Shigehiko Katsuragawa

Image feature analysis and computer-aided diagnosis in digital radiography : Detection and characterization of interstitial lung disease in digital chest radiographs

We are developing an automated method for determining physical measures of lung textures in digital chest radiographs in order to detect and characterize interstitial lung disease. With this method, the underlying background density variations caused by the gross lung and chest wall anatomy are corrected for in order to isolate the fluctuating patterns of the underlying lung texture for subsequent computer analysis. The power spectrum of lung texture, which is obtained from the two-dimensional Fourier transform, is filtered by the visual system response of the human observer. The magnitude and coarseness (or fineness) of the lung textures are then quantified by the root-mean-square (rms) variation and the first moment of the power spectrum, respectively. Preliminary results indicate that the rms variations and/or the first moments of the texture of abnormal lungs with various interstitial diseases are clearly different from those of normal lungs. Our results suggest strongly that quantitative texture measures calculated from digital chest images may be useful to radiologists in their assessment of interstitial disease.

Computerized scheme for determination of the likelihood measure of malignancy for pulmonary nodules on low-dose CT images

An automated computerized scheme has been developed for determination of the likelihood measure of malignancy of pulmonary nodules on low-dose helical CT (LDCT) images. Our database consisted of 76 primary lung cancers (147 slices) and 413 benign nodules (576 slices). With this automated computerized scheme, the location of a nodule was first indicated by a radiologist. The outline of the nodule was segmented automatically by use of a dynamic programming technique. Various objective features on the nodules were determined by use of outline analysis and image analysis, and the likelihood measure of malignancy was determined by use of linear discriminant analysis (LDA). The effect of many different combinations of features and the performance of LDA in distinguishing benign nodules from malignant ones were evaluated by means of receiver operating characteristic (ROC) analysis. The Az value (area under the ROC curve) obtained by the computerized scheme in distinguishing benign nodules from malignant ones was 0.828 when a single slice was employed for each of the nodules. However, the Az value was improved to 0.846 when multiple slices were used for determination of the likelihood measure of malignancy. The Az values obtained by the computerized scheme on LDCT images were significantly greater than the Az value of 0.70, which was obtained from our previous observer studies by radiologists in distinguishing benign nodules from malignant ones on LDCT images. The automated computerized scheme for determination of the likelihood measure of malignancy would be useful in assisting radiologists to distinguish between benign and malignant pulmonary nodules on LDCT images.

Iterative image warping technique for temporal subtraction of sequential chest radiographs to detect interval change

A temporal subtraction technique has been developed to assist radiologists in the detection of interval changes on chest radiographs. Although the overall performance of the current temporal subtraction technique is relatively good, severe misregistration errors, mainly due to AP inclination and/or rotation, are observed in some cases. In order to reduce these errors, we attempted to improve the subtraction scheme by applying an iterative image warping technique. In cases obtained with the new temporal subtraction technique 177 (97.8%) of 181 showed adequate, good, or excellent quality. We also found that 156 (86.2%) of cases obtained with the new scheme showed improvements in the quality of the subtraction images compared with the previous scheme. The results indicate that the performance of the temporal subtraction technique was greatly improved by use of the iterative image warping technique.

Image feature analysis and computer-aided diagnosis in digital radiography: classification of normal and abnormal lungs with interstitial disease in chest images.

In order to detect and characterize interstitial disease in the lungs, we are developing an automated method for the determination of physical texture measures, which assess the magnitude and coarseness (or fineness) of lung texture in digital chest radiographs. This method is based on an analysis of the power spectrum of lung texture. We now describe an automated classification method for distinction between normal and abnormal lungs with interstitial disease, in which we employ these texture measures and their data base. This computerized method includes three independent tests, one for a definitely abnormal focal pattern, one for a relatively localized abnormal pattern, and one for a diffuse abnormal pattern. The performance of this computerized classification scheme is compared with that of radiologists by means of receiver operating characteristic (ROC) analysis. Our results indicate that this computerized method can be a valuable aid to radiologists in their assessment of interstitial infiltrates.

Application of temporal subtraction for detection of interval changes on chest radiographs: Improvement of subtraction images using automated initial image matching

The authors developed a temporal subtraction scheme based on a nonlinear geometric warping technique to assist radiologists in the detection of interval changes in chest radiographs obtained on different occasions. The performance of the current temporal subtraction scheme is reasonably good; however, severe misregistration can occur in some cases. The authors evaluated the quality of 100 chest temporal subtraction images selected from their clinical image database. Severe misregistration was mainly attributable to initial incorrect global matching. Therefore, they attempted to improve the quality of the subtraction images by applying a new initial image matching technique to determine the global shift value between the current and the previous chest images. A cross-correlation method was employed for the initial image matching by use of blurred low-resolution chest images. Nineteen cases (40.4%) among 47 poor registered subtraction images were improved. These results show that the new initial image matching technique is very effective for improving the quality of chest temporal subtraction images, which can greatly enhance subtle changes in chest radiographs.

Artificial neural networks in chest radiography: application to the differential diagnosis of interstitial lung disease.

RATIONALE AND OBJECTIVES The authors evaluated the usefulness of artificial neural networks (ANNs) in the differential diagnosis of interstitial lung disease. MATERIALS AND METHODS The authors used three-layer, feed-forward ANNs with a back-propagation algorithm. The ANNs were designed to distinguish between 11 interstitial lung diseases on the basis of 10 clinical parameters and 16 radiologic findings extracted by chest radiologists. Thus, the ANNs consisted of 26 input units and 11 output units. One hundred fifty actual clinical cases, 110 cases from previously published articles, and 110 hypothetical cases were used for training and testing the ANNs by using a round-robin (or leave-one-out) technique. ANN performance was evaluated with receiver operating characteristic (ROC) analysis. RESULTS The Az (area under the ROC curve) obtained with actual clinical cases was 0.947, and both the sensitivity and specificity of the ANNs were approximately 90% in terms of indicating the correct diagnosis with the two largest output values among the 11 diseases. CONCLUSION ANNs using clinical parameters and radiologic findings may be useful for making the differential diagnosis of interstitial lung disease on chest radiographs.

Image feature analysis and computer‐aided diagnosis in digital radiography: Effect of digital parameters on the accuracy of computerized analysis of interstitial disease in digital chest radiographs

We are developing a computerized method for measurement of lung texture in digital chest radiographs for detection and characterization of interstitial disease. Physical texture measures are obtained from analysis of the power spectrum of the lung texture. We have investigated the effect of digital parameters such as pixel size, regions of interest size, the number of quantitation levels, and the peak frequency of the visual system response, as well as the effect of the unsharp masking technique on the performance of this computerized method. We calculated the texture measures by changing digital parameters for 100 normal lungs and 100 abnormal lungs in our database. Receiver operating characteristic (ROC) curves were employed for evaluation of the performance of this computerized method for distinguishing between normal and abnormal lungs. We used the area under the ROC curve to compare the detection accuracy for interstitial infiltrates. We believe that the results of this study may be useful as a guide in the design of computerized schemes for lung texture analysis in digital chest radiographs.

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 analysis of interstitial disease in chest radiographs: improvement of geometric-pattern feature analysis.

We have been developing automated computerized schemes to assist radiologists in interpreting chest radiographs for interstitial disease based on texture analysis and geometric-pattern feature analysis. In this study, we attempted to improve the performance of the geometric-pattern feature analysis, because the current classification performance with geometric-pattern feature analysis is considerably lower than that of texture analysis. In order to improve the performance in distinguishing between normal lungs and abnormal lungs with interstitial disease, we attempted to remove rib edges in regions of interest (ROIs) by using an edge detection technique, and also to reduce false positives by using feature analysis techniques. In addition, the effects of many parameters on classification performance were investigated to identify proper threshold levels, and subsequently the specificity of the geometric-pattern feature analysis was improved from 69.5% to 86.1% at a sensitivity of 95.0%. Using a combined rule-based method with texture analysis and geometric-pattern feature analysis plus the artificial neural network (ANN) method for classification, a high specificity of 96.1% was obtained at a sensitivity of 95.0%.

Localization of inter‐rib spaces for lung texture analysis and computer‐aided diagnosis in digital chest images

An automated method for sampling lung textures in digital posterior/anterior chest images is being developed for use in computer-aided diagnosis of interstitial pulmonary diseases. In our present approach, two vertical profiles in the periphery of both lungs are fitted with a shift-variant sinusoidal function from which we estimate locations of posterior ribs and inter-rib spaces. Regions of interest (ROIs) for sampling lung textures are then automatically centered on the calculated locations of inter-rib spaces. In tests with 66 chest images, the overall success rate in placing 6.4 mm X 6.4 mm ROIs within inter-rib spaces with this method was 71%, with an average of 18 ROIs selected in 4-5 s/image by a VAX11/750 computer. When four additional alternative ROIs were selected on the sides of each original ROI, the success rate in having at least one ROI correctly located in an inter-rib space increased to 94%. Since we are still developing a fully automated sampling method, the present approach has been incorporated into a semiautomated method that is currently being used to sample lung textures from a large number of clinical cases.