Share Email Print
cover

Proceedings Paper

Boosting CNN performance for lung texture classification using connected filtering
Author(s): Sebastián Roberto Tarando; Catalin Fetita; Young-Wouk Kim; Hyoun Cho; Pierre-Yves Brillet
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Infiltrative lung diseases describe a large group of irreversible lung disorders requiring regular follow-up with CT imaging. Quantifying the evolution of the patient status imposes the development of automated classification tools for lung texture. This paper presents an original image pre-processing framework based on locally connected filtering applied in multiresolution, which helps improving the learning process and boost the performance of CNN for lung texture classification. By removing the dense vascular network from images used by the CNN for lung classification, locally connected filters provide a better discrimination between different lung patterns and help regularizing the classification output. The approach was tested in a preliminary evaluation on a 10 patient database of various lung pathologies, showing an increase of 10% in true positive rate (on average for all the cases) with respect to the state of the art cascade of CNNs for this task.

Paper Details

Date Published: 27 February 2018
PDF: 13 pages
Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 1057505 (27 February 2018); doi: 10.1117/12.2293093
Show Author Affiliations
Sebastián Roberto Tarando, TELECOM SudParis, Institut Mines-Telecom, CNRS (France)
Catalin Fetita, TELECOM SudParis, Institut Mines-Telecom, CNRS (France)
Young-Wouk Kim, Avicenne Hospital (France)
Hyoun Cho, Pitié-Salpêtrière Hospital (France)
Pierre-Yves Brillet, Univ. Paris13 (France)
Avicenne Hospital (France)


Published in SPIE Proceedings Vol. 10575:
Medical Imaging 2018: Computer-Aided Diagnosis
Nicholas Petrick; Kensaku Mori, Editor(s)

© SPIE. Terms of Use
Back to Top