EUVIMEDEUVIMED entdecken
ValidierungsstudieVergleichsstudieOpen Access · CC BY 4.0

Training and assessing convolutional neural network performance in automatic vascular segmentation using Ga-68 DOTATATE PET/CT

R Parry, K Wright, J W Bellinge, M A Ebert, P Rowshanfarzad, R J Francis, C J Schultz

The International Journal of Cardiovascular Imaging · 05.07.2024 · 40 (9) · 1847-1861

DOI: 10.1007/s10554-024-03171-2 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift The International Journal of Cardiovascular Imaging, online erschienen am 05.07.2024. Verfasst von R Parry und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, The University of Western Australia, Perth, Australia. reece.parry@health.wa.gov.au. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Predictive Value of Tests, Radiopharmaceuticals, Vascular Calcification. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Health, Government of Western Australia, Department of Education, Australian Government, University of Western Australia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To evaluate a convolutional neural network’s performance (nnU-Net) in the assessment of vascular contours, calcification and PET tracer activity using Ga-68 DOTATATE PET/CT. Patients who underwent Ga-68 DOTATATE PET/CT imaging over a 12-month period for neuroendocrine investigation were included. Manual cardiac and aortic segmentations were performed by an experienced observer. Scans were randomly allocated in ratio 64:16:20 for training, validation and testing of the nnU-Net model. PET tracer uptake and calcium scoring were compared between segmentation methods and different observers. 116 patients (53.5% female) with a median age of 64.5 years (range 23–79) were included. There were strong, positive correlations between all segmentations (mostly r > 0.98). There were no significant differences between manual and AI segmentation of SUV mean for global cardiac (mean ± SD 0.71 ± 0.22 vs. 0.71 ± 0.22; mean diff 0.001 ± 0.008, p > 0.05), ascending aorta (mean ± SD 0.44 ± 0.14 vs. 0.44 ± 0.14; mean diff 0.002 ± 0.01, p > 0.05), aortic arch (mean ± SD 0.44 ± 0.10 vs. 0.43 ± 0.10; mean diff 0.008 ± 0.16, p > 0.05) and descending aorta (mean ± SD < 0.001; 0.58 ± 0.12 vs. 0.57 ± 0.12; mean diff 0.01 ± 0.03, p > 0.05) contours. There was excellent agreement between the majority of manual and AI segmentation measures (r ≥ 0.80) and in all vascular contour calcium scores. Compared with the manual segmentation approach, the CNN required a significantly lower workflow time. AI segmentation of vascular contours using nnU-Net resulted in very similar measures of PET tracer uptake and vascular calcification when compared to an experienced observer and significantly reduced workflow time.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Positron Emission Tomography Computed TomographyPredictive Value of TestsRadiopharmaceuticalsVascular CalcificationHumansFemaleMiddle AgedMaleAgedAdultReproducibility of ResultsYoung AdultOrganometallic CompoundsDeep LearningAutomationImage Interpretation, Computer-AssistedObserver VariationRetrospective StudiesAortic DiseasesNeural Networks, Computer

Stichwörter der Autor:innen

Artificial intelligenceAutomatic segmentationCardiovascular inflammationCoronary artery diseaseDeep learningGallium-68 DOTATATE positron emission tomographyNeural network

Substanzen

RadiopharmaceuticalsOrganometallic Compounds

Autor:innen und Institutionen

  • School of Medicine, The University of Western Australia, Perth, Australia. reece.parry@health.wa.gov.au.
  • Department of Cardiology, Royal Perth Hospital, Perth, Australia. reece.parry@health.wa.gov.au.
  • School of Physics, Mathematics and Computing, The University of Western Australia, Crawley, WA, Australia.
  • School of Medicine, The University of Western Australia, Perth, Australia.
  • Department of Cardiology, Royal Perth Hospital, Perth, Australia.
  • Department of Radiation Oncology, Sir Charles Gairdner Hospital, Perth, Australia.

Förderung

  • Department of Health, Government of Western Australia
  • Department of Education, Australian Government
  • University of Western Australia
  • Royal Perth Hospital Medical Research Foundation

Zitieren

APA

Parry, R., Wright, K., Bellinge, J. W., Ebert, M. A., Rowshanfarzad, P., Francis, R. J., & Schultz, C. J. (2024). Training and assessing convolutional neural network performance in automatic vascular segmentation using Ga-68 DOTATATE PET/CT. The International Journal of Cardiovascular Imaging, 40(9), 1847-1861. https://doi.org/10.1007/s10554-024-03171-2

Vancouver

Parry R, Wright K, Bellinge JW, Ebert MA, Rowshanfarzad P, Francis RJ, et al. Training and assessing convolutional neural network performance in automatic vascular segmentation using Ga-68 DOTATATE PET/CT. The International Journal of Cardiovascular Imaging. 2024;40(9):1847-1861. doi:10.1007/s10554-024-03171-2

BibTeX
@article{Parry2024,
  author = {Parry, R and Wright, K and Bellinge, J W and Ebert, M A and Rowshanfarzad, P and Francis, R J and Schultz, C J},
  title = {Training and assessing convolutional neural network performance in automatic vascular segmentation using Ga-68 DOTATATE PET/CT},
  journal = {The International Journal of Cardiovascular Imaging},
  year = {2024},
  volume = {40},
  number = {9},
  pages = {1847--1861},
  doi = {10.1007/s10554-024-03171-2}
}
Kostenlos starten →