Using convolutional neural network denoising to reduce ambiguity in X-ray coherent diffraction imaging

open access.

Détails bibliographiques
Publié dans:Journal of synchrotron radiation. - 1994. - 31(2024), Pt 5 vom: 01. Sept., Seite 1340-1345
Auteur principal: Chu, Kang Ching (Auteur)
Autres auteurs: Yeh, Chia Hui, Lin, Jhih Min, Chen, Chun Yu, Cheng, Chi Yuan, Yeh, Yi Qi, Huang, Yu Shan, Tsai, Yi Wei
Format: Article en ligne
Langue:English
Publié: 2024
Accès à la collection:Journal of synchrotron radiation
Sujets:Journal Article Noise2Noise coherent diffraction imaging machine learning mixed-scale dense network
LEADER 01000caa a22002652c 4500
001 NLM375897828
003 DE-627
005 20250306120954.0
007 cr uuu---uuuuu
008 240806s2024 xx |||||o 00| ||eng c
024 7 |a 10.1107/S1600577524006519  |2 doi 
028 5 2 |a pubmed25n1252.xml 
035 |a (DE-627)NLM375897828 
035 |a (NLM)39102364 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chu, Kang Ching  |e verfasserin  |4 aut 
245 1 0 |a Using convolutional neural network denoising to reduce ambiguity in X-ray coherent diffraction imaging 
264 1 |c 2024 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 05.09.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a open access. 
520 |a The inherent ambiguity in reconstructed images from coherent diffraction imaging (CDI) poses an intrinsic challenge, as images derived from the same dataset under varying initial conditions often display inconsistencies. This study introduces a method that employs the Noise2Noise approach combined with neural networks to effectively mitigate these ambiguities. We applied this methodology to hundreds of ambiguous reconstructed images retrieved from a single diffraction pattern using a conventional retrieval algorithm. Our results demonstrate that ambiguous features in these reconstructions are effectively treated as inter-reconstruction noise and are significantly reduced. The post-Noise2Noise treated images closely approximate the average and singular value decomposition analysis of various reconstructions, providing consistent and reliable reconstructions 
650 4 |a Journal Article 
650 4 |a Noise2Noise 
650 4 |a coherent diffraction imaging 
650 4 |a machine learning 
650 4 |a mixed-scale dense network 
700 1 |a Yeh, Chia Hui  |e verfasserin  |4 aut 
700 1 |a Lin, Jhih Min  |e verfasserin  |4 aut 
700 1 |a Chen, Chun Yu  |e verfasserin  |4 aut 
700 1 |a Cheng, Chi Yuan  |e verfasserin  |4 aut 
700 1 |a Yeh, Yi Qi  |e verfasserin  |4 aut 
700 1 |a Huang, Yu Shan  |e verfasserin  |4 aut 
700 1 |a Tsai, Yi Wei  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t Journal of synchrotron radiation  |d 1994  |g 31(2024), Pt 5 vom: 01. Sept., Seite 1340-1345  |w (DE-627)NLM09824129X  |x 1600-5775  |7 nnas 
773 1 8 |g volume:31  |g year:2024  |g number:Pt 5  |g day:01  |g month:09  |g pages:1340-1345 
856 4 0 |u http://dx.doi.org/10.1107/S1600577524006519  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_40 
912 |a GBV_ILN_350 
912 |a GBV_ILN_2005 
951 |a AR 
952 |d 31  |j 2024  |e Pt 5  |b 01  |c 09  |h 1340-1345