Diagnostic accuracy of Fischer Senoscan Digital Mammography versus screen-film mammography in a diagnostic mammography population

Deep learning can be used to train naïve, nonprofessional observers to detect diagnostic visual patterns of certain cancers in mammograms: a proof-of-principle study

The scientific, clinical, and pedagogical significance of devising methodologies to train nonprofessional subjects to recognize diagnostic visual patterns in medical images has been broadly recognized. However, systematic approaches to doing so remain poorly established. Using mammography as an exemplar case, we use a series of experiments to demonstrate that deep learning (DL) techniques can, in principle, be used to train naïve subjects to reliably detect certain diagnostic visual patterns of cancer in medical images. In the main experiment, subjects were required to learn to detect statistical visual patterns diagnostic of cancer in mammograms using only the mammograms and feedback provided following the subjects' response. We found not only that the subjects learned to perform the task at statistically significant levels, but also that their eye movements related to image scrutiny changed in a learning-dependent fashion. Two additional, smaller exploratory experiments suggested that allowing subjects to re-examine the mammogram in light of various items of diagnostic information may help further improve DL of the diagnostic patterns. Finally, a fourth small, exploratory experiment suggested that the image information learned was similar across subjects. Together, these results prove the principle that DL methodologies can be used to train nonprofessional subjects to reliably perform those aspects of medical image perception tasks that depend on visual pattern recognition expertise.

The Reproducibility of Changes in Diagnostic Figures of Merit Across Laboratory and Clinical Imaging Reader Studies

RATIONALE AND OBJECTIVES

In this paper we examine which comparisons of reading performance between diagnostic imaging systems made in controlled retrospective laboratory studies may be representative of what we observe in later clinical studies. The change in a meaningful diagnostic figure of merit between two diagnostic modalities should be qualitatively or quantitatively comparable across all kinds of studies.

MATERIALS AND METHODS

In this meta-study we examine the reproducibility of relative measures of sensitivity, false positive fraction (FPF), area under the receiver operating characteristic (ROC) curve, and expected utility across laboratory and observational clinical studies for several different breast imaging modalities, including screen film mammography, digital mammography, breast tomosynthesis, and ultrasound.

RESULTS

Across studies of all types, the changes in the FPFs yielded very small probabilities of having a common mean value. The probabilities of relative sensitivity being the same across ultrasound and tomosynthesis studies were low. No evidence was found for different mean values of relative area under the ROC curve or relative expected utility within any of the study sets.

CONCLUSION

The comparison demonstrates that the ratios of areas under the ROC curve and expected utilities are reproducible across laboratory and clinical studies, whereas sensitivity and FPF are not.

A study on mastectomy samples to evaluate breast imaging quality and potential clinical relevance of differential phase contrast mammography

OBJECTIVES

Differential phase contrast and scattering-based x-ray mammography has the potential to provide additional and complementary clinically relevant information compared with absorption-based mammography. The purpose of our study was to provide a first statistical evaluation of the imaging capabilities of the new technique compared with digital absorption mammography.

MATERIALS AND METHODS

We investigated non-fixed mastectomy samples of 33 patients with invasive breast cancer, using grating-based differential phase contrast mammography (mammoDPC) with a conventional, low-brilliance x-ray tube. We simultaneously recorded absorption, differential phase contrast, and small-angle scattering signals that were combined into novel high-frequency-enhanced images with a dedicated image fusion algorithm. Six international, expert breast radiologists evaluated clinical digital and experimental mammograms in a 2-part blinded, prospective independent reader study. The results were statistically analyzed in terms of image quality and clinical relevance.

RESULTS

The results of the comparison of mammoDPC with clinical digital mammography revealed the general quality of the images to be significantly superior (P < 0.001); sharpness, lesion delineation, as well as the general visibility of calcifications to be significantly more assessable (P < 0.001); and delineation of anatomic components of the specimens (surface structures) to be significantly sharper (P < 0.001). Spiculations were significantly better identified, and the overall clinically relevant information provided by mammoDPC was judged to be superior (P < 0.001).

CONCLUSIONS

Our results demonstrate that complementary information provided by phase and scattering enhanced mammograms obtained with the mammoDPC approach deliver images of generally superior quality. This technique has the potential to improve radiological breast diagnostics.

Evolution of breast cancer screening in the Medicare population: clinical and economic implications

BACKGROUND

Newer approaches to mammography, including digital image acquisition and computer-aided detection (CAD), and adjunct imaging (e.g., magnetic resonance imaging [MRI]) have diffused into clinical practice. The impact of these technologies on screening-related cost and outcomes remains undefined, particularly among older women.

METHODS

Using the Surveillance, Epidemiology, and End Results-Medicare linked database, we constructed two cohorts of women without a history of breast cancer and followed each cohort for 2 years. We compared the use and cost of screening mammography including digital mammography and CAD, adjunct procedures including breast ultrasound, MRI, and biopsy between the period of 2001 and 2002 and the period of 2008 and 2009 using χ(2) and t test. We also assessed the change in breast cancer stage and incidence rates using χ(2) and Poisson regression. All statistical tests were two-sided.

RESULTS

There were 137150 women (mean age = 76.0 years) in the early cohort (2001-2002) and 133097 women (mean age = 77.3 years) in the later cohort (2008-2009). The use of digital image acquisition for screening mammography increased from 2.0% in 2001 and 2002 to 29.8% in 2008 and 2009 (P < .001). CAD use increased from 3.2% to 33.1% (P < .001). Average screening-related cost per capita increased from $76 to $112 (P < .001), with annual national fee-for-service Medicare spending increasing from $666 million to $962 million. There was no statistically significant change in detection rates of early-stage tumors (2.45 vs 2.57 per 1000 person-years; P = .41).

CONCLUSIONS

Although breast cancer screening-related costs increased substantially from 2001 through 2009 among Medicare beneficiaries, a clinically significant change in stage at diagnosis was not observed.

Comparison of radiologist performance with photon-counting full-field digital mammography to conventional full-field digital mammography

RATIONALE AND OBJECTIVES

The purpose of this study was to assess the performance of a MicroDose photon-counting full-field digital mammography (PCM) system in comparison to full-field digital mammography (FFDM) for area under the receiver-operating characteristic (ROC) curve (AUC), sensitivity, specificity, and feature analysis of standard-view mammography for women presenting for screening mammography, diagnostic mammography, or breast biopsy.

MATERIALS AND METHODS

A total of 133 women were enrolled in this study at two European medical centers, with 67 women who had a pre-existing 10-36 months FFDM enrolled prospectively into the study and 66 women who underwent breast biopsy and had screening PCM and diagnostic FFDM, including standard craniocaudal and mediolateral oblique views of the breast with the lesion, enrolled retrospectively. The case mix consisted of 49 cancers, 17 biopsy-benign cases, and 67 normal cases. Sixteen radiologists participated in the reader study and interpreted all 133 cases in both conditions, separated by washout period of ≥4 weeks. ROC curve and free-response ROC curve analyses were performed for noninferiority of PCM compared to FFDM using a noninferiority margin Δ value of 0.10. Feature analysis of the 66 cases with lesions was conducted with all 16 readers at the conclusion of the blinded reads. Mean glandular dose was recorded for all cases.

RESULTS

The AUC for PCM was 0.947 (95% confidence interval [CI], 0.920-0.974) and for FFDM was 0.931 (95% CI, 0.898-0.964). Sensitivity per case for PCM was 0.936 (95% CI, 0.897-0.976) and for FFDM was 0.908 (95% CI, 0.856-0.960). Specificity per case for PCM was 0.764 (95% CI, 0.688-0.841) and for FFDM was 0.749 (95% CI, 0.668-0.830). Free-response ROC curve figures of merit were 0.920 (95% CI, 0.881-0.959) and 0.903 (95% CI, 0.858-0.948) for PCM and FFDM, respectively. Sensitivity per lesion was 0.903 (95% CI, 0.846-0.960) and 0.883 (95% CI, 0.823-0.944) for PCM and FFDM, respectively. The average false-positive marks per image of noncancer cases were 0.265 (95% CI, 0.171-0.359) and 0.281 (95% CI, 0.188-0.374) for PCM and FFDM, respectively. Noninferiority P values for AUC, sensitivity (per case and per lesion), specificity, and average false-positive marks per image were all statistically significant (P < .001). The noninferiority P value for free-response ROC was <.025, from the 95% CI for the difference. Feature analysis resulted in PCM being preferred to FFDM by the readers for ≥70% of the cases. The average mean glandular dose for PCM was 0.74 mGy (95% CI, 0.722-0.759 mGy) and for FFDM was 1.23 mGy (95% CI, 1.199-1.262 mGy).

CONCLUSIONS

In this study, radiologist performance with PCM was not inferior to that with conventional FFDM at an average 40% lower mean glandular dose.

Utility of the PANAS-X in Predicting Social Phobia in African American Females

Burgeoning literature in the field of social anxiety suggests that social phobia may diverge from the other anxiety disorders in terms of the association it shares with low positive affect. Research examining positive affect and social anxiety has contributed to the understanding of social phobia in non-Hispanic White populations, but the cross-cultural generalization of anxiety in African Americans remains unknown. The current study used receiver operating characteristic analysis to estimate the extent to which scores on the Positive and Negative Affect Scales of the Positive and Negative Affect Schedule–Expanded form (PANAS-X) predicted anxiety disorder diagnoses in a sample of 91 community-dwelling African American females. Subsequent receiver operating characteristic analyses were conducted to evaluate the utility of the Positive and Negative Affect Scales of the PANAS-X in predicting social phobia specifically. Results suggest that the PANAS-X is a clinically useful measure for predicting anxiety disorder diagnosis and, more specifically, social phobia in African American females. Additionally, optimal cutoff scores were identified, underscoring the potential use of the PANAS-X as a screening device for anxiety in African American females.

Evaluating imaging and computer-aided detection and diagnosis devices at the FDA

This report summarizes the Joint FDA-MIPS Workshop on Methods for the Evaluation of Imaging and Computer-Assist Devices. The purpose of the workshop was to gather information on the current state of the science and facilitate consensus development on statistical methods and study designs for the evaluation of imaging devices to support US Food and Drug Administration submissions. Additionally, participants expected to identify gaps in knowledge and unmet needs that should be addressed in future research. This summary is intended to document the topics that were discussed at the meeting and disseminate the lessons that have been learned through past studies of imaging and computer-aided detection and diagnosis device performance.

Comparative evaluation of digital mammography and film mammography: systematic review and meta-analysis

CONTEXT AND OBJECTIVE

Mammography is the best method for breast-cancer screening and is capable of reducing mortality rates. Studies that have assessed the clinical impact of mammography have been carried out using film mammography. Digital mammography has been proposed as a substitute for film mammography given the benefits inherent to digital technology. The aim of this study was to compare the performance of digital and film mammography.

DESIGN

Systematic review and meta-analysis.

METHOD

The Medline, Scopus, Embase and Lilacs databases were searched looking for paired studies, cohorts and randomized controlled trials published up to 2009 that compared the performance of digital and film mammography, with regard to cancer detection, recall rates and tumor characteristics. The reference lists of included studies were checked for any relevant citations.

RESULTS

A total of 11 studies involving 190,322 digital and 638,348 film mammography images were included. The cancer detection rates were significantly higher for digital mammography than for film mammography (risk relative, RR = 1.17; 95% confidence interval, CI = 1.06-1.29; I² = 19%). The advantage of digital mammography seemed greatest among patients between 50 and 60 years of age. There were no significant differences between the two methods regarding patient recall rates or the characteristics of the tumors detected.

CONCLUSION

The cancer detection rates using digital mammography are slightly higher than the rates using film mammography. There are no significant differences in recall rates between film and digital mammography. The characteristics of the tumors are similar in patients undergoing the two methods.

Conspicuity of microcalcifications on digital screening mammograms using varying degrees of monitor zooming

RATIONALE AND OBJECTIVES

American College of Radiology guidelines suggest that digital screening mammographic images should be viewed at the full resolution at which they were acquired. This slows interpretation speed. The aim of this study was to examine the effect of various levels of zooming on the detection and conspicuity of microcalcifications.

MATERIALS AND METHODS

Six radiologists viewed 40 mammographic images five times in different random orders using five different levels of zooming: full resolution (100%) and 30%, 61%, 88%, and 126% of that size. Thirty-three images contained microcalcifications varying in subtlety, all associated with breast cancer. The clusters were circled. Seven images contained no malignant calcifications but also had randomly placed circles. The radiologists graded the presence or absence and visual conspicuity of any calcifications compared to calcifications in a reference image. They also counted the microcalcifications.

RESULTS

The radiologists saw the microcalcifications in 94% of the images at 30% size and in either 99% or 100% of the other tested levels of zooming. Conspicuity ratings were worst for the 30% size and fairly similar for the others. Using the 30% size, two radiologists failed to see the microcalcifications on either the craniocaudal or mediolateral oblique view taken from one patient. Interobserver agreement regarding the number of calcifications was lowest for the 30% images and second lowest for the 100% images.

CONCLUSIONS

Images at 30% size should not be relied on alone for systematic scanning for microcalcifications. The other four levels of magnification all performed well enough to warrant further testing.

The effect of Premium View post-processing software on digital mammographic reporting

The aim of this study was to identify the effect of the installation of Premium View post-processing software on our mammographic reporting performance, in particular the effects on our recall rate, biopsy rate and cancer detection rate. The case notes and imaging of all patients discussed at the weekly indeterminate imaging multidisciplinary team meeting were reviewed retrospectively before, immediately after and at a delayed interval following the installation of Premium View post-processing software. Factors recorded included the mammographic abnormality, further investigations and final histology. The indeterminate mammogram rate increased significantly from a baseline of 5.7% (before Premium View) to 8.7% in the time period immediately after the installation of Premium View (p=0.002). The stereotactic biopsy rate also increased from 0.8% to 2.4% (p=0.001), with a significant increase in the overall cancer detection rate from 3.4% to 4.4% (p=0.02). In the follow-up period several months after the installation of Premium View, the indeterminate mammogram rate returned to a level similar to that before Premium View (6%; p=0.7). The stereotactic biopsy rate remained significantly higher at 1.6% (p=0.07), as did the overall cancer detection rate of 5.0% (p=0.003). In conclusion, the use of Premium View may lead to higher cancer detection rates, at the expense of an initial increase in recall rate. Although prospective studies are suggested, this result is of interest in light of the proposed installation of digital mammography across the NHS Breast Screening Programme.

Why does it take longer to read digital than film-screen screening mammograms? A partial explanation

Digital screening mammograms (DM) take longer to interpret than film-screen screening mammograms (FSM). We evaluated what part of the process takes long in our reading environment. We selected cases from those for which timed readings had been performed as part of a previous study. Readers were timed as they performed various computer manipulations on groups of DM cases and as they moved the alternator and adjusted lighting and manual shutters for FSM cases. Subtracting manipulation time from the original interpretation times yielded estimated times to reach a decision. Manipulation times for DM ranged from a low of 11 s when four-view DM were simply opened and closed in a 4-on-1 hanging protocol before moving on to the next study to 113.8 s when each view of six-view DM were brought up 1-on-1, enlarged to 100% resolution, and panned through. Manipulation times for groups of FSM ranged from 8.3 to 12.1 s. Estimated decision-making times for DM ranged from 128.0 to 202.2 s, while estimated decision-making time for FSM ranged from 60.9 to 146.3 s. Computer manipulation time partially explains the discrepancy in interaction times between DM and FSM. Radiologists also appear to spend more time looking at DM than at FSM before making a decision.

Timed efficiency of interpretation of digital and film-screen screening mammograms

OBJECTIVE

Our objective was to compare interpretation speeds for digital and film-screen screening mammograms to test whether other variables might affect interpretation times and thus contribute to the apparent difference in interpretation speed between digital mammograms and film-screen mammograms, and to test whether the use of digital rather than film comparison studies might result in significant time savings.

MATERIALS AND METHODS

Four readers were timed in the course of actual clinical interpretation of digital mammograms and film-screen mammograms. Interpretation times were compared for subgroups of studies based on the interpretation of the study by BI-RADS code, the number of images, the presence or absence of comparison studies and the type of comparison study, and whether the radiologist personally selected and hung additional films; the same comparisons were made among individual readers.

RESULTS

For all four readers, mean interpretation times were longer for digital mammograms than for film-screen mammograms, with differences ranging from 76 to 202 seconds. The difference in interpretation speed between digital and film-screen mammograms was independent of other variables. Digital mammogram interpretation times were significantly longer than film-screen mammogram interpretation times regardless of whether the digital mammograms were matched with film or digital comparison studies.

CONCLUSION

In screening mammography interpretation, digital mammograms take longer to read than film-screen mammograms, independent of other variables. Exclusive use of digital comparison studies may not cause interpretation times to drop enough to approach the interpretation time required for film-screen mammograms.

Evaluation of computer-aided diagnosis on a large clinical full-field digital mammographic dataset

RATIONALE AND OBJECTIVES

To convert and optimize our previously developed computerized analysis methods for use with images from full-field digital mammography (FFDM) for breast mass classification to aid in the diagnosis of breast cancer.

MATERIALS AND METHODS

An institutional review board approved protocol was obtained, with waiver of consent for retrospective use of mammograms and pathology data. Seven hundred thirty-nine FFDM images, which contained 287 biopsy-proven breast mass lesions, of which 148 lesions were malignant and 139 lesions were benign, were retrospectively collected. Lesion margins were delineated by an expert breast radiologist and were used as the truth for lesion-segmentation evaluation. Our computerized image analysis method consisted of several steps: 1) identified lesions were automatically extracted from the parenchymal background using computerized segmentation methods; 2) a set of image characteristics (mathematic descriptors) were automatically extracted from image data of the lesions and surrounding tissues; and 3) selected features were merged into an estimate of the probability of malignancy using a Bayesian artificial neural network classifier. Performance of the analyses was evaluated at various stages of the conversion using receiver-operating characteristic analysis.

RESULTS

An area under the curve value of 0.81 was obtained in the task of distinguishing between malignant and benign mass lesions in a round-robin by case evaluation on the entire FFDM dataset. We failed to show a statistically significant difference (P = .83) compared to results from our previous study in which the computerized classification was performed on digitized screen-film mammograms.

CONCLUSIONS

Our computerized analysis methods developed on digitized screen-film mammography can be converted for use with FFDM. Results show that the computerized analysis methods for the diagnosis of breast mass lesions on FFDM are promising, and can potentially be used to aid clinicians in the diagnostic interpretation of FFDM.

Results of a survey on digital screening mammography: prevalence, efficiency, and use of ancillary diagnostic AIDS

OBJECTIVE

As the use of full-field digital screening mammography grows rapidly, this study was conducted to determine the time required to interpret digital soft-copy (filmless) mammography compared with conventional film-screen screening mammography and to evaluate radiologists' use of ancillary diagnostic aids when interpreting digital mammography (DM) and conventional film-screen mammography (FSM).

MATERIALS AND METHODS

An 18-question survey was sent to 1,703 members of the Society of Breast Imaging, whose e-mail addresses were provided by the society. After subtracting those from whom out-of-office e-mail responses were received and three who wrote back to exclude themselves, there were 1,659 potential participants. Data from the respondents were collected and analyzed by tabulation and cross-tabulation.

RESULTS

In total, 396 members of the Society of Breast Imaging completed and returned surveys, for a 23.9% response rate. Of the respondents, 49.0% said that they had access to and interpreted DM. Their estimated average time to read a single digital mammographic study was 2.6 minutes, compared with 2.0 minutes for reading a single film-screen mammographic study. Therefore, the perceived time difference was 0.6 minutes. Magnification was the main ancillary diagnostic aid used in interpreting both DM and FSM: 74.2% of respondents used computer-based magnification at least half the time in interpreting DM, and 90.9% used optical magnification at least half the time in interpreting FSM. Optical magnification was also used by 28.5% of respondents at least half the time in interpreting DM. The respondents also used computer-aided detection frequently: 91.0% and 76.3% of those who had computer-aided detection available said that they used it at least 75% of the time in interpreting DM and FSM, respectively.

CONCLUSION

Digital mammography takes longer to interpret than FSM. Radiologists use various ancillary diagnostic aids, but magnification and computer-aided detection are the two most commonly used aids.

Accuracy of soft-copy digital mammography versus that of screen-film mammography according to digital manufacturer: ACRIN DMIST retrospective multireader study

PURPOSE

To retrospectively compare the accuracy for cancer diagnosis of digital mammography with soft-copy interpretation with that of screen-film mammography for each digital equipment manufacturer, by using results of biopsy and follow-up as the reference standard.

MATERIALS AND METHODS

The primary HIPAA-compliant Digital Mammographic Imaging Screening Trial (DMIST) was approved by the institutional review board of each study site, and informed consent was obtained. The approvals and consent included use of data for future HIPAA-compliant retrospective research. The American College of Radiology Imaging Network DMIST collected screening mammography studies performed by using both digital and screen-film mammography in 49 528 women (mean age, 54.6 years; range, 19-92 years). Digital mammography systems from four manufacturers (Fischer, Fuji, GE, and Hologic) were used. For each digital manufacturer, a cancer-enriched reader set of women screened with both digital and screen-film mammography in DMIST was constructed. Each reader set contained all cancer-containing studies known for each digital manufacturer at the time of reader set selection, together with a subset of negative and benign studies. For each reader set, six or 12 experienced radiologists attended two randomly ordered reading sessions 6 weeks apart. Each radiologist identified suspicious findings and rated suspicion of breast cancer in identified lesions by using a seven-point scale. Results were analyzed according to digital manufacturer by using areas under the receiver operating characteristic curve (AUCs), sensitivity, and specificity for soft-copy digital and screen-film mammography. Results for Hologic digital are not presented owing to the fact that few cancer cases were available. The implemented design provided 80% power to detect average AUC differences of 0.09, 0.08, and 0.06 for Fischer, Fuji, and GE, respectively.

RESULTS

No significant difference in AUC, sensitivity, or specificity was found between Fischer, Fuji, and GE soft-copy digital and screen-film mammography. Large reader variations occurred with each modality.

CONCLUSION

No statistically significant differences were found between soft-copy digital and screen-film mammography for Fischer, Fuji, and GE digital mammography equipment.

Issues to consider in converting to digital mammography

This article outlines the reasons that many radiology practices are converting to digital mammography. In addition, it provides basic information about the issues that must be considered in making the transformation. These issues include technical matters regarding image display, storage, and retrieval as well as clinical and ergonomic considerations.

Computer-aided detection systems for breast masses: comparison of performances on full-field digital mammograms and digitized screen-film mammograms

RATIONALE AND OBJECTIVES

To compare the performance of computer aided detection (CAD) systems on pairs of full-field digital mammogram (FFDM) and screen-film mammogram (SFM) obtained from the same patients.

MATERIALS AND METHODS

Our CAD systems on both modalities have similar architectures that consist of five steps. For FFDMs, the input raw image is first log-transformed and enhanced by a multiresolution preprocessing scheme. For digitized SFMs, the input image is smoothed and subsampled to a pixel size of 100 microm x 100 microm. For both CAD systems, the mammogram after preprocessing undergoes a gradient field analysis followed by clustering-based region growing to identify suspicious breast structures. Each of these structures is refined in a local segmentation process. Morphologic and texture features are then extracted from each detected structure, and trained rule-based and linear discriminant analysis classifiers are used to differentiate masses from normal tissues. Two datasets, one with masses and the other without masses, were collected. The mass dataset contained 131 cases with 131 biopsy proven masses, of which 27 were malignant and 104 benign. The true locations of the masses were identified by an experienced Mammography Quality Standards Act (MQSA) radiologist. The no-mass data set contained 98 cases. The time interval between the FFDM and the corresponding SFM was 0 to 118 days.

RESULTS

Our CAD system achieved case-based sensitivities of 70%, 80%, and 90% at 0.9, 1.5, and 2.6 false positive (FP) marks/image, respectively, on FFDMs, and the same sensitivities at 1.0, 1.4, and 2.6 FP marks/image, respectively, on SFMs.

CONCLUSIONS

The difference in the performances of our FFDM and SFM CAD systems did not achieve statistical significance.

Revisión de la evidencia científica sobre la aplicación clínica de la mamografía digital

OBJECTIVE

To review the scientific evidence with respect to the use of digital mammography and compare it with analogical mammography in the clinical context.

MATERIAL AND METHOD

We searched Medline and EMbase for studies published between 1989 and 2005 that compared the results of digital and analogical mammography in the same group of patients or in two different groups of patients to evaluate their respective diagnostic accuracy (sensitivity, specificity, area under the ROC curve), recall rate, biopsy rate, and exposure to radiation. We reviewed and compared the different methodologies of the studies published.

RESULTS

Eight articles and eight presentations at congresses were found. No statistically significant differences were observed between digital and analogical mammography for the detection of breast cancer. Until the publication of the Oslo II (2004) and Digital Mammographic Imaging Screening Trial (2005) studies, the series presented were small and used a variety of methodologies. This made it impossible to appreciate small differences in diagnostic accuracy between the two techniques and to group the, sometimes, contradictory results. Furthermore, these first series did not include follow-up.

CONCLUSION

There are no statistically significant differences between the two techniques for diagnostic accuracy, except in women with dense or heterogeneously dense breasts, in those under 50 years of age, and in peri- or pre-menopausal women, in which cases digital mammography is significantly better. These data should be confirmed in longer term studies to enable the effects on the breast cancer mortality rate to be specifically evaluated. Cost-effectiveness studies are important when considering changing techniques.

[DR (a-Se) versus CR (DLR)--is an improvement of the accuracy possible? A retrospective histologic analysis (n = 100)]

PURPOSE

A retrospective clinical-histological study to determine the diagnostic accuracy using high-resolution digital phosphor storage plates (CR) (hardcopy) and full-field digital mammography (DR) (hardcopy) for microcalcifications and focal lesions (BI-RADS category 4 or 5) (n = 100).

MATERIALS AND METHODS

From 01/2004 to 06/2004, 100 patients underwent digital storage plate mammography (CR) and, after diagnosis and preoperative wire localization, full-field digital mammography (a-Se) (DR) with the same exposure parameters. Five investigators retrospectively determined the diagnosis after the operation from randomly distributed mediolateral views (hardcopy reading). These results were correlated with the final histology.

RESULTS

The accuracy of digital storage plate mammography (CR) and full-field digital mammography (DR) was 73% and 76% for all findings (n = 100), 74%, 78% for microcalcifications (n = 50) and 72%, 74% for focal lesions (n = 50). The overall results showed no difference.

CONCLUSION

Our findings indicate equivalence of high-resolution digital phosphor storage plate mammography (CR) and full-field digital mammography (a-Se) (DR).

Computer-aided detection system for clustered microcalcifications: comparison of performance on full-field digital mammograms and digitized screen-film mammograms

We have developed a computer-aided detection (CAD) system to detect clustered microcalcifications automatically on full-field digital mammograms (FFDMs) and a CAD system for screen-film mammograms (SFMs). The two systems used the same computer vision algorithms but their false positive (FP) classifiers were trained separately with sample images of each modality. In this study, we compared the performance of the CAD systems for detection of clustered microcalcifications on pairs of FFDM and SFM obtained from the same patient. For case-based performance evaluation, the FFDM CAD system achieved detection sensitivities of 70%, 80% and 90% at an average FP cluster rate of 0.07, 0.16 and 0.63 per image, compared with an average FP cluster rate of 0.15, 0.38 and 2.02 per image for the SFM CAD system. The difference was statistically significant with the alternative free-response receiver operating characteristic (AFROC) analysis. When evaluated on data sets negative for microcalcification clusters, the average FP cluster rates of the FFDM CAD system were 0.04, 0.11 and 0.33 per image at detection sensitivity level of 70%, 80% and 90% compared with an average FP cluster rate of 0.08, 0.14 and 0.50 per image for the SFM CAD system. When evaluated for malignant cases only, the difference of the performance of the two CAD systems was not statistically significant with AFROC analysis.

Detection of masses and microcalcifications of breast cancer on digital mammograms: comparison among hard-copy film, 3-megapixel liquid crystal display (LCD) monitors and 5-megapixel LCD monitors: an observer performance study

The purpose of the study was to compare observer performance in the detection of masses and microcalcifications of breast cancer among hard-copy reading and soft-copy readings using 3-megapixel (3M) and 5-megapixel (5M) liquid crystal display (LCD) monitors. For the microcalcification detection test, we prepared 100 mammograms: 40 surgically verified cancer cases and 60 normal cases. For the mass detection test, we prepared 100 mammograms: 50 cancer cases and 50 normal cases. After six readers assessed both microcalcifications and masses set for each modality, receiver operating characteristic (ROC) analysis was performed. The average A(z)s for mass detection using a hard copy and 3M and 5M LCD monitors were 0.923, 0.927 and 0.920, respectively; there were no significant differences. The average A(z) for microcalcification detection using hard copy, 3M and 5M LCD monitors was 0.977, 0.954 and 0.972, respectively. There were no significant differences, but the P-values between the hard copy and 3M LCD monitor and that between the 3M and 5M LCD monitor were 0.08 and 0.09, respectively. In conclusion, the observer performances for detecting masses of breast cancers were comparable among the hard copy and two LCD monitors; however, soft-copy reading with a 3M LCD monitor showed slightly lower observer performance for detecting microcalcifications of breast cancers than hard-copy or 5M LCD monitor reading.

Computer aided detection of clusters of microcalcifications on full field digital mammograms

We are developing a computer-aided detection (CAD) system to identify microcalcification clusters (MCCs) automatically on full field digital mammograms (FFDMs). The CAD system includes six stages: preprocessing; image enhancement; segmentation of microcalcification candidates; false positive (FP) reduction for individual microcalcifications; regional clustering; and FP reduction for clustered microcalcifications. At the stage of FP reduction for individual microcalcifications, a truncated sum-of-squares error function was used to improve the efficiency and robustness of the training of an artificial neural network in our CAD system for FFDMs. At the stage of FP reduction for clustered microcalcifications, morphological features and features derived from the artificial neural network outputs were extracted from each cluster. Stepwise linear discriminant analysis (LDA) was used to select the features. An LDA classifier was then used to differentiate clustered microcalcifications from FPs. A data set of 96 cases with 192 images was collected at the University of Michigan. This data set contained 96 MCCs, of which 28 clusters were proven by biopsy to be malignant and 68 were proven to be benign. The data set was separated into two independent data sets for training and testing of the CAD system in a cross-validation scheme. When one data set was used to train and validate the convolution neural network (CNN) in our CAD system, the other data set was used to evaluate the detection performance. With the use of a truncated error metric, the training of CNN could be accelerated and the classification performance was improved. The CNN in combination with an LDA classifier could substantially reduce FPs with a small tradeoff in sensitivity. By using the free-response receiver operating characteristic methodology, it was found that our CAD system can achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.21, 0.61, and 1.49 FPs/image, respectively. For case-based performance evaluation, a sensitivity of 70, 80, and 90 % can be achieved at 0.07, 0.17, and 0.65 FPs/image, respectively. We also used a data set of 216 mammograms negative for clustered microcalcifications to further estimate the FP rate of our CAD system. The corresponding FP rates were 0.15, 0.31, and 0.86 FPs/image for cluster-based detection when negative mammograms were used for estimation of FP rates.

Digital and Screen-Film Mammography: Comparison of Image Acquisition and Interpretation Times

OBJECTIVE

The objective of our study was to compare acquisition times and interpretation times of screening examinations using screen-film mammography and soft-copy digital mammography.

MATERIALS AND METHODS

Technologist study acquisition time from examination initiation to release of the screenee was measured for both screen-film and digital mammography (100 cases each) in routine clinical practice. The total interpretation time for screening mammography was also measured for 183 hard-copy screen-film cases and 181 soft-copy digital cases interpreted by a total of seven breast imaging radiologists, four experienced breast imagers, and three breast imaging fellows.

RESULTS

Screening mammography acquisition time averaged 21.6 minutes for screen-film and 14.1 minutes for digital, a highly significant 35% shorter time for digital than screen-film (p < 10(-17)). The average number of images per case acquired with digital mammography was higher than that for screen-film mammography (4.23 for screen-film, 4.50 for digital; p = 0.047). The total interpretation time averaged 1.4 minutes for screen-film mammography and 2.3 minutes for digital mammography, a highly significant 57% longer interpretation time for digital (p < 10(-11)). In addition, technical problems delaying interpretation were encountered in none of the 183 screen-film cases but occurred in nine (5%) of the 181 digital cases.

CONCLUSION

Compared with screen-film mammography, the use of digital mammography for screening examinations significantly shortened acquisition time but significantly increased interpretation time. In addition, more technical problems were encountered that delayed the interpretation of digital cases.

Dose comparison between screen/film and full-field digital mammography

The study purpose was the comparison between doses delivered by a full-field digital mammography system and a screen/film mammography unit, both using the same type of X-ray tube. Exposure parameters and breast thickness were collected for 300 screen/film (GE Senographe DMR) and 296 digital mammograms (GE Senographe 2000D). The entrance surface air kerma (ESAK) was calculated from anode/filter combination, kV(p) and mAs values and breast thickness, by simulating spectra through a program based on a catalogue of experimental X-ray spectra. The average glandular dose (AGD) was also computed. Results showed an overall reduction of average glandular dose by 27% of digital over screen/film mammography. The dose saving was about 15% for thin and thick breasts, while it was between 30% and 40% for intermediate thicknesses. Full-field digital mammography dose reduction is allowed by wider dynamic range and higher efficiency of digital detector, which can be exposed at higher energy spectra than screen/film mammography, and by the separation between acquisition and displaying processes.

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.

The effect of image display size on observer performance an assessment of variance components

RATIONALE AND OBJECTIVE

Our goal was to investigate the effect of the displayed image size on variance components during the performance of an observer performance study to detect masses on abdominal computed tomography (CT) examinations.

MATERIALS AND METHODS

A previously performed receiver operating characteristic (ROC) study with eight observers to detect abdominal masses on 166 CT examinations was reanalyzed to assess variance components when comparing two similar modes with displayed image sizes varying by a factor of 2. Case, mode, and reader-related variance components were estimated for the group of eight observers and subsets of readers after excluding each of the participants.

RESULTS

There was no significant difference in the average area under the ROC curves between the two modes using the two image sizes (P > .05). Reader and reader-by-case variability were substantially larger for the mode displaying enlarged images for the group and all subsets formed by excluding a single reader. Reader variability was affected by one observer who actually performed better with the enlarged images.

CONCLUSION

Sequential viewing of enlarged CT images for the detection of abdominal masses did not improve performance and increased reader variability.

Exploring the boundary between temperament and generalized anxiety disorder: a receiver operating characteristic analysis

Studies of individuals with an increased tendency to experience negative emotions such as fear, sadness, and anger have documented links between this temperamental trait and anxiety disorders. There exists debate, however, concerning the degree to which high levels of a temperamental trait are a necessary and/or sufficient component of a DSM diagnosis. In this study, receiver operating characteristic (ROC) analyses assessed the relations between levels of harm avoidance (HA) and generalized anxiety disorder (GAD) diagnoses in 334 children and their parents. Analyses revealed HA scores to be highly predictive of GAD diagnoses in children (AUC=.791, P<.001) and adults (AUC=.818, P<.001). However, there were many individuals with high HA scores who did not qualify for a GAD diagnosis. These findings suggest that while there are strong associations between HA and GAD, high levels of HA are neither necessary nor sufficient in the formation of clinically significant anxiety symptoms.

Variability in observer performance studies experimental observations

RATIONALE AND OBJECTIVES

The aim of the study is to assess variance components in observer performance studies and the possible impact on study results and conclusions.

MATERIALS AND METHODS

Two previously performed retrospective receiver operating characteristic-type observer performance studies to evaluate the performance of seven radiologists in detecting interstitial disease on conventional posteroanterior chest films and nine radiologists in detecting interstitial disease on a high-resolution workstation were reanalyzed by using the Beiden, Wagner, and Campbell nine-component model to estimate the different variance components. We estimated case-, reader-, and mode-related components of the variance for the group as a whole and after excluding (round robin) each reader. Overall variance was evaluated, and the effect of individual readers on overall study conclusions was assessed.

RESULTS

Overall results and conclusions of the reanalysis agreed with the original one in that, as a group, radiologists performed significantly better when using conventional films (P < .05) in both studies. Reader variability was large compared with all other components, and in one study, it was substantially larger for the workstation reading mode. Reader variability was affected substantially by one observer in each study, and in one study, reader-by-mode variability was affected by another reader who performed better on the workstation.

CONCLUSION

Estimates of variance components can shed light on the appropriateness of study design, as well as the sensitivity of results to the inclusion (or exclusion) of individual observers.

Diagnostic performance of digital versus film mammography for breast-cancer screening

BACKGROUND

Film mammography has limited sensitivity for the detection of breast cancer in women with radiographically dense breasts. We assessed whether the use of digital mammography would avoid some of these limitations.

METHODS

A total of 49,528 asymptomatic women presenting for screening mammography at 33 sites in the United States and Canada underwent both digital and film mammography. All relevant information was available for 42,760 of these women (86.3 percent). Mammograms were interpreted independently by two radiologists. Breast-cancer status was ascertained on the basis of a breast biopsy done within 15 months after study entry or a follow-up mammogram obtained at least 10 months after study entry. Receiver-operating-characteristic (ROC) analysis was used to evaluate the results.

RESULTS

In the entire population, the diagnostic accuracy of digital and film mammography was similar (difference between methods in the area under the ROC curve, 0.03; 95 percent confidence interval, -0.02 to 0.08; P=0.18). However, the accuracy of digital mammography was significantly higher than that of film mammography among women under the age of 50 years (difference in the area under the curve, 0.15; 95 percent confidence interval, 0.05 to 0.25; P=0.002), women with heterogeneously dense or extremely dense breasts on mammography (difference, 0.11; 95 percent confidence interval, 0.04 to 0.18; P=0.003), and premenopausal or perimenopausal women (difference, 0.15; 95 percent confidence interval, 0.05 to 0.24; P=0.002).

CONCLUSIONS

The overall diagnostic accuracy of digital and film mammography as a means of screening for breast cancer is similar, but digital mammography is more accurate in women under the age of 50 years, women with radiographically dense breasts, and premenopausal or perimenopausal women. (ClinicalTrials.gov number, NCT00008346.)

American College of Radiology Imaging Network digital mammographic imaging screening trial: objectives and methodology

This study was approved by the Institutional Review Board (IRB) of the American College of Radiology Imaging Network (ACRIN) and each participating site and by the IRB and the Cancer Therapy Evaluation Program at the National Cancer Institute. The study was monitored by an independent Data Safety and Monitoring Board, which received interim analyses of data to ensure that the study would be terminated early if indicated by trends in the outcomes. The ACRIN, which is funded by the National Cancer Institute, conducted the Digital Mammographic Imaging Screening Trial (DMIST) primarily to compare the diagnostic accuracy of digital and screen-film mammography in asymptomatic women presenting for screening for breast cancer. Over the 25.5 months of enrollment, a total of 49 528 women were included at the 33 participating sites, which used five different types of digital mammography equipment. All participants underwent both screen-film and digital mammography. The digital and screen-film mammograms of each subject were independently interpreted by two radiologists. If findings of either examination were interpreted as abnormal, subsequent work-up occurred according to the recommendations of the interpreting radiologist. Breast cancer status was determined at biopsy or follow-up mammography 11-15 months after study entry. In addition to the measurement of diagnostic accuracy by using the interpretations of mammograms at the study sites, DMIST included evaluations of the relative cost-effectiveness and quality-of-life effects of digital versus screen-film mammography. Six separate reader studies using the de-identified archived DMIST mammograms will also assess the diagnostic accuracy of each of the individual digital mammography machines versus screen-film mammography machines, the effect of breast density on diagnostic accuracy of digital and screen-film mammography, and the effect of different rates of breast cancer on the diagnostic accuracy in a reader study.

[Clinical results of digital mammography]

Digital mammography is the technology of the future in breast diagnosis. This article provides an overview of all digital mammography units admitted by the Food and Drug Administration (FDA), results of clinical studies, soft copy reading, CAD (computer aided detection), and presents an overview on possible further developments. It is obvious that clinical results are equivalent to conventional screen film mammography and digital mammography.

Are phantoms useful for predicting the potential of dose reduction in full-field digital mammography?

A phantom study was performed in full-field digital mammography to investigate the opportunity and the magnitude of a possible dose reduction that would leave the image quality above the accepted thresholds associated with some classical phantoms. This preliminary work is intended to lay the groundwork for a future clinical study on the impact of dose reduction on clinical results. Three different mammography phantoms (ACR RMI 156, CIRS 11A and CDMAM 3.4) were imaged by a full-field digital mammography unit (GE Senographe 2000D) at different dose levels. Images were rated by three observers with softcopy reading and scoring methods specific to each phantom. Different types of data analysis were applied to the ACR (American College of Radiology) and the other two phantoms, respectively. With reference to the minimum acceptance score in screen/film accreditation programmes, the ACR phantom showed that about 45% dose reduction could be applied, while keeping the phantom scores above that threshold. A relative comparison was done for CIRS and CDMAM, for which no threshold is defined. CIRS scoring remained close to the reference level down to 40% dose reduction, the inter- and intra-observer variability being the main source of uncertainty. Contrast-detail curves provided by CDMAM overlapped down to 50% dose reduction, at least for object contrast values ranging between 30% and 3%. This multi-phantom study shows the potential of further reducing the dose in full-field digital mammography beyond the current values. A common dose reduction factor around 50% seems acceptable for all phantoms. However, caution is required before extrapolating the results for clinical use, given the limitations of these widely used phantoms, mainly related to their limited dynamic range and uniform background.

Digital mammography

In digital mammography, the processes of image acquisition, display, and storage are separated, which allows optimization of each. Radiation transmitted through the breast is absorbed by an electronic detector, the response of which is faithful over a wide range of intensities. Once this information is recorded, it can be displayed by using computer image-processing techniques to allow arbitrary settings of image brightness and contrast, without the need for further exposure to the patient. In this article, the current state of the art in technology for digital mammography and data from clinical trials that support the use of the technology will be reviewed. In addition, several potentially useful applications that are being developed with digital mammography will be described.

Image quality measurements and metrics in full field digital mammography: an overview

This paper gives an overview of test procedures developed to assess the performance of full field digital mammography systems. We make a distinction between tests of the individual components of the imaging chain and global system tests. Most tests are not yet fully standardised. Where possible, we illustrate the test methodologies on a selenium flat-panel system.