Filtering, segmentation and region classification by hyperspectral mathematical morphology of DCE-MRI series for angiogenesis imaging

Guillaume Noyel (1) , Jesus Angulo (1) , Dominique Jeulin (1) , D. Balvay (2, 3) , C. A. Cuénod (2, 3)

1 CMM - Centre de Morphologie Mathématique
2 LRI-EA4062
3 Service de radiologie (AP-HP - HEGP)

Segmenting dynamic contrast enhanced-MRI series of small animal, which are intrinsically noisy and low contrasted images with low resolution, is the aim of this paper. To do this, a segmentation method taking into account the temporal (spectral) and spatial information is presented on several series. The idea is to start from a temporal classification, and to build a probability density function of contours conditionally to this classification. Then, this function is segmented to find potentially tumorous areas. The method is presented on several series after a range normalization histogram in order to compare the series.

Mots clés: angiogenesis imaging; segmentation; Multivariate images; hyperspectral images; probability; tumours; biomedical MRI; blood vessels; cancer; edge detection; filtering theory; image classification; image enhancement; image segmentation; mathematical morphology; medical image processing; Dynamic Contrast Enhanced MRI

Domaines: Imagerie médicale; Traitement d'image; Cancer; Traitement des images [eess.IV]; Imagerie; Mathématiques appliquées

Guillaume Noyel, Jesus Angulo, Dominique Jeulin, D. Balvay, C. A. Cuénod. Filtering, segmentation and region classification by hyperspectral mathematical morphology of DCE-MRI series for angiogenesis imaging. 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008, May 2008, Paris, France. pp.1517-1520, ⟨10.1109/ISBI.2008.4541297⟩. ⟨hal-00834030v1⟩