Self-configuring nnU-net pipeline enables fully automatic infarct segmentation in late enhancement MRI after myocardial infarction

Please always quote using this URN: urn:nbn:de:bvb:20-opus-323418
  • Purpose To fully automatically derive quantitative parameters from late gadolinium enhancement (LGE) cardiac MR (CMR) in patients with myocardial infarction and to investigate if phase sensitive or magnitude reconstructions or a combination of both results in best segmentation accuracy. Methods In this retrospective single center study, a convolutional neural network with a U-Net architecture with a self-configuring framework (“nnU-net”) was trained for segmentation of left ventricular myocardium and infarct zone in LGE-CMR. A database ofPurpose To fully automatically derive quantitative parameters from late gadolinium enhancement (LGE) cardiac MR (CMR) in patients with myocardial infarction and to investigate if phase sensitive or magnitude reconstructions or a combination of both results in best segmentation accuracy. Methods In this retrospective single center study, a convolutional neural network with a U-Net architecture with a self-configuring framework (“nnU-net”) was trained for segmentation of left ventricular myocardium and infarct zone in LGE-CMR. A database of 170 examinations from 78 patients with history of myocardial infarction was assembled. Separate fitting of the model was performed, using phase sensitive inversion recovery, the magnitude reconstruction or both contrasts as input channels. Manual labelling served as ground truth. In a subset of 10 patients, the performance of the trained models was evaluated and quantitatively compared by determination of the Sørensen-Dice similarity coefficient (DSC) and volumes of the infarct zone compared with the manual ground truth using Pearson’s r correlation and Bland-Altman analysis. Results The model achieved high similarity coefficients for myocardium and scar tissue. No significant difference was observed between using PSIR, magnitude reconstruction or both contrasts as input (PSIR and MAG; mean DSC: 0.83 ± 0.03 for myocardium and 0.72 ± 0.08 for scars). A strong correlation for volumes of infarct zone was observed between manual and model-based approach (r = 0.96), with a significant underestimation of the volumes obtained from the neural network. Conclusion The self-configuring nnU-net achieves predictions with strong agreement compared to manual segmentation, proving the potential as a promising tool to provide fully automatic quantitative evaluation of LGE-CMR.show moreshow less
Metadaten
Author: Julius F. Heidenreich, Tobias Gassenmaier, Markus J. AnkenbrandORCiD, Thorsten A. Bley, Tobias Wech
URN:urn:nbn:de:bvb:20-opus-323418
Document Type:Preprint
Faculties:Medizinische Fakultät / Institut für diagnostische und interventionelle Radiologie (Institut für Röntgendiagnostik)
Fakultät für Biologie / Center for Computational and Theoretical Biology
Medizinische Fakultät / Deutsches Zentrum für Herzinsuffizienz (DZHI)
Language:English
Year of Completion:2021
Edition:accepted version
Source:European Journal of Radiologyy (2021) 141:109817. https://doi.org/10.1016/j.ejrad.2021.109817
URL:https://doi.org/10.1016/j.ejrad.2021.109817
DOI:https://doi.org/10.1016/j.ejrad.2021.109817
Dewey Decimal Classification:6 Technik, Medizin, angewandte Wissenschaften / 61 Medizin und Gesundheit / 610 Medizin und Gesundheit
Tag:CMR; Deep learning; Myocardial infarction; Scar; Segmentation; nnU-net
Release Date:2023/08/11
Licence (German):License LogoCC BY-NC-ND: Creative-Commons-Lizenz: Namensnennung, Nicht kommerziell, Keine Bearbeitungen 4.0 International