Unsupervised clustering algorithms improve the reproducibility of dynamic contrast-enhanced magnetic resonance imaging pulmonary perfusion quantification in muco-obstructive lung diseases

Marilisa Konietzke; Simon M F Triphan; Monika Eichinger; Sebastian Bossert; Hartmut Heller; Sabine Wege; Ralf Eberhardt; Michael U Puderbach; Hans-Ulrich Kauczor; Gudula Heußel; Claus P Heußel; Frank Risse; Mark O Wielpütz

doi:10.3389/fmed.2022.1022981

Unsupervised clustering algorithms improve the reproducibility of dynamic contrast-enhanced magnetic resonance imaging pulmonary perfusion quantification in muco-obstructive lung diseases

Front Med (Lausanne). 2022 Oct 24:9:1022981. doi: 10.3389/fmed.2022.1022981. eCollection 2022.

Authors

Marilisa Konietzke^{1

2

3}, Simon M F Triphan^{2

3

4}, Monika Eichinger^{2

3

4}, Sebastian Bossert¹, Hartmut Heller¹, Sabine Wege⁵, Ralf Eberhardt^{3

5}, Michael U Puderbach^{2

3

4

6}, Hans-Ulrich Kauczor^{2

3

4}, Gudula Heußel^{2

3

4}, Claus P Heußel^{2

3

4}, Frank Risse¹, Mark O Wielpütz^{2

3

4}

Affiliations

¹ Boehringer Ingelheim Pharma GmbH and Co. KG, Biberach an der Riß, Germany.
² Department of Diagnostic and Interventional Radiology, Subdivision of Pulmonary Imaging, University Hospital of Heidelberg, Heidelberg, Germany.
³ Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.
⁴ Department of Diagnostic and Interventional Radiology With Nuclear Medicine, Thoraxklinik at the University Hospital of Heidelberg, Heidelberg, Germany.
⁵ Department of Pulmonology and Respiratory Medicine, Thoraxklinik at the University Hospital of Heidelberg, Heidelberg, Germany.
⁶ Department of Diagnostic and Interventional Radiology, Hufeland Hospital, Bad Langensalza, Germany.

Abstract

Background: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows the assessment of pulmonary perfusion, which may play a key role in the development of muco-obstructive lung disease. One problem with quantifying pulmonary perfusion is the high variability of metrics. Quantifying the extent of abnormalities using unsupervised clustering algorithms in residue function maps leads to intrinsic normalization and could reduce variability.

Purpose: We investigated the reproducibility of perfusion defects in percent (QDP) in clinically stable patients with cystic fibrosis (CF) and chronic obstructive pulmonary disease (COPD).

Methods: 15 CF (29.3 ± 9.3y, FEV1%predicted = 66.6 ± 15.8%) and 20 COPD (66.5 ± 8.9y, FEV1%predicted = 42.0 ± 13.3%) patients underwent DCE-MRI twice 1 month apart. QDP, pulmonary blood flow (PBF), and pulmonary blood volume (PBV) were computed from residue function maps using an in-house quantification pipeline. A previously validated MRI perfusion score was visually assessed by an expert reader.

Results: Overall, mean QDP, PBF, and PBV did not change within 1 month, except for QDP in COPD (p < 0.05). We observed smaller limits of agreement (± 1.96 SD) related to the median for QDP (CF: ± 38%, COPD: ± 37%) compared to PBF (CF: ± 89%, COPD: ± 55%) and PBV (CF: ± 55%, COPD: ± 51%). QDP correlated moderately with the MRI perfusion score in CF (r = 0.46, p < 0.05) and COPD (r = 0.66, p < 0.001). PBF and PBV correlated poorly with the MRI perfusion score in CF (r =-0.29, p = 0.132 and r =-0.35, p = 0.067, respectively) and moderately in COPD (r =-0.57 and r =-0.57, p < 0.001, respectively).

Conclusion: In patients with muco-obstructive lung diseases, QDP was more robust and showed a higher correlation with the MRI perfusion score compared to the traditionally used perfusion metrics PBF and PBV.

Keywords: chronic obstructive pulmonary disease (COPD); contrast agent lung perfusion; cystic fibrosis (CF); functional imaging; muco-obstructive lung disease.