Deep learning segmentation of major vessels in X-ray coronary angiography. Yang, S., Kweon, J., Roh, J., Lee, J., Kang, H., Park, L., Kim, D. J., Yang, H., Hur, J., Kang, D., Lee, P. H., Ahn, J., Kang, S., Park, D., Lee, S., Kim, Y., Lee, C. W., Park, S., & Park, S. Scientific Reports, 9(1):16897, November, 2019. Number: 1 Publisher: Nature Publishing Group![Deep learning segmentation of major vessels in X-ray coronary angiography [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7% of the images exhibited a high F1 score \textgreater 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.
@article{yang_deep_2019,
title = {Deep learning segmentation of major vessels in {X}-ray coronary angiography},
volume = {9},
copyright = {2019 The Author(s)},
issn = {2045-2322},
url = {https://www.nature.com/articles/s41598-019-53254-7},
doi = {10.1038/s41598-019-53254-7},
abstract = {X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7\% of the images exhibited a high F1 score {\textgreater} 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.},
language = {en},
number = {1},
urldate = {2020-05-11},
journal = {Scientific Reports},
author = {Yang, Su and Kweon, Jihoon and Roh, Jae-Hyung and Lee, Jae-Hwan and Kang, Heejun and Park, Lae-Jeong and Kim, Dong Jun and Yang, Hyeonkyeong and Hur, Jaehee and Kang, Do-Yoon and Lee, Pil Hyung and Ahn, Jung-Min and Kang, Soo-Jin and Park, Duk-Woo and Lee, Seung-Whan and Kim, Young-Hak and Lee, Cheol Whan and Park, Seong-Wook and Park, Seung-Jung},
month = nov,
year = {2019},
note = {Number: 1
Publisher: Nature Publishing Group},
pages = {16897},
}
Downloads: 0
{"_id":"HFiGg9oGBtaw4LN3H","bibbaseid":"yang-kweon-roh-lee-kang-park-kim-yang-etal-deeplearningsegmentationofmajorvesselsinxraycoronaryangiography-2019","authorIDs":[],"author_short":["Yang, S.","Kweon, J.","Roh, J.","Lee, J.","Kang, H.","Park, L.","Kim, D. J.","Yang, H.","Hur, J.","Kang, D.","Lee, P. H.","Ahn, J.","Kang, S.","Park, D.","Lee, S.","Kim, Y.","Lee, C. W.","Park, S.","Park, S."],"bibdata":{"bibtype":"article","type":"article","title":"Deep learning segmentation of major vessels in X-ray coronary angiography","volume":"9","copyright":"2019 The Author(s)","issn":"2045-2322","url":"https://www.nature.com/articles/s41598-019-53254-7","doi":"10.1038/s41598-019-53254-7","abstract":"X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7% of the images exhibited a high F1 score \\textgreater 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.","language":"en","number":"1","urldate":"2020-05-11","journal":"Scientific Reports","author":[{"propositions":[],"lastnames":["Yang"],"firstnames":["Su"],"suffixes":[]},{"propositions":[],"lastnames":["Kweon"],"firstnames":["Jihoon"],"suffixes":[]},{"propositions":[],"lastnames":["Roh"],"firstnames":["Jae-Hyung"],"suffixes":[]},{"propositions":[],"lastnames":["Lee"],"firstnames":["Jae-Hwan"],"suffixes":[]},{"propositions":[],"lastnames":["Kang"],"firstnames":["Heejun"],"suffixes":[]},{"propositions":[],"lastnames":["Park"],"firstnames":["Lae-Jeong"],"suffixes":[]},{"propositions":[],"lastnames":["Kim"],"firstnames":["Dong","Jun"],"suffixes":[]},{"propositions":[],"lastnames":["Yang"],"firstnames":["Hyeonkyeong"],"suffixes":[]},{"propositions":[],"lastnames":["Hur"],"firstnames":["Jaehee"],"suffixes":[]},{"propositions":[],"lastnames":["Kang"],"firstnames":["Do-Yoon"],"suffixes":[]},{"propositions":[],"lastnames":["Lee"],"firstnames":["Pil","Hyung"],"suffixes":[]},{"propositions":[],"lastnames":["Ahn"],"firstnames":["Jung-Min"],"suffixes":[]},{"propositions":[],"lastnames":["Kang"],"firstnames":["Soo-Jin"],"suffixes":[]},{"propositions":[],"lastnames":["Park"],"firstnames":["Duk-Woo"],"suffixes":[]},{"propositions":[],"lastnames":["Lee"],"firstnames":["Seung-Whan"],"suffixes":[]},{"propositions":[],"lastnames":["Kim"],"firstnames":["Young-Hak"],"suffixes":[]},{"propositions":[],"lastnames":["Lee"],"firstnames":["Cheol","Whan"],"suffixes":[]},{"propositions":[],"lastnames":["Park"],"firstnames":["Seong-Wook"],"suffixes":[]},{"propositions":[],"lastnames":["Park"],"firstnames":["Seung-Jung"],"suffixes":[]}],"month":"November","year":"2019","note":"Number: 1 Publisher: Nature Publishing Group","pages":"16897","bibtex":"@article{yang_deep_2019,\n\ttitle = {Deep learning segmentation of major vessels in {X}-ray coronary angiography},\n\tvolume = {9},\n\tcopyright = {2019 The Author(s)},\n\tissn = {2045-2322},\n\turl = {https://www.nature.com/articles/s41598-019-53254-7},\n\tdoi = {10.1038/s41598-019-53254-7},\n\tabstract = {X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7\\% of the images exhibited a high F1 score {\\textgreater} 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2020-05-11},\n\tjournal = {Scientific Reports},\n\tauthor = {Yang, Su and Kweon, Jihoon and Roh, Jae-Hyung and Lee, Jae-Hwan and Kang, Heejun and Park, Lae-Jeong and Kim, Dong Jun and Yang, Hyeonkyeong and Hur, Jaehee and Kang, Do-Yoon and Lee, Pil Hyung and Ahn, Jung-Min and Kang, Soo-Jin and Park, Duk-Woo and Lee, Seung-Whan and Kim, Young-Hak and Lee, Cheol Whan and Park, Seong-Wook and Park, Seung-Jung},\n\tmonth = nov,\n\tyear = {2019},\n\tnote = {Number: 1\nPublisher: Nature Publishing Group},\n\tpages = {16897},\n}\n\n","author_short":["Yang, S.","Kweon, J.","Roh, J.","Lee, J.","Kang, H.","Park, L.","Kim, D. J.","Yang, H.","Hur, J.","Kang, D.","Lee, P. H.","Ahn, J.","Kang, S.","Park, D.","Lee, S.","Kim, Y.","Lee, C. W.","Park, S.","Park, S."],"key":"yang_deep_2019","id":"yang_deep_2019","bibbaseid":"yang-kweon-roh-lee-kang-park-kim-yang-etal-deeplearningsegmentationofmajorvesselsinxraycoronaryangiography-2019","role":"author","urls":{"Paper":"https://www.nature.com/articles/s41598-019-53254-7"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/m.shamimkaiser","creationDate":"2021-02-19T18:04:08.958Z","downloads":0,"keywords":[],"search_terms":["deep","learning","segmentation","major","vessels","ray","coronary","angiography","yang","kweon","roh","lee","kang","park","kim","yang","hur","kang","lee","ahn","kang","park","lee","kim","lee","park","park"],"title":"Deep learning segmentation of major vessels in X-ray coronary angiography","year":2019,"dataSources":["yda423vBhGBN7Q3WB"]}