Lung contour detection in chest radiographs using <inline-formula>1-<roman>D</roman></inline-formula> convolution neural networks

Abstract

The purposes of this research are to investigate the effectiveness of our novel lung contour detection method in chest radiographs. The proposed method consists of five sections as follows. First, in order to reduce the amount of information, the images are smoothed and subsampled from 2 k by 2.5 k pixels to 256 by 310 pixels with rescaling from 12-bit to 8-bit based on the image maximum and minimum. Second, that the image is resolved into the profiles for two directions (i.e., horizontal x and vertical y axes). Then, for each direction, those profiles are tested by the neural network which has been trained using the profiles from 14 pairs of original and target images. Note that both horizontal and vertical neural networks are trained with the horizontal and vertical profiles, respectively. For each direction, the whole two-dimensional image is reconstructed from the output profiles of the neural network. Next, the binarization process followed by the labeling process is applied to each reconstructed image individually. Finally, two postprocessed images are combined through the OR operation, and the labeling process is performed for the combined image to get the final contour. 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. Fourteen images were used for the training of the neural networks and the remaining 71 images for testing. The proposed method can detect the lung contour at 94% accuracy for test images following the same rules as for the training images.

Review: On Segmentation of Nodules from Posterior and Anterior Chest Radiographs

“…al [ 9 ], Osamu Tsujii, MS Matthew et. al [ 10 ] N. F. Vittitoe, R. Vargas-Voracek, and C. E. Floyd et. al [ 11 ], Bram van Ginnekena, and Bart M. ter Haar Romeny [ 12 ].…”

“…The same authors [ 13 ] in their next proposed technique used locally calculated features to classify pixels into one of the several anatomical classes. Since subset of features that were used for classification gives reduced computational complexity as well as reduced time with efficiency comparable to the full set of features, Osamu Tsujii et.al [ 10 ] proposed a method for automatic lung segmentation; initial size of the image is reduced and smoothed; in the next step, image is resolved into horizontal and vertical profiles. These profiles were given as input for two convolution neural networks.…”