Detection of lung nodules in digital chest radiographs using artificial neural networks: A pilot study

Radiologists can fail to detect up to 30% of pulmonary nodules in chest radiographs. A back-propagation neural network was used to detect lung nodules in digital chest radiographs to assist radiologists in the diagnosis of lung cancer. Regions of interest (ROIs) that cantained nodules and normal tissues in the lung were selected from digitized chest radiographs by a previously developed computer-aided diagnosis (CAD) scheme. Different preprocessing techniques were used to produce input data to the neural network. The performance of the neural network was evaluated by receiver operating characteristic (ROC) analysis. We found that subsampling of original 64- × 64-pixel ROIs to smaller 8- × 8-pixel ROIs provides the optimal preprocessing for the neural network to distinguish ROIs containing nodules from false-positive ROIs containing normal regions. The neural network was able to detect obvious nodules very well with an A_z value (area under ROC curve) of 0.93, but was unable to detect subtle nodules. However, with a training method that uses different orientations of the original ROIs, we were able to improve the performance of the neural network to detect subtle nodules. Artificial neural networks have the potential to serve as a useful classifier to help to eliminate the false-positive detections of the CAD scheme.     

Automated detection of lung nodules in CT scans: preliminary results

We have developed a fully automated computerized method for the detection of lung nodules in helical computed tomography (CT) scans of the thorax. This method is based on two-dimensional and three-dimensional analyses of the image data acquired during diagnostic CT scans. Lung segmentation proceeds on a section-by-section basis to construct a segmented lung volume within which further analysis is performed. Multiple gray-level thresholds are applied to the segmented lung volume to create a series of thresholded lung volumes. An 18-point connectivity scheme is used to identify contiguous three-dimensional structures within each thresholded lung volume, and those structures that satisfy a volume criterion are selected as initial lung nodule candidates. Morphological and gray-level features are computed for each nodule candidate. After a rule-based approach is applied to greatly reduce the number of nodule candidates that corresponds to nonnodules, the features of remaining candidates are merged through linear discriminant analysis. The automated method was applied to a database of 43 diagnostic thoracic CT scans. Receiver operating characteristic (ROC) analysis was used to evaluate the ability of the classifier to differentiate nodule candidates that correspond to actual nodules from false-positive candidates. The area under the ROC curve for this categorization task attained a value of 0.90 during leave-one-out-by-case evaluation. The automated method yielded an overall nodule detection sensitivity of 70% with an average of 1.5 false-positive detections per section when applied to the complete 43-case database. A corresponding nodule detection sensitivity of 89% with an average of 1.3 false-positive detections per section was achieved with a subset of 20 cases that contained only one or two nodules per case.     

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

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 classification provided improved detection of pulmonary nodules on chest radiographs for 924 lung nodule cases.     

True Detection Versus “Accidental” Detection of Small Lung Cancer by a Computer-Aided Detection (CAD) Program on Chest Radiographs

To evaluate the number of actual detections versus “accidental” detections by a computer-aided detection (CAD) system for small nodular lung cancers (≤30 mm) on chest radiographs, using two different criteria for measuring performance. A Food-and-Drug-Administration-approved CAD program (version 1.0; Riverain Medical) was applied to 34 chest radiographs with a “radiologist-missed” nodular cancer and 36 radiographs with a radiologist-mentioned nodule (a newer version 3.0 was also applied to the 36-case database). The marks applied by this CAD system consisted of 5-cm-diameter circles. A strict “nodule-in-center” criterion and a generous “nodule-in-circle” criterion were compared as methods for the calculation of CAD sensitivity. The increased sensitivities by the nodule-in-circle criterion were considered as nodules detected by chance. The number of false-positive (FP) marks was also analyzed. For the 34 radiologist-missed cancers, the nodule-in-circle criterion caused eight more cancers (24%) to be detected by chance, as compared to the nodule-in-center criterion, when using the version 1.0 results. For the 36 radiologist-mentioned nodules, the nodule-in-circle criterion caused seven more lesions (19%) to be detected by chance, as compared to the nodule-in-center criterion, when using the version 1.0 results, and three more lesions (8%) to be detected by chance when using the version 3.0 results. Version 1.0 yielded a mean of six FP marks per image, while version 3.0 yielded only three FP marks per image. The specific criteria used to define true- and false-positive CAD detections can substantially influence the apparent accuracy of a CAD system.     

Automatic lung nodule detection using profile matching and back-propagation neural network techniques

The potential advantages of using digital techniques instead of film-based radiography have been discussed extensively for the past 10 years. A major future application of digital techniques is computer-assisted diagnosis: the use of computer techniques to assist the radiologist in the diagnostic process. One aspect of this assistance is computer-assisted detection. The detection of small lung nodule has been recognized as a clinically difficult task for many years. Most of the literature has indicated that the rate for finding lung nodules (size range from 3 mm to 15 mm) is only approximately 65%, in those cases in which the undetected nodules could be found retrospectively. In recent published research, image processing techniques, such as thresholding and morphological analysis, have been used to enhance true-positive detection. However, these methods still produce many false-positive detections. We have been investigating the use of neural networks to distinguish true-positives nodule detections among those areas of interest that are generated from a signal enhanced image. The initial results show that the trained neural networks program can increase true-positive detections and moderately reduce the number of false-positive detections. The program reported here can perform three modes of lung nodule detection: thresholding, profile matching analysis, and neural network. This program is fully automatic and has been implemented in a DEC 5000/200 (Digital Equipment Corp, Maynard, MA) workstation. The total processing time for all three methods is less than 35 seconds. In this report, key image processing techniques and neural network for the lung nodule detection are described and the results of this initial study are reported.     

Lung nodule detection in low-dose and thin-slice computed tomography

A computer-aided detection (CAD) system for the identification of small pulmonary nodules in low-dose and thin-slice CT scans has been developed. The automated procedure for selecting the nodule candidates is mainly based on a filter enhancing spherical-shaped objects. A neural approach based on the classification of each single voxel of a nodule candidate has been purposely developed and implemented to reduce the amount of false-positive findings per scan. The CAD system has been trained to be sensitive to small internal and sub-pleural pulmonary nodules collected in a database of low-dose and thin-slice CT scans. The system performance has been evaluated on a data set of 39 CT containing 75 internal and 27 sub-pleural nodules. The FROC curve obtained on this data set shows high values of sensitivity to lung nodules (80-85% range) at an acceptable level of false positive findings per patient (10-13 FP/scan).     

Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography

In this study, we investigated a pattern-recognition technique based on an artificial neural network (ANN), which is called a massive training artificial neural network (MTANN), for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography (CT) images. The MTANN consists of a modified multilayer ANN, which is capable of operating on image data directly. The MTANN is trained by use of a large number of subregions extracted from input images together with the teacher images containing the distribution for the "likelihood of being a nodule." The output image is obtained by scanning an input image with the MTANN. The distinction between a nodule and a non-nodule is made by use of a score which is defined from the output image of the trained MTANN. In order to eliminate various types of non-nodules, we extended the capability of a single MTANN, and developed a multiple MTANN (Multi-MTANN). The Multi-MTANN consists of plural MTANNs that are arranged in parallel. Each MTANN is trained by using the same nodules, but with a different type of non-nodule. Each MTANN acts as an expert for a specific type of non-nodule, e.g., five different MTANNs were trained to distinguish nodules from various-sized vessels; four other MTANNs were applied to eliminate some other opacities. The outputs of the MTANNs were combined by using the logical AND operation such that each of the trained MTANNs eliminated none of the nodules, but removed the specific type of non-nodule with which the MTANN was trained, and thus removed various types of non-nodules. The Multi-MTANN consisting of nine MTANNs was trained with 10 typical nodules and 10 non-nodules representing each of nine different non-nodule types (90 training non-nodules overall) in a training set. The trained Multi-MTANN was applied to the reduction of false positives reported by our current computerized scheme for lung nodule detection based on a database of 63 low-dose CT scans (1765 sections), which contained 71 confirmed nodules including 66 biopsy-confirmed primary cancers, from a lung cancer screening program. The Multi-MTANN was applied to 58 true positives (nodules from 54 patients) and 1726 false positives (non-nodules) reported by our current scheme in a validation test; these were different from the training set. The results indicated that 83% (1424/1726) of non-nodules were removed with a reduction of one true positive (nodule), i.e., a classification sensitivity of 98.3% (57 of 58 nodules). By using the Multi-MTANN, the false-positive rate of our current scheme was improved from 0.98 to 0.18 false positives per section (from 27.4 to 4.8 per patient) at an overall sensitivity of 80.3% (57/71).     

Computer-aided diagnostic scheme for lung nodule detection in digital chest radiographs by use of a multiple-template matching technique.

We have been developing a computer-aided diagnostic (CAD) scheme to assist radiologists in improving the detection of pulmonary nodules in chest radiographs, because radiologists can miss as many as 30% of pulmonary nodules in routine clinical practice. A key to the successful clinical application of a CAD scheme is to ensure that there are only a small number of false positives that are incorrectly reported as nodules by the scheme. In order to significantly reduce the number of false positives in our CAD scheme, we developed, in this study, a multiple-template matching technique, in which a test candidate can be identified as a false positive and thus eliminated, if its largest cross-correlation value with non-nodule templates is larger than that with nodule templates. We describe the technique for determination of cross-correlation values for test candidates with nodule templates and non-nodule templates, the technique for creation of a large number of nodule templates and non-nodule templates, and the technique for removal of nodulelike non-nodule templates and non-nodulelike nodule templates, in order to achieve a good performance. In our study, a large number of false positives (44.3%) were removed with reduction of a very small number of true positives (2.3%) by use of the multiple-template matching technique. We believe that this technique can be used to significantly improve the performance of CAD schemes for lung nodule detection in chest radiographs.     

Computerized detection of pulmonary nodules in digital chest images: use of morphological filters in reducing false-positive detections

Currently, radiologists can fail to detect lung nodules in up to 30% of actually positive cases. If a computerized scheme could alert the radiologist to locations of suspected nodules, then potentially the number of missed nodules could be reduced. We are developing such a computerized scheme that involves a difference-image approach and various feature-extraction techniques. In this paper, we describe our use of digital morphological processing in the reduction of computer-identified false-positive detections. A feature-extraction technique, which includes the sequential application of nonlinear filters of erosion and dilation, is employed to reduce the camouflaging effect of ribs and vessels on nodule detection. This additional feature-extraction technique reduced the true-positive rate of the computerized scheme by 13% and the false-positive rate by 50%. In a comparison of the scheme with and without the additional feature-extraction technique, inclusion of the additional technique increased the detection sensitivity by about half at the level of three to four false-positive detections per chest image.     

Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an "optimal" method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect.     

Computerized Analysis of Pneumoconiosis in Digital Chest Radiography: Effect of Artificial Neural Network Trained with Power Spectra

It is difficult for radiologists to classify pneumoconiosis with small nodules on chest radiographs. Therefore, we have developed a computer-aided diagnosis (CAD) system based on the rule-based plus artificial neural network (ANN) method for distinction between normal and abnormal regions of interest (ROIs) selected from chest radiographs with and without pneumoconiosis. The image database consists of 11 normal and 12 abnormal chest radiographs. These abnormal cases included five silicoses, four asbestoses, and three other pneumoconioses. ROIs (matrix size, 32 × 32) were selected from normal and abnormal lungs. We obtained power spectra (PS) by Fourier transform for the frequency analysis. A rule-based method using PS values at 0.179 and 0.357 cycles per millimeter, corresponding to the spatial frequencies of nodular patterns, were employed for identification of obviously normal or obviously abnormal ROIs. Then, ANN was applied for classification of the remaining normal and abnormal ROIs, which were not classified as obviously abnormal or normal by the rule-based method. The classification performance was evaluated by the area under the receiver operating characteristic curve (Az value). The Az value was 0.972 ± 0.012 for the rule-based plus ANN method, which was larger than that of 0.961 ± 0.016 for the ANN method alone (P ≤ 0.15) and that of 0.873 for the rule-based method alone. We have developed a rule-based plus pattern recognition technique based on the ANN for classification of pneumoconiosis on chest radiography. Our CAD system based on PS would be useful to assist radiologists in the classification of pneumoconiosis.     

Multiview-based computer-aided detection scheme for breast masses

In this study, we developed and tested a new multiview-based computer-aided detection (CAD) scheme that aims to maintain the same case-based sensitivity level as a single-image-based scheme while substantially increasing the number of masses being detected on both ipsilateral views. An image database of 450 four-view examinations (1800 images) was assembled. In this database, 250 cases depicted malignant masses, of which 236 masses were visible on both views and 14 masses were visible only on one view. First, we detected suspected mass regions depicted on each image in the database using a single-image-based CAD. For each identified region (with detection score > or = 0.55), we then identified a matching strip of interest on the ipsilateral view based on the projected distance to the nipple along the centerline. By lowering CAD operating threshold inside the matching strip, we searched for a region located inside the strip and paired it with the original region. A multifeature-based artificial neural network scored the likelihood of the paired "matched" regions representing true-positive masses. All single (unmatched) regions except for those either with very high detection scores (> or = 0.85) or those located near the chest wall that cannot be matched on the other view were discarded. The original single-image-based CAD scheme detected 186 masses (74.4% case-based sensitivity) and 593 false-positive regions. Of the 186 identified masses, 91 were detected on two views (48.9%) and 95 were detected only on one view (51.1%). Of the false-positive detections, 54 were paired on the ipsilateral view inside the corresponding matching strips and the remaining 485 were not, which represented 539 case-based false-positive detections (0.3 per image). Applying the multiview-based CAD scheme, the same case-based sensitivity was maintained while cueing 169 of 186 masses (90.9%) on both views and at the same time reducing the case-based false-positive detection rate by 23.7% (from 539 to 411). The study demonstrated that the new multiview-based CAD scheme could substantially increase the number of masses being cued on two ipsilateral views while reducing the case-based false-positive detection rate.     

Automated detection of lung nodules in CT scans: effect of image reconstruction algorithm

We have investigated the effect of computed tomography (CT) image reconstruction algorithm on the performance of our automated lung nodule detection method. Commercial CT scanners offer a choice of several algorithms for the reconstruction of projection data into transaxial images. Different algorithms produce images with substantially different properties that are apparent not only quantitatively, but also through visual assessment. During some clinical thoracic CT examinations, patient scans are reconstructed with multiple reconstruction algorithms. Thirty-eight such cases were collected to form two databases: one with patient projection data reconstructed with the "standard" reconstruction algorithm and the other with the same patient projection data reconstructed with the "lung" reconstruction algorithm. The automated nodule detection method was applied to both databases. This method is based on gray-level-thresholding techniques to segment the lung regions from each CT section to create a segmented lung volume. Further gray-level-thresholding techniques are applied within the segmented lung volume to identify a set of lung nodule candidates. Rule-based and linear discriminant classifiers are used to differentiate between lung nodule candidates that correspond to actual nodules and those that correspond to non-nodules. The automated method that was applied to both databases was exactly the same, except that the classifiers were calibrated separately for each database. For comparison, the classifier then was trained on one database and tested independently on the other database. When applied to the databases in this manner, the automated method demonstrated overall a similar level of performance, indicating an encouraging degree of robustness.     

Automated lung nodule classification following automated nodule detection on CT: a serial approach

We have evaluated the performance of an automated classifier applied to the task of differentiating malignant and benign lung nodules in low-dose helical computed tomography (CT) scans acquired as part of a lung cancer screening program. The nodules classified in this manner were initially identified by our automated lung nodule detection method, so that the output of automated lung nodule detection was used as input to automated lung nodule classification. This study begins to narrow the distinction between the "detection task" and the "classification task." Automated lung nodule detection is based on two- and three-dimensional analyses of the CT image data. Gray-level-thresholding techniques are used to identify initial lung nodule candidates, for which morphological and gray-level features are computed. A rule-based approach is applied to reduce the number of nodule candidates that correspond to non-nodules, and the features of remaining candidates are merged through linear discriminant analysis to obtain final detection results. Automated lung nodule classification merges the features of the lung nodule candidates identified by the detection algorithm that correspond to actual nodules through another linear discriminant classifier to distinguish between malignant and benign nodules. The automated classification method was applied to the computerized detection results obtained from a database of 393 low-dose thoracic CT scans containing 470 confirmed lung nodules (69 malignant and 401 benign nodules). Receiver operating characteristic (ROC) analysis was used to evaluate the ability of the classifier to differentiate between nodule candidates that correspond to malignant nodules and nodule candidates that correspond to benign lesions. The area under the ROC curve for this classification task attained a value of 0.79 during a leave-one-out evaluation.     

Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images

A novel automated computerized scheme has been developed to assist radiologists for their distinction between benign and malignant solitary pulmonary nodules on chest images. Our database consisted of 55 chest radiographs (33 primary lung cancers and 22 benign nodules). In this method, the location of a nodule was indicated first by a radiologist. The difference image with a nodule was produced by use of filters and then represented in a polar coordinate system. The nodule was segmented automatically by analysis of contour lines of the gray-level distribution based on the polar-coordinate representation. Two clinical parameters (age and sex) and 75 image features were determined from the outline, the image, and histogram analysis for inside and outside regions of the segmented nodule. Linear discriminant analysis (LDA) and knowledge about benign and malignant nodules were used to select initial feature combinations. Many combinations for subgroups of 77 features were evaluated as input to artificial neural networks (ANNs). The performance of ANNs with the selected 7 features by use of the round-robin test showed Az = 0.872, which was greater than Az = 0.854 obtained previously with the manual method (P= 0.53). The performance of LDA (Az = 0.886) was slightly improved compared to that of ANNs (P = 0.59) and was greater than that of the manual method (Az = 0.854) reported previously (P = 0.40). The high level of its performance indicates the potential usefulness of this automated computerized scheme in assisting radiologists as a second opinion for distinction between benign and malignant solitary pulmonary nodules on chest images.     

Parameter optimization of a computer-aided diagnosis scheme for the segmentation of microcalcification clusters in mammograms

Our purpose in this study is to develop a parameter optimization technique for the segmentation of suspicious microcalcification clusters in digitized mammograms. In previous work, a computer-aided diagnosis (CAD) scheme was developed that used local histogram analysis of overlapping subimages and a fuzzy rule-based classifier to segment individual microcalcifications, and clustering analysis for reducing the number of false positive clusters. The performance of this previous CAD scheme depended on a large number of parameters such as the intervals used to calculate fuzzy membership values and on the combination of membership values used by each decision rule. These parameters were optimized empirically based on the performance of the algorithm on the training set. In order to overcome the limitations of manual training and rule generation, the segmentation algorithm was modified in order to incorporate automatic parameter optimization. For the segmentation of individual microcalcifications, the new algorithm used a neural network with fuzzy-scaled inputs. The fuzzy-scaled inputs were created by processing the histogram features with a family of membership functions, the parameters of which were automatically extracted from the distribution of the feature values. The neural network was trained to classify feature vectors as either positive or negative. Individual microcalcifications were segmented from positive subimages. After clustering, another neural network was trained to eliminate false positive clusters. A database of 98 images provided training and testing sets to optimize the parameters and evaluate the CAD scheme, respectively. The performance of the algorithm was evaluated with a FROC analysis. At a sensitivity rate of 93.2%, there was an average of 0.8 false positive clusters per image. The results are very comparable with those taken using our previously published rule-based method. However, the new algorithm is more suited to generalize its performance on a larger population, depends on two monotonic outputs making its evaluation much easier and can be trained in an automatic way making practical its application on a large database.     

Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields

We are investigating the characteristic features of lung nodules and the surrounding normal anatomic background in order to develop an algorithm of computer vision for use as an aid in the detection of nodules in digital chest radiographs. Our technique involves an attempt to eliminate the background anatomic structures in the lung fields by means of a difference image approach. Then, feature-extraction techniques, such as tests for circularity, size, and their variation with threshold level, are applied so that suspected nodules can be isolated. Preliminary results of this automated detection scheme yielded high true-positive rates and low false-positive rates in the peripheral lung regions of the chest. This detection scheme, which can assist the final diagnosis by the clinician, has the potential to improve the early detection of lung carcinomas.     

A weighted rule based method for predicting malignancy of pulmonary nodules by nodule characteristics

Predicting malignancy of solitary pulmonary nodules from computer tomography scans is a difficult and important problem in the diagnosis of lung cancer. This paper investigates the contribution of nodule characteristics in the prediction of malignancy. Using data from Lung Image Database Consortium (LIDC) database, we propose a weighted rule based classification approach for predicting malignancy of pulmonary nodules. LIDC database contains CT scans of nodules and information about nodule characteristics evaluated by multiple annotators. In the first step of our method, votes for nodule characteristics are obtained from ensemble classifiers by using image features. In the second step, votes and rules obtained from radiologist evaluations are used by a weighted rule based method to predict malignancy. The rule based method is constructed by using radiologist evaluations on previous cases. Correlations between malignancy and other nodule characteristics and agreement ratio of radiologists are considered in rule evaluation. To handle the unbalanced nature of LIDC, ensemble classifiers and data balancing methods are used. The proposed approach is compared with the classification methods trained on image features. Classification accuracy, specificity and sensitivity of classifiers are measured. The experimental results show that using nodule characteristics for malignancy prediction can improve classification results.     

Effect of Multiscale Processing in Digital Chest Radiography on Automated Detection of Lung Nodule with a Computer Assistance System

The aim of this study is to evaluate the effect of multiscale processing in digital chest radiography on automated detection of lung nodule with a computer-aided diagnosis (CAD) system. The study involved 58 small-nodule patient cases and 58 normal cases. The 58 patient cases included a total of 64 noncalcified lung nodules up to 15 mm in diameter. Each case underwent an examination with a digital radiography system (Digital Diagnost, Philips Medical Systems), and the acquired image was processed by the following three types of multiscale processing (Unique Image Processing Package, Philips Medical Systems) respectively: (1) standard image from the default processing parameter (structure preference, 0.0), (2) high-pass image with structure preference of 0.4, (3) low-pass image with structure preference of ?0.4. The CAD output images were produced with a real-time computer assistance system (IQQA?-Chest, EDDA Technology). Two experienced chest radiologists established the nodule gold standard by consensus reading according to computed tomography results, and analyzed and recorded the detection of lung nodules and false-positive detections of these CAD output images. For the entire cases involved (each case with three types of different processing), a total of 348 observations were evaluated by the receiver operating characteristic (ROC) analysis. The mean area under the ROC curve (A _z ) value was 0.700 for the standard images, 0.587 for the high-pass images, and 0.783 for the low-pass images. There were statistically significant A _z values among these three types of processed images (p?<?0.01). Multiscale processing in digital chest radiography can affect the automated detection of lung nodule by CAD, which is consistent with effects from visual inspection.     

Application of artificial neural networks for quantitative analysis of image data in chest radiographs for detection of interstitial lung disease

The authors have developed an automated computeraided diagnostic (CAD) scheme by using artificial neural networks (ANNs) on quantitative analysis of image data. Three separate ANNs were applied for detection of interstitial disease on digitized chest images. The first ANN was trained with horizontal profiles in regions of interest (ROIs) selected from normal and abnormal chest radiographs for distinguishing between normal and abnormal patterns. For training and testing of the second ANN, the vertical output patterns obtained from the 1st ANN were used for each ROI. The output value of the second ANN was used to distinguish between normal and abnormal ROIs with interstitial infiltrates. If the ratio of the number of abnormal ROIs to the total number of all ROIs in a chest image was greater than a specified threshold level, the image was classified as abnormal. In addition, the third ANN was applied to distinguish between normal and abnormal chest images. The combination of the rule-based method and the third ANN also was applied to the classification between normal and abnormal chest images. The performance of the ANNs was evaluated by means of receiver operating characteristic (ROC) analysis. The average A_z value (area under the ROC curve) for distinguishing between normal and abnormal cases was 0.976±0.012 for 100 chest radiographs that were not used in training of ANNs. The results indicate that the ANN trained with image data can learn some statistical properties associated with interstitial infiltrates in chest radiographs.