Tuberculosis is a major health threat in many regions of the world. Opportunistic infections in immunocompromised HIV/AIDS patients and multi-drug-resistant bacterial strains have exacerbated the problem, while diagnosing tuberculosis still remains a challenge. When left undiagnosed and thus untreated, mortality rates of patients with tuberculosis are high. Standard diagnostics still rely on methods developed in the last century. They are slow and often unreliable. In an effort to reduce the burden of the disease, this paper presents our automated approach for detecting tuberculosis in conventional posteroanterior chest radiographs. We first extract the lung region using a graph cut segmentation method. For this lung region, we compute a set of texture and shape features, which enable the X-rays to be classified as normal or abnormal using a binary classifier. We measure the performance of our system on two datasets: a set collected by the tuberculosis control program of our local county's health department in the United States, and a set collected by Shenzhen Hospital, China. The proposed computer-aided diagnostic system for TB screening, which is ready for field deployment, achieves a performance that approaches the performance of human experts. We achieve an area under the ROC curve (AUC) of 87% (78.3% accuracy) for the first set, and an AUC of 90% (84% accuracy) for the second set. For the first set, we compare our system performance with the performance of radiologists. When trying not to miss any positive cases, radiologists achieve an accuracy of about 82% on this set, and their false positive rate is about half of our system's rate.

A reliability study was conducted. OBJECTIVE.: To modify a grading system for lumbar disc degeneration and to test the reliability of this modified grading system. The 5-level Pfirrmann grading system for disc degeneration did not prove discriminatory when used to assess disc degeneration in the elderly spine. Such discriminatory power is necessary to test the association between other variables and severity of disc degeneration. An 8-level modified grading system for lumbar disc degeneration was developed including a description of the changes expected for each grade and a 24-image reference panel. The reliability of the modified grading system was tested on 260 lumbar intervertebral discs in 52 subjects (26 men, 26 female) with a mean age of 73 years (range, 67-83 years). All examinations were analyzed independently by 3 readers. Intraobserver and interobserver reliabilities were assessed by calculating weighted kappa statistics. On average, for all 3 readers, 0.39% of the 260 discs were classified as Grade 2, 22% were classified as Grade 3, 21.5% were classified as Grade 4, 25.3% were classified as Grade 5, 19.1% were classified as Grade 6, 7.1% were classified as Grade 7, and 4.8% were classified as Grade 8. Intraobserver agreement was excellent (weighted kappa range, 0.79-0.91) with substantial interobserver agreement (weighted kappa range, 0.65-0.67). Complete intraobserver agreement was obtained, on average, in 85% of all discs with 84% of disagreement being as a result of a 1 grade difference. Complete interobserver agreement was obtained, on average, in 66% of all discs with 91% of disagreement being as a result of a 1 grade difference. The modified Pfirrmann grading system is useful at discriminating severity of disc degeneration in elderly subjects. The system can be applied with good intra- and interobserver agreement.