Computer-aided diagnosis system for the Acute Respiratory Distress Syndrome from chest radiographs

Abstract

This paper presents a computer-aided diagnosis (CAD) system for the assessment of Acute Respiratory Distress Syndrome (ARDS) from chest radiographs. Our method consists in automatically extracting intercostal patches from chest radiographs belonging to the test database using a semiautomatic segmentation method of the ribs. Statistical and spectral features are computed from each patch then a method of feature transformation is applied using the Linear Discriminant Analysis (LDA). A training database of 321 patches was classified by an expert in two classes, a class of normal patches and a class of abnormal patches. Patches belonging to the test database are then classified using the SVM classifier. Finally, the rate of abnormal patches is calculated for each quadrant to decide if the chest radiograph presents an ARDS. The method has been evaluated on 90 radiographs where 53 images present ARDS. The results show a sensitivity of 90.6% at a specificity of 86.5%.

Keywords: Acute Respiratory Distress Syndrome (ARDS); Automatic classification; Chest radiographs; Computer-aided diagnosis system; Texture analysis.