Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis

Mark Lachmann; Elena Rippen; Daniel Rueckert; Tibor Schuster; Erion Xhepa; Moritz von Scheidt; Costanza Pellegrini; Teresa Trenkwalder; Tobias Rheude; Anja Stundl; Ruth Thalmann; Gerhard Harmsen; Shinsuke Yuasa; Heribert Schunkert; Adnan Kastrati; Michael Joner; Christian Kupatt; Karl Ludwig Laugwitz

doi:10.1093/ehjdh/ztac004

Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis

Eur Heart J Digit Health. 2022 Apr 22;3(2):153-168. doi: 10.1093/ehjdh/ztac004. eCollection 2022 Jun.

Authors

Mark Lachmann¹, Elena Rippen¹, Daniel Rueckert^{2

3}, Tibor Schuster⁴, Erion Xhepa^{5

6}, Moritz von Scheidt^{5

6}, Costanza Pellegrini⁵, Teresa Trenkwalder⁵, Tobias Rheude⁵, Anja Stundl¹, Ruth Thalmann¹, Gerhard Harmsen⁷, Shinsuke Yuasa⁸, Heribert Schunkert^{5

6}, Adnan Kastrati^{5

6}, Michael Joner^{5

6}, Christian Kupatt^{1

6}, Karl Ludwig Laugwitz^{1

6}

Affiliations

¹ First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich, Ismaninger Straße 22, 81675 Munich, Germany.
² Institute for AI and Informatics in Medicine, Faculty of Informatics and Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
³ Department of Computing, Imperial College London, London, UK.
⁴ Department of Family Medicine, McGill University, Montreal, Quebec, Canada.
⁵ Department of Cardiology, German Heart Centre Munich, Technical University of Munich, Munich, Germany.
⁶ DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance, Munich, Germany.
⁷ Department of Physics, University of Johannesburg, Auckland Park, South Africa.
⁸ Department of Cardiology, Keio University School of Medicine, Minato, Tokyo, Japan.

Abstract

Aims: Hypothesizing that aortic outflow velocity profiles contain more valuable information about aortic valve obstruction and left ventricular contractility than can be captured by the human eye, features of the complex geometry of Doppler tracings from patients with severe aortic stenosis (AS) were extracted by a convolutional neural network (CNN).

Methods and results: After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Among 366 eligible patients [age: 79.8 ± 6.77 years; 146 (39.9%) women] with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR), good quality Doppler tracings from 101 patients were analysed. The convolutional part of the pre-trained VGG-16 model in conjunction with principal component analysis and k-means clustering distinguished two shapes of aortic outflow velocity profiles. Kaplan-Meier analysis revealed that mortality in patients from Cluster 2 (n = 40, 39.6%) was significantly increased [hazard ratio (HR) for 2-year mortality: 3; 95% confidence interval (CI): 1-8.9]. Apart from reduced cardiac output and mean aortic valve gradient, patients from Cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function, and right atrial enlargement. After training an extreme gradient boosting algorithm on these 101 patients, validation on the remaining 265 patients confirmed that patients assigned to Cluster 2 show increased mortality (HR for 2-year mortality: 2.6; 95% CI: 1.4-5.1, P-value: 0.004).

Conclusion: Transfer learning enables sophisticated pattern recognition even in clinical data sets of limited size. Importantly, it is the left ventricular compensation capacity in the face of increased afterload, and not so much the actual obstruction of the aortic valve, that determines fate after TAVR.

Keywords: Aortic outflow velocity profile; Convolutional neural network; Severe aortic stenosis; Transcatheter aortic valve replacement; Transfer learning.