A Comparative Study of Conventional Mammography Film Interpretations with Soft Copy Readings of the Same Examinations

An acceptable mammography film digitizer must provide high-quality images at a level of diagnostic accuracy comparable to reading conventional film examinations. The purpose of this study was to determine if there are significant differences between the interpretations of conventional film-screen mammography examinations and soft copy readings of the images produced by a mammography film digitizer. Eight radiologists interpreted 120 mammography examinations, half as original films and the other half as digital images on a soft copy work station. No radiologist read the same examination twice. The interpretations were recorded in accordance with the Breast Imaging Reporting and Data System and included other variables such as perceived image quality and diagnostic difficulty and confidence. The results provide support for the hypothesis that there are no significant differences between the interpretations of conventional film-screen mammography examinations and soft copy examinations produced by a mammography film digitizer. The study was conducted primarily at the Johns Hopkins Medical Institutions in Baltimore, MD where all of the authors except Dr. Chad Mitchell are located. He is a Naval Officer at the Uniformed Services University of the Health Sciences in Bethesda, MD.     

Soft Copy versus Hard Copy Reading in Digital Mammography

The objective of this study was to compare soft copy reading at a mammography work station with hard copy reading of full-field digital mammographic images. Mammograms of 60 patients (n = 29 malignant, n = 31 benign) performed with full-field digital mammography (Senographe 2000D, GE, Buc, France) were evaluated. Reading was performed based on hard copy prints (Scopix, Agfa, Leverkusen, Germany) and on 2 k × 2.5 k high-resolution monitors (Sun Ultra 60, Sun Microsystems, Palo Alto, California, USA). Four readers with different levels of experience in mammography categorized the mammograms according to the BI-RADS classification. The comparative study was performed by four readers, and at least 2 months elapsed between the reading sessions. Postprocessing, of course, was available only at the work station (windowing and leveling, zooming, inversion). Sensitivity, specificity, and positive predictive value were evaluated. Diagnostic accuracy of the evaluation was determined. Sensitivity for malignant lesions in hard copy versus soft copy reading was 97% vs 90%, 97% vs 97%, 93% vs 97%, and 76% vs 76% for the four readers, respectively. Specificity was 52% vs 68%, 58% vs 74%, 65% vs 48%, and 61% vs 68%. Accuracy for the classification of malignant lesions according to the BI-RADS categories showed no difference between hard copy and soft copy reading. Soft copy reading is possible with the available system and enables radiologists to use the advantages of a digital system.     

A Mammography Database and View System for African-American Patients

We have digitized mammography films of African-American patients treated in the Howard University Hospital Radiology Department and have developed a database using these images. Two hundred and sixty cases totaling more than 5,000 images have been scanned with a high resolution Kodak LS85 laser scanner. The database system and web-based search engine were developed using MySQL and PHP. The database has been evaluated by medical professionals, and the experimental results obtained so far are promising with high image quality and fast access time. We have also developed an image viewing system, D-Viewer, to display these digitized mammograms. This viewer is coded in Microsoft Visual C# and is intended to help medical professionals view and retrieve large data sets in near real time. Finally, we are currently developing an image content-based retrieval function for the database system to provide improved search capability for the medical professionals.     

Étude de la faisabilité du scorage automatique de fantômes mammographiques par traitement d’image

Nowadays, X-ray mammography is one of the most effective methods for early and reliable breast cancer detection and diagnosis. Periodic quality control in mammographic facilities is necessary to provide high quality mammograms. This evaluation is done by visual observation of mammographic phantom films. To prepare Full Field Digital Mammography advent and to get rid of this subjective quality control, digital image and signal processing techniques may be used in order to make this control easier and more objective. This paper presents an automatic method for scoring mammographic phantoms using digital image processing. Phantom films were first digitized and images containing microcalcifications, masses and fibers were extracted. Theses noisy and low contrasted images were preprocessed using an adaptive contrast enhancement method and then segmented in order to extract objects embedded in phantom images. Nine digitized phantom films were studied and results show that a more objective quality control evaluation of mammographic facilities can be done using digital image processing techniques on phantom images.     

An Interactive System for Computer-Aided Diagnosis of Breast Masses

Although mammography is the only clinically accepted imaging modality for screening the general population to detect breast cancer, interpreting mammograms is difficult with lower sensitivity and specificity. To provide radiologists “a visual aid” in interpreting mammograms, we developed and tested an interactive system for computer-aided detection and diagnosis (CAD) of mass-like cancers. Using this system, an observer can view CAD-cued mass regions depicted on one image and then query any suspicious regions (either cued or not cued by CAD). CAD scheme automatically segments the suspicious region or accepts manually defined region and computes a set of image features. Using content-based image retrieval (CBIR) algorithm, CAD searches for a set of reference images depicting “abnormalities” similar to the queried region. Based on image retrieval results and a decision algorithm, a classification score is assigned to the queried region. In this study, a reference database with 1,800 malignant mass regions and 1,800 benign and CAD-generated false-positive regions was used. A modified CBIR algorithm with a new function of stretching the attributes in the multi-dimensional space and decision scheme was optimized using a genetic algorithm. Using a leave-one-out testing method to classify suspicious mass regions, we compared the classification performance using two CBIR algorithms with either equally weighted or optimally stretched attributes. Using the modified CBIR algorithm, the area under receiver operating characteristic curve was significantly increased from 0.865 ± 0.006 to 0.897 ± 0.005 (p < 0.001). This study demonstrated the feasibility of developing an interactive CAD system with a large reference database and achieving improved performance.     

An adaptive algorithm for the detection of microcalcifications in simulated low-dose mammography

This paper uses the task of microcalcification detection as a benchmark problem to assess the potential for dose reduction in x-ray mammography. We present the results of a newly developed algorithm for detection of microcalcifications as a case study for a typical commercial film-screen system (Kodak Min-R 2000/2190). The first part of the paper deals with the simulation of dose reduction for film-screen mammography based on a physical model of the imaging process. Use of a more sensitive film-screen system is expected to result in additional smoothing of the image. We introduce two different models of that behaviour, called moderate and strong smoothing. We then present an adaptive, model-based microcalcification detection algorithm. Comparing detection results with ground-truth images obtained under the supervision of an expert radiologist allows us to establish the soundness of the detection algorithm. We measure the performance on the dose-reduced images in order to assess the loss of information due to dose reduction. It turns out that the smoothing behaviour has a strong influence on detection rates. For moderate smoothing. a dose reduction by 25% has no serious influence on the detection results. whereas a dose reduction by 50% already entails a marked deterioration of the performance. Strong smoothing generally leads to an unacceptable loss of image quality. The test results emphasize the impact of the more sensitive film-screen system and its characteristics on the problem of assessing the potential for dose reduction in film-screen mammography. The general approach presented in the paper can be adapted to fully digital mammography.     

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

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

Evaluation of digital mammography in diagnosis of breast cancer

Mammography has been digitized in all cases at our hospital. Digital mammography (MMG) of our hospital and its diagnostic accuracy were described in this report. Fuji Computed Radiography (FCR; Fuji Medical Systems, Tokyo, Japan) imaging plate was used and imaging data were processed with FCR 7000 or FCR 9000. Each image was output to a single hard copy. Sampling pitches for reading and output were 0.1 mm. The rate of breast cancer diagnosis by digital MMG was 67%, 95%, 94%, and 100% for unpalpable tumor, tumor less than ϕ 2 cm, tumor of ϕ 2 to 5 cm, and tumor greater than ϕ 5 cm, respectively, being 94% overall. Digital MMG enables us to establish goal-oriented image-processing conditions. The use of digital MMG, which provides an excellent diagnostic rate similar to that of screen-film MMG, is expected to became wide-spread in the near future.

     

Dual-energy imaging in full-field digital mammography: a phantom study

A dual-energy technique which employs the basis decomposition method is being investigated for application to digital mammography. A three-component phantom, made up of plexiglas, polyethylene, and water, was doubly exposed with the full-field digital mammography system manufactured by General Electric. The 'low' and 'high' energy images were recorded with a Mo/Mo anode-filter combination and a Rh/Rh combination, respectively. The total dose was kept within the acceptable levels of conventional mammography. The first hybrid images obtained with the dual-energy algorithm are presented in comparison with a conventional radiograph of the phantom. Image-quality characteristics at contrast cancellation angles between plexiglas and water are discussed. Preliminary results show that a combination of a standard Mo-anode 28 kV radiograph with a Rh-anode 49 kV radiograph provides the best compromise between image-quality and dose in the hybrid image.     

Comparison of full-field digital mammography to screen-film mammography with respect to contrast and spatial resolution in tissue equivalent breast phantoms

To determine if the improved contrast resolution of full-field digital mammography (FFDM) with reduced spatial resolution allows for superior or equal phantom object detection compared with screen-film mammography (SFM). Tissue equivalent breast phantoms simulating an adipose to glandular ratio of 50/50,30/70, and 20/80 were imaged according to each manufacturers' recommendation with four full-field digital mammography units (Fuji, Sectra, Fischer, and General Electric) and a screen-film mammography unit (MammoMatII 2000, Siemens, Munich, Germany). A total of 20 images were obtained in both hard- and soft-copy formats. For the purpose of soft-copy display, the screen-film hard-copy images were digitized with a 50 microm micron scanner. Six radiologists, experts in breast imaging, and three physicists, experts in scoring mammography phantoms, participated in a reader study where each reader scored each phantom for visibility of line-pairs and for 24 objects (fibers, clusters of specks, and masses). The data were recorded, entered into a database, and analyzed by a mixed-effect model. The limiting spatial resolution in line-pairs per millimeter visible with the digital units was less, regardless of display modality used, than that provided by the screen-film unit. The difference was statistically significant for the General Electric (p < 0.01) and Fuji digital mammography units (p = 0.03). With respect to the number of visible objects, a statistically significant higher number could be detected with the screen-film unit as compared to the Fischer (p < 0.01) and Sectra (p < 0.01) digital mammography units, but there was no significant difference between the other digital units and screen film. Overall, there was significantly better performance on the 50/50 phantom than with the 30/70 and 20/80 phantoms (p = 0.01, p < 0.01) for object visibility. For the digital mammography units, soft-copy display performed better than hard-copy display for the Fischer and Sectra images, but worse for Fuji and General Electric. In addition, soft-copy display of digitized screen-film images was significantly better than hard-copy display (p =0.02) of the original screen films for object visibility, but worse for spatial resolution. The higher contrast resolution of the FFDM units tested did not result in improved detection of line-pair resolution or objects in the phantoms tested versus screen-film mammography. The phantom performance of a digital mammography unit seems to be influenced by the type of detection task (line-pair resolution versus object visibility), the display modality (soft-copy versus hard-copy) chosen to score the phantoms, and the parenchymal pattern composition of the phantom.     

Contrast enhancement in dense breast images using the modulation transfer function

This work proposes a method aimed at enhancing the contrast in dense breast images in mammography. It includes a new preprocessing technique, which uses information on the modulation transfer function (MTF) of the mammographic system in the whole radiation field. The method is applied to improve the efficiency of a computer-aided diagnosis (CAD) scheme. Seventy-five regions of interest (ROIs) from dense mammograms were acquired in two pieces of equipment (a CGR Senographe 500t and a Philips Mammodiagnost) and were digitized in a Lumiscan 50 laser scanner. A computational procedure determines the effective focal spot size in each region of interest from the measured focal spot in the center for a given mammographic equipment. Using computational simulation the MTF is then calculated for each field region. A procedure that enlarges the high-frequency portion of this function is applied and a convolution between the resulting new function and the original image is performed. Both original and enhanced images were submitted to a processing procedure for detecting clustered microcalcifications in order to compare the performance for dense breast images. ROIs were divided into four groups, two for each piece of equipment-one with clustered microcalcifications and another without microcalcifications. Our results show that in about 10% of the enhanced images more signals were detected when compared to the results for the original dense breast images. This is important because the usual processing techniques used in CAD schemes present poor results when applied to dense breast images. Since the MTF method is a well-recognized tool in the evaluation of radiographic systems, this new technique could be used to associate quality assurance procedures with the processing schemes employed in CAD for mammography.     

Performance gain in computer-assisted detection schemes by averaging scores generated from artificial neural networks with adaptive filtering.

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 testing image databases 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 (Az) for the testing database 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 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<0.001) with Az value of 0.95+/-0.01.     

An observer study comparing spot imaging regions selected by radiologists and a computer for an automated stereo spot mammography technique

We are developing an automated stereo spot mammography technique for improved imaging of suspicious dense regions within digital mammograms. The technique entails the acquisition of a full-field digital mammogram, automated detection of a suspicious dense region within that mammogram by a computer aided detection (CAD) program, and acquisition of a stereo pair of images with automated collimation to the suspicious region. The latter stereo spot image is obtained within seconds of the original full-field mammogram, without releasing the compression paddle. The spot image is viewed on a stereo video display. A critical element of this technique is the automated detection of suspicious regions for spot imaging. We performed an observer study to compare the suspicious regions selected by radiologists with those selected by a CAD program developed at the University of Michigan. True regions of interest (TROIs) were separately determined by one of the radiologists who reviewed the original mammograms, biopsy images, and histology results. We compared the radiologist and computer-selected regions of interest (ROIs) to the TROIs. Both the radiologists and the computer were allowed to select up to 3 regions in each of 200 images (mixture of 100 CC and 100 MLO views). We computed overlap indices (the overlap index is defined as the ratio of the area of intersection to the area of interest) to quantify the agreement between the selected regions in each image. The averages of the largest overlap indices per image for the 5 radiologist-to-computer comparisons were directly related to the average number of regions per image traced by the radiologists (about 50% for 1 region/image, 84% for 2 regions/image and 96% for 3 regions/image). The average of the overlap indices with all of the TROIs was 73% for CAD and 76.8% +/- 10.0% for the radiologists. This study indicates that the CAD determined ROIs could potentially be useful for a screening technique that includes stereo spot mammography imaging.     

A method to test the reproducibility and to improve performance of computer-aided detection schemes for digitized mammograms

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 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.     

Characterization of mammographic masses based on level set segmentation with new image features and patient information

Computer-aided diagnosis (CAD) for characterization of mammographic masses as malignant or benign has the potential to assist radiologists in reducing the biopsy rate without increasing false negatives. The purpose of this study was to develop an automated method for mammographic mass segmentation and explore new image based features in combination with patient information in order to improve the performance of mass characterization. The authors' previous CAD system, which used the active contour segmentation, and morphological, textural, and spiculation features, has achieved promising results in mass characterization. The new CAD system is based on the level set method and includes two new types of image features related to the presence of microcalcifications with the mass and abruptness of the mass margin, and patient age. A linear discriminant analysis (LDA) classifier with stepwise feature selection was used to merge the extracted features into a classification score. The classification accuracy was evaluated using the area under the receiver operating characteristic curve. The authors' primary data set consisted of 427 biopsy-proven masses (200 malignant and 227 benign) in 909 regions of interest (ROIs) (451 malignant and 458 benign) from multiple mammographic views. Leave-one-case-out resampling was used for training and testing. The new CAD system based on the level set segmentation and the new mammographic feature space achieved a view-based Az value of 0.83 +/- 0.01. The improvement compared to the previous CAD system was statistically significant (p = 0.02). When patient age was included in the new CAD system, view-based and case-based Az values were 0.85 +/- 0.01 and 0.87 +/- 0.02, respectively. The study also demonstrated the consistency of the newly developed CAD system by evaluating the statistics of the weights of the LDA classifiers in leave-one-case-out classification. Finally, an independent test on the publicly available digital database for screening mammography with 132 benign and 197 malignant ROIs containing masses achieved a view-based Az value of 0.84 +/- 0.02.     

A completely automated CAD system for mass detection in a large mammographic database

Mass localization plays a crucial role in computer-aided detection (CAD) systems for the classification of suspicious regions in mammograms. In this article we present a completely automated classification system for the detection of masses in digitized mammographic images. The tool system we discuss consists in three processing levels: (a) Image segmentation for the localization of regions of interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima of the mammogram. (b) ROI characterization by means of textural features computed from the gray tone spatial dependence matrix (GTSDM), containing second-order spatial statistics information on the pixel gray level intensity. As the images under study were recorded in different centers and with different machine settings, eight GTSDM features were selected so as to be invariant under monotonic transformation. In this way, the images do not need to be normalized, as the adopted features depend on the texture only, rather than on the gray tone levels, too. (c) ROI classification by means of a neural network, with supervision provided by the radiologist's diagnosis. The CAD system was evaluated on a large database of 3369 mammographic images [2307 negative, 1062 pathological (or positive), containing at least one confirmed mass, as diagnosed by an expert radiologist]. To assess the performance of the system, receiver operating characteristic (ROC) and free-response ROC analysis were employed. The area under the ROC curve was found to be Az = 0.783 +/- 0.008 for the ROI-based classification. When evaluating the accuracy of the CAD against the radiologist-drawn boundaries, 4.23 false positives per image are found at 80% of mass sensitivity.     

New methods of MR image intensity standardization via generalized scale

Image intensity standardization is a post-acquisition processing operation designed for correcting acquisition-to-acquisition signal intensity variations (non-standardness) inherent in Magnetic Resonance (MR) images. While existing standardization methods based on histogram landmarks have been shown to produce a significant gain in the similarity of resulting image intensities, their weakness is that in some instances the same histogram-based landmark may represent one tissue, while in other cases it may represent different tissues. This is often true for diseased or abnormal patient studies in which significant changes in image intensity characteristics may occur. In an attempt to overcome this problem, in this paper, we present two new intensity standardization methods based on two scale concepts developed in Madabhushi et al. [Computer Vision Image Understanding 101, 100-121 (2006)] for image processing applications. These scale concepts are utilized in this paper to accurately determine principal tissue regions within MR images. Landmarks derived from these regions are used to perform intensity standardization. The new methods were qualitatively and quantitatively evaluated on a total of 67 clinical three dimensional (3D) MR images corresponding to four different protocols and to normal, Multiple Sclerosis (MS), and brain tumor patient studies. The new scale-based methods were found to be better than the existing methods, with a significant improvement observed for severely diseased and abnormal patient studies.     

Automated detection of microcalcification clusters for digital breast tomosynthesis using projection data only: a preliminary study

Digital breast tomosynthesis (DBT) is a promising modality for breast imaging in which an anisotropic volume image of the breast is obtained. We present an algorithm for computerized detection of microcalcification clusters (MCCs) for DBT. This algorithm operates on the projection views only. Therefore it does not depend on reconstruction, and is computationally efficient. The algorithm was developed using a database of 30 image sets with microcalcifications, and a control group of 30 image sets without visible findings. The patient data were acquired on the first DBT prototype at Massachusetts General Hospital. Algorithm sensitivity was estimated to be 0.86 at 1.3 false positive clusters, which is below that of current MCC detection algorithms for full-field digital mammography. Because of the small number of patient cases, algorithm parameters were not optimized and one linear classifier was used. An actual limitation of our approach may be that the signal-to-noise ratio in the projection images is too low for microcalcification detection. Furthermore, the database consisted of predominantly small MCC. This may be related to the image quality obtained with this first prototype.     

A whole-slide imaging based workflow reduces the reading time of pathologists

Even though entirely digitized microscopic tissue sections (whole slide images, WSIs) are increasingly being used in histopathology diagnostics, little data is still available on the effect of this technique on pathologists' reading time. This study aimed to compare the time required to perform the microscopic assessment by pathologists between a conventional workflow (an optical microscope) and digitized WSIs. WSI was used in primary diagnostics at the Laboratory for Pathology Eastern Netherlands for several years (LabPON, Hengelo, The Netherlands). Cases were read either in a traditional workflow, with the pathologist recording the time required for diagnostics and reporting, or entirely digitally. Reading times were extracted from image management system log files, and the digitized workflow was fully integrated into the laboratory information system. The digital workflow saved time in the majority of case categories, with prostate biopsies saving the most (68% time gain). Taking into account case distribution, the digital workflow produced an average gain of 12.3%. Using WSI instead of conventional microscopy significantly reduces pathologists' reading times. Pathologists must work in a fully integrated environment to fully reap the benefits of a digital workflow.     

Differential Use of Image Enhancement Techniques by Experienced and Inexperienced Observers

Full-field digital mammography (FFDM) systems are currently being used to acquire mammograms in digital format, but digital displays are less than ideal compared to traditional film-screen display. Certain physical properties of softcopy displays [e.g., modulation transfer function (MTF)] are less than optimal compared to film. We developed methods to compensate for some of these softcopy display deficiencies, based on careful physical characterization of the displays and image-processing software. A series of 100 FFDM and 60 digitized images was shown to six observers—half experienced (mammographers) and half inexperienced (radiology residents). The observers had to decide if a mass or microcalcification cluster was present and classify it as benign or malignant. A window could be activated that brought the image detail within the window to full resolution and corrected for the nonisotropic MTF of the Cathode Ray Tube (CRT) display. Experienced readers had better diagnostic performance and took less time to view the images. Experienced readers used window/level more than inexperienced readers, but inexperienced readers used magnification and the MTF compensation tool more often. Use of the magnification and the MTF tool increased reader decision confidence. Experienced and inexperienced readers use image-processing tools differently, with certain tools increasing reader confidence. Understanding how observers use image-processing tools may help in the development of better and more automated user interfaces.