||eng c
024 7 |a 10.1016/j.pacs.2022.100402  |2 doi 
035 |a (DE-627)1832518582 
035 |a (DE-599)KXP1832518582 
035 |a (OCoLC)1389535991 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Schellenberg, Melanie  |d 1994-  |e VerfasserIn  |0 (DE-588)1237779464  |0 (DE-627)176477745X  |4 aut 
245 1 0 |a Photoacoustic image synthesis with generative adversarial networks  |c Melanie Schellenberg, Janek Gröhl, Kris K. Dreher, Jan-Hinrich Nölke, Niklas Holzwarth, Minu D. Tizabi, Alexander Seitel, Lena Maier-Hein 
264 1 |c 13 September 2022 
300 |a 10 
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 26.01.2023 
520 |a Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties with high spatial resolution. However, previous attempts to solve the optical inverse problem with supervised machine learning were hampered by the absence of labeled reference data. While this bottleneck has been tackled by simulating training data, the domain gap between real and simulated images remains an unsolved challenge. We propose a novel approach to PAT image synthesis that involves subdividing the challenge of generating plausible simulations into two disjoint problems: (1) Probabilistic generation of realistic tissue morphology, and (2) pixel-wise assignment of corresponding optical and acoustic properties. The former is achieved with Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data. According to a validation study on a downstream task our approach yields more realistic synthetic images than the traditional model-based approach and could therefore become a fundamental step for deep learning-based quantitative PAT (qPAT). 
650 4 |a Deep learning 
650 4 |a Generative adversarial networks 
650 4 |a Optoacoustic imaging 
650 4 |a Optoacoustic tomography 
650 4 |a Photoacoustic imaging 
650 4 |a Photoacoustic tomography 
650 4 |a Synthetic data 
700 1 |a Gröhl, Janek  |d 1991-  |e VerfasserIn  |0 (DE-588)1197628673  |0 (DE-627)1679293109  |4 aut 
700 1 |a Dreher, Kris  |e VerfasserIn  |0 (DE-588)1237780837  |0 (DE-627)176477969X  |4 aut 
700 1 |a Nölke, Jan-Hinrich  |e VerfasserIn  |0 (DE-588)1197270973  |0 (DE-627)1679066692  |4 aut 
700 1 |a Holzwarth, Niklas  |e VerfasserIn  |0 (DE-588)1379696747  |0 (DE-627)1939356407  |4 aut 
700 1 |a Tizabi, Minu  |d 1992-  |e VerfasserIn  |0 (DE-588)1140542494  |0 (DE-627)89854632X  |0 (DE-576)493859608  |4 aut 
700 1 |a Seitel, Alexander  |d 1980-  |e VerfasserIn  |0 (DE-588)1025312058  |0 (DE-627)722029861  |0 (DE-576)370197003  |4 aut 
700 1 |a Maier-Hein, Lena  |d 1980-  |e VerfasserIn  |0 (DE-588)1075029252  |0 (DE-627)832869899  |0 (DE-576)190090804  |4 aut 
773 0 8 |i Enthalten in  |t Photoacoustics  |d Amsterdam [u.a.] : Elsevier, 2013  |g 28(2022), Artikel-ID 100402, Seite 1-10  |h Online-Ressource  |w (DE-627)746705697  |w (DE-600)2716706-9  |w (DE-576)382628608  |x 2213-5979  |7 nnas  |a Photoacoustic image synthesis with generative adversarial networks 
773 1 8 |g volume:28  |g year:2022  |g elocationid:100402  |g pages:1-10  |g extent:10  |a Photoacoustic image synthesis with generative adversarial networks 
856 4 0 |u https://doi.org/10.1016/j.pacs.2022.100402  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://www.sciencedirect.com/science/article/pii/S2213597922000672  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20230126 
993 |a Article 
994 |a 2022 
998 |g 1075029252  |a Maier-Hein, Lena  |m 1075029252:Maier-Hein, Lena  |d 110000  |e 110000PM1075029252  |k 0/110000/  |p 8  |y j 
998 |g 1140542494  |a Tizabi, Minu  |m 1140542494:Tizabi, Minu  |p 6 
998 |g 1197270973  |a Nölke, Jan-Hinrich  |m 1197270973:Nölke, Jan-Hinrich  |d 130000  |e 130000PN1197270973  |k 0/130000/  |p 4 
998 |g 1237780837  |a Dreher, Kris  |m 1237780837:Dreher, Kris  |d 130000  |e 130000PD1237780837  |k 0/130000/  |p 3 
998 |g 1197628673  |a Gröhl, Janek  |m 1197628673:Gröhl, Janek  |p 2 
998 |g 1237779464  |a Schellenberg, Melanie  |m 1237779464:Schellenberg, Melanie  |d 110000  |e 110000PS1237779464  |k 0/110000/  |p 1  |x j 
999 |a KXP-PPN1832518582  |e 4252216532 
BIB |a Y 
SER |a journal 
JSO |a {"name":{"displayForm":["Melanie Schellenberg, Janek Gröhl, Kris K. Dreher, Jan-Hinrich Nölke, Niklas Holzwarth, Minu D. Tizabi, Alexander Seitel, Lena Maier-Hein"]},"id":{"eki":["1832518582"],"doi":["10.1016/j.pacs.2022.100402"]},"physDesc":[{"extent":"10 S."}],"recId":"1832518582","origin":[{"dateIssuedDisp":"13 September 2022","dateIssuedKey":"2022"}],"person":[{"display":"Schellenberg, Melanie","family":"Schellenberg","given":"Melanie","role":"aut"},{"display":"Gröhl, Janek","family":"Gröhl","given":"Janek","role":"aut"},{"given":"Kris","role":"aut","family":"Dreher","display":"Dreher, Kris"},{"family":"Nölke","role":"aut","given":"Jan-Hinrich","display":"Nölke, Jan-Hinrich"},{"display":"Holzwarth, Niklas","family":"Holzwarth","given":"Niklas","role":"aut"},{"display":"Tizabi, Minu","given":"Minu","role":"aut","family":"Tizabi"},{"display":"Seitel, Alexander","family":"Seitel","given":"Alexander","role":"aut"},{"given":"Lena","role":"aut","family":"Maier-Hein","display":"Maier-Hein, Lena"}],"relHost":[{"disp":"Photoacoustic image synthesis with generative adversarial networksPhotoacoustics","recId":"746705697","physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["746705697"],"issn":["2213-5979"],"zdb":["2716706-9"]},"title":[{"title_sort":"Photoacoustics","title":"Photoacoustics"}],"part":{"volume":"28","text":"28(2022), Artikel-ID 100402, Seite 1-10","extent":"10","pages":"1-10","year":"2022"},"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"note":["Gesehen am 11.08.20"],"origin":[{"publisher":"Elsevier","dateIssuedDisp":"2013-","dateIssuedKey":"2013","publisherPlace":"Amsterdam [u.a.]"}],"pubHistory":["1.2013 -"]}],"language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 26.01.2023"],"title":[{"title_sort":"Photoacoustic image synthesis with generative adversarial networks","title":"Photoacoustic image synthesis with generative adversarial networks"}]} 
SRT |a SCHELLENBEPHOTOACOUS1320