Automated segmentation of anatomic regions in chest radiographs using an adaptive-sized hybrid neural network.

The purposes of this research are to investigate the effectiveness of our novel image features for segmentation of anatomic regions such as the lungs and the mediastinum in chest radiographs and to develop an automatic computerized method for image processing. A total of 85 screening chest radiographs from Johns Hopkins University Hospital were digitized to 2 K by 2.5 K pixels with 12 bit gray scale. To reduce the amount of information, the images were smoothed and subsampled to 256 by 310 pixels with 8 bit. The determination approach consists of classifying each pixel into two anatomic classes (lung and others) on the basis of several image features: (1) relative pixel address (Rx, Ry) based on lung edges extracted through image processing using profile, (2) density normalized from lungs and mediastinum density, and (3) histogram equalized entropy. The combinations of image features were evaluated using an adaptive-sized hybrid neural network consisting of an input, a hidden, and an output layer. Fourteen images were used for the training of the neural network and the remaining 71 images for testing. Using four features of relative address (Rx, Ry), normalized density, and histogram equalized entropy, the neural networks classified lungs at 92% accuracy against test images following the same rules as for the training images.

[1]  K. Doi,et al.  Image feature analysis for computer-aided diagnosis: accurate determination of ribcage boundary in chest radiographs. , 1995, Medical physics.

[2]  Matthew T. Freedman,et al.  Anatomic region-based dynamic range compression for chest radiographs using warping transformation of correlated distribution , 1997, Medical Imaging.

[3]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[4]  J. Boone,et al.  A fully automated algorithm for the segmentation of lung fields on digital chest radiographic images. , 1995, Medical physics.

[5]  S. Dwyer,et al.  Automated radiographic diagnosis via feature extraction and classification of cardiac size and shape descriptors. , 1972, IEEE transactions on bio-medical engineering.

[6]  A. Ardeshir Goshtasby,et al.  Automatic detection of rib borders in chest radiographs , 1995, IEEE Trans. Medical Imaging.

[7]  Gerald Tesauro,et al.  Scaling Relationships in Back-propagation Learning , 1988, Complex Syst..

[8]  S Katsuragawa,et al.  Image feature analysis and computer-aided diagnosis in digital radiography: detection and characterization of interstitial lung disease in digital chest radiographs. , 1988, Medical physics.

[9]  H. K. Huang,et al.  Feature selection in the pattern classification problem of digital chest radiograph segmentation , 1995, IEEE Trans. Medical Imaging.

[10]  Kunio Doi,et al.  Neural network approach for differential diagnosis of interstitial lung diseases , 1990, Medical Imaging: Image Processing.

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

[12]  Akira Hasegawa,et al.  Segmentation and analysis of breast cancer pathological images by an adaptive-sized hybrid neural network , 1996, Medical Imaging.

[13]  Michael F. McNitt-Gray,et al.  Pattern classification approach to segmentation of chest radiographs , 1993 .

[14]  Matthew T. Freedman,et al.  Convolution neural-network-based detection of lung structures , 1994, Medical Imaging.