Analysis of lymph node tumor features in PET/CT for segmentation

Diana Lucia Farfan Cabrera (1, 2) , Eloïse Grossiord (3) , Nicolas Gogin (2) , Dimitri Papathanassiou (1, 4) , Nicolas Passat (1)

1 CRESTIC - Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804
2 GE Healthcare - General Electric Medical Systems [Buc]
3 IMT - Institut de Mathématiques de Toulouse UMR5219
4 Institut Jean Godinot [Reims]

In the context of breast cancer, the detection and segmentation of cancerous lymph nodes in PET/CT imaging is of crucial importance, in particular for staging issues. In order to guide such image analysis procedures, some dedicated descriptors can be considered, especially region-based features. In this article, we focus on the issue of choosing which features should be embedded for lymph node tumor segmentation from PET/CT. This study is divided into two steps. We first investigate the relevance of various features by considering a Random Forest framework. In a second time, we validate the expected relevance of the best scored features by involving them in a U-Net segmentation architecture. We handle the region-based definition of these features thanks to a hierarchical modeling of the PET images. This analysis emphasizes a set of features that can significantly improve / guide the segmentation of lymph nodes in PET/CT.

Mots clés: U-Net; component-tree; region-based features; tumor segmentation; lymph nodes; breast cancer; PET/CT; feature analysis; Random Forest

Domaines: Informatique [cs]; Imagerie médicale; Traitement des images [eess.IV]; Intelligence artificielle [cs.AI]

Diana Lucia Farfan Cabrera, Eloïse Grossiord, Nicolas Gogin, Dimitri Papathanassiou, Nicolas Passat. Analysis of lymph node tumor features in PET/CT for segmentation. International Symposium on Biomedical Imaging (ISBI), 2021, Nice, France. pp.588-592, ⟨10.1109/ISBI48211.2021.9433791⟩. ⟨hal-03104417⟩