Alain Rakotomamonjy1, Caroline Petitjean2, Mathieu Salaün3, Luc Thiberville3. 1. Laboration Informatique, Traitement de l'Information et Systèmes EA4108, University of Rouen, Avenue de l'université, 76800 Saint Etienne du Rouvray, France. Electronic address: alain.rakotomamonjy@insa-rouen.fr. 2. Laboration Informatique, Traitement de l'Information et Systèmes EA4108, University of Rouen, Avenue de l'université, 76800 Saint Etienne du Rouvray, France. 3. Clinique Pneumologique, Centre Hospitalier Universitaire de Rouen, 1 rue de Germont, 76031 Rouen Cedex, France.
Abstract
OBJECTIVE: To assess the feasibility of lung cancer diagnosis using fibered confocal fluorescence microscopy (FCFM) imaging technique and scattering features for pattern recognition. METHODS: FCFM imaging technique is a new medical imaging technique for which interest has yet to be established for diagnosis. This paper addresses the problem of lung cancer detection using FCFM images and, as a first contribution, assesses the feasibility of computer-aided diagnosis through these images. Towards this aim, we have built a pattern recognition scheme which involves a feature extraction stage and a classification stage. The second contribution relies on the features used for discrimination. Indeed, we have employed the so-called scattering transform for extracting discriminative features, which are robust to small deformations in the images. We have also compared and combined these features with classical yet powerful features like local binary patterns (LBP) and their variants denoted as local quinary patterns (LQP). RESULTS: We show that scattering features yielded to better recognition performances than classical features like LBP and their LQP variants for the FCFM image classification problems. Another finding is that LBP-based and scattering-based features provide complementary discriminative information and, in some situations, we empirically establish that performance can be improved when jointly using LBP, LQP and scattering features. CONCLUSIONS: In this work we analyze the joint capability of FCFM images and scattering features for lung cancer diagnosis. The proposed method achieves a good recognition rate for such a diagnosis problem. It also performs well when used in conjunction with other features for other classical medical imaging classification problems.
OBJECTIVE: To assess the feasibility of lung cancer diagnosis using fibered confocal fluorescence microscopy (FCFM) imaging technique and scattering features for pattern recognition. METHODS: FCFM imaging technique is a new medical imaging technique for which interest has yet to be established for diagnosis. This paper addresses the problem of lung cancer detection using FCFM images and, as a first contribution, assesses the feasibility of computer-aided diagnosis through these images. Towards this aim, we have built a pattern recognition scheme which involves a feature extraction stage and a classification stage. The second contribution relies on the features used for discrimination. Indeed, we have employed the so-called scattering transform for extracting discriminative features, which are robust to small deformations in the images. We have also compared and combined these features with classical yet powerful features like local binary patterns (LBP) and their variants denoted as local quinary patterns (LQP). RESULTS: We show that scattering features yielded to better recognition performances than classical features like LBP and their LQP variants for the FCFM image classification problems. Another finding is that LBP-based and scattering-based features provide complementary discriminative information and, in some situations, we empirically establish that performance can be improved when jointly using LBP, LQP and scattering features. CONCLUSIONS: In this work we analyze the joint capability of FCFM images and scattering features for lung cancer diagnosis. The proposed method achieves a good recognition rate for such a diagnosis problem. It also performs well when used in conjunction with other features for other classical medical imaging classification problems.
Authors: Susan Fernandes; Gareth Williams; Elvira Williams; Katjana Ehrlich; James Stone; Neil Finlayson; Mark Bradley; Robert R Thomson; Ahsan R Akram; Kevin Dhaliwal Journal: Eur Respir J Date: 2021-03-25 Impact factor: 16.671
Authors: Sohan Seth; Ahsan R Akram; Paul McCool; Jody Westerfeld; David Wilson; Stephen McLaughlin; Kevin Dhaliwal; Christopher K I Williams Journal: Sci Rep Date: 2016-08-23 Impact factor: 4.379