Automatic detection of the lung orientation in digital PA chest radiographs

An image processing algorithm is presented that can identify the orientation as well as the left/right side (parity) of the digitized radiographs. The orientation was found by computing the mean square deviation between the sampled gray values along the center and their best-fit linear regression relations. The parity was determined by comparing the area difference between two thresholded images of the left and the right side around the heart, which is assumed to be around the center of the image. This method was tested with 86 images with their orientations intentionally rotated. The rotation was limited to multiples of 90 degrees, as this was the way the rotation is most likely to happen in the clinical environment. We obtained positive responses for 85 out of 86 images subject to the screening.

[1]  M L Giger,et al.  Computerized detection of abnormal asymmetry in digital chest radiographs. , 1994, Medical physics.

[2]  M.L. Giger.  Computerized scheme for the detection of pulmonary nodules , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[3]  K Doi,et al.  Localization of inter-rib spaces for lung texture analysis and computer-aided diagnosis in digital chest images. , 1988, Medical physics.

[4]  Huai Li,et al.  Artificial convolution neural network for medical image pattern recognition , 1995, Neural Networks.

[5]  Jae-Cheul Lee.  Retro-self-focusing and pinholing effect in a refractive index grating , 1997 .

[6]  S Katsuragawa,et al.  Image feature analysis and computer-aided diagnosis in digital radiography: classification of normal and abnormal lungs with interstitial disease in chest images. , 1989, Medical physics.

[7]  M. Giger,et al.  Potential usefulness of computerized nodule detection in screening programs for lung cancer. , 1992, Investigative radiology.

[8]  Matthew T. Freedman,et al.  Artificial convolution neural network techniques and applications for lung nodule detection , 1995, IEEE Trans. Medical Imaging.

[9]  S. Cha,et al.  Thermal fixing of multiple holographic gratings in magnesium oxide doped lithium niobate crystal: erratum , 1997 .

[10]  Maryellen L. Giger,et al.  Computerized scheme for the detection of pulmonary nodules. A nonlinear filtering technique. , 1992 .

[11]  K. Doi,et al.  Image feature analysis and computer-aided diagnosis in digital radiography: automated analysis of sizes of heart and lung in chest images. , 1990, Medical physics.