A Computational Method to Aid the Detection and Annotation of Pleural Lesions in CT Images of the Thorax

摘要

Several thoracic diseases can affect the pleural space. Pleural-based lesions usually require a careful and timeconsumingvisual inspection of the computed tomography (CT) slices to be detected. In order to facilitate thistask, we propose a computational method that automatically detects pleural-based lesion candidates in the lung'ssurface. The first step of this method is the segmentation of both lungs. For that purpose, any segmentationmethod can be applied but in this work we used ALTIS, a fast sequence of image processing operators thatautomatically segments each lung (i.e., air volume) and the trachea. The proposed approach helps the specialistduring the annotation process, allowing the creation of properly annotated datasets, and the development ofmachine learning methods for computer-aided diagnosis. The evaluation of the proposed method was performedin a set of 40 CT scans of patients with pleural plaques and tumor (lung nodules). Two thoracic radiologistsand one pulmonologist assessed the images and provided clinical data. Experiments indicate that the proposedmethod managed to detect most anomalies in a matter of seconds.