Abstract

AGUILLON PEREZ, Julián Mauricio; DUARTE PACHECO, Sergio Alejandro  and  HERRERA GARCIA, Rodrigo Javier. Highlight of lung nodule candidates in chest radiographs by convergence Filters. ing. [online]. 2014, vol.19, n.2, pp.85-104. ISSN 0121-750X.

This paper describes the development of a method that highlights suspicious areas of lung nodules on chest radiographs. Lung nodules are lesions found in the lung region, which are the first indicators of the presence of cancerous tumors. First, an automatic segmentation method is implemented. Next, to highlight the candidates, convergence filters were used in order to evaluate the degree in which the surrounding area converged to the pixel of interest, assuming a circular shape for potential nodule candidates. Four convergence filters were implemented: Coin filter, Iris filter, Adaptive Ring filter and Sliding Band filter. Coin and adaptive ring filters obtained better results in terms of detection and number of candidates per image, images from the database of the JSRT (Japanese Society of Radiological Technology). Applying the contralateral subtraction technique together with filters based on geometric features such as areas, roundness and eccentricity, it was possible to reduce the number of candidates.

Keywords : Chest radiographs; lung nodules; segmentation; convergence index filters.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )