Mitosis Extraction in Breast-Cancer Histopathological Whole Slide Images

Vincent Roullier (1) , Olivier Lezoray (1) , Vinh Thong Ta (2) , Abderrahim Elmoataz (1)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique

In this paper, we present a graph-based multi-resolution approach for mitosis extraction in breast cancer histological whole slide images. The proposed segmentation uses a multi-resolution approach which reproduces the slide examination done by a pathologist. Each resolution level is analyzed with a focus of attention resulting from a coarser resolution level analysis. At each resolution level, a spatial refinement by semi-supervised clustering is performed to obtain more accurate segmen- tation around edges. The proposed segmentation is fully unsupervised by using domain specific knowledge.

Domaines: Traitement des images [eess.IV]

Vincent Roullier, Olivier Lezoray, Vinh Thong Ta, Abderrahim Elmoataz. Mitosis Extraction in Breast-Cancer Histopathological Whole Slide Images. International Symposium on Visual Computing, 2010, Las Vegas, Nevada, United States. pp.539-548, ⟨10.1007/978-3-642-17289-2_52⟩. ⟨hal-00708980⟩