Search

As one of the most prevalent chronic disorders, airway disease is a major cause of morbidity and mortality worldwide. In order to understand its underlying mechanisms and to enable assessment of therapeutic efficacy of a variety of possible interventions, noninvasive investigation of the airways in a large number of subjects is of great research interest. Due to its high resolution in temporal and spatial domains, computed tomography (CT) has been widely used in clinical practices for studying the normal and abnormal manifestations of lung diseases, albeit there is a need to clearly demonstrate the benefits in light of the cost and radiation dose associated with CT examinations performed for the purpose of airway analysis. Whereas a single CT examination consists of a large number of images, manually identifying airway morphological characteristics and computing features to enable thorough investigations of airway and other lung diseases is very time-consuming and susceptible to errors. Hence, automated and semiautomated computerized analysis of human airways is becoming an important research area in medical imaging. A number of computerized techniques have been developed to date for the analysis of lung airways. In this review, we present a summary of the primary methods developed for computerized analysis of human airways, including airway segmentation, airway labeling, and airway morphometry, as well as a number of computer-aided clinical applications, such as virtual bronchoscopy. Both successes and underlying limitations of these approaches are discussed, while highlighting areas that may require additional work.

Purpose: The authors developed and tested a multiprobe-based resonance-frequency-based electrical impedance spectroscopy (REIS) system. The purpose of this study was to preliminarily assess the performance of this system in classifying younger women into two groups, those ultimately recommended for biopsy during imaging-based diagnostic workups that followed screening and those rated as negative during mammography. Methods: A seven probe-based REIS system was designed, assembled, and is currently being tested in the breast imaging facility. During an examination, contact is made with the nipple and six concentric points on the breast skin. For each measurement channel between the center probe and one of the six external probes, a set of electrical impedance spectroscopy (EIS) signal sweeps is performed and signal outputs ranging from 200 to 800 kHz at 5 kHz interval are recorded. An initial subset of 174 examinations from an ongoing prospective clinical study was selected for this preliminary analysis. An initial set of 35 features, 33 of which represented the corresponding EIS signal differences between the left and right breasts, was established. A Gaussian mixture model (GMM) classifier was developed to differentiate between “positive” (biopsy recommended) cases and “negative” (nonbiopsy) cases. Selecting an optimal feature set was performed using genetic algorithms with an area under a receiver operating characteristic curve (AUC) as the fitness criterion. Results: The recorded EIS signal sweeps showed that, in general, negative (nonbiopsy) examinations have a higher level of electrical impedance symmetry between the two breasts than positive (biopsy) examinations. Fourteen features were selected by genetic algorithm and used in the optimized GMM classifier. Using a leave-one-case-out test, the GMM classifier yielded a performance level of AUC=0.78, which compared favorably to other three widely used classifiers including support vector machine, classification tree, and linear discriminant analysis. These results also suggest that the REIS signal based GMM classifier could be used as a prescreening tool to correctly identify a fraction of younger women at higher risk of developing breast cancer (i.e., 47% sensitivity at 90% specificity). Conclusions: The study confirms that asymmetry in electrical impedance characteristics between two breasts provides valuable information regarding the presence of a developing breast abnormality; hence, REIS data may be useful in classifying younger women into two groups of “average” and “significantly higher than average” risk of having or developing a breast abnormality that would ultimately result in a later imaging-based recommendation for biopsy.

Purpose: The development of computer-aided diagnostic (CAD) methods for lung nodule detection, classification, and quantitative assessment can be facilitated through a well-characterized repository of computed tomography (CT) scans. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) completed such a database, establishing a publicly available reference for the medical imaging research community. Initiated by the National Cancer Institute (NCI), further advanced by the Foundation for the National Institutes of Health (FNIH), and accompanied by the Food and Drug Administration (FDA) through active participation, this public-private partnership demonstrates the success of a consortium founded on a consensus-based process. Methods: Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve challenging organizational, technical, and clinical issues to provide a solid foundation for a robust database. The LIDC/IDRI Database contains 1018 cases, each of which includes images from a clinical thoracic CT scan and an associated XML file that records the results of a two-phase image annotation process performed by four experienced thoracic radiologists. In the initial blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories (" nodule�3 mm," " nodule

Purpose: Knowledge of pulmonary interlobar fissure integrity is of interest in a number of clinical and investigational applications. The authors developed and tested a high resolution CT based automated computerized scheme for this purpose. Methods: The fissure integrity assessment scheme consists of the following steps: (1) Fissure detection, (2) individual fissure identification, (3) fissure type determination, (4) “complete” interlobe surface estimation, and (5) fissure integrity estimation. For evaluation purposes, 50 anonymized chest CT examinations were ascertained and the complete and “incomplete” regions of the fissures of interest were manually marked by two experienced radiologists. After applying the scheme to the same examinations, differences among fissure percent completeness estimates based on the radiologists’ manual markings and the automated computerized scheme were computed and compared. Results: Average differences in estimated fissure percent completeness (integrity) between the results of the computerized scheme and that based on each of the two radiologists’ markings were 6.88%±5.86%, 9.57%±7.77%, and 4.19%±5.64% for the right major fissures, the right minor fissures, and the left major fissures, respectively. The differences between results based on radiologists’ markings for the same fissures were 4.27%±3.32%, 7.02%±5.54%, and 4.23%±4.93%, respectively. The difference among the three matched measurement sets for each fissure were statistically significant (Friedman’s test, p≤0.005) but paired comparisons showed that much of the observed difference was related to inter-reader differences rather than reader-computerized scheme differences. Computerized estimates were correlated with each of the radiologist’s estimates (Spearman, p

The authors investigated radiologists, performances during retrospective interpretation of screening mammograms when using a binary decision whether to recall a woman for additional procedures or not and compared it with their receiver operating characteristic (ROC) type performance curves using a semi-continuous rating scale. Under an Institutional Review Board approved protocol nine experienced radiologists independently rated an enriched set of 155 examinations that they had not personally read in the clinic, mixed with other enriched sets of examinations that they had individually read in the clinic, using both a screening BI-RADS rating scale (recall/not recall) and a semi-continuous ROC type rating scale (0 to 100). The vertical distance, namely the difference in sensitivity levels at the same specificity levels, between the empirical ROC curve and the binary operating point were computed for each reader. The vertical distance averaged over all readers was used to assess the proximity of the performance levels under the binary and ROC-type rating scale. There does not appear to be any systematic tendency of the readers towards a better performance when using either of the two rating approaches, namely four readers performed better using the semi-continuous rating scale, four readers performed better with the binary scale, and one reader had the point exactly on the empirical ROC curve. Only one of the nine readers had a binary "operating point" that was statistically distant from the same reader's empirical ROC curve. Reader-specific differences ranged from -0.046 to 0.128 with an average width of the corresponding 95% confidence intervals of 0.2 and p-values ranging for individual readers from 0.050 to 0.966. On average, radiologists performed similarly when using the two rating scales in that the average distance between the run in individual reader's binary operating point and their ROC curve was close to zero. The 95% confidence interval for the fixed-reader average (0.016) was (-0.0206, 0.0631) (two-sided p-value 0.35). In conclusion the authors found that in retrospective observer performance studies the use of a binary response or a semi-continuous rating scale led to consistent results in terms of performance as measured by sensitivity-specificity operating points.

The authors present a new computerized scheme to automatically detect lung nodules depicted on computed tomography (CT) images. The procedure is performed in the signed distance field of the CT images. To obtain an accurate signed distance field, CT images are first interpolated linearly along the axial direction to form an isotropic data set. Then a lung segmentation strategy is applied to smooth the lung border aiming to include as many juxtapleural nodules as possible while minimizing over segmentations of the lung regions. Potential nodule regions are then detected by locating local maximas of signed distances in each subvolume with values and the sizes larger than the smallest nodule of interest in the three-dimensional space. Finally, all detected candidates are scored by computing the similarity distance of their medial axis-like shapes obtained through a progressive clustering strategy combined with a marching cube algorithm from a sphere based shape. A free-response receiver operating characteristics curve is computed to assess the scheme performance. A performance test on 52 low-dose CT screening examinations that depict 184 verified lung nodules showed that during the initial stage the scheme achieved an asymptotic maximum sensitivity of 95.1% (175∕184) with an average of 1200 suspicious voxels per CT examination. The nine missed nodules included two small solid nodules (with a diameter ≤3.1 mm) and seven nonsolid nodules. The final performance level after the similarity scoring stage was an absolute sensitivity level, namely, including the nine missed during the initial stage, of 81.5% (150∕184) with 6.5 false-positive identifications per CT examination. This preliminary study demonstrates the feasibility of applying a simple and robust geometric model using the signed distance field to identify suspicious lung nodules. In the authors’ data set the sensitivity of this scheme is not affected by nodule size. In addition to potentially being a stand alone approach, the signed distance field based method can be easily implemented as an initial filtering step in other computer-aided detection schemes.

The task of searching and detecting multiple abnormalities depicted on an image, or a series of images, is a common problem in different areas such as military target detection or diagnostic medical imaging. A free response receiver operating characteristic (FROC) approach for assessing performance in many of these scenarios entails marking the locations of suspected abnormalities and indicating a level of suspicion at each of the marked locations. One of the important characteristics of a system being evaluated under the FROC paradigm is its performance in the conventional ROC domain, namely classifying a subject (or a unit of interest) as “negative” or “positive” in regard to the presence of the abnormality (or any of the abnormalities) of interest. With FROC data we can compare subjects by specifying a function of multiple scores within a subject. This approach allows formulating subject-based ROC type indices that can be estimated using existing ROC concepts. In this article we focus on indices that reflect the ability of the system to discriminate between actually negative and actually positive subjects. We consider a previously proposed index that is based on the comparison of the highest scores on subjects and two new indices that are based on potentially more stable comparison functions, namely comparison of average scores and stochastic dominance. Based on these indices we develop nonparametric procedures for comparing subject-based discriminative ability of diagnostic systems being evaluated under the FROC paradigm. We also investigate the properties of the statistical procedures in a simulation study.

When reading mammograms, radiologists routinely search for and compare suspicious breast lesions identified on two corresponding craniocaudal (CC) and mediolateral oblique (MLO) views. Automatically identifying and matching the same true-positive breast lesions depicted on two views is an important step for developing successful multiview based computer-aided detection (CAD) schemes. The authors developed a method to automatically register breast areas and detect matching strips of interest used to identify the matched mass regions depicted on CC and MLO views. The method uses an ellipse based model to fit the breast boundary contour (skin line) and set a local Cartesian coordinate system for each view. One intersection point between the major/minor axis and the fitted ellipse perimeter passed through breast boundary is selected as the origin and the majoraxis and the minoraxis of the ellipse are used as the two axis of the Cartesian coordinate system. When a mass is identified on one view, the scheme computes its position in the local coordinate system. Then, the distance is mapped onto the local coordinate of the other view. At the end of the mapped distance a registered centerline of the matching strip is created. The authors established an image database that includes 200 test examinations each depicting one verified mass visible on the two views. They tested whether the registered centerline identified on another view can be used to locate the matched mass region. The experiments show that the average distance between the mass region centers and the registered centerlines was ±8.3 mm and in 91% of testing cases the registered centerline actually passes through the matched mass regions. A matching strip width of 47 mm was required to achieve 100% sensitivity for the test database. The results demonstrate the feasibility of the proposed method to automatically identify masses depicted on CC and MLO views, which may improve future development of multiview based CAD schemes.

We developed and tested a fully automated computerized scheme that identifies pulmonary airway sections depicted on computed tomography (CT) images and computes their sizes including the lumen and airway wall areas. The scheme includes four processing modules that (1) segment left and right lung areas, (2) identify airway locations, (3) segment airway walls from neighboring pixels, and (4) compute airway sizes. The scheme uses both a raster scanning and a labeling algorithm complemented by simple classification rules for region size and circularity to automatically search for and identify airway sections of interest. A profile tracking method is used to segment airway walls from neighboring pixels including those associated with dense tissue (i.e., pulmonary arteries) along scanning radial rays. A partial pixel membership method is used to compute airway size. The scheme was tested on ten randomly selected CT studies that included 26 sets of CT images acquired using both low and conventional dose CT examinations with one of four reconstruction algorithms (namely, 'bone', 'lung', 'soft', and 'standard' convolution kernels). Three image section thicknesses (1.25, 2.5, and 5 mm) were evaluated. The scheme detected a large number of quantifiable airway sections when the CT images were reconstructed using high spatial frequencymore » convolution kernels. The detection results demonstrated a consistent trend for all test image sets in that as airway lumen size increases, on average the airway wall area increases as well and the wall area percentage decreases. The study suggested that CT images reconstructed using high spatial frequency convolution kernels and thin-section thickness were most amenable to automated detection, reasonable segmentation, and quantified assessment when the airways are close to being perpendicular to the CT image plane.« less

The purpose of this study was to develop and test a method for selecting "visually similar" regions of interest depicting breast masses from a reference library to be used in an interactive computer-aided diagnosis (CAD) environment. A reference library including 1000 malignant mass regions and 2000 benign and CAD-generated false-positive regions was established. When a suspicious mass region is identified, the scheme segments the region and searches for similar regions from the reference library using a multifeature based k-nearest neighbor (KNN) algorithm. To improve selection of reference images, we added an interactive step. All actual masses in the reference library were subjectively rated on a scale from 1 to 9 as to their "visual margins speculations". When an observer identifies a suspected mass region during a case interpretation he/she first rates the margins and the computerized search is then limited only to regions rated as having similar levels of spiculation (within +/-1 scale difference). In an observer preference study including 85 test regions, two sets of the six "similar" reference regions selected by the KNN with and without the interactive step were displayed side by side with each test region. Four radiologists and five nonclinician observers selected the more appropriate ("similar") reference set in a two alternative forced choice preference experiment. All four radiologists and five nonclinician observers preferred the sets of regions selected by the interactive method with an average frequency of 76.8% and 74.6%, respectively. The overall preference for the interactive method was highly significant (p < 0.001). The study demonstrated that a simple interactive approach that includes subjectively perceived ratings of one feature alone namely, a rating of margin "spiculation," could substantially improve the selection of "visually similar" reference images.

The authors compared two methodological approaches, Jackknife ROC and JAFROC, in analyzing data ascertained during FROC (free-response receiver operating characteristics) type studies. Observer rating data obtained from two observer performance studies were analyzed. During the first study, seven radiologists interpreted 120 mammography examinations depicting 57 masses under five different conditions with and without the results of computer-aided detection(CAD). In the second study, eight radiologists interpreted 110 examinations depicting 51 masses under six different display conditions with and without CAD results. Readers rated the detection task in a FROC type response. Jackknife ROC (using the software of LABMRMC with the highest rating per case) and JAFROC were used to compute differences, if any, in summary performance levels among all reading modes in each study as well as for all paired data sets. The results of the different analytical approaches are compared. The overall results for all modes were significantly different for the first study ( p 0.05 ) and not significant ( p > 0.05 ) for the second study using either analytical approach. In the first study, the performance levels represented by three paired data sets were significantly different ( p 0.05 ) when computed using LABMRMC and four pairs were significantly different ( p 0.05 ) using JAFROC. In eight of ten pairs, JAFROC produced lower p values than LABMRMC. In the second study, LABMRMC showed no significant differences for any paired data sets and JAFROC showed a significant difference for one pair. In 15 of 16 pairs, p values computed by JAFROC were lower than those computed by LABMRMC.

The purpose of this study is to develop a new method for assessment of the reproducibility of computer-aided detection (CAD) schemes for digitized mammograms and to evaluate the possibility of using the implemented approach for improving CAD performance. Two thousand digitized mammograms (representing 500 cases) with 300 depicted verified masses were selected in the study. Series of images were generated for each digitized image by resampling after a series of slight image rotations. A CAD scheme developed in our laboratory was applied to all images to detect suspicious mass regions. We evaluated the reproducibility of the scheme using the detection sensitivity and false-positive rates for the original and resampled images. We also explored the possibility of improving CAD performance using three methods of combining results from the original and resampled images, including simple grouping, averaging output scores, and averaging output scores after grouping. The CAD scheme generated a detection score (from 0 to 1) for each identified suspicious region. A region with a detection score >0.5 was considered as positive. The CAD scheme detected 238 masses (79.3% case-based sensitivity) and identified 1093 false-positive regions (average 0.55 per image) in the original image dataset. In eleven repeated tests using original andmore » ten sets of rotated and resampled images, the scheme detected a maximum of 271 masses and identified as many as 2359 false-positive regions. Two hundred and eighteen masses (80.4%) and 618 false-positive regions (26.2%) were detected in all 11 sets of images. Combining detection results improved reproducibility and the overall CAD performance. In the range of an average false-positive detection rate between 0.5 and 1 per image, the sensitivity of the scheme could be increased approximately 5% after averaging the scores of the regions detected in at least four images. At low false-positive rate (e.g., {

A method for quantitatively estimating lesion "size" from mammographic images was developed and evaluated. The main idea behind the measure, termed "integrated density" (ID), is that the total x-ray attenuation attributable to an object is theoretically invariant with respect to the projected view and object deformation. Because it is possible to estimate x-ray attenuation of a lesion from relative film densities, after appropriate corrections for background, the invariant property of the measure is expected to result in an objective method for evaluating the "sizes" of breast lesions. ID was calculated as the integral of the estimated image density attributable to a lesion, relative to surrounding background, over the area of the lesion and after corrections for the nonlinearity of the film characteristic curve. This effectively provides a measure proportional to lesion volume. We computed ID and more traditional measures of size (such as "mass diameter" and "effective size") for 100 pairs of ipsilateral mammographic views, each containing a lesion that was relatively visible in both views. The correlation between values calculated for each measure from corresponding pairs of ipsilateral views were computed and compared. All three size-related measures (mass diameter, effective size, and ID) exhibited reasonable linear relationship between paired views (r2>0.7, P

A dual-screen computed radiography (CR) technique has been developed to improve and optimize the overall image signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). With this technique, two CR screens are exposed together and separately scanned to form a front and a back image. These two images are then superimposed to form an image of improved SNR and CNR. A mathematical model has been derived to describe the improvement and optimization of the SNR and CNR. Based on this model, the front and back images should be weighted in proportion to their SNR squared to optimize the SNR of the composite image. Imaging experiments have been conducted to verify the theoretical model under mammographic and chest imaging conditions. The results largely agree with the theoretical predictions. It has also been found that optimization of the SNR results in nearly optimal CNR and vice versa. For mammographic imaging, a 14%-22% improvement in the SNR and a 13%-19% improvement in the CNR have been demonstrated. For chest imaging, a 31%-36% improvement in the SNR and a 28%-30% improvement in the CNR has been demonstrated.

Computer-aided detection and diagnosis (CAD) systems are increasingly being used as an aid by clinicians for detection and interpretation of diseases. Computer-aided detection systems mark regions of an image that may reveal specific abnormalities and are used to alert clinicians to these regions during image interpretation. Computer-aided diagnosis systems provide an assessment of a disease using image-based information alone or in combination with other relevant diagnostic data and are used by clinicians as a decision support in developing their diagnoses. While CAD systems are commercially available, standardized approaches for evaluating and reporting their performance have not yet been fully formalized in the literature or in a standardization effort. This deficiency has led to difficulty in the comparison of CAD devices and in understanding how the reported performance might translate into clinical practice. To address these important issues, the American Association of Physicists in Medicine (AAPM) formed the Computer Aided Detection in Diagnostic Imaging Subcommittee (CADSC), in part, to develop recommendations on approaches for assessing CAD system performance. The purpose of this paper is to convey the opinions of the AAPM CADSC members and to stimulate the development of consensus approaches and “best practices” for evaluating CAD systems. Both the assessment of a standalone CAD system and the evaluation of the impact of CAD on end-users are discussed. It is hoped that awareness of these important evaluation elements and the CADSC recommendations will lead to further development of structured guidelines for CAD performance assessment. Proper assessment of CAD system performance is expected to increase the understanding of a CAD system's effectiveness and limitations, which is expected to stimulate further research and development efforts on CAD technologies, reduce problems due to improper use, and eventually improve the utility and efficacy of CAD in clinical practice.

As one of the most prevalent chronic disorders, airway disease is a major cause of morbidity and mortality worldwide. In order to understand its underlying mechanisms and to enable assessment of therapeutic efficacy of a variety of possible interventions, noninvasive investigation of the airways in a large number of subjects is of great research interest. Due to its high resolution in temporal and spatial domains, computed tomography (CT) has been widely used in clinical practices for studying the normal and abnormal manifestations of lung diseases, albeit there is a need to clearly demonstrate the benefits in light of the cost and radiation dose associated with CT examinations performed for the purpose of airway analysis. Whereas a single CT examination consists of a large number of images, manually identifying airway morphological characteristics and computing features to enable thorough investigations of airway and other lung diseases is very time-consuming and susceptible to errors. Hence, automated and semiautomated computerized analysis of human airways is becoming an important research area in medical imaging. A number of computerized techniques have been developed to date for the analysis of lung airways. In this review, we present a summary of the primary methods developed for computerized analysis of human airways, including airway segmentation, airway labeling, and airway morphometry, as well as a number of computer-aided clinical applications, such as virtual bronchoscopy. Both successes and underlying limitations of these approaches are discussed, while highlighting areas that may require additional work.

When comparing binary test results from two diagnostic systems, superiority in both "sensitivity" and "specificity" also implies differences in all conventional summary indices and locally in the underlying receiver operating characteristics (ROC) curves. However, when one of the two binary tests has higher sensitivity and lower specificity (or vice versa), comparisons of their performance levels are nontrivial and the use of different summary indices may lead to contradictory conclusions. A frequently used approach that is free of subjectivity associated with summary indices is based on the comparison of the underlying ROC curves that requires the collection of rating data using multicategory scales, whether natural or experimentally imposed. However, data for reliable estimation of ROC curves are frequently unavailable. The purpose of this article is to develop an approach of using "diagnostic likelihood ratios", namely, likelihood ratios of "positive" or "negative" responses, to make simple inferences regarding the underlying ROC curves and associated areas in the absence of reliable rating data or regarding the relative binary characteristics, when these are of primary interest.For inferences related to underlying curves, the authors exploit the assumption of concavity of the true underlying ROC curve to describe conditions under which these curves have to be different and under which the curves have different areas. For scenarios when the binary characteristics are of primary interest, the authors use characteristics of "chance performance" to demonstrate that the derived conditions provide strong evidence of superiority of one binary test as compared to another. By relating these derived conditions to hypotheses about the true likelihood ratios of two binary diagnostic tests being compared, the authors enable a straightforward statistical procedure for the corresponding inferences.The authors derived simple algebraic and graphical methods for describing the conditions for superiority of one of two diagnostic tests with respect to their binary characteristics, the underlying ROC curves, or the areas under the curves. The graphical regions are useful for identifying potential differences between two systems, which then have to be tested statistically. The simple statistical tests can be performed with well known methods for comparison of diagnostic likelihood ratios. The developed approach offers a solution for some of the more difficult to analyze scenarios, where diagnostic tests do not demonstrate concordant differences in terms of both sensitivity and specificity. In addition, the resulting inferences do not contradict the conclusions that can be obtained using conventional and reasonably defined summary indices.When binary diagnostic tests are of primary interest, the proposed approach offers an objective and powerful method for comparing two binary diagnostic tests. The significant advantage of this method is that it enables objective analyses when one test has higher sensitivity but lower specificity, while ensuring agreement with study conclusions based on other reasonable and widely acceptable summary indices. For truly multicategory diagnostic tests, the proposed method can help in concluding inferiority of one of the diagnostic tests based on binary data, thereby potentially saving the need for conducting a more expensive multicategory ROC study.

An experimental high‐contrast sensitivity storage phosphorimaging system was used to produce double‐exposure localization portal images of abdominal and pelvic treatment fields. The images were contrast enhanced by using an analog windowing technique and edge enhanced with a digital unsharp masking routine. A laser printer was used to print the storage phosphorimages onto film. Conventional images were obtained by placing film in the cassette with the storage phosphor plates prior to exposure. Four radiation oncologists rated the storage phosphor and conventional films for perceptibility of anatomical detail needed to verify the placement of the treatment field. Contrast enhancement alone did not result in a significant improvement in perceptibility over unprocessed conventional film (p>0.20). However, the combination of contrast and edge enhancement did result in a significant improvement over conventional film (p

We developed and tested a fully automated computerized scheme that identifies pulmonary airway sections depicted on computed tomography (CT) images and computes their sizes including the lumen and airway wall areas. The scheme includes four processing modules that (1) segment left and right lung areas, (2) identify airway locations, (3) segment airway walls from neighboring pixels, and (4) compute airway sizes. The scheme uses both a raster scanning and a labeling algorithm complemented by simple classification rules for region size and circularity to automatically search for and identify airway sections of interest. A profile tracking method is used to segment airway walls from neighboring pixels including those associated with dense tissue (i.e., pulmonary arteries) along scanning radial rays. A partial pixel membership method is used to compute airway size. The scheme was tested on ten randomly selected CT studies that included 26 sets of CT images acquired using both low and conventional dose CT examinations with one of four reconstruction algorithms (namely, "bone," "lung," "soft," and "standard" convolution kernels). Three image section thicknesses (1.25, 2.5, and 5 mm) were evaluated. The scheme detected a large number of quantifiable airway sections when the CT images were reconstructed using high spatial frequency convolution kernels. The detection results demonstrated a consistent trend for all test image sets in that as airway lumen size increases, on average the airway wall area increases as well and the wall area percentage decreases. The study suggested that CT images reconstructed using high spatial frequency convolution kernels and thin-section thickness were most amenable to automated detection, reasonable segmentation, and quantified assessment when the airways are close to being perpendicular to the CT image plane.

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 scoreor = 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.

The purpose of this study was to develop and test a method for selecting "visually similar" regions of interest depicting breast masses from a reference library to be used in an interactive computer-aided diagnosis (CAD) environment. A reference library including 1000 malignant mass regions and 2000 benign and CAD-generated false-positive regions was established. When a suspicious mass region is identified, the scheme segments the region and searches for similar regions from the reference library using a multifeature based k-nearest neighbor (KNN) algorithm. To improve selection of reference images, we added an interactive step. All actual masses in the reference library were subjectively rated on a scale from 1 to 9 as to their "visual margins speculations". When an observer identifies a suspected mass region during a case interpretation he/she first rates the margins and the computerized search is then limited only to regions rated as having similar levels of spiculation (within +/-1 scale difference). In an observer preference study including 85 test regions, two sets of the six "similar" reference regions selected by the KNN with and without the interactive step were displayed side by side with each test region. Four radiologists and five nonclinician observers selected the more appropriate ("similar") reference set in a two alternative forced choice preference experiment. All four radiologists and five nonclinician observers preferred the sets of regions selected by the interactive method with an average frequency of 76.8% and 74.6%, respectively. The overall preference for the interactive method was highly significant (p0.001). The study demonstrated that a simple interactive approach that includes subjectively perceived ratings of one feature alone namely, a rating of margin "spiculation," could substantially improve the selection of "visually similar" reference images.

The authors compared two methodological approaches, Jackknife ROC and JAFROC, in analyzing data ascertained during FROC (free-response receiver operating characteristics) type studies. Observer rating data obtained from two observer performance studies were analyzed. During the first study, seven radiologists interpreted 120 mammography examinations depicting 57 masses under five different conditions with and without the results of computer-aided detection (CAD). In the second study, eight radiologists interpreted 110 examinations depicting 51 masses under six different display conditions with and without CAD results. Readers rated the detection task in a FROC type response. Jackknife ROC (using the software of LABMRMC with the highest rating per case) and JAFROC were used to compute differences, if any, in summary performance levels among all reading modes in each study as well as for all paired data sets. The results of the different analytical approaches are compared. The overall results for all modes were significantly different for the first study (p0.05) and not significant (p0.05) for the second study using either analytical approach. In the first study, the performance levels represented by three paired data sets were significantly different (p0.05) when computed using LABMRMC and four pairs were significantly different (p0.05) using JAFROC. In eight of ten pairs, JAFROC produced lower p values than LABMRMC. In the second study, LABMRMC showed no significant differences for any paired data sets and JAFROC showed a significant difference for one pair. In 15 of 16 pairs, p values computed by JAFROC were lower than those computed by LABMRMC.

As research efforts for developing computer-aided diagnosis (CAD) schemes of digitized mammograms increase and interscheme results are compared, the desire to establish an acceptable consistent reporting protocol of the distribution of abnormal characteristic is becoming an issue. "Mass contrast" is very important and frequently reported in current CAD studies. In this report, 100 verified mass regions were analyzed systemically using 6 different definitions of "mass contrast." Measured variability in mass contrast was demonstrated by the distribution shift in this group masses. The need for universally accepted and largely standardized descriptors of objects of interest is clearly demonstrated.

The purpose of this study is to develop a new method for assessment of the reproducibility of computer-aided detection (CAD) schemes for digitized mammograms and to evaluate the possibility of using the implemented approach for improving CAD performance. Two thousand digitized mammograms (representing 500 cases) with 300 depicted verified masses were selected in the study. Series of images were generated for each digitized image by resampling after a series of slight image rotations. A CAD scheme developed in our laboratory was applied to all images to detect suspicious mass regions. We evaluated the reproducibility of the scheme using the detection sensitivity and false-positive rates for the original and resampled images. We also explored the possibility of improving CAD performance using three methods of combining results from the original and resampled images, including simple grouping, averaging output scores, and averaging output scores after grouping. The CAD scheme generated a detection score (from 0 to 1) for each identified suspicious region. A region with a detection score0.5 was considered as positive. The CAD scheme detected 238 masses (79.3% case-based sensitivity) and identified 1093 false-positive regions (average 0.55 per image) in the original image dataset. In eleven repeated tests using original and ten sets of rotated and resampled images, the scheme detected a maximum of 271 masses and identified as many as 2359 false-positive regions. Two hundred and eighteen masses (80.4%) and 618 false-positive regions (26.2%) were detected in all 11 sets of images. Combining detection results improved reproducibility and the overall CAD performance. In the range of an average false-positive detection rate between 0.5 and 1 per image, the sensitivity of the scheme could be increased approximately 5% after averaging the scores of the regions detected in at least four images. At low false-positive rate (e.g.,or =average 0.3 per image), the grouping method alone could increase CAD sensitivity by 7%. The study demonstrated that reproducibility of a CAD scheme can be tested using a set of slightly rotated and resampled images. Because the reproducibility of true-positive detections is generally higher than that of false-positive detections, combining detection results generated from subsets of rotated and resampled images could improve both reproducibility and overall performance of CAD schemes.

The authors investigated a new method to optimize artificial neural networks (ANNs) with adaptive filtering used in computer-assisted detection schemes in digitized mammograms and to assess performance changes when averaging classification scores from three sets of optimized schemes. Two independent training and testingimagedatabases involving 978 and 830 digitized mammograms, respectively, were used in this study. In the training data set, initial filtering and subtraction resulted in the identification of 592 mass regions and 3790 suspicious, but actually negative regions. These regions (including both true-positive and negative regions) were segmented into three subsets three times based on the calculation of the values of three features as segmentation indices. The indices were “mass” size multiplied by their digital value contrast, conspicuity, and circularity. Nine ANN-based classifiers were separately optimized using a genetic algorithm for each subset of regions. Each region was assigned three classification scores after applying the three adaptive ANNs. The performance gain of the CAD scheme after averaging the three scores for each suspicious region was tested using an independent data set and a ROC methodology. The experimental results showed that the areas under ROC curves (A z ) for the testingdatabase using three sets of optimized ANNs individually were 0.84±0.01, 0.83±0.01, and 0.84±0.01, respectively. The between-index correlations of three A z values were 0.013, −0.007, and 0.086. Similar to averaging diagnostic ratings from independent observers, by averaging three ANN-generated scores for each testing region, the performance of the CAD scheme was significantly improved (p with A z value of 0.95±0.01.

We propose a principled formulation of the ROC curve that is constrained in a realistic way by the mechanism of probability summation. The constrained and conventional ROC formulations were fitted to 150 separate sets of rating data taken from previous observer studies of 250 or 529 chest radiographs. A total of 20 different readers had used either discrete or continuous rating scales to evaluate those chest cases for likelihood of separate specified abnormalities: interstitial disease, pulmonary nodule, pneumothorax, alveolar infiltrate, or rib fracture. Both ROC formulations were fitted separately to every set of rating data using maximum-likelihood statistical procedures that specified each ROC curve by normally distributed latent variables with two scaling parameters, and estimated the area below the ROC curve (Az) with its standard error. The conventional and constrained binormal formulations usually fitted ROC curves that were nearly indistinguishable in form and in Az. But when fitted to asymmetric rating data that contained few false-positive cases, the conventional ROC curves often rose steeply, then flattened and extrapolated into an unrealistic upward "hook" at the higher false-positive rates. For those sets of rating data, the constrained ROC curves (without hooks) estimated larger values for Az with smaller standard errors. The constrained ROC formulation describes observers' ratings of cases at least as well as the conventional ROC, and always guarantees a realistic fitted curve for observer performance. Its estimated parameters are easy to interpret, and may also be used to predict observer accuracy in localizing the image abnormalities.

The purpose of this work was to develop and evaluate a computer-aided detection (CAD) scheme for the improvement of mass identification on digitized mammograms using a knowledge-based approach. Three hundred pathologically verified masses and 300 negative, but suspicious, regions, as initially identified by a rule-based CAD scheme, were randomly selected from a large clinical database for development purposes. In addition, 500 different positive and 500 negative regions were used to test the scheme. This suspicious region pruning scheme includes a learning process to establish a knowledge base that is then used to determine whether a previously identified suspicious region is likely to depict a true mass. This is accomplished by quantitatively characterizing the set of known masses, measuring "similarity" between a suspicious region and a "known" mass, then deriving a composite "likelihood" measure based on all "known" masses to determine the state of the suspicious region. To assess the performance of this method, receiver-operating characteristic (ROC) analyses were employed. Using a leave-one-out validation method with the development set of 600 regions, the knowledge-based CAD scheme achieved an area under the ROC curve of 0.83. Fifty-one percent of the previously identified false-positive regions were eliminated, while maintaining 90% sensitivity. During testing of the 1,000 independent regions, an area under the ROC curve as high as 0.80 was achieved. Knowledge-based approaches can yield a significant reduction in false-positive detections while maintaining reasonable sensitivity. This approach has the potential of improving the performance of other rule-based CAD schemes.

Six radiologists used continuous scales to rate 529 chest-film cases for likelihood of five different types of abnormalities (interstitial disease, nodule, pneumothorax, alveolar infiltrate, and rib fracture) in each of six replicated readings, yielding 36 separate ratings of each case for the five abnormalities. Separate data analyses of all cases and subsets of the difficult/subtle cases for each abnormality estimated the relative gains in accuracy (linear-scaled area below the ROC curve) obtained by averaging the case-ratings across (a) six independent replications by each reader (25% gain), (b) six different readers within each replication (34% gain), or (c) all 36 readings (48% gain). Although accuracy differed among both readers and abnormalities, ROC curves for the median ratings showed similar relative gains in accuracy, somewhat greater than those predicted from the measured rating correlations. A model for variance components in the observer’s latent decision variable could predict these gains from measured correlations in the single ratings of cases. Depending on whether the model’s estimates were based on realized accuracy gains or on rating correlations, about 48% or 39% of each reader’s total decision variance (summed variance for positive and negative cases) consisted of random (within-reader) error that was uncorrelated between replications, another 10% or 14% came from idiosyncratic responses to individual cases, and about 43% or 47% was systematic variation that all readers found in the sampled cases.

Computer-aided detection and diagnosis (CAD) systems are increasingly being used as an aid by clinicians for detection and interpretation of diseases. Computer-aided detection systems mark regions of an image that may reveal specific abnormalities and are used to alert clinicians to these regions during image interpretation. Computer-aided diagnosis systems provide an assessment of a disease using image-based information alone or in combination with other relevant diagnostic data and are used by clinicians as a decision support in developing their diagnoses. While CAD systems are commercially available, standardized approaches for evaluating and reporting their performance have not yet been fully formalized in the literature or in a standardization effort. This deficiency has led to difficulty in the comparison of CAD devices and in understanding how the reported performance might translate into clinical practice. To address these important issues, the American Association of Physicists in Medicine (AAPM) formed the Computer Aided Detection in Diagnostic Imaging Subcommittee (CADSC), in part, to develop recommendations on approaches for assessing CAD system performance. The purpose of this paper is to convey the opinions of the AAPM CADSC members and to stimulate the development of consensus approaches and “best practices” for evaluating CAD systems. Both the assessment of a standalone CAD system and the evaluation of the impact of CAD on end-users are discussed. It is hoped that awareness of these important evaluation elements and the CADSC recommendations will lead to further development of structured guidelines for CAD performance assessment. Proper assessment of CAD system performance is expected to increase the understanding of a CAD system's effectiveness and limitations, which is expected to stimulate further research and development efforts on CAD technologies, reduce problems due to improper use, and eventually improve the utility and efficacy of CAD in clinical practice.

Purpose: To develop an approach of estimating subject-centered free-response receiver operating characteristic (FROC) curve for providing patient-centered inferences regarding detection-localization characteristics of a diagnostic system. Methods: The authors examine properties of the conventional, target-centered, FROC curve and demonstrate that in scenarios where the diagnostic performance correlates with the total number of targets on a subject, it may lead to inadequate inferences from the perspective of possible benefits to a patient. Following solutions to patient-centered approaches in other applications, the authors define a subject-centered FROC curve and develop its formulation as a covariate-adjusted FROC curve. The authors also conduct a numerical study illustrating the relative properties of the conventional and subject-centered approach and provide an example. Results: A simple-to-implement approach for estimating the subject-centered FROC curve and its overall index can be formulated as a type of stratified FROC analysis. The authors demonstrate that when diagnostic performance is associated with the number of targets, the diagnostic system with apparently superior target-centered characteristics (conventional approach) can be actually inferior from the subject-centered perspective. The authors show that under some clinically reasonable conditions the magnitude of disagreement in results could be substantial. An example from an actual observer performance study illustrates the natural setting where the developed approach would be relevant and lead to conclusions that are contradictory to those obtained from conventional analysis. Conclusions: The authors developed a subject-centered FROC curve and its overall index provides tools for inferences that may be relevant from a perspective of potential benefits to a patient.

Computer‐Aided Detection (CAD) is intended to be used in a specific way and several studies have shown that when it is used appropriately improvements in performance can be realized. The effect seems to be much more noticeable in the laboratory than in the clinic. Data ascertained in both environments clearly suggest that the measurement methodology is extremely important as is the actual use of CAD as a part of the clinical workflow. Our observations suggest the following: 1) regardless of the actual improvement (or not) in accuracy, CAD is an important tool; 2) most radiologist do not use it in the clinical environment as originally intended; 3) comparison of sequential viewing “without” followed by “with” CAD may not be the appropriate/optimal way to analyze accuracy improvements; 4) change in detection rates are expected to be low and temporary, while change in average size (or stage) are expected to be small and persistent; 5) performance of the CAD alone does affect observer performance; 6) reliance on CAD in the area of micro‐calcifications may result in an increase in biopsy rates; 7) there is a significant difference in the performance of current CAD systems in regards to the detection of micro‐calcifications and masses, and this difference results in a significant difference in the level of reliance on CAD results with respect to the two abnormalities. These observations and the supporting experimental data will be shown and discussed. Educational Objectives: 1. Understanding the difficulty in measuring performance changes with the incorporation of CAD technology into the clinical environment. 2. Understanding the importance of study design in measuring the impact of CAD technology. 3. Understanding the magnitude of the “human” factor in observer performance studies.

The errors associated with derivation of cerebral blood flow values by the xenon-enhanced computed tomography (CT) method have been evaluated as a function of tissue heterogeneity and CT noise. The results of this study indicate that CT noise introduces large errors in the derived flow value when data for a single, unprocessed voxel are used for this purpose. CT noise increases the derived flow values in a systematic way. Tissue heterogeneity results in a systematic error which lowers the derived flow values. Errors due to both parameters are computed for typical and extreme conditions.

Studies in which the rate of local cerebral blood flow is determined by xenon-enhanced computerized tomography require measurement of end-tidal gas. A mass spectrometer and a thermoconductivity detector were compared in measuring the concentration of xenon in end-tidal gas both in humans and in a clinically simulated ("breathing bag") system. The experiments showed that the two instruments provided virtually identical results up to a rate of 18 breaths/min, at which rate recorded concentrations showed marginal degradation with the thermoconductivity detector. Given the absence of a significant difference in the ability of the mass spectrometer and the thermoconductivity detector to measure end-tidal xenon concentration, the thermoconductivity detector appears to be a satisfactory alternative in studies measuring the rate of local cerebral blood flow by enhanced computerized tomography.

Errors in the determination of xenon concentrations in arterial blood during inhalation of xenon-oxygen mixtures are used to assess errors in the derivation of regional cerebral blood flow by the xenon-enhanced computed tomography (CT) method. The results of this study indicate that approximating the arterial buildup by a single exponential introduces relatively small errors in estimated flow values. The most significant systematic error is introduced by errors in estimation of the xenon arrival time to the brain in relationship to sequential (CT) scanning times.

Two drawbacks in quality of portal radiographs in radiation therapy are their low contrast and low spatial resolution. These are due to the low differential absorption of body tissues at therapeutic energies and to a relatively large radiation source. We used an experimental, high‐contrast sensitivity storage phosphorimaging system (Eastman Kodak Co.) to produce portal images. The system consists of a storage phosphor detector, a high‐contrast sensitivity laser scanner (12 bit), an image processing module, and a laser printer (12 bit). Patients undergoing radiation therapytreatments had both a conventional portal image and a storage phosphorimage taken. Both were displayed side‐by‐side and were evaluated independently by three radiotherapists according to quality of information to verify the treatment field. Each of the three radiotherapists rated the storage phosphorimages to be better (p

A commercially available variable electron beam applicator designed for the Phillips SL-75/20 linear accelerator was tested for possible clinical use. The basic design of this collimator consists of four movable L-shaped stainless steel blades forming the corners. In addition, four smaller fixed blades of the same material and thickness fill in the sides. Film placed in polystyrene phantoms were exposed in all experiments. Field size, field flatness, beam homogeneity and penumbra measurements, all indicated that the applicator is acceptable for clinical use. However, for use with large field sizes and/or high energy electron beams some minor modifications are suggested.

A simple, easy to use, quality assurance and performance test phantom was developed for the xenon/computed tomography (CT) cerebral blood flow method. The phantom combines an inhalation system which allows for the simulation of xenon buildup or washout in the arterial blood as well as a multisection translatable cylinder in which several sections can be scanned during a preselected protocol to simulate the CT enhancement in brain tissue during a study. The phantom and scanning protocol are described and their use is demonstrated. The results compare favorably to the theoretically expected fast, intermediate, and slow ‘‘flow’’ values designed into the phantom.

Fast neutron contamination in photon beams in the 20 MV range have been reported in recent years. In order to determine if the variations were due mainly to differences in measurement procedures, or inherent in the design of the accelerators, three different 18-MV (BJR) photon beams were compared using identical analytical techniques. The units studied were a Philips SL/75-20 and a Siemens Mevatron-20 linear accelerators and a Schimadzu betatron. Gamma spectroscopy of an activated aluminum foil was the method used. By comparing the relative amounts of neutron contamination, errors associated with absolute measurements such as detector efficiency and differences in activation foils were eliminated. Fast neutron contaminations per rad of x rays in a ratio of 6.7:3.7:1 were found for the Philips, Schimadzu and Siemens accelerators, respectively.

The amount of x-ray contamination near the surface of a phantom irradiated with electron beams was measured directly. Measurements were done to ascertain if photon contamination in the beam contributes a higher dose to the more superficial layers of an irradiated medium than indicated by conventional methods. A 1.4-kG magnetic field was used to deflect the electron beams generated by a Philips SL/75-20 linear accelerator. The electron energies studied were 8, 10, 12, 14, 17, and 20 Mev. After sweeping the electron beam, a significant amount of photon contamination was measured in all cases. The characteristic qualities of the photon contamination were measured directly in a water tank. They were found to agree with those of bremsstrahlung spectra generated in a thin target with a virtual source at the location of the scattering foil.

Fast- and slow-neutron contamination in an 18-MV photon beam from a Philips SL/75-20 linear accelerator has been measured. Aluminum and indium foils were activated to determine fast- and slow-neutron fluence, which were largely independent of field sizes. Measured fast-neutron fluences were typically 13.9 x 10/sup 4/ and 4.4 x 10/sup 4/ neutrons/cm/sup 2//rad of x ray inside and 5 cm outside the field, respectively. Slow-neutron fluences, 1.3 x 10/sup 4/ neutrons/cm/sup 2//rad of x ray, remained relatively constant inside and outside the field. The reported results are about three times higher than neutron fluences recently reported with a betatron operated at the same energy.