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

Patient and Radiologist Characteristics Associated With Accuracy of Two Types of Diagnostic Mammograms

OBJECTIVE

Earlier studies of diagnostic mammography found wide unexplained variability in accuracy among radiologists. We assessed patient and radiologist characteristics associated with the interpretive performance of two types of diagnostic mammography.

MATERIALS AND METHODS

Radiologists interpreting mammograms in seven regions of the United States were invited to participate in a survey that collected information on their demographics, practice setting, breast imaging experience, and self-reported interpretive volume. Survey data from 244 radiologists were linked to data on 274,401 diagnostic mammograms performed for additional evaluation of a recent abnormal screening mammogram or to evaluate a breast problem, between 1998 and 2008. These data were also linked to patients' risk factors and follow-up data on breast cancer. We measured interpretive performance by false-positive rate, sensitivity, and AUC. Using logistic regression, we evaluated patient and radiologist characteristics associated with false-positive rate and sensitivity for each diagnostic mammogram type.

RESULTS

Mammograms performed for additional evaluation of a recent mammogram had an overall false-positive rate of 11.9%, sensitivity of 90.2%, and AUC of 0.894; examinations done to evaluate a breast problem had an overall false-positive rate of 7.6%, sensitivity of 83.9%, and AUC of 0.871. Multiple patient characteristics were associated with measures of interpretive performance, and radiologist academic affiliation was associated with higher sensitivity for both indications for diagnostic mammograms.

CONCLUSION

These results indicate the potential for improved radiologist training, using evaluation of their own performance relative to best practices, and for improved clinical outcomes with health care system changes to maximize access to diagnostic mammography interpretation in academic settings.

Histopathological image analysis: a review

Over the past decade, dramatic increases in computational power and improvement in image analysis algorithms have allowed the development of powerful computer-assisted analytical approaches to radiological data. With the recent advent of whole slide digital scanners, tissue histopathology slides can now be digitized and stored in digital image form. Consequently, digitized tissue histopathology has now become amenable to the application of computerized image analysis and machine learning techniques. Analogous to the role of computer-assisted diagnosis (CAD) algorithms in medical imaging to complement the opinion of a radiologist, CAD algorithms have begun to be developed for disease detection, diagnosis, and prognosis prediction to complement the opinion of the pathologist. In this paper, we review the recent state of the art CAD technology for digitized histopathology. This paper also briefly describes the development and application of novel image analysis technology for a few specific histopathology related problems being pursued in the United States and Europe.

Histopathological image analysis: a review

Over the past decade, dramatic increases in computational power and improvement in image analysis algorithms have allowed the development of powerful computer-assisted analytical approaches to radiological data. With the recent advent of whole slide digital scanners, tissue histopathology slides can now be digitized and stored in digital image form. Consequently, digitized tissue histopathology has now become amenable to the application of computerized image analysis and machine learning techniques. Analogous to the role of computer-assisted diagnosis (CAD) algorithms in medical imaging to complement the opinion of a radiologist, CAD algorithms have begun to be developed for disease detection, diagnosis, and prognosis prediction to complement the opinion of the pathologist. In this paper, we review the recent state of the art CAD technology for digitized histopathology. This paper also briefly describes the development and application of novel image analysis technology for a few specific histopathology related problems being pursued in the United States and Europe.

Performance of computer-aided detection applied to full-field digital mammography in detection of breast cancers

OBJECTIVE

The aim of this retrospective study was to evaluate performance of computer-aided detection (CAD) with full-field digital mammography (FFDM) in detection of breast cancers.

MATERIALS AND METHODS

CAD was retrospectively applied to standard mammographic views of 127 cases with biopsy proven breast cancers detected with FFDM (Senographe 2000, GE Medical Systems). CAD sensitivity was assessed in total group of 127 cases and for subgroups based on breast density, mammographic lesion type, mammographic lesion size, histopathology and mode of presentation.

RESULTS

Overall CAD sensitivity was 91% (115 of 127 cases). There were no statistical differences (p > 0.1) in CAD detection of cancers in dense breasts 90% (53/59) versus non-dense breasts 91% (62/68). There was statistical difference (p < 0.05) in CAD detection of cancers that appeared mammographically as microcalcifications only versus other mammographic manifestations. CAD detected 100% (44/44) of cancers manifesting as microcalcifications, 89% (47/53) as no-calcified masses or asymmetries, 88% (14/16) as masses with associated calcifications, and 71% (10/14) as architectural distortions. CAD sensitivity for cancers 1-10mm was 84% (38/45); 11-20mm 93% (55/59); and >20mm 97% (22/23).

CONCLUSION

CAD applied to FFDM showed 100% sensitivity in identifying cancers manifesting as microcalcifications only and high sensitivity 86% (71/83) for other mammographic appearances of cancer. Sensitivity is influenced by lesion size. CAD in FFDM is an adjunct helping radiologist in early detection of breast cancers.

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.

How does age affect baseline screening mammography performance measures? A decision model

Background

In order to promote consumer-oriented informed medical decision-making regarding screening mammography, we created a decision model to predict the age dependence of the cancer detection rate, the recall rate and the secondary performance measures (positive predictive values, total intervention rate, and positive biopsy fraction) for a baseline mammogram.

Methods

We constructed a decision tree to model the possible outcomes of a baseline screening mammogram in women ages 35 to 65. We compared the single baseline screening mammogram decision with the no screening alternative. We used the Surveillance Epidemiology and End Results national cancer database as the primary input to estimate cancer prevalence. For other probabilities, the model used population-based estimates for screening mammography accuracy and diagnostic mammography outcomes specific to baseline exams. We varied radiologist performance for screening accuracy.

Results

The cancer detection rate increases from 1.9/1000 at age 40 to 7.2/1000 at age 50 to 15.1/1000 at age 60. The recall rate remains relatively stable at 142–157/1000, which varies from 73–236/1000 at age 50 depending on radiologist performance. The positive predictive value of a screening mammogram increases from 1.3% at age 40 to 9.8% at age 60, while the positive predictive value of a diagnostic mammogram varies from 2.9% at age 40 to 19.2% at age 60. The model predicts the total intervention rate = 0.013*AGE² - 0.67*AGE + 40, or 34/1000 at age 40 to 47/1000 at age 60. Therefore, the positive biopsy (intervention) fraction varies from 6% at age 40 to 32% at age 60.

Conclusion

Breast cancer prevalence, the cancer detection rate, and all secondary screening mammography performance measures increase substantially with age.