Improved texture analysis for automatic detection of Tuberculosis (TB) on Chest Radiographs with Bone Suppression images

Computer aided detection (CAD) of tuberculosis (TB) on chest radiographs (CXR) is challenging due to overlapping structures. Suppression of normal structures can reduce overprojection effects and can enhance the appearance of diffuse parenchymal abnormalities. In this work, we compare two CAD systems to detect textural abnormalities in chest radiographs of TB suspects. One CAD system was trained and tested on the original CXR and the other CAD system was trained and tested on bone suppression images (BSI). BSI were created using a commercially available software (ClearRead 2.4, Riverain Medical). The CAD system is trained with 431 normal and 434 abnormal images with manually outlined abnormal regions. Subtlety rating (1-3) is assigned to each abnormal region, where 3 refers to obvious and 1 refers to subtle abnormalities. Performance is evaluated on normal and abnormal regions from an independent dataset of 900 images. These contain in total 454 normal and 1127 abnormal regions, which are divided into 3 subtlety categories containing 280, 527 and 320 abnormal regions respectively. For normal regions, original/BSI CAD has an average abnormality score of 0.094A,A+-0.027/0.085A,A+-0.032 (p < 0.001). For abnormal regions, subtlety 1, 2, 3 categories have average abnormality scores for original/BSI of 0.155A,A+-0.073/0.156A,A+-0.089 (p = 0.73), 0.194A,A+-0.086/0.207A,A+-0.101 (p < 0.001), 0.225A,A+-0.119/0.247A,A+-0.117 (p < 0.001) respectively. CAD prototype is benefited by BSI in terms of increased accuracy of abnormality probabilistic maps. We therefore conclude that the use of bone suppression results in slightly but significantly improved automated detection of textural abnormalities in chest radiographs.