Classification of endomicroscopic images of the lung based on random subwindows and extra-trees

Chesner Désir (1) , Caroline Petitjean (1) , Laurent Heutte (1) , Mathieu Salaün (1) , Luc Thiberville (1)

1 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes

Recently, the in-vivo imaging of pulmonary alveoli was made possible thanks to confocal microscopy. For these images, we wish to aid the clinician by developing a computeraided diagnosis system, able to discriminate between healthy and pathological subjects. The lack of expertise currently available on these images has first led us to choose a generic approach, based on pixel-value description of randomly extracted subwindows and decision tree ensemble for classification (extra-trees). In order to deal with the great complexity of our images, we adapt this method by introducing a texture-based description of the subwindows, based on Local Binary Patterns (LBP). We show through our experimental protocol that this adaptation is a promising way to classify FCFM images. In addition, we introduce a rejection mechanism on the classifier output to prevent non detection errors.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Chesner Désir, Caroline Petitjean, Laurent Heutte, Mathieu Salaün, Luc Thiberville. Classification of endomicroscopic images of the lung based on random subwindows and extra-trees. IEEE Transactions on Biomedical Engineering, 2012, Volume 59, (Issue 9), pp. 2677- 2683. ⟨10.1109/TBME.2012.2204747⟩. ⟨hal-00796593⟩