Multivariate mathematical morphology for DCE-MRI image analysis in angiogenesis studies

Guillaume Noyel (1) , Jesus Angulo (1) , Dominique Jeulin (1) , Daniel Balvay (2) , Charles-André Cuenod (2)

1 CMM - Centre de Morphologie Mathématique
2 PARCC - UMR-S U970 - Paris-Centre de Recherche Cardiovasculaire

We propose a new computer aided detection framework for tumours acquired on DCE-MRI (Dynamic Contrast Enhanced Magnetic Resonance Imaging) series on small animals. In this approach we consider DCE-MRI series as multivariate images. A full multivariate segmentation method based on dimensionality reduction, noise filtering, supervised classification and stochastic watershed is explained and tested on several data sets. The two main key-points introduced in this paper are noise reduction preserving contours and spatio temporal segmentation by stochastic watershed. Noise reduction is performed in a special way that selects factorial axes of Factor Correspondence Analysis in order to preserves contours. Then a spatio-temporal approach based on stochastic watershed is used to segment tumours. The results obtained are in accordance with the diagnosis of the medical doctors.

Mots clés: DCE-MRI series; multivariate Mathematical Morphology; segmentation; tumours; medical imaging; Mathematical Morphology; stochastic watershed; classification; cancer; hyperspectral Mathematical Morphology

Domaines: Algorithme et structure de données [cs.DS]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Imagerie médicale; Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]; Cancer; Imagerie

Guillaume Noyel, Jesus Angulo, Dominique Jeulin, Daniel Balvay, Charles-André Cuenod. Multivariate mathematical morphology for DCE-MRI image analysis in angiogenesis studies. Image Analysis & Stereology, 2015, 34, pp.1-25. ⟨10.5566/ias.1109⟩. ⟨hal-01152401v1⟩