Zugriffsnummer 52049
Dokumenttyp Zeitschriftenartikel Open Access Hybrid
Peer Review mit Peer Review
Sprache Englisch
Titel Simulation of acquisition shifts in T2 weighted fluid-attenuated inversion recovery magnetic resonance images to stress test artificial intelligence segmentation networks
Autor(in); Institution
Posselt, Christiane; University of Applied Sciences, Faculty of Electrical and Industrial Engineering, Landshut, GERMANY
Avci, Mehmet Yigit; deepc GmbH, Munich, GERMANY
Yigitsoy, Mehmet; deepc GmbH, Munich, GERMANY
Schünke, Patrick; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin
Kolbitsch, Christoph; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin
Schäffter, Tobias; 8.1, Biomedizinische Magnetresonanz, PTB-Berlin; Technical University of Berlin, Department of Medical Engineering, Berlin, GERMANY
Remmele, Stefanie; University of Applied Sciences, Faculty of Electrical and Industrial Engineering, Landshut, GERMANY
Quelle/Jahr Journal of Medical Imaging: 11 (2024), 2, 024013-1 - 024013-17
Artikelnummer 024013
ISSN 2329-4310 (online)
DOI
Verlag Bellingham, Wash.: SPIE
Freie Schlagworte T2w fluid attenuated inversion recovery ; artificial intelligence validation ; magnetic resonance image simulation ; magnetic resonance imaging sequence ; multiple sclerosis lesion segmentation
Zusammenfassung Purpose: To provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2 weighted (T2w) fluid-attenuated inversion recovery magnetic resonance imaging protocols. Approach: The approach simulates "acquisition shift derivatives" of MR images based on MR signal equations. Experiments comprise the validation of the simulated images by real MR scans and example stress tests on state-of-the-art multiple sclerosis lesion segmentation networks to explore a generic model function to describe the F1 score in dependence of the contrast-affecting sequence parameters echo time (TE) and inversion time (TI). Results: The differences between real and simulated images range up to 19% in gray and white matter for extreme parameter settings. For the segmentation networks under test, the F1 score dependency on TE and TI can be well described by quadratic model functions (R02 >0.9). The coefficients of the model functions indicate that changes of TE have more influence on the model performance than TI. Conclusions: We show that these deviations are in the range of values as may be caused by erroneous or individual differences in relaxation times as described by literature. The coefficients of the F1 model function allow for a quantitative comparison of the influences of TE and TI. Limitations arise mainly from tissues with a low baseline signal (like cerebrospinal fluid) and when the protocol contains contrast-affecting measures that cannot be modeled due to missing information in the DICOM header.
Kostenfreier Zugang Open Access Hybrid
Rechteinformation CC BY 4.0 ; Creative Commons Attribution 4.0 License

Zitierung

Posselt, C., Avci, M. Y., Yigitsoy, M., Schünke, P., Kolbitsch, C., Schäffter, T., & Remmele, S. (2024). Simulation of acquisition shifts in T2 weighted fluid-attenuated inversion recovery magnetic resonance images to stress test artificial intelligence segmentation networks. Journal of Medical Imaging, 11(2), 024013-1–024013-17. https://doi.org/10.1117/1.JMI.11.2.024013

Exportieren

RIS BibTeX

PTB-Publica Menü

Sprache wechseln: uk flag
Erweiterte Suche