False-positive reduction technique for detection of masses on digital mammograms: global and local multiresolution texture analysis

We investigated the application of multiresolution global and local texture features to reduce false-positive detection in a computerized mass detection program. One hundred and sixty-eight digitized mammograms were randomly and equally divided into training and test groups. From these mammograms, two datasets were formed. The first dataset (manual) contained four regions of interest (ROIs) selected manually from each of the mammograms. One of the four ROIs contained a biopsy-proven mass and the other three contained normal parenchyma, including dense, mixed dense/fatty, and fatty tissues. The second dataset (hybrid) contained the manually extracted mass ROIs, along with normal tissue ROIs extracted by an automated Density-Weighted Contrast Enhancement (DWCE) algorithm as false-positive detections. A wavelet transform was used to decompose an ROI into several scales. Global texture features were derived from the low-pass coefficients in the wavelet transformed images. Local texture features were calculated from the suspicious object and the peripheral subregions. Linear discriminant models using effective features selected from the global, local, or combined feature spaces were established to maximize the separation between masses and normal tissue. Receiver Operating Characteristic (ROC) analysis was conducted to evaluate the classifier performance. The classification accuracy using global features were comparable to that using local features. With both global and local features, the average area, Az, under the test ROC curve, reached 0.92 for the manual dataset and 0.96 for the hybrid dataset, demonstrating statistically significant improvement over those obtained with global or local features alone. The results indicated the effectiveness of the combined global and local features in the classification of masses and normal tissue for false-positive reduction.

Computerized classification of malignant and benign microcalcifications on mammograms: texture analysis using an artificial neural network

We investigated the feasibility of using texture features extracted from mammograms to predict whether the presence of microcalcifications is associated with malignant or benign pathology. Eighty-six mammograms from 54 cases (26 benign and 28 malignant) were used as case samples. All lesions had been recommended for surgical biopsy by specialists in breast imaging. A region of interest (ROI) containing the microcalcifications was first corrected for the low-frequency background density variation. Spatial grey level dependence (SGLD) matrices at ten different pixel distances in both the axial and diagonal directions were constructed from the background-corrected ROI. Thirteen texture measures were extracted from each SGLD matrix. Using a stepwise feature selection technique, which maximized the separation of the two class distributions, subsets of texture features were selected from the multi-dimensional feature space. A backpropagation artificial neural network (ANN) classifier was trained and tested with a leave-one-case-out method to recognize the malignant or benign microcalcification clusters. The performance of the ANN was analysed with receiver operating characteristic (ROC) methodology. It was found that a subset of six texture features provided the highest classification accuracy among the feature sets studied. The ANN classifier achieved an area under the ROC curve of 0.88. By setting an appropriate decision threshold, 11 of the 28 benign cases were correctly identified (39% specificity) without missing any malignant cases (100% sensitivity) for patients who had undergone biopsy. This preliminary result indicates that computerized texture analysis can extract mammographic information that is not apparent by visual inspection. The computer-extracted texture information may be used to assist in mammographic interpretation, with the potential to reduce biopsies of benign cases and improve the positive predictive value of mammography.

Computerized classification of malignant and benign microcalcifications on mammograms: texture analysis using an artificial neural network

We investigated the feasibility of using texture features extracted from mammograms to predict whether the presence of microcalcifications is associated with malignant or benign pathology. Eighty-six mammograms from 54 cases (26 benign and 28 malignant) were used as case samples. All lesions had been recommended for surgical biopsy by specialists in breast imaging. A region of interest (ROI) containing the microcalcifications was first corrected for the low-frequency background density variation. Spatial grey level dependence (SGLD) matrices at ten different pixel distances in both the axial and diagonal directions were constructed from the background-corrected ROI. Thirteen texture measures were extracted from each SGLD matrix. Using a stepwise feature selection technique, which maximized the separation of the two class distributions, subsets of texture features were selected from the multi-dimensional feature space. A backpropagation artificial neural network (ANN) classifier was trained and tested with a leave-one-case-out method to recognize the malignant or benign microcalcification clusters. The performance of the ANN was analysed with receiver operating characteristic (ROC) methodology. It was found that a subset of six texture features provided the highest classification accuracy among the feature sets studied. The ANN classifier achieved an area under the ROC curve of 0.88. By setting an appropriate decision threshold, 11 of the 28 benign cases were correctly identified (39% specificity) without missing any malignant cases (100% sensitivity) for patients who had undergone biopsy. This preliminary result indicates that computerized texture analysis can extract mammographic information that is not apparent by visual inspection. The computer-extracted texture information may be used to assist in mammographic interpretation, with the potential to reduce biopsies of benign cases and improve the positive predictive value of mammography.

Investigation of the line-pair pattern method for evaluating mammographic focal spot performance

The latest American College of Radiology (ACR) Mammography Quality Control Manual contains a new method for evaluating focal spot performance, which this paper refers to as the "line-pair pattern test." The ACR describes a variety of methods for performing this test, and does not advocate one method over another. The authors of this paper conducted an investigation to compare the optional ways for performing the test. Resolution measurements were obtained using a prototype line-pair resolution phantom imaged with a GE DMR mammography unit. Measurements were made with the line-pair pattern 4.5 cm above the breast support platforms in both conventional (contact) and magnification geometries. Both 4.5 cm of air and Lucite were tested as attenuators between the line-pair pattern and the breast support platform. Image receptors that were employed included film alone, screen-film, and screen-film that was not allowed to wait the recommended 15 min before exposure. kVp was varied as was the orientation of the line-pair pattern relative to the chest wall. For the air attenuator case, the screen degraded the measured resolution by 1-3 lp/mm when compared to the direct film. The Lucite attenuator reduced the resolution by an additional 1 1p/mm. Increasing kVp improved the resolution slightly for the conventional mode, but decreased it slightly for the magnification mode. Based upon the results of this study, recommendations are made for improving the test protocol. For a test of focal spot performance, one should use the no-attenuation with direct film detector setup. For a measure of the resolution of the entire imaging chain, one should use the Lucite attenuator with screen-film detector setup.

Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification

This paper presents segmentation and classification results of an automated algorithm for the detection of breast masses on digitized mammograms. Potential mass regions were first identified using density-weighted contrast enhancement (DWCE) segmentation applied to single-view mammograms. Once the potential mass regions had been identified, multiresolution texture features extracted from wavelet coefficients were calculated, and linear discriminant analysis (LDA) was used to classify the regions as breast masses or normal tissue. In this article the overall detection results for two independent sets of 84 mammograms used alternately for training and test were evaluated by free-response receiver operating characteristics (FROC) analysis. The test results indicate that this new algorithm produced approximately 4.4 false positive per image at a true positive detection rate of 90% and 2.3 false positives per image at a true positive rate of 80%.

Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue

We investigated a new approach to feature selection, and demonstrated its application in the task of differentiating regions of interest (ROIs) on mammograms as either mass or normal tissue. The classifier included a genetic algorithm (GA) for image feature selection, and a linear discriminant classifier or a backpropagation neural network (BPN) for formulation of the classifier outputs. The GA-based feature selection was guided by higher probabilities of survival for fitter combinations of features, where the fitness measure was the area Az under the receiver operating characteristic (ROC) curve. We studied the effect of different GA parameters on classification accuracy, and compared the results to those obtained with stepwise feature selection. The data set used in this study consisted of 168 ROIs containing biopsy-proven masses and 504 ROIs containing normal tissue. From each ROI, a total of 587 features were extracted, of which 572 were texture features and 15 were morphological features. The GA was trained and tested with several different partitionings of the ROIs into training and testing sets. With the best combination of the GA parameters, the average test Az value using a linear discriminant classifier reached 0.90, as compared to 0.89 for stepwise feature selection. Test Az values with a BPN classifier and a more limited feature pool were 0.90 with GA-based feature selection, and 0.89 for stepwise feature selection. The use of a GA in tailoring classifiers with specific design characteristics was also discussed. This study indicates that a GA can provide versatility in the design of linear or nonlinear classifiers without a trade-off in the effectiveness of the selected features.

Image compression in digital mammography: effects on computerized detection of subtle microcalcifications

Our previous receiver operating characteristic (ROC) study indicated that the detection accuracy of microcalcifications by radiologists is significantly reduced if mammograms are digitized at 0.1 mm x 0.1 mm. Our recent study also showed that detection accuracy by computer decreases as the pixel size increases from 0.035 mm x 0.035 mm. It is evident that very large matrix sizes have to be used for digitizing mammograms in order to preserve the information in the image. Efficient compression techniques will be needed to facilitate communication and archiving of digital mammograms. In this study, we evaluated two compression techniques: full frame discrete cosine transform (DCT) with entropy coding and Laplacian pyramid hierarchical coding (LPHC). The dependence of their efficiency on the compression parameters was investigated. The techniques were compared in terms of the trade-off between the bit rate and the detection accuracy of subtle microcalcifications by an automated detection algorithm. The mean-square errors in the reconstructed images were determined and the visual quality of the error images was examined. It was found that with the LPHC method, the highest compression ratio achieved without a significant degradation in the detectability was 3.6:1. The full frame DCT method with entropy coding provided a higher compression efficiency of 9.6:1 at comparable detection accuracy. The mean-square errors did not correlate with the detection accuracy of the microcalcifications. This study demonstrated the importance of determining the quality of the decompressed images by the specific requirements of the task for which the decompressed images are to be used. Further investigation is needed for selection of optimal compression technique for digital mammograms.

Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images

The authors investigated the classification of regions of interest (ROI's) on mammograms as either mass or normal tissue using a convolution neural network (CNN). A CNN is a backpropagation neural network with two-dimensional (2-D) weight kernels that operate on images. A generalized, fast and stable implementation of the CNN was developed. The input images to the CNN were obtained from the ROI's using two techniques. The first technique employed averaging and subsampling. The second technique employed texture feature extraction methods applied to small subregions inside the ROI. Features computed over different subregions were arranged as texture images, which were subsequently used as CNN inputs. The effects of CNN architecture and texture feature parameters on classification accuracy were studied. Receiver operating characteristic (ROC) methodology was used to evaluate the classification accuracy. A data set consisting of 168 ROIs containing biopsy-proven masses and 504 ROI's containing normal breast tissue was extracted from 168 mammograms by radiologists experienced in mammography. This data set was used for training and testing the CNN. With the best combination of CNN architecture and texture feature parameters, the area under the test ROC curve reached 0.87, which corresponded to a true-positive fraction of 90% at a false positive fraction of 31%. The authors' results demonstrate the feasibility of using a CNN for classification of masses and normal tissue on mammograms.

An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection

Presents a novel approach for segmentation of suspicious mass regions in digitized mammograms using a new adaptive density-weighted contrast enhancement (DWCE) filter in conjunction with Laplacian-Gaussian (LG) edge detection. The DWCE enhances structures within the digitized mammogram so that a simple edge detection algorithm can be used to define the boundaries of the objects. Once the object boundaries are known, morphological features are extracted and used by a classification algorithm to differentiate regions within the image. This paper introduces the DWCE algorithm and presents results of a preliminary study based on 25 digitized mammograms with biopsy proven masses. It also compares morphological feature classification based on sequential thresholding, linear discriminant analysis, and neural network classifiers for reduction of false-positive detections.

Normalized average glandular dose in magnification mammography

PURPOSE

To evaluate the normalized average glandular dose (the average glandular dose per unit entrance skin exposure) in magnification mammography.

MATERIALS AND METHODS

Photon transport in the breast was simulated by using Monte Carlo methods. A semielliptical cylinder containing glandular and adipose tissue was used to simulate the breast. Measured mammography spectra for a molybdenum target-molybdenum filter unit were utilized. The normalized average glandular dose was calculated as a function of half-value layer, tube voltage, breast thickness, and breast composition for typical magnification geometries.

RESULTS

The normalized average glandular dose in magnification mammography is 7%-25% lower than that with the contact (nonmagnification) technique because of the effects of partial irradiation, smaller field size, and greater percentage depth dose gradient at the reduced source-to-skin distance.

CONCLUSION

The normalized average glandular dose in magnification mammography is lower than that in contact mammography. The average glandular dose in magnification mammography, however, is still substantially greater due to the two to three times greater entrance skin exposure.

Computer-aided detection of mammographic microcalcifications: pattern recognition with an artificial neural network

We are developing a computer program for automated detection of clustered microcalcifications on mammograms. In this study, we investigated the effectiveness of a signal classifier based on a convolution neural network (CNN) approach for improvement of the accuracy of the detection program. Fifty-two mammograms with clustered microcalcifications were selected from patient files. The clusters on the mammograms were ranked by experienced mammographers and divided into an obvious group, an average group, and a subtle group. The average and subtle groups were combined and randomly divided into two sets, each of which was used as training or test set alternately. The obvious group served as an additional independent test set. Regions of interest (ROIs) containing potential individual microcalcifications were first located on each mammogram by the automated detection program. The ROIs from one set of the mammograms were used to train CNNs of different configurations with a back-propagation method. The generalization capability of the trained CNNs was then examined by their accuracy of classifying the ROIs from the other set and from the obvious group. The classification accuracy of the CNNs for the ROIs was evaluated by receiver operating characteristic (ROC) analysis. It was found that CNNs of many different configurations can reach approximately the same performance level, with the area under the ROC curve (Az) of 0.9. We incorporated a trained CNN into the detection program and evaluated the improvement of the detection accuracy by the CNN using free response ROC analysis. Our results indicated that, over a wide range of true-positive (TP) cluster detection rate, the CNN classifier could reduce the number of false-positive (FP) clusters per image by more than 70%. For the obvious cases, at a TP rate of 100%, the FP rate reduced from 0.35 cluster per image to 0.1 cluster per image. For the average and subtle cases, the detection accuracy improved from a TP rate of 87% at an FP rate of four clusters per image to a TP rate of 90% at an FP rate of 1.5 clusters per image.

Classification of mass and normal breast tissue on digital mammograms: multiresolution texture analysis

We investigated the feasibility of using multiresolution texture analysis for differentiation of masses from normal breast tissue on mammograms. The wavelet transform was used to decompose regions of interest (ROIs) on digitized mammograms into several scales. Multiresolution texture features were calculated from the spatial gray level dependence matrices of (1) the original images at variable distances between the pixel pairs, (2) the wavelet coefficients at different scales, and (3) the wavelet coefficients up to certain scale and then at variable distances between the pixel pairs. In this study, 168 ROIs containing biopsy-proven masses and 504 ROIs containing normal parenchyma were used as the data set. The mass ROIs were randomly and equally divided into training and test groups along with corresponding normal ROIs from the same film. Stepwise linear discriminant analysis was used to select optimal features from the multiresolution texture feature space to maximize the separation of mass and normal tissue for all ROIs. We found that texture features at large pixel distances are important for the classification task. The wavelet transform can effectively condense the image information into its coefficients. With texture features based on the wavelet coefficients and variable distances, the area Az under the receiver operating characteristic curve reached 0.89 and 0.86 for the training and test groups, respectively. The results demonstrate that a linear discriminant classifier using the multiresolution texture features can effectively classify masses from normal tissue on mammograms.

Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space

We studied the effectiveness of using texture features derived from spatial grey level dependence (SGLD) matrices for classification of masses and normal breast tissue on mammograms. One hundred and sixty-eight regions of interest (ROIS) containing biopsy-proven masses and 504 ROIS containing normal breast tissue were extracted from digitized mammograms for this study. Eight features were calculated for each ROI. The importance of each feature in distinguishing masses from normal tissue was determined by stepwise linear discriminant analysis. Receiver operating characteristic (ROC) methodology was used to evaluate the classification accuracy. We investigated the dependence of classification accuracy on the input features, and on the pixel distance and bit depth in the construction of the SGLD matrices. It was found that five of the texture features were important for the classification. The dependence of classification accuracy on distance and bit depth was weak for distances greater than 12 pixels and bit depths greater than seven bits. By randomly and equally dividing the data set into two groups, the classifier was trained and tested on independent data sets. The classifier achieved an average area under the ROC curve, Az, of 0.84 during training and 0.82 during testing. The results demonstrate the feasibility of using linear discriminant analysis in the texture feature space for classification of true and false detections of masses on mammograms in a computer-aided diagnosis scheme.

Solarization in clinical imaging

X-ray exposure levels at which solarization occurs were determined for a new screen-film system and its predecessor, both from the same manufacturer and both with a speed class of 400. Solarization (contrast reversal [lead markers imaged as black on a lighter back-ground]) was clearly evident with the new system at a cassette exposure level of 132 mR (3.4 x 10(-5) C/kg). No solarization was exhibited by the old system even at five times this exposure. In rare cases, solarization can obscure bone and soft-tissue detail, thereby degrading the diagnostic accuracy of the radiograph.

Breast thickness in routine mammograms: effect on image quality and radiation dose

OBJECTIVE

The purpose of this study was to compare the thickness of the compressed breast between mediolateral oblique and craniocaudal mammograms and to relate these differences in thickness to image quality and radiation dose. These differences may partially explain why some subtle tumors are better visualized on the craniocaudal view.

SUBJECTS AND METHODS

The study population consisted of 250 paired mediolateral oblique and craniocaudal mammograms obtained on one mammographic unit by seven certified mammography technologists during a 2-month period. Only women with breast implants, prior lumpectomy and radiotherapy, or chest wall deformity were excluded. The digital readout of compressed breast thickness and applied compression force was recorded. Mammographic positioning was assessed using standard criteria. Absorbed radiation dose at different thicknesses was measured with a BR-12 breast phantom. Image quality differences for geometric unsharpness and contrast were calculated for the observed breast thickness differences between mediolateral oblique and craniocaudal mammograms.

RESULTS

The mean thickness of the compressed breast on the craniocaudal view was less than the mean thickness on the mediolateral oblique view (4.4 versus 4.8 cm, p < .0001) despite the greater force used to compress the breast for mediolateral oblique than for craniocaudal views (93 versus 86 newtons, p < .0001). The breast thickness on the mediolateral oblique view exceeded that on the craniocaudal view in 98 (84%) of 117 pairs that differed in thickness by 5 mm or more and 46 (94%) of 49 pairs that differed by 10 mm or more (p < .0001). Geometric unsharpness increased by 8% and 19% when a 4.4-cm-thick breast was compared to a 4.8- and 5.4-cm-thick breast, respectively. A 5% and 12% loss of contrast was noted when a 4.4-cm-thick breast was compared to a 4.8- and 5.4-cm-thick breast. Mean glandular radiation dose at 4.4, 4.8, and 5.4 cm was 1.40, 1.70, and 2.33 mGy, respectively.

CONCLUSION

The compressed breast is 8% thicker on mediolateral oblique than on craniocaudal mammograms, a small but statistically significant difference. This difference results in a small loss of spatial and contrast resolution on the mediolateral oblique views and an increase in radiation dose. These image quality differences may partially explain why some subtle carcinomas are better visualized on the craniocaudal view.

The estimation of occupational effective dose in diagnostic radiology with two dosimeters

Annual effective dose limits have been proposed by national and international radiation protection committees. Radiation protection agencies must decide upon a method of converting the radiation dose measured from dosimeters to an estimate of effective dose. A proposed method for the estimation of effective dose from the radiation dose to two dosimeters is presented. Correction factors are applied to an over-apron collar dose and an under-apron dose to estimate the effective dose. Correction factors are suggested for two cases, both with and without a thyroid shield. Effective dose may be estimated by the under-apron dose plus 6% of the over-collar dose if a thyroid shield is not worn or plus 2% of the over-collar dose if a thyroid shield is worn. This method provides a reasonable estimate of effective dose that is independent of lead apron thickness and accounts for the use of a thyroid shield.

Automated segmentation of regions of interest on hand radiographs

Most radiologists do not use texture information contained in the trabecular patterns of hand radiographs to diagnose erosive changes and demineralization due to systemic inflammatory diseases that affect the skeletal system. However, high-resolution digitization achievable by a laser digitizer now makes it possible to access texture information that may not be perceived visually. We are studying the feasibility of computer-assisted early detection of these processes with particular attention to patients with hyperparathyroidism. In this paper the methods used to extract a region of interest (ROI) for texture analysis are discussed. The techniques include multiresolution sensing, automatic adaptive thresholding, detection of orientation angle, and projection taken perpendicular to the line of least second moment. The methods were tested on a database of 50 pairs of hand radiographs. We segmented the middle and the index fingers with an average success rate of 83% per hand. For the segmented finger strips, we located ROIs on both the middle and the proximal phalanges correctly over 84% of the times. Texture information was collected in the form of a concurrence matrix within the ROI. This study is a prelude to evaluating the correlation between classification based on texture analysis and diagnosis made by experienced radiologists.

Evaluation of a parallel hole grid for bedside chest imaging

RATIONALE AND OBJECTIVES

The application of a new parallel hole grid designed for bedside radiography is investigated. This grid is constructed of sheets of holes and is designed to have more tolerance to positioning errors than conventional grids.

METHODS

The parallel hole grid is compared to conventional 6:1 and 12:1 grids using phantoms. The contrast improvement, scatter fractions, exposure, and tolerance to positioning errors are measured.

RESULTS

The parallel hole grid has much more tolerance to positioning errors than conventional grids. The contrast improvement and scatter rejection are significantly less than those obtained with a conventional 6:1 ratio grid. Compared with nongrid techniques, the parallel hole grid provides 13% to 20% higher lung contrast.

CONCLUSIONS

The parallel hole grid may be used for bedside imaging without the need for accurate alignment. The parallel hole grid requires approximately 2.7 times the entrance exposure of a nongrid technique. Lung contrast improvement is approximately half of that from an accurately aligned 6:1 conventional grid. For grid angulation greater than 8 degrees, the parallel hole grid provides higher contrast than the 6:1 grid.

Digitization requirements in mammography: effects on computer-aided detection of microcalcifications

We have developed a computerized method for detection of microcalcifications on digitized mammograms. The program has achieved an accuracy that can detect subtle microcalcifications which may potentially be missed by radiologists. In this study, we evaluated the dependence of the detection accuracy on the pixel size and pixel depth of the digitized mammograms. The mammograms were digitized with a laser film scanner at a pixel size of 0.035 mm x0.035 mm and 12-bit gray levels. Digitization with larger pixel sizes or fewer number of bits was simulated by averaging adjacent pixels or by eliminating the least significant bits, respectively. The SNR enhancement filter and the signal-extraction criteria in the computer program were adjusted to maximize the accuracy of signal detection for each pixel size. The overall detection accuracy was compared using the free response receiver operating characteristic curves. The results indicate that the detection accuracy decreases significantly as the pixel size increases from 0.035 mm x 0.035 mm to 0.07 mm x 0.07 mm (P < 0.007) and from 0.07 mm x 0.07 mm to 0.105 mm x 0.105 mm (P < 0.002). The detection accuracy is essentially independent of pixel depth from 12 to 9 bits and decreases significantly (P < 0.003) from 9 to 8 bits; a rapid decrease is observed as the pixel depth decreases further from 8 to 7 bits (P < 0.03) or from 7 to 6 bits (P < 0.02).(ABSTRACT TRUNCATED AT 250 WORDS)

Computer-aided diagnosis: detection and characterization of hyperparathyroidism in digital hand radiographs

An automated method is developed for the detection and staging of skeletal changes due to hyperparathyroidism on digitized hand radiographs. Subperiosteal bony resorption, particularly along the radial margins of the middle and proximal phalanges, is among the earliest manifestations of secondary hyperparathyroidism. In order to quantify the severity of bone resorption in these regions, the computer method analyzes the roughness of the phalangeal margins, as projected on the radiograph. The regions of interest, which contain the phalanges, are obtained from the digitized hand radiographs by an image preprocessor. The radial margin of each phalanx is detected by a model-guided boundary-tracking scheme. The roughness of these boundaries is then quantified by the mean-square variation and the first moment of the power spectrum. A receiver operating characteristic (ROC) study comparing the computer detection of hyperparathyroidism with the diagnosis by three experienced skeletal radiologists was performed by evaluating 84 hand images from 22 patients. Our present computer method can achieve a true-positive rate of 94% and a true-negative rate of 92%. Such a computer-aided diagnosis system may assist radiologists in their assessment of primary and secondary hyperparathyroidism, since it is both accurate and not subject to either intra- or interobserver variations.

Interventional radiologists: occupational radiation doses and risks

Interventional radiologists receive nonuniform occupational radiation doses, with relatively high doses to the head and extremities and low doses to the trunk, which is protected by a lead apron. Twenty-eight interventional radiologists from 17 institutions wore thermoluminescent dosimeters over their collars and under their aprons for a 2-month period. The estimated annual radiation dose was converted to effective dose as suggested by the International Commission on Radiological Protection. Effective dose is used to relate the risk associated with nonuniform dose to that associated with an equivalent uniform whole-body dose. The mean annual effective dose was 3.16 mSv (316 mrem), with a range of 0.37-10.1 mSv. The mean annual effective dose is approximately equal to the mean natural background dose of 3 mSv per year from radon and other natural sources and is only 6% of the National Council on Radiation Protection and Measurements' recommended effective dose equivalent limit of 50 mSv per year. The annual radiation risk of fatal cancer would be less than one per 10,000 for almost the entire career of an interventional radiologist.

Portable chest imaging: comparison of storage phosphor digital, asymmetric screen-film, and conventional screen-film systems

The quality of chest images obtained with portable radiography was evaluated for a conventional screen-film system, a new asymmetric screen-film chest system, and computed radiography (CR). Sixty chest images were obtained in 20 patients in an intensive care unit. The CR system was ranked by all three evaluating radiologists as substantially better in overall diagnostic quality, interpretability of the lungs, and musculoskeletal detail and by two of the three observers as better for the visibility of catheters and lines. In the upper abdomen and mediastinum, there was not a clear preference. Standard deviations of film density were +/- 0.12, +/- 0.41, and +/- 0.39 for the CR, conventional, and asymmetric systems, respectively. For the same systems, phantom results indicated the relative lung contrast values were 1.2, 1.0, and 0.89, respectively. Similarly, the limiting resolution values in the lung were 2.0, 4.2, and 6.3 line pairs per millimeter. The CR system had twice the root-mean-square noise of the screen-film systems. Overall, the preferred system for portable chest imaging was the CR system.

Automated tracking and computer reproduction of vessels in DSA images

We are developing an automated vessel-tracking method based on the double-square-box region-of-search technique, for efficient tracking of the connected vascular tree in a digital subtraction angiography (DSA) image. Tracking points and branch vessels are located by searching of the perimeter of boxes, which are centered on previously determined tracking points. The most accurate results (90% true-positive rate with six false-positives per image) are obtained by tracking using the double-square-box method. In relatively straight regions of vessels, a large box is employed for efficient tracking; in curved regions of vessels, a small box is employed to ensure accurate tracking. When tracking is completed, accurate vessel information, ie, the vessel position, size, and contrast determined at each tracking point, is available for further quantitative analysis. Computer reproductions of tracked vessel trees appear to correspond well to those in DSA images.

Improvement in radiologists' detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis

Relatively simple, but important, detection tasks in radiology are nearing accessibility to computer-aided diagnostic (CAD) methods. The authors have studied one such task, the detection of clustered microcalcifications on mammograms, to determine whether CAD can improve radiologists' performance under controlled but generally realistic circumstances. The results of their receiver operating characteristic (ROC) study show that CAD, as implemented by their computer code in its present state of development, does significantly improve radiologists' accuracy in detecting clustered microcalcifications under conditions that simulate the rapid interpretation of screening mammograms. The results suggest also that a reduction in the computer's false-positive rate will further improve radiologists' diagnostic accuracy, although the improvement falls short of statistical significance in this study.

Studies of performance of antiscatter grids in digital radiography: effect on signal-to-noise ratio

We developed a theoretical model which describes the improvement of signal-to-noise ratio (SNR) by a grid in digital radiography. The model takes into account the effects of spatial variations in the scatter-to-primary ratio and in the large-area contrast over an image with structured background on quantum noise, and the effects of noise in the imaging system such as electronic noise and digitization noise. Based on the theoretical model, we analyzed the effects of these factors on the SNR when a grid is employed. We performed experimental measurements to evaluate the improvement in the SNR by a grid when quantum noise is the dominant noise source. It was found that the measured SNR improvement factor due to quantum noise agreed closely with that determined from the measured transmission values of a grid, as predicted from our theoretical model. In order to evaluate the relative performance of grids with various geometric design parameters for digital radiographic systems, we employed Monte Carlo calculations and determined the transmission values of a number of grids under various scatter conditions. The calculated SNR improvement factor, due to quantum noise, correlated well with the measured improvement of the SNR by the grids. Our model predicts that the SNR improvement factor depends strongly on the local contrast ratio and also on the scatter-to-primary ratio. The SNR improvement factor is higher in the underpenetrated regions than in the well-penetrated regions of an image.