Cover Image

Efficient photoacoustic image synthesis with deep learning

Photoacoustic imaging potentially allows for the real-time visualization of functional human tissue parameters such as oxygenation but is subject to a challenging underlying quantification problem. While in silico studies have revealed the great potential of deep learning (DL) methodology in solving...

Full description

Saved in:
Bibliographic Details
Main Authors: Rix, Tom (Author) , Dreher, Kris (Author) , Nölke, Jan-Hinrich (Author) , Schellenberg, Melanie (Author) , Tizabi, Minu D. (Author) , Seitel, Alexander (Author) , Maier-Hein, Lena (Author)
Format: Article (Journal)
Language:English
Published: 2023
In: Sensors
Year: 2023, Volume: 23, Issue: 16, Pages: 1-13
ISSN:1424-8220
DOI:10.3390/s23167085
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.3390/s23167085
Verlag, kostenfrei, Volltext: https://www.mdpi.com/1424-8220/23/16/7085
Get full text
Author Notes:Tom Rix, Kris K. Dreher, Jan-Hinrich Nölke, Melanie Schellenberg, Minu D. Tizabi, Alexander Seitel and Lena Maier-Hein

MARC

LEADER 00000caa a2200000 c 4500
001 1866187988
003 DE-627
005 20240307045459.0
007 cr uuu---uuuuu
008 231018s2023 xx |||||o 00| ||eng c
024 7 |a 10.3390/s23167085  |2 doi 
035 |a (DE-627)1866187988 
035 |a (DE-599)KXP1866187988 
035 |a (OCoLC)1425210228 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Rix, Tom  |e VerfasserIn  |0 (DE-588)1306437059  |0 (DE-627)1866188666  |4 aut 
245 1 0 |a Efficient photoacoustic image synthesis with deep learning  |c Tom Rix, Kris K. Dreher, Jan-Hinrich Nölke, Melanie Schellenberg, Minu D. Tizabi, Alexander Seitel and Lena Maier-Hein 
264 1 |c 2023 
300 |a 13 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Veröffentlicht: 10. August 2023 
500 |a Gesehen am 18.10.2023 
520 |a Photoacoustic imaging potentially allows for the real-time visualization of functional human tissue parameters such as oxygenation but is subject to a challenging underlying quantification problem. While in silico studies have revealed the great potential of deep learning (DL) methodology in solving this problem, the inherent lack of an efficient gold standard method for model training and validation remains a grand challenge. This work investigates whether DL can be leveraged to accurately and efficiently simulate photon propagation in biological tissue, enabling photoacoustic image synthesis. Our approach is based on estimating the initial pressure distribution of the photoacoustic waves from the underlying optical properties using a back-propagatable neural network trained on synthetic data. In proof-of-concept studies, we validated the performance of two complementary neural network architectures, namely a conventional U-Net-like model and a Fourier Neural Operator (FNO) network. Our in silico validation on multispectral human forearm images shows that DL methods can speed up image generation by a factor of 100 when compared to Monte Carlo simulations with 5×108 photons. While the FNO is slightly more accurate than the U-Net, when compared to Monte Carlo simulations performed with a reduced number of photons (5×106), both neural network architectures achieve equivalent accuracy. In contrast to Monte Carlo simulations, the proposed DL models can be used as inherently differentiable surrogate models in the photoacoustic image synthesis pipeline, allowing for back-propagation of the synthesis error and gradient-based optimization over the entire pipeline. Due to their efficiency, they have the potential to enable large-scale training data generation that can expedite the clinical application of photoacoustic imaging. 
650 4 |a deep learning 
650 4 |a Fourier Neural Operator 
650 4 |a image synthesis 
650 4 |a Monte Carlo simulation 
650 4 |a multispectral functional imaging 
650 4 |a photoacoustic imaging 
650 4 |a surrogate model 
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 Schellenberg, Melanie  |d 1994-  |e VerfasserIn  |0 (DE-588)1237779464  |0 (DE-627)176477745X  |4 aut 
700 1 |a Tizabi, Minu D.  |e VerfasserIn  |4 aut 
700 1 |a Seitel, Alexander  |e VerfasserIn  |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 Sensors  |d Basel : MDPI, 2001  |g 23(2023), 16, Artikel-ID 7085, Seite 1-13  |h Online-Ressource  |w (DE-627)331640910  |w (DE-600)2052857-7  |w (DE-576)281205191  |x 1424-8220  |7 nnas  |a Efficient photoacoustic image synthesis with deep learning 
773 1 8 |g volume:23  |g year:2023  |g number:16  |g elocationid:7085  |g pages:1-13  |g extent:13  |a Efficient photoacoustic image synthesis with deep learning 
856 4 0 |u https://doi.org/10.3390/s23167085  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u https://www.mdpi.com/1424-8220/23/16/7085  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20231018 
993 |a Article 
994 |a 2023 
998 |g 1075029252  |a Maier-Hein, Lena  |m 1075029252:Maier-Hein, Lena  |d 110000  |e 110000PM1075029252  |k 0/110000/  |p 7  |y j 
998 |g 1237779464  |a Schellenberg, Melanie  |m 1237779464:Schellenberg, Melanie  |d 110000  |e 110000PS1237779464  |k 0/110000/  |p 4 
998 |g 1197270973  |a Nölke, Jan-Hinrich  |m 1197270973:Nölke, Jan-Hinrich  |d 130000  |e 130000PN1197270973  |k 0/130000/  |p 3 
998 |g 1237780837  |a Dreher, Kris  |m 1237780837:Dreher, Kris  |d 130000  |e 130000PD1237780837  |k 0/130000/  |p 2 
998 |g 1306437059  |a Rix, Tom  |m 1306437059:Rix, Tom  |d 50000  |e 50000PR1306437059  |k 0/50000/  |p 1  |x j 
999 |a KXP-PPN1866187988  |e 4391969521 
BIB |a Y 
SER |a journal 
JSO |a {"language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"2023"}],"physDesc":[{"extent":"13 S."}],"relHost":[{"part":{"extent":"13","volume":"23","year":"2023","text":"23(2023), 16, Artikel-ID 7085, Seite 1-13","pages":"1-13","issue":"16"},"physDesc":[{"extent":"Online-Ressource"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"origin":[{"publisher":"MDPI","dateIssuedDisp":"2001-","publisherPlace":"Basel","dateIssuedKey":"2001"}],"language":["eng"],"title":[{"title":"Sensors","title_sort":"Sensors"}],"disp":"Efficient photoacoustic image synthesis with deep learningSensors","note":["Gesehen am 12.12.19"],"pubHistory":["1.2001 -"],"id":{"eki":["331640910"],"zdb":["2052857-7"],"issn":["1424-8220"]},"recId":"331640910"}],"recId":"1866187988","id":{"eki":["1866187988"],"doi":["10.3390/s23167085"]},"person":[{"role":"aut","family":"Rix","roleDisplay":"VerfasserIn","display":"Rix, Tom","given":"Tom"},{"family":"Dreher","role":"aut","given":"Kris","roleDisplay":"VerfasserIn","display":"Dreher, Kris"},{"family":"Nölke","role":"aut","given":"Jan-Hinrich","roleDisplay":"VerfasserIn","display":"Nölke, Jan-Hinrich"},{"family":"Schellenberg","role":"aut","roleDisplay":"VerfasserIn","display":"Schellenberg, Melanie","given":"Melanie"},{"roleDisplay":"VerfasserIn","display":"Tizabi, Minu D.","given":"Minu D.","role":"aut","family":"Tizabi"},{"display":"Seitel, Alexander","roleDisplay":"VerfasserIn","given":"Alexander","role":"aut","family":"Seitel"},{"family":"Maier-Hein","role":"aut","roleDisplay":"VerfasserIn","display":"Maier-Hein, Lena","given":"Lena"}],"note":["Veröffentlicht: 10. August 2023","Gesehen am 18.10.2023"],"name":{"displayForm":["Tom Rix, Kris K. Dreher, Jan-Hinrich Nölke, Melanie Schellenberg, Minu D. Tizabi, Alexander Seitel and Lena Maier-Hein"]},"title":[{"title":"Efficient photoacoustic image synthesis with deep learning","title_sort":"Efficient photoacoustic image synthesis with deep learning"}]} 
SRT |a RIXTOMDREHEFFICIENTP2023 

Similar Items