Clinical feasibility of deep learning based synthetic contrast enhanced abdominal CT in patients undergoing non enhanced CT scans.
Humans
Deep Learning
Tomography, X-Ray Computed
/ methods
Contrast Media
/ chemistry
Feasibility Studies
Female
Male
Middle Aged
Aged
Retrospective Studies
Adult
Radiographic Image Interpretation, Computer-Assisted
/ methods
Aged, 80 and over
Radiography, Abdominal
/ methods
Abdomen
/ diagnostic imaging
Abdomen
Deep learning
Diagnosis
Tomography
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
31 Jul 2024
31 Jul 2024
Historique:
received:
13
03
2024
accepted:
25
07
2024
medline:
1
8
2024
pubmed:
1
8
2024
entrez:
31
7
2024
Statut:
epublish
Résumé
Our objective was to develop and evaluate the clinical feasibility of deep-learning-based synthetic contrast-enhanced computed tomography (DL-SynCCT) in patients designated for nonenhanced CT (NECT). We proposed a weakly supervised learning with the utilization of virtual non-contrast CT (VNC) for the development of DL-SynCCT. Training and internal validations were performed with 2202 pairs of retrospectively collected contrast-enhanced CT (CECT) images with the corresponding VNC images acquired from dual-energy CT. Clinical validation was performed using an external validation set including 398 patients designated for true nonenhanced CT (NECT), from multiple vendors at three institutes. Detection of lesions was performed by three radiologists with only NECT in the first session and an additionally provided DL-SynCCT in the second session. The mean peak signal-to-noise ratio (PSNR) and structural similarity index map (SSIM) of the DL-SynCCT compared to CECT were 43.25 ± 0.41 and 0.92 ± 0.01, respectively. With DL-SynCCT, the pooled sensitivity for lesion detection (72.0% to 76.4%, P < 0.001) and level of diagnostic confidence (3.0 to 3.6, P < 0.001) significantly increased. In conclusion, DL-SynCCT generated by weakly supervised learning showed significant benefit in terms of sensitivity in detecting abnormal findings when added to NECT in patients designated for nonenhanced CT scans.
Identifiants
pubmed: 39085456
doi: 10.1038/s41598-024-68705-z
pii: 10.1038/s41598-024-68705-z
doi:
Substances chimiques
Contrast Media
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
17635Subventions
Organisme : National Research Foundation of Korea
ID : NRF-2020R1A2C1101215
Organisme : SNUH Research Fund
ID : 04-2023-0590
Informations de copyright
© 2024. The Author(s).
Références
Cao, C. F. et al. CT Scans and cancer risks: A systematic review and dose-response meta-analysis. BMC Cancer 22, 1238. https://doi.org/10.1186/s12885-022-10310-2 (2022).
doi: 10.1186/s12885-022-10310-2
pubmed: 36451138
pmcid: 9710150
Schockel, L. et al. Developments in X-Ray contrast media and the potential impact on computed tomography. Invest. Radiol. 55, 592–597. https://doi.org/10.1097/RLI.0000000000000696 (2020).
doi: 10.1097/RLI.0000000000000696
pubmed: 32701620
Bae, K. T. Intravenous contrast medium administration and scan timing at CT: Considerations and approaches. Radiology 256, 32–61. https://doi.org/10.1148/radiol.10090908 (2010).
doi: 10.1148/radiol.10090908
pubmed: 20574084
Kaiser, S., Finnbogason, T., Jorulf, H. K., Soderman, E. & Frenckner, B. Suspected appendicitis in children: Diagnosis with contrast-enhanced versus nonenhanced Helical CT. Radiology 231, 427–433. https://doi.org/10.1148/radiol.2312030240 (2004).
doi: 10.1148/radiol.2312030240
pubmed: 15031433
Faucon, A. L., Bobrie, G. & Clement, O. Nephrotoxicity of iodinated contrast media: From pathophysiology to prevention strategies. Eur. J. Radiol. 116, 231–241. https://doi.org/10.1016/j.ejrad.2019.03.008 (2019).
doi: 10.1016/j.ejrad.2019.03.008
pubmed: 31054788
Kang, H. R., Jeong, J. & Brockow, K. Diagnosis and prevention of hypersensitivity reactions to iodinated contrast media. Allergy Asthma Immunol. Res. 14, 348–360. https://doi.org/10.4168/aair.2022.14.4.348 (2022).
doi: 10.4168/aair.2022.14.4.348
pubmed: 35837820
pmcid: 9293596
Schwab, S. J. et al. Contrast nephrotoxicity: A randomized controlled trial of a nonionic and an ionic radiographic contrast agent. N. Engl. J. Med. 320, 149–153. https://doi.org/10.1056/nejm198901193200304 (1989).
doi: 10.1056/nejm198901193200304
pubmed: 2643042
Coresh, J. et al. Prevalence of chronic kidney disease in the United States. JAMA 298, 2038–2047. https://doi.org/10.1001/jama.298.17.2038 (2007).
doi: 10.1001/jama.298.17.2038
pubmed: 17986697
Schieppati, A. & Remuzzi, G. Chronic renal diseases as a public health problem: epidemiology, social, and economic implications. Kidney Int. Suppl. 68, S7–S10. https://doi.org/10.1111/j.1523-1755.2005.09801.x (2005).
doi: 10.1111/j.1523-1755.2005.09801.x
Dona, I. et al. Hypersensitivity reactions to multiple iodinated contrast media. Front Pharmacol 11, 575437. https://doi.org/10.3389/fphar.2020.575437 (2020).
doi: 10.3389/fphar.2020.575437
pubmed: 33071787
pmcid: 7538657
Kelly, J., Raptopoulos, V., Davidoff, A., Waite, R. & Norton, P. The value of non-contrast-enhanced CT in blunt abdominal trauma. AJR Am. J. Roentgenol. 152, 41–48. https://doi.org/10.2214/ajr.152.1.41 (1989).
doi: 10.2214/ajr.152.1.41
pubmed: 2783289
Lamoureux, C., Weber, S., Hanna, T., Grabiel, A. J. & Clark, R. H. Effect of intravenous contrast for CT abdomen and pelvis on detection of urgent and non-urgent pathology: can repeat CT within 72 hours be avoided?. Emerg. Radiol. 26, 601–608. https://doi.org/10.1007/s10140-019-01704-0 (2019).
doi: 10.1007/s10140-019-01704-0
pubmed: 31332644
Miyakawa, K. et al. Evaluation of non-contrast-enhanced CT in blunt abdominal trauma. Nippon Igaku Hoshasen Gakkai Zasshi 52, 300–307 (1992).
pubmed: 1579426
Semaan, H., Bazerbashi, M. F., Siesel, G., Aldinger, P. & Obri, T. Diagnostic accuracy of non-contrast abdominal CT scans performed as follow-up for patients with an established cancer diagnosis: a retrospective study. Acta Oncol. 57, 426–430. https://doi.org/10.1080/0284186x.2017.1360512 (2018).
doi: 10.1080/0284186x.2017.1360512
pubmed: 28766397
Gong, E., Pauly, J. M., Wintermark, M. & Zaharchuk, G. Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J. Magn. Reson. Imaging 48, 330–340. https://doi.org/10.1002/jmri.25970 (2018).
doi: 10.1002/jmri.25970
pubmed: 29437269
Seo, M. et al. in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) 3972–3981 (2021).
Chun, J. et al. Synthetic contrast-enhanced computed tomography generation using a deep convolutional neural network for cardiac substructure delineation in breast cancer radiation therapy: A feasibility study. Radiat. Oncol. 17, 83. https://doi.org/10.1186/s13014-022-02051-0 (2022).
doi: 10.1186/s13014-022-02051-0
pubmed: 35459221
pmcid: 9034542
Kleesiek, J. et al. Can virtual contrast enhancement in brain mri replace gadolinium?: A feasibility study. Invest. Radiol. 54, 653–660. https://doi.org/10.1097/rli.0000000000000583 (2019).
doi: 10.1097/rli.0000000000000583
pubmed: 31261293
Kim, S. W. et al. The feasibility of deep learning-based synthetic contrast-enhanced CT from nonenhanced CT in emergency department patients with acute abdominal pain. Sci. Rep. 11, 20390. https://doi.org/10.1038/s41598-021-99896-4 (2021).
doi: 10.1038/s41598-021-99896-4
pubmed: 34650183
pmcid: 8516935
Sauter, A. P. et al. Dual-layer spectral computed tomography: Virtual non-contrast in comparison to true non-contrast images. Eur. J. Radiol. 104, 108–114. https://doi.org/10.1016/j.ejrad.2018.05.007 (2018).
doi: 10.1016/j.ejrad.2018.05.007
pubmed: 29857855
Toepker, M. et al. Virtual non-contrast in second-generation, dual-energy computed tomography: Reliability of attenuation values. Eur. J. Radiol. 81, e398-405. https://doi.org/10.1016/j.ejrad.2011.12.011 (2012).
doi: 10.1016/j.ejrad.2011.12.011
pubmed: 22236702
Wang, T. et al. A review on medical imaging synthesis using deep learning and its clinical applications. J. Appl. Clin. Med. Phys. 22, 11–36. https://doi.org/10.1002/acm2.13121 (2021).
doi: 10.1002/acm2.13121
pubmed: 33305538
Florkow, M. C. et al. Deep learning-based MR-to-CT synthesis: The influence of varying gradient echo-based MR images as input channels. Magn. Reson. Med. 83, 1429–1441. https://doi.org/10.1002/mrm.28008 (2020).
doi: 10.1002/mrm.28008
pubmed: 31593328
Li, W. et al. Magnetic resonance image (MRI) synthesis from brain computed tomography (CT) images based on deep learning methods for magnetic resonance (MR)-guided radiotherapy. Quant. Imaging Med. Surg. 10, 1223–1236. https://doi.org/10.21037/qims-19-885 (2020).
doi: 10.21037/qims-19-885
pubmed: 32550132
pmcid: 7276358
Pasquini, L. et al. Synthetic post-contrast imaging through artificial intelligence: Clinical applications of virtual and augmented contrast media. Pharmaceutics 14, 2378. https://doi.org/10.3390/pharmaceutics14112378 (2022).
doi: 10.3390/pharmaceutics14112378
pubmed: 36365197
pmcid: 9695136
Choi, J. W. et al. Generating synthetic contrast enhancement from non-contrast chest computed tomography using a generative adversarial network. Sci. Rep. 11, 20403. https://doi.org/10.1038/s41598-021-00058-3 (2021).
doi: 10.1038/s41598-021-00058-3
pubmed: 34650076
pmcid: 8516920
Sung, H. et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 71, 209–249. https://doi.org/10.3322/caac.21660 (2021).
doi: 10.3322/caac.21660
pubmed: 33538338
Naeger, D. M. et al. Correctly using sensitivity, specificity, and predictive values in clinical practice: how to avoid three common pitfalls. AJR Am. J. Roentgenol. 200, W566-570. https://doi.org/10.2214/AJR.12.9888 (2013).
doi: 10.2214/AJR.12.9888
pubmed: 23701086
Ronneberger, O., Fischer, P. & Brox, T. 2015 In: eds N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (eds). Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 (Springer International Publishing, 2015).