Spatial Reasoning Loss for Weakly Supervised Segmentation of Skin Histological Images

Mateus Sangalli (1, 2) , Santiago Velasco-Forero (1) , José Márcio Martins da Cruz (1) , Virginie Flouret (3) , Charlène Gayrard (3) , Thérèse Baldeweck (3) , Etienne Decencière (1)

1 CMM - Centre de Morphologie Mathématique
2 ARMINES
3 L’Oréal Recherche & Innovation

Biological images often follow some kind of geometrical structure. For example, histological images of reconstructed human skin follow a structural order with the stratum corneum as the outer layer and the living epidermis just below it. In this paper such spatial relationships are leveraged to define a loss function that penalizes structures that do not respect the given pattern as a form of weak supervision. The proposed loss function is based on fuzzy ontological spatial reasoning and morphological operators. The model is tested in a segmentation task on skin images, where a small number of labeled images and a large number of unlabeled ones are available. The proposed method leverages information in unlabeled images to improve segmentation results, compared with training only on the labeled data.

Mots clés: weak supervision; mathematical morphology; image segmentation; spatial reasoning

Domaines: Machine Learning [stat.ML]

Mateus Sangalli, Santiago Velasco-Forero, José Márcio Martins da Cruz, Virginie Flouret, Charlène Gayrard, et al.. Spatial Reasoning Loss for Weakly Supervised Segmentation of Skin Histological Images. 21st IEEE International Symposium on Biomedical Imaging, The IEEE Signal Processing Society and the IEEE Engineering in Medicine and Biology Society, May 2024, Athens, Greece. ⟨hal-04485439⟩