Fusion of Local and Global Detection Systems to Detect Tuberculosis in Chest Radiographs
Automatic detection of tuberculosis (TB) on chest radiographs is a difficult problem because of the diverse presentation of the disease. A combination of detection systems for abnormalities and normal anatomy is used to improve detection performance. A textural abnormality detection system operating at the pixel level is combined with a clavicle detection system to suppress false positive responses. The output of a shape abnormality detection system operating at the image level is combined in a next step to further improve performance by reducing false negatives. Strategies for combining systems based on serial and parallel configurations were evaluated using the minimum, maximum, product, and mean probability combination rules. The performance of TB detection increased, as measured using the area under the ROC curve, from 0.67 for the textural abnormality detection system alone to 0.86 when the three systems were combined. The best result was achieved using the sum and product rule in a parallel combination of outputs.
KeywordsReceiver Operator Characteristic Curve Chest Radiograph Linear Discriminant Analysis Abnormal Image Training Database
- 1.Arzhaeva, Y., Hogeweg, L., de Jong, P.A., Viergever, M.A., van Ginneken, B.: Global and local multi-valued dissimilarity-based classification: Application to computer-aided detection of tuberculosis. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 724–731. Springer, Heidelberg (2009)CrossRefGoogle Scholar
- 4.Hanley, J.A., McNeil, B.J.: A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 148(3), 839–843 (1983)Google Scholar
- 8.Tax, D.: One-class classification. PhD thesis, Delft University of Technology (2001)Google Scholar
- 10.World Health Organization. WHO report 2009: Global tuberculosis control, epidemiology, strategy, financing (2009)Google Scholar