Diffuse nodular lung disease on chest radiographs: a pilot study of characterization by fractal dimension

Computer-Aided Diagnosis for Chest Radiographs in Intensive Care

The chest radiograph is an essential tool for the diagnosis of several lung diseases in intensive care units (ICU). However, several factors make the interpretation of the chest radiograph difficult including the number of X-rays done daily in ICU, the quality of the chest radiograph, and the lack of a standardized interpretation. To overcome these limitations in the interpretation of chest radiographs, researchers have developed computer-aided diagnosis (CAD) systems. In this review, the authors report the methodology used to develop CAD systems including identification of the region of interest, analysis of these regions, and classification. Currently, only a few CAD systems for chest X-ray interpretation are commercially available. Some promising research is ongoing, but the involvement of the pediatric research community is needed for the development and validation of such CAD systems dedicated to pediatric intensive care.

Effect of aging on lung structure in vivo: assessment with densitometric and fractal analysis of high-resolution computed tomography data

PURPOSE

To test the hypothesis that there is a difference between the lung computed tomography (CT) microstructure of asymptomatic older individuals and that of young individuals as evaluated by objective indices of complexity and density.

MATERIALS AND METHODS

Two study groups of nonsmoking urban-dwelling individuals over 75 years and under 55 years were prospectively identified. Thirty-three consecutive volunteers (21 older than 75 y and 12 less than 55 y) were included, and CTs were performed with concurrent pulmonary function testing. Pulmonary regions of interest (ROIs) were evaluated with fractal dimension (FD) analysis (an index of complexity), mean lung density (MLD), and percentage of pixels with lung density (LD) less than thresholds of -910 HU and -950 HU. The Student t test and the Mann-Whitney test were used to evaluate for differences in mean values between groups. The Pearson correlation coefficient was used to correlate mean FD value and LD data with pulmonary function.

RESULTS

Significant correlations of ROI MLD, LD -910 HU, and LD -950 HU with age and sex were shown (P = 0.029-0.003). The ROI mean FD value was greater in younger individuals compared with older individuals (76.5 ± 1.7 vs. 70.3 ± 1.2; P = 0.004). There was a correlation between Kco (gas-diffusing capacity adjusted for alveolar volume) and mean FD value (P = 0.006) and MLD (P = 0.015).

CONCLUSION

The lung parenchyma of nonsmoking older urban-dwelling asymptomatic individuals has significantly different CT density and complexity compared with younger individuals.

Recent progress in computer-aided diagnosis of lung nodules on thin-section CT

Computer-aided diagnosis (CAD) provides a computer output as a "second opinion" in order to assist radiologists in the diagnosis of various diseases on medical images. Currently, a significant research effort is being devoted to the detection and characterization of lung nodules in thin-section computed tomography (CT) images, which represents one of the newest directions of CAD development in thoracic imaging. We describe in this article the current status of the development and evaluation of CAD schemes for the detection and characterization of lung nodules in thin-section CT. We also review a number of observer performance studies in which it was attempted to assess the potential clinical usefulness of CAD schemes for nodule detection and characterization in thin-section CT. Whereas current CAD schemes for nodule characterization have achieved high performance levels and would be able to improve radiologists' performance in the characterization of nodules in thin-section CT, current schemes for nodule detection appear to report many false positives, and, therefore, significant efforts are needed in order further to improve the performance levels of current CAD schemes for nodule detection in thin-section CT.

Fractal-feature distance analysis of radiographic image

RATIONALE AND OBJECTIVES

We have conducted a fractal analysis of low-dose digital chest phantom radiographs and evaluated the relationship between the fractal-feature distance and the tube current-exposure time product.

MATERIALS AND METHODS

Chest phantom radiographs were obtained at various mAs values (0.5-4.0 mAs) and 140 kVp with a computed radiography system, and the reference images were acquired at 13 mAs. The lung field images were converted to binary images after processing them using the rolling-ball technique; a fractal analysis was conducted using the box-counting method for these binary images. The fractal-feature distances between the low-dose and reference images were calculated using the fractal dimension and the complexity.

RESULTS

For all binary images of lung fields, the relationship between the length of the square boxes and the number of boxes needed to cover the positive pixels of the binary image was linear on a log-log scale (r > or = 0.99). For mAs > or = 3.0, the fractal-feature distances were almost constant, whereas for mAs < or = 2.5, they increased depending on the reduction in mAs values.

CONCLUSION

We have shown that a binary image of the lung field obtained from a chest phantom radiograph can be analyzed by the box-counting method and that its fractal-feature distance grows as the radiation dose declines.

A fully automated method for lung nodule detection from postero-anterior chest radiographs

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.

Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN)

When lung nodules overlap with ribs or clavicles in chest radiographs, it can be difficult for radiologists as well as computer-aided diagnostic (CAD) schemes to detect these nodules. In this paper, we developed an image-processing technique for suppressing the contrast of ribs and clavicles in chest radiographs by means of a multiresolution massive training artificial neural network (MTANN). An MTANN is a highly nonlinear filter that can be trained by use of input chest radiographs and the corresponding "teaching" images. We employed "bone" images obtained by use of a dual-energy subtraction technique as the teaching images. For effective suppression of ribs having various spatial frequencies, we developed a multiresolution MTANN consisting of multiresolution decomposition/composition techniques and three MTANNs for three different-resolution images. After training with input chest radiographs and the corresponding dual-energy bone images, the multiresolution MTANN was able to provide "bone-image-like" images which were similar to the teaching bone images. By subtracting the bone-image-like images from the corresponding chest radiographs, we were able to produce "soft-tissue-image-like" images where ribs and clavicles were substantially suppressed. We used a validation test database consisting of 118 chest radiographs with pulmonary nodules and an independent test database consisting of 136 digitized screen-film chest radiographs with 136 solitary pulmonary nodules collected from 14 medical institutions in this study. When our technique was applied to nontraining chest radiographs, ribs and clavicles in the chest radiographs were suppressed substantially, while the visibility of nodules and lung vessels was maintained. Thus, our image-processing technique for rib suppression by means of a multiresolution MTANN would be potentially useful for radiologists as well as for CAD schemes in detection of lung nodules on chest radiographs.

A study on the computerized fractal analysis of architectural distortion in screening mammograms

Architectural distortion (AD) is a sign of malignancy often missed during mammographic interpretation. The purpose of this study was to explore the application of fractal analysis to the investigation of AD in screening mammograms. The study was performed using mammograms from the Digital Database for Screening Mammography (DDSM). The fractal dimension (FD) of mammographic regions of interest (ROIs) was calculated using the circular average power spectrum technique. Initially, the variability of the FD estimates depending on ROI location, mammographic view and breast side was studied on normal mammograms. Then, the estimated FD was evaluated using receiver operating characteristics (ROC) analysis to determine if it can discriminate ROIs depicting AD from those depicting normal breast parenchyma. The effect of several factors such as ROI size, image subsampling and breast density was studied in detail. Overall, the average FD of the normal ROIs was statistically significantly higher than that of the ROIs with AD. This result was consistent across all factors studied. For the studied set of implementation parameters, the best ROC performance achieved was 0.89 +/- 0.02. The generalizability of these conclusions across different digitizers was also demonstrated.

False-positive reduction in computer-aided diagnostic scheme for detecting nodules in chest radiographs by means of massive training artificial neural network

RATIONALE AND OBJECTIVE

We developed a technique that uses a multiple massive-training artificial neural network (multi-MTANN) to reduce the number of false-positive results in a computer-aided diagnostic (CAD) scheme for detecting nodules in chest radiographs.

MATERIALS AND METHODS

Our database consisted of 91 solitary pulmonary nodules, including 64 malignant nodules and 27 benign nodules, in 91 chest radiographs. With our current CAD scheme based on a difference-image technique and linear discriminant analysis, we achieved a sensitivity of 82.4%, with 4.5 false positives per image. We developed the multi-MTANN for further reduction of the false positive rate. An MTANN is a highly nonlinear filter that can be trained with input images and corresponding teaching images. To reduce the effects of background levels in chest radiographs, we applied a background-trend-correction technique, followed by contrast normalization, to the input images for the MTANN. For enhancement of nodules, the teaching image was designed to contain the distribution for a "likelihood of being a nodule." Six MTANNs in the multi-MTANN were trained by using typical nodules and six different types of non-nodules (false positives).

RESULTS

Use of the trained multi-MTANN eliminated 68.3% of false-positive findings with a reduction of one true-positive result. The false-positive rate of our original CAD scheme was improved from 4.5 to 1.4 false positives per image, at an overall sensitivity of 81.3%.

CONCLUSION

Use of a multi-MTANN substantially reduced the false-positive rate of our CAD scheme for lung nodule detection on chest radiographs, while maintaining a level of sensitivity.

Fractal analysis of small peripheral pulmonary nodules in thin-section CT: evaluation of the lung-nodule interfaces

OBJECTIVES

To analyze the lung-nodule interfaces on small peripheral pulmonary nodules (<2 cm) in thin-section CT (HRCT) images with fractal analysis.

METHODS

Thin-section CT images from 70 patients with bronchogenic carcinomas (61 adenocarcinomas and 9 squamous cell carcinomas) and 47 patients with benign pulmonary nodules (23 hamartomas, 13 organizing pneumonias, and 11 tuberculomas) were used. For calculation of fractal dimensions (FDs), the authors used a box-counting method for binary- and gray-scale images of nodules. FD(two-dimensional [2D]) was an FD obtained from the binary image, and FD(three-dimensional [3D]) was an FD obtained from the gray-scale image.

RESULTS

The FD(2D)s of hamartomas were smaller than those of other nodules ( < 0.05). The FD(3D)s obtained from the gray-scale images of organizing pneumonias and tuberculomas were greater than those of bronchogenic carcinomas ( < 0.0001) and hamartomas ( < 0.0001). In bronchogenic carcinomas, FD(3D)s of adenocarcinomas were greater than those of squamous cell carcinomas ( < 0.05).

CONCLUSIONS

Fractal dimensions reflect the characteristics of the lung-nodule interfaces of small peripheral pulmonary nodules. The FD(2D)s revealed the irregularities of the contours. On the other hand, FD(3D)s revealed the complexities of the heterogeneous textures. With use of FD(2D) and FD(3D), it may be possible to distinguish bronchogenic carcinomas from benign pulmonary nodules. Moreover, FD(3D) may make it possible to distinguish between adenocarcinomas and squamous cell carcinomas.

Computer-aided diagnosis in chest radiography: a survey

The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images, which comprises over 150 papers published in the last 30 years. Remaining challenges are indicated and some directions for future research are given.

Fractal texture analysis of perfusion lung scans

The purpose of this study is to investigate if fractal texture analysis can assist in the diagnostic interpretation of perfusion lung scans. Forty-five perfusion scans were acquired from patients with clinical suspicion of acute pulmonary embolism (PE) who underwent pulmonary angiography for final diagnosis. Fractal texture analysis was performed on 270 regions of interest (ROIs) extracted from the posterior view of the lung scans. Specifically, there were 94 normally perfused ROIs and 176 abnormal ROIs representing various lung diseases including PE and obstructive pulmonary disease (OPD). The average fractal dimension (FD) of normal ROIs was statistically significantly higher than that of abnormal ROIs. Furthermore, the FDs of abnormal ROIs with PE were significantly lower than the FDs of ROIs with OPD present.

Slice simulation from a model of the parenchymous vascularization to evaluate texture features: work in progress

RATIONALE AND OBJECTIVES

To demonstrate the usefulness of a model of the parenchymous vascularization to evaluate texture analysis methods.

METHODS

Slices with thickness varying from 1 to 4 mm were reformatted from a 3D vascular model corresponding to either normal tissue perfusion or local hypervascularization. Parameters of statistical methods were measured on 16128x128 regions of interest, and mean values and standard deviation were calculated. For each parameter, the performances (discrimination power and stability) were evaluated.

RESULTS

Among 11 calculated statistical parameters, three (homogeneity, entropy, mean of gradients) were found to have a good discriminating power to differentiate normal perfusion from hypervascularization, but only the gradient mean was found to have a good stability with respect to the thickness. Five parameters (run percentage, run length distribution, long run emphasis, contrast, and gray level distribution) were found to have intermediate results. In the remaining three, curtosis and correlation was found to have little discrimination power, skewness none.

CONCLUSION

This 3D vascular model, which allows the generation of various examples of vascular textures, is a powerful tool to assess the performance of texture analysis methods. This improves our knowledge of the methods and should contribute to their a priori choice when designing clinical studies.