CAD4TB is an automated reading software for the detection of active pulmonary tuberculosis on chest radiographs. Its output is an abnormality score between 0 - 100. We evaluated the performance of version 3.07 (updated) on a set of 861 presumptive TB patients enrolled in the TB Cohort and TB CHILD studies at Ifakara Health Institute, Bagamoyo, Tanzania. Culture-confirmed pumonary tuberculosis was used as the positive reference standard. Two human readers (one expert and one clinical officer) interpreted the same set of images. Performance of human and automated reading was compared.