Pathological Cluster Identification by Unsupervised Analysis in 3,822 UK Biobank Cardiac MRIs

Qiao Zheng (1) , Hervé Delingette (1) , Kenneth Fung (2) , Steffen E Petersen (2, 3) , Nicholas Ayache (1)

1 EPIONE - E-Patient : Images, données & mOdèles pour la médeciNe numériquE
2 William Harvey Research Institute, Barts and the London Medical School
3 Barts Health NHS Trust [London, UK]

We perform unsupervised analysis of image-derived shape and motion features extracted from 3,822 cardiac Magnetic resonance imaging (MRIs) of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 feature values characterizing both the cardiac shape and motion. Second, a feature selection is performed to remove highly correlated feature pairs. Third, clustering is carried out using a Gaussian mixture model on the selected features. After analysis, we identify 2 small clusters that probably correspond to 2 pathological categories. Further confirmation using a trained classification model and dimensionality reduction tools is carried out to support this finding. Moreover, we examine the differences between the other large clusters and compare our measures with the ground truth.

Mots clés: Cluster analysis; Gaussian mixture model; Cine MRI; Cardiac pathology; Feature extraction; UK Biobank; Cardiac motion

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Imagerie médicale; Apprentissage [cs.LG]; Traitement des images [eess.IV]

Qiao Zheng, Hervé Delingette, Kenneth Fung, Steffen E Petersen, Nicholas Ayache. Pathological Cluster Identification by Unsupervised Analysis in 3,822 UK Biobank Cardiac MRIs. Frontiers in Cardiovascular Medicine, 2020, 7, pp.164. ⟨10.3389/fcvm.2020.539788⟩. ⟨hal-02043380⟩