Academic Journal
Feasibility of U-Net model for cerebral arteries segmentation with low-dose computed tomography angiographic images with pre-processing methods.
| Τίτλος: | Feasibility of U-Net model for cerebral arteries segmentation with low-dose computed tomography angiographic images with pre-processing methods. |
|---|---|
| Συγγραφείς: | Kang SH; Department of Radiological Science, Gachon University, 191, Hambakmoe-ro, Yeonsu-gu, Incheon, 21936, Republic of Korea., Kim K; Institute of Human Convergence Health Science, Gachon University, 191, Hambakmoe-ro, Yeonsu-gu, Incheon, 21936, Republic of Korea., Shim J; Department of Radiotechnology, Wonkwang Health Science University, 514, Iksan-daero, Iksan-si, Jeonbuk-do, 54538, Republic of Korea., Lee Y; Department of Radiological Science, Gachon University, 191, Hambakmoe-ro, Yeonsu-gu, Incheon, 21936, Republic of Korea. yj20@gachon.ac.kr. |
| Πηγή: | Scientific reports [Sci Rep] 2025 Apr 17; Vol. 15 (1), pp. 13281. Date of Electronic Publication: 2025 Apr 17. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : Nature Publishing Group, copyright 2011- |
| Ιατρικοί όροι (MeSH): | Cerebral Arteries*/diagnostic imaging , Computed Tomography Angiography*/methods , Image Processing, Computer-Assisted*/methods , Deep Learning*, Humans ; Radiation Dosage ; Algorithms ; Datasets as Topic |
| Περίληψη: | Subtraction computed tomography angiography (sCTA) can effectively separate enhanced cerebral arteries from similar signal intensity and proximity (i.e., vertebrae and skull). However, sCTA is not considered mainstream because of the high radiation dose generated by the two-scan protocol. We aimed to solve the overexposure problem by training a U-Net-based CA segmentation model using a low-dose computed tomographic angiography (CTA) image-based dataset with various pre-processing methods to achieve a performance similar to that of sCTA. We optimized a non-local means (NLM) algorithm using the coefficient of variation and contrast-to-noise ratio. In addition, datasets were constructed by predicting the CA mask using a semiautomatic thresholding technique based on region growing method. Then, CTA images of 35 (2052 slices), 4 (248 slices), and 5 patients (594 slices) were used, respectively, for the train, validation, and test sets. To evaluate the performance of the U-Net-based CA segmentation model quantitatively according to the constructed dataset, the average precision (AP), intersection over union (IoU), and F1-score were calculated. For the dataset to which both the optimized NLM algorithm and semiautomatic thresholding technique were applied, the segmentation model showed the most improved performance. In particular, the quantitative evaluation of the low-dose CTA image with the NLM algorithm and the semiautomatic thresholding-based U-Net model calculated AP, IoU, and F1-scores of approximately 0.880, 0.955, and 0.809, respectively, which were most similar to the CA segmentation performance of the sCTA technique. The proposed U-Net model provided CA segmentation results without additional radiation exposure. In addition, the selection and optimization of an appropriate pre-processing methods were identified as essential for achieving higher segmentation performance for the U-Net model. (© 2025. The Author(s).) |
| Competing Interests: | Declarations. Competing interests: The authors declare no competing interests. Institutional review board statement: The study was conducted in accordance with the Declaration of Helsinki and approved by the Severance hospital Institutional Review Board (No. 4-2020-1364). Informed consent: Patient consent was waived because this was a retrospective study, and all data in this study were used after being anonymized. |
| References: | J Xray Sci Technol. 2024;32(6):1553-1570. (PMID: 39729441) Phys Med Biol. 2020 Mar 11;65(6):065002. (PMID: 31978921) J Xray Sci Technol. 2020;28(6):1037-1054. (PMID: 33044222) Eur Radiol. 2006 Apr;16(4):889-97. (PMID: 16267665) BMC Neurol. 2020 Sep 3;20(1):334. (PMID: 32883220) AJNR Am J Neuroradiol. 2000 Jun-Jul;21(6):1011-5. (PMID: 10871004) AJNR Am J Neuroradiol. 2005 May;26(5):1012-21. (PMID: 15891154) Am J Cardiol. 2009 Aug 1;104(3):318-26. (PMID: 19616661) AJNR Am J Neuroradiol. 2007 Jan;28(1):97-103. (PMID: 17213433) J Neurol. 2002 Jan;249(1):43-9. (PMID: 11954867) Minim Invasive Neurosurg. 2006 Oct;49(5):286-90. (PMID: 17163342) Radiology. 2008 Jun;247(3):841-6. (PMID: 18487538) Int J Cardiovasc Imaging. 2013 Oct;29(7):1491-8. (PMID: 23686460) Dis Markers. 2020 Jan 13;2020:8536471. (PMID: 32399089) Radiology. 2012 Feb;262(2):605-12. (PMID: 22143927) Invest Radiol. 2017 Apr;52(4):245-254. (PMID: 27875338) Insights Imaging. 2019 Jan 28;10(1):2. (PMID: 30689062) Eur Radiol. 2011 Aug;21(8):1677-86. (PMID: 21365195) J Neuroradiol. 2014 May;41(2):117-23. (PMID: 23774002) Surg Radiol Anat. 2014 Jul;36(5):455-61. (PMID: 24061702) J Comput Assist Tomogr. 2018 Nov/Dec;42(6):831-839. (PMID: 30052616) Eur Radiol. 2007 Jul;17(7):1738-45. (PMID: 17077978) Prog Cardiovasc Dis. 2021 Mar-Apr;65:55-59. (PMID: 33592207) Phys Med Biol. 2018 Jul 16;63(14):145011. (PMID: 29923839) Ultrason Imaging. 2022 Jan;44(1):25-38. (PMID: 34986724) Biomed Eng Online. 2019 May 28;18(1):66. (PMID: 31138235) Med Image Comput Comput Assist Interv. 2005;8(Pt 2):846-53. (PMID: 16686039) Med Phys. 2019 May;46(5):2157-2168. (PMID: 30810231) Phys Med. 2015 Dec;31(8):1098-1104. (PMID: 26429385) Sensors (Basel). 2021 Nov 12;21(22):. (PMID: 34833602) Echocardiography. 2016 Nov;33(11):1735-1740. (PMID: 27528234) Int J Comput Assist Radiol Surg. 2018 Jul;13(7):967-975. (PMID: 29556905) Clin Radiol. 2013 Jan;68(1):e15-20. (PMID: 23142024) Radiology. 2001 Mar;218(3):799-808. (PMID: 11230659) Med Image Anal. 2010 Dec;14(6):759-69. (PMID: 20605737) Comput Biol Med. 2023 Jan;152:106387. (PMID: 36495750) J Atheroscler Thromb. 2014;21(9):930-40. (PMID: 24834981) Med Image Anal. 2024 Oct;97:103247. (PMID: 38941857) Int J Comput Assist Radiol Surg. 2019 Oct;14(10):1775-1784. (PMID: 31367806) Invest Radiol. 2009 May;44(5):257-64. (PMID: 19550377) IEEE Trans Med Imaging. 2025 Feb 13;PP:. (PMID: 40031818) Sci Rep. 2019 Dec 2;9(1):18109. (PMID: 31792291) Int J Med Inform. 2020 Dec;144:104284. (PMID: 32992136) Exp Ther Med. 2016 May;11(5):1930-1936. (PMID: 27168830) |
| Grant Information: | NRF2021R1F1A1061440 National Research Foundation of Korea |
| Contributed Indexing: | Keywords: Cerebral artery segmentation; Deep learning model; Non-local means algorithm; Subtraction computed tomography angiography |
| Entry Date(s): | Date Created: 20250417 Date Completed: 20250421 Latest Revision: 20250421 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC12006485 |
| DOI: | 10.1038/s41598-025-98098-6 |
| PMID: | 40247104 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!