Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep-Learning Reconstruction and Other Reconstruction Algorithms
A super-resolution deep-learning based reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA. To compare SR-DLR and other reconstruction algorithms in terms of image quality measures r...
Gespeichert in:
| Veröffentlicht in: | American journal of roentgenology (1976) 2023-11, Vol.221 (5), p.599-610 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 610 |
|---|---|
| container_issue | 5 |
| container_start_page | 599 |
| container_title | American journal of roentgenology (1976) |
| container_volume | 221 |
| creator | Nagayama, Yasunori Emoto, Takafumi Hayashi, Hidetaka Kidoh, Masafumi Oda, Seitaro Nakaura, Takeshi Sakabe, Daisuke Funama, Yoshinori Tabata, Noriaki Ishii, Masanobu Yamanaga, Kenshi Fujisue, Koichiro Takashio, Seiji Yamamoto, Eiichiro Tsujita, Kenichi Hirai, Toshinori |
| description | A super-resolution deep-learning based reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA.
To compare SR-DLR and other reconstruction algorithms in terms of image quality measures related to coronary stent evaluation in patients undergoing coronary CTA.
This retrospective study included patients with at least one coronary artery stent who underwent coronary CTA between January 2020 and December 2020. Examinations were performed using a 320-row normal-resolution scanner and reconstructed with hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning reconstruction (NR-DLR), and SR-DLR algorithms. Quantitative image quality measures were determined. Two radiologists independently reviewed images to rank the four reconstructions (1=worst reconstruction, 4=best reconstruction) for qualitative measures, and to score diagnostic confidence (5-point scale; score≥3 indicating an assessable stent). Assessability rate was calculated for stents with diameter ≤3.0 mm.
The sample included 24 patients (18 men, 6 women; mean age, 72.8±9.8 years), with 51 stents. SR-DLR, in comparison with the other reconstructions, yielded lower stent-related blooming artifacts (median, 40.3 vs 53.4-58.2), stent-induced attenuation increase ratio (0.17 vs 0.27-0.31), and quantitative image noise (18.1 vs 20.9-30.4 HU), and higher in-stent lumen diameter (2.41 vs. 1.74-1.94 mm), stent strut sharpness (327 vs 147-210 ΔHU/mm), and CNR (30.0 vs 16.0-25.6), (all p |
| doi_str_mv | 10.2214/AJR.23.29506 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2830669203</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2830669203</sourcerecordid><originalsourceid>FETCH-LOGICAL-c357t-95e44cf9be4ee5ebf1e4d49e895f12e1dd99895b4c5b501b0629a2882b2784e83</originalsourceid><addsrcrecordid>eNpdkUlPwzAQhS0EgrLcOCMfOZDiLYu5lVKgqBKiLRK3yEkmJSixg-2A-j_4wYSyHDjNaN437_AeQseUDBmj4nx0Nx8yPmQyJNEWGtBQRAGngm6jAeERDRLCn_bQvnMvhJA4kfEu2uMxj2MesQH6GBtrtLJrvPCgPZ68qbpTvjIaZ2s8Xo4u8LRRK8APnaor359M0ypbuR64BP8OoPGia8EGc3Cm7jafVwBtMANldaVXeA650c7bLt-IShf43j-D_S-M6pWxlX9u3CHaKVXt4OhnHqDH68lyfBvM7m-m49EsyHkY-0CGIEReygwEQAhZSUEUQkIiw5IyoEUhZb9nIg-zkNCMREwqliQsY3EiIOEH6PTbt7XmtQPn06ZyOdS10mA6l7KEkyiSjPAePftGc2ucs1Cmra2aPreUkvSrh7TvIWU83fTQ4yc_zl3WQPEH_wbPPwFqdoX8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2830669203</pqid></control><display><type>article</type><title>Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep-Learning Reconstruction and Other Reconstruction Algorithms</title><source>American Roentgen Ray Society</source><source>Alma/SFX Local Collection</source><creator>Nagayama, Yasunori ; Emoto, Takafumi ; Hayashi, Hidetaka ; Kidoh, Masafumi ; Oda, Seitaro ; Nakaura, Takeshi ; Sakabe, Daisuke ; Funama, Yoshinori ; Tabata, Noriaki ; Ishii, Masanobu ; Yamanaga, Kenshi ; Fujisue, Koichiro ; Takashio, Seiji ; Yamamoto, Eiichiro ; Tsujita, Kenichi ; Hirai, Toshinori</creator><creatorcontrib>Nagayama, Yasunori ; Emoto, Takafumi ; Hayashi, Hidetaka ; Kidoh, Masafumi ; Oda, Seitaro ; Nakaura, Takeshi ; Sakabe, Daisuke ; Funama, Yoshinori ; Tabata, Noriaki ; Ishii, Masanobu ; Yamanaga, Kenshi ; Fujisue, Koichiro ; Takashio, Seiji ; Yamamoto, Eiichiro ; Tsujita, Kenichi ; Hirai, Toshinori</creatorcontrib><description>A super-resolution deep-learning based reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA.
To compare SR-DLR and other reconstruction algorithms in terms of image quality measures related to coronary stent evaluation in patients undergoing coronary CTA.
This retrospective study included patients with at least one coronary artery stent who underwent coronary CTA between January 2020 and December 2020. Examinations were performed using a 320-row normal-resolution scanner and reconstructed with hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning reconstruction (NR-DLR), and SR-DLR algorithms. Quantitative image quality measures were determined. Two radiologists independently reviewed images to rank the four reconstructions (1=worst reconstruction, 4=best reconstruction) for qualitative measures, and to score diagnostic confidence (5-point scale; score≥3 indicating an assessable stent). Assessability rate was calculated for stents with diameter ≤3.0 mm.
The sample included 24 patients (18 men, 6 women; mean age, 72.8±9.8 years), with 51 stents. SR-DLR, in comparison with the other reconstructions, yielded lower stent-related blooming artifacts (median, 40.3 vs 53.4-58.2), stent-induced attenuation increase ratio (0.17 vs 0.27-0.31), and quantitative image noise (18.1 vs 20.9-30.4 HU), and higher in-stent lumen diameter (2.41 vs. 1.74-1.94 mm), stent strut sharpness (327 vs 147-210 ΔHU/mm), and CNR (30.0 vs 16.0-25.6), (all p<.001). For both observers, all ranked measures (image sharpness; image noise; noise texture; delineation of stent strut, in-stent lumen, coronary artery wall, and calcified plaque surrounding the stent) and diagnostic confidence showed a higher score for SR-DLR (median, 4.0 for all features) than for the other reconstructions (range, 1.0-3.0) (all p<.001). Assessability rate for stents with diameter ≤3.0 mm (n=37) was higher for SR-DLR (observer 1: 86.5%; observer 2: 89.2%) than for HIR (35.1%, 43.2%), MBIR (59.5%, 62.2%), or NR-DLR (62.2%, 64.9%) (all p<.05).
SR-DLR yielded improved delineation of the stent strut and in-stent lumen, with better image sharpness and less image noise and blooming artifacts, in comparison with HIR, MBIR, and NR-DLR.
SR-DLR may facilitate coronary stent assessment on a 320-row normal-resolution scanner, particularly for small-diameter stents.</description><identifier>ISSN: 0361-803X</identifier><identifier>EISSN: 1546-3141</identifier><identifier>DOI: 10.2214/AJR.23.29506</identifier><identifier>PMID: 37377362</identifier><language>eng</language><publisher>United States</publisher><ispartof>American journal of roentgenology (1976), 2023-11, Vol.221 (5), p.599-610</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c357t-95e44cf9be4ee5ebf1e4d49e895f12e1dd99895b4c5b501b0629a2882b2784e83</citedby><cites>FETCH-LOGICAL-c357t-95e44cf9be4ee5ebf1e4d49e895f12e1dd99895b4c5b501b0629a2882b2784e83</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,4106,27905,27906</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37377362$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Nagayama, Yasunori</creatorcontrib><creatorcontrib>Emoto, Takafumi</creatorcontrib><creatorcontrib>Hayashi, Hidetaka</creatorcontrib><creatorcontrib>Kidoh, Masafumi</creatorcontrib><creatorcontrib>Oda, Seitaro</creatorcontrib><creatorcontrib>Nakaura, Takeshi</creatorcontrib><creatorcontrib>Sakabe, Daisuke</creatorcontrib><creatorcontrib>Funama, Yoshinori</creatorcontrib><creatorcontrib>Tabata, Noriaki</creatorcontrib><creatorcontrib>Ishii, Masanobu</creatorcontrib><creatorcontrib>Yamanaga, Kenshi</creatorcontrib><creatorcontrib>Fujisue, Koichiro</creatorcontrib><creatorcontrib>Takashio, Seiji</creatorcontrib><creatorcontrib>Yamamoto, Eiichiro</creatorcontrib><creatorcontrib>Tsujita, Kenichi</creatorcontrib><creatorcontrib>Hirai, Toshinori</creatorcontrib><title>Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep-Learning Reconstruction and Other Reconstruction Algorithms</title><title>American journal of roentgenology (1976)</title><addtitle>AJR Am J Roentgenol</addtitle><description>A super-resolution deep-learning based reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA.
To compare SR-DLR and other reconstruction algorithms in terms of image quality measures related to coronary stent evaluation in patients undergoing coronary CTA.
This retrospective study included patients with at least one coronary artery stent who underwent coronary CTA between January 2020 and December 2020. Examinations were performed using a 320-row normal-resolution scanner and reconstructed with hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning reconstruction (NR-DLR), and SR-DLR algorithms. Quantitative image quality measures were determined. Two radiologists independently reviewed images to rank the four reconstructions (1=worst reconstruction, 4=best reconstruction) for qualitative measures, and to score diagnostic confidence (5-point scale; score≥3 indicating an assessable stent). Assessability rate was calculated for stents with diameter ≤3.0 mm.
The sample included 24 patients (18 men, 6 women; mean age, 72.8±9.8 years), with 51 stents. SR-DLR, in comparison with the other reconstructions, yielded lower stent-related blooming artifacts (median, 40.3 vs 53.4-58.2), stent-induced attenuation increase ratio (0.17 vs 0.27-0.31), and quantitative image noise (18.1 vs 20.9-30.4 HU), and higher in-stent lumen diameter (2.41 vs. 1.74-1.94 mm), stent strut sharpness (327 vs 147-210 ΔHU/mm), and CNR (30.0 vs 16.0-25.6), (all p<.001). For both observers, all ranked measures (image sharpness; image noise; noise texture; delineation of stent strut, in-stent lumen, coronary artery wall, and calcified plaque surrounding the stent) and diagnostic confidence showed a higher score for SR-DLR (median, 4.0 for all features) than for the other reconstructions (range, 1.0-3.0) (all p<.001). Assessability rate for stents with diameter ≤3.0 mm (n=37) was higher for SR-DLR (observer 1: 86.5%; observer 2: 89.2%) than for HIR (35.1%, 43.2%), MBIR (59.5%, 62.2%), or NR-DLR (62.2%, 64.9%) (all p<.05).
SR-DLR yielded improved delineation of the stent strut and in-stent lumen, with better image sharpness and less image noise and blooming artifacts, in comparison with HIR, MBIR, and NR-DLR.
SR-DLR may facilitate coronary stent assessment on a 320-row normal-resolution scanner, particularly for small-diameter stents.</description><issn>0361-803X</issn><issn>1546-3141</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNpdkUlPwzAQhS0EgrLcOCMfOZDiLYu5lVKgqBKiLRK3yEkmJSixg-2A-j_4wYSyHDjNaN437_AeQseUDBmj4nx0Nx8yPmQyJNEWGtBQRAGngm6jAeERDRLCn_bQvnMvhJA4kfEu2uMxj2MesQH6GBtrtLJrvPCgPZ68qbpTvjIaZ2s8Xo4u8LRRK8APnaor359M0ypbuR64BP8OoPGia8EGc3Cm7jafVwBtMANldaVXeA650c7bLt-IShf43j-D_S-M6pWxlX9u3CHaKVXt4OhnHqDH68lyfBvM7m-m49EsyHkY-0CGIEReygwEQAhZSUEUQkIiw5IyoEUhZb9nIg-zkNCMREwqliQsY3EiIOEH6PTbt7XmtQPn06ZyOdS10mA6l7KEkyiSjPAePftGc2ucs1Cmra2aPreUkvSrh7TvIWU83fTQ4yc_zl3WQPEH_wbPPwFqdoX8</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>Nagayama, Yasunori</creator><creator>Emoto, Takafumi</creator><creator>Hayashi, Hidetaka</creator><creator>Kidoh, Masafumi</creator><creator>Oda, Seitaro</creator><creator>Nakaura, Takeshi</creator><creator>Sakabe, Daisuke</creator><creator>Funama, Yoshinori</creator><creator>Tabata, Noriaki</creator><creator>Ishii, Masanobu</creator><creator>Yamanaga, Kenshi</creator><creator>Fujisue, Koichiro</creator><creator>Takashio, Seiji</creator><creator>Yamamoto, Eiichiro</creator><creator>Tsujita, Kenichi</creator><creator>Hirai, Toshinori</creator><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20231101</creationdate><title>Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep-Learning Reconstruction and Other Reconstruction Algorithms</title><author>Nagayama, Yasunori ; Emoto, Takafumi ; Hayashi, Hidetaka ; Kidoh, Masafumi ; Oda, Seitaro ; Nakaura, Takeshi ; Sakabe, Daisuke ; Funama, Yoshinori ; Tabata, Noriaki ; Ishii, Masanobu ; Yamanaga, Kenshi ; Fujisue, Koichiro ; Takashio, Seiji ; Yamamoto, Eiichiro ; Tsujita, Kenichi ; Hirai, Toshinori</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c357t-95e44cf9be4ee5ebf1e4d49e895f12e1dd99895b4c5b501b0629a2882b2784e83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nagayama, Yasunori</creatorcontrib><creatorcontrib>Emoto, Takafumi</creatorcontrib><creatorcontrib>Hayashi, Hidetaka</creatorcontrib><creatorcontrib>Kidoh, Masafumi</creatorcontrib><creatorcontrib>Oda, Seitaro</creatorcontrib><creatorcontrib>Nakaura, Takeshi</creatorcontrib><creatorcontrib>Sakabe, Daisuke</creatorcontrib><creatorcontrib>Funama, Yoshinori</creatorcontrib><creatorcontrib>Tabata, Noriaki</creatorcontrib><creatorcontrib>Ishii, Masanobu</creatorcontrib><creatorcontrib>Yamanaga, Kenshi</creatorcontrib><creatorcontrib>Fujisue, Koichiro</creatorcontrib><creatorcontrib>Takashio, Seiji</creatorcontrib><creatorcontrib>Yamamoto, Eiichiro</creatorcontrib><creatorcontrib>Tsujita, Kenichi</creatorcontrib><creatorcontrib>Hirai, Toshinori</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>American journal of roentgenology (1976)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nagayama, Yasunori</au><au>Emoto, Takafumi</au><au>Hayashi, Hidetaka</au><au>Kidoh, Masafumi</au><au>Oda, Seitaro</au><au>Nakaura, Takeshi</au><au>Sakabe, Daisuke</au><au>Funama, Yoshinori</au><au>Tabata, Noriaki</au><au>Ishii, Masanobu</au><au>Yamanaga, Kenshi</au><au>Fujisue, Koichiro</au><au>Takashio, Seiji</au><au>Yamamoto, Eiichiro</au><au>Tsujita, Kenichi</au><au>Hirai, Toshinori</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep-Learning Reconstruction and Other Reconstruction Algorithms</atitle><jtitle>American journal of roentgenology (1976)</jtitle><addtitle>AJR Am J Roentgenol</addtitle><date>2023-11-01</date><risdate>2023</risdate><volume>221</volume><issue>5</issue><spage>599</spage><epage>610</epage><pages>599-610</pages><issn>0361-803X</issn><eissn>1546-3141</eissn><abstract>A super-resolution deep-learning based reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA.
To compare SR-DLR and other reconstruction algorithms in terms of image quality measures related to coronary stent evaluation in patients undergoing coronary CTA.
This retrospective study included patients with at least one coronary artery stent who underwent coronary CTA between January 2020 and December 2020. Examinations were performed using a 320-row normal-resolution scanner and reconstructed with hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning reconstruction (NR-DLR), and SR-DLR algorithms. Quantitative image quality measures were determined. Two radiologists independently reviewed images to rank the four reconstructions (1=worst reconstruction, 4=best reconstruction) for qualitative measures, and to score diagnostic confidence (5-point scale; score≥3 indicating an assessable stent). Assessability rate was calculated for stents with diameter ≤3.0 mm.
The sample included 24 patients (18 men, 6 women; mean age, 72.8±9.8 years), with 51 stents. SR-DLR, in comparison with the other reconstructions, yielded lower stent-related blooming artifacts (median, 40.3 vs 53.4-58.2), stent-induced attenuation increase ratio (0.17 vs 0.27-0.31), and quantitative image noise (18.1 vs 20.9-30.4 HU), and higher in-stent lumen diameter (2.41 vs. 1.74-1.94 mm), stent strut sharpness (327 vs 147-210 ΔHU/mm), and CNR (30.0 vs 16.0-25.6), (all p<.001). For both observers, all ranked measures (image sharpness; image noise; noise texture; delineation of stent strut, in-stent lumen, coronary artery wall, and calcified plaque surrounding the stent) and diagnostic confidence showed a higher score for SR-DLR (median, 4.0 for all features) than for the other reconstructions (range, 1.0-3.0) (all p<.001). Assessability rate for stents with diameter ≤3.0 mm (n=37) was higher for SR-DLR (observer 1: 86.5%; observer 2: 89.2%) than for HIR (35.1%, 43.2%), MBIR (59.5%, 62.2%), or NR-DLR (62.2%, 64.9%) (all p<.05).
SR-DLR yielded improved delineation of the stent strut and in-stent lumen, with better image sharpness and less image noise and blooming artifacts, in comparison with HIR, MBIR, and NR-DLR.
SR-DLR may facilitate coronary stent assessment on a 320-row normal-resolution scanner, particularly for small-diameter stents.</abstract><cop>United States</cop><pmid>37377362</pmid><doi>10.2214/AJR.23.29506</doi><tpages>12</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0361-803X |
| ispartof | American journal of roentgenology (1976), 2023-11, Vol.221 (5), p.599-610 |
| issn | 0361-803X 1546-3141 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2830669203 |
| source | American Roentgen Ray Society; Alma/SFX Local Collection |
| title | Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep-Learning Reconstruction and Other Reconstruction Algorithms |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T04%3A22%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Coronary%20Stent%20Evaluation%20by%20CTA:%20Image%20Quality%20Comparison%20Between%20Super-Resolution%20Deep-Learning%20Reconstruction%20and%20Other%20Reconstruction%20Algorithms&rft.jtitle=American%20journal%20of%20roentgenology%20(1976)&rft.au=Nagayama,%20Yasunori&rft.date=2023-11-01&rft.volume=221&rft.issue=5&rft.spage=599&rft.epage=610&rft.pages=599-610&rft.issn=0361-803X&rft.eissn=1546-3141&rft_id=info:doi/10.2214/AJR.23.29506&rft_dat=%3Cproquest_cross%3E2830669203%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2830669203&rft_id=info:pmid/37377362&rfr_iscdi=true |