Computer‐aided diagnostic scheme for the detection of lung nodules on chest radiographs: Localized search method based on anatomical classification

Abstract

We developed an advanced computer-aided diagnostic (CAD) scheme for the detection of various types of lung nodules on chest radiographs intended for implementation in clinical situations. We used 924 digitized chest images (992 noncalcified nodules) which had a 500 x 500 matrix size with a 1024 gray scale. The images were divided randomly into two sets which were used for training and testing of the computerized scheme. In this scheme, the lung field was first segmented by use of a ribcage detection technique, and then a large search area (448 x 448 matrix size) within the chest image was automatically determined by taking into account the locations of a midline and a top edge of the segmented ribcage. In order to detect lung nodule candidates based on a localized search method, we divided the entire search area into 7 x 7 regions of interest (ROIs: 64 x 64 matrix size). In the next step, each ROI was classified anatomically into apical, peripheral, hilar, and diaphragm/heart regions by use of its image features. Identification of lung nodule candidates and extraction of image features were applied for each localized region (128 x 128 matrix size), each having its central part (64 x 64 matrix size) located at a position corresponding to a ROI that was classified anatomically in the previous step. Initial candidates were identified by use of the nodule-enhanced image obtained with the average radial-gradient filtering technique, in which the filter size was varied adaptively depending on the location and the anatomical classification of the ROI. We extracted 57 image features from the original and nodule-enhanced images based on geometric, gray-level, background structure, and edge-gradient features. In addition, 14 image features were obtained from the corresponding locations in the contralateral subtraction image. A total of 71 image features were employed for three sequential artificial neural networks (ANNs) in order to reduce the number of false-positive candidates. All parameters for ANNs, i.e., the number of iterations, slope of sigmoid functions, learning rate, and threshold values for removing the false positives, were determined automatically by use of a bootstrap technique with training cases. We employed four different combinations of training and test image data sets which was selected randomly from the 924 cases. By use of our localized search method based on anatomical classification, the average sensitivity was increased to 92.5% with 59.3 false positives per image at the level of initial detection for four different sets of test cases, whereas our previous technique achieved an 82.8% of sensitivity with 56.8 false positives per image. The computer performance in the final step obtained from four different data sets indicated that the average sensitivity in detecting lung nodules was 70.1% with 5.0 false positives per image for testing cases and 70.4% sensitivity with 4.2 false positives per image for training cases. The advanced CAD scheme involving the localized search method with anatomical clas...

Computer-Aided Diagnosis for Improved Detection of Lung Nodules by Use of Posterior-Anterior and Lateral Chest Radiographs

“…In addition, the computation time can be reduced by use of a small matrix size. We used 106 lateral-view images for development of a CAD scheme for the detection of lung nodules on lateral views, whereas 106 PA view images were used only for testing by use of our existing CAD scheme (9) for the detection of lung nodules on standard chest radiographs. In this way, we obtain the overall performance of the CAD scheme for PA and lateral views.…”

“…In order to obtain the baseline computer performance for the detection of lung nodules on PA views, we used an existing CAD scheme, which was trained with one half of 924 chest images and then tested with the remaining images (9). There were 38 cases (39 lung nodules) that overlapped with cases in the database used for the development of a CAD scheme for lateral views.…”

“…The computer performance obtained from four different data sets, which were derived from the 924-image database, indicated that the average sensitivity in detecting lung nodules was 70.1% with 5.0 false positives per image for test cases and 70.4% sensitivity with 4.2 false positives per image for training cases (9). Figure 1 illustrates an overall computerized scheme for the detection of lung nodules on lateral views.…”

“…Lung nodule detection and image feature extraction-Nodule-enhanced images were produced by sequential application of the ARG filter and the Gaussian filter for identifying initial candidates of lung nodules (9).…”

“…Computer-aided diagnosis (CAD) for the detection of lung nodules on chest images has been developed (8,9) and has become available for clinical practice (10)(11)(12). However, CAD methods employed only posterior-anterior (PA) views of chest images, even if both PA and lateral views for the same patient were available.…”