Artifact removal using a hybrid-domain convolutional neural network for limited-angle computed tomography imaging
The suppression of streak artifacts in computed tomography with a limited-angle configuration is challenging. Conventional analytical algorithms, such as filtered backprojection (FBP), are not successful due to incomplete projection data. Moreover, model-based iterative total variation algorithms effectively reduce small streaks but do not work well at eliminating large streaks. In contrast, FBP mapping networks and deep-learning-based postprocessing networks are outstanding at removing large streak artifacts; however, these methods perform processing in separate domains, and the advantages of multiple deep learning algorithms operating in different domains have not been simultaneously explored. In this paper, we present a hybrid-domain convolutional neural network (hdNet) for the reduction of streak artifacts in limited-angle computed tomography. The network consists of three components: the first component is a convolutional neural network operating in the sinogram domain, the second is a domain transformation operation, and the last is a convolutional neural network operating in the CT image domain. After training the network, we can obtain artifact-suppressed CT images directly from the sinogram domain. Verification results based on numerical, experimental and clinical data confirm that the proposed method can significantly reduce serious artifacts.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - volume:65 |
---|---|
Enthalten in: |
Physics in medicine and biology - 65(2020), 15 vom: 05. Aug., Seite 155010 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhang, Qiyang [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 30.10.2020 Date Revised 30.10.2020 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1088/1361-6560/ab9066 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM309532809 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM309532809 | ||
003 | DE-627 | ||
005 | 20231225134123.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1088/1361-6560/ab9066 |2 doi | |
028 | 5 | 2 | |a pubmed24n1031.xml |
035 | |a (DE-627)NLM309532809 | ||
035 | |a (NLM)32369793 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhang, Qiyang |e verfasserin |4 aut | |
245 | 1 | 0 | |a Artifact removal using a hybrid-domain convolutional neural network for limited-angle computed tomography imaging |
264 | 1 | |c 2020 | |
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 Completed 30.10.2020 | ||
500 | |a Date Revised 30.10.2020 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a The suppression of streak artifacts in computed tomography with a limited-angle configuration is challenging. Conventional analytical algorithms, such as filtered backprojection (FBP), are not successful due to incomplete projection data. Moreover, model-based iterative total variation algorithms effectively reduce small streaks but do not work well at eliminating large streaks. In contrast, FBP mapping networks and deep-learning-based postprocessing networks are outstanding at removing large streak artifacts; however, these methods perform processing in separate domains, and the advantages of multiple deep learning algorithms operating in different domains have not been simultaneously explored. In this paper, we present a hybrid-domain convolutional neural network (hdNet) for the reduction of streak artifacts in limited-angle computed tomography. The network consists of three components: the first component is a convolutional neural network operating in the sinogram domain, the second is a domain transformation operation, and the last is a convolutional neural network operating in the CT image domain. After training the network, we can obtain artifact-suppressed CT images directly from the sinogram domain. Verification results based on numerical, experimental and clinical data confirm that the proposed method can significantly reduce serious artifacts | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Hu, Zhanli |e verfasserin |4 aut | |
700 | 1 | |a Jiang, Changhui |e verfasserin |4 aut | |
700 | 1 | |a Zheng, Hairong |e verfasserin |4 aut | |
700 | 1 | |a Ge, Yongshuai |e verfasserin |4 aut | |
700 | 1 | |a Liang, Dong |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Physics in medicine and biology |d 1956 |g 65(2020), 15 vom: 05. Aug., Seite 155010 |w (DE-627)NLM000336505 |x 1361-6560 |7 nnns |
773 | 1 | 8 | |g volume:65 |g year:2020 |g number:15 |g day:05 |g month:08 |g pages:155010 |
856 | 4 | 0 | |u http://dx.doi.org/10.1088/1361-6560/ab9066 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 65 |j 2020 |e 15 |b 05 |c 08 |h 155010 |