Effectiveness of bone suppression imaging in the diagnosis of tuberculosis from chest radiographs in Vietnam: An observer study.

OBJECTIVE: To assess the effectiveness of bone suppression imaging (BSI) in the diagnosis of tuberculosis from chest radiographs (CXRs) in Vietnam. MATERIALS AND METHODS: A total of 97 images (50 tuberculosis and 47 normal) comprised the dataset for this observer study with unanimous consensus of a panel of 3 expert radiologists. The participants were 9 Vietnamese radiologists (6 chest radiologists and 3 non-chest radiologists). Participants recorded their confidence levels regarding the presence of tuberculosis after reading a standard chest radiograph directly first and then after BSI processing. Receiver operating characteristic (ROC) analysis was used to evaluate participant performance. In addition, the change in participants' decision regarding the presence or absence of tuberculosis after BSI processing was recorded for each patient. Improvements in sensitivity and specificity were calculated. RESULTS: The average AUC for non-chest radiologists improved from 0.882 without BSI to 0.933 with BSI (P = 0.048). In addition, BSI improved sensitivity by 10.0% whereas specificity decreased by 2.8% among non-chest radiologists. CONCLUSION: Using BSI improved the accuracy of tuberculosis diagnosis from CXRs, particularly by non-chest radiologists.

Effectiveness of Bone Suppression Imaging in the Detection of Lung Nodules on Chest Radiographs: Relevance to Anatomic Location and Observer's Experience.

OBJECTIVE: To evaluate the effectiveness of bone suppression imaging (BSI) software in lung-nodule detection on chest radiographs (CXRs) in relation to nodule location and observer's experience. MATERIALS AND METHODS: The CXRs of 80 patients, of which 40 had a lung nodule (8 to 30 mm in diameter) and 40 did not have any nodules, were interpreted by 20 observers comprising of 7 pulmonologists with >10 years of experience and 13 pulmonology residents. Each patient's image was sequentially read, first using the standard CXR and thereafter with the BSI software. The nodule location and confidence level with regard to the presence of a lung nodule were recorded. Receiver operating characteristic analysis was used to evaluate observer performance. RESULTS: The average area under the curve (AUC) for the observers' receiver operating characteristic significantly improved from 0.867 to 0.900 (P=0.004) with the use of the BSI software. The average AUC for experienced pulmonologists improved from 0.877 to 0.924 (P=0.017) for lung nodules located in the apical and peripheral areas but not for those in the inner area. The average AUC for residents improved regardless of nodule location. CONCLUSION: The use of BSI software improved the performance in lung-nodule detection on CXRs regardless of observer's experience and was more effective for observers with limited experience.