The “Sweet Spot” Revisited: Optimal Recall Rates for Cancer Detection With 2D and 3D Digital Screening Mammography in the Metro Chicago Breast Cancer Registry

Rauscher, Garth H.; Murphy, Anne M.; Qiu, Qiong; Dolecek, Therese A.; Tossas, Katherine Y.; Liu, Yanyang; Alsheik, Nila

doi:10.2214/ajr.19.22429

Cited by 16 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To choose it, constructors aim for a recall rate that is approximately 20 to 40% for a cancer-enriched cohort. Currently, the recall rate in the United States is more than approximately 10% in a screening population (22).…”

Section: Discussionmentioning

confidence: 99%

Comparative Clinical Evaluation of 3 Artificial Intelligence Algorithms for Breast Cancer Screening with Mammography

Brion,

Dang,

Poncelet

et al. 2024

Preprint

View full text Add to dashboard Cite

Objectives: Few studies have evaluated and compared artificial intelligence (AI) models for breast cancer detection on the same database. The purpose is to compare the performances of 3 artificial intelligence algorithms on the same dataset at a free operative threshold and to evaluate how the performance is impacted by the chosen threshold. Materials: In this retrospective single-center study, a dataset of 314 2D screening mammograms performed between 2012 and 2020 was established with a prevalence of 19.6% of histologically proven cancer. Three AI constructors using CE (European conformity) marking algorithms have agreed to take part in the study by submitting the cancer-enriched cohort to their algorithm. They chose a free operative threshold to distinguish benign and malignant mammograms. The most suspicious lesion was marked and correctly located by the AI algorithm. Statistical parameters were analyzed and compared between the algorithms. Results: Regarding both sensitivity and specificity, at the chosen threshold, AI 1 had the best compromise between sensitivity (74%) and specificity (79%). AI 2 had a statistically lower sensitivity (52%; p<0.05) with a higher specificity (98.4%) than the other AI algorithms. AI 3 had a nonsignificant sensitivity difference (69.9%) but a significantly lower specificity (45.3%; p<0.001) than the other two. The performances varied depending on the chosen threshold; when the AI 2 threshold was lowered, the sensitivity increased (69.9%), while a higher specificity (86.1%) was maintained. Conclusion: Two AI algorithms stood out in terms of performance when the threshold was optimized, resulting in an acceptable sensitivity and specificity.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparative Clinical Evaluation of 3 Artificial Intelligence Algorithms for Breast Cancer Screening with Mammography

Brion,

Dang,

Poncelet

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, policy makers should develop policies that encourage an appropriate baseline for OP-9. While a typical recall rate for a facility is around 9%, research should be conducted to inform policy makers of an optimal efficiency score (Rauscher et al, 2021; Vasen et al, 2016).…”

Section: Discussion and Policy Implicationsmentioning

confidence: 99%

Observational Trends in Publicly Reported Quality Measures of Hospital Outpatient Quality Reporting Program, 2013-2019

Hamadi

Zhao

Haley

et al. 2022

Journal of Ambulatory Care Management

View full text Add to dashboard Cite

In 2011, the Centers for Medicare & Medicaid Services (CMS) implemented the Hospital Outpatient Quality Reporting Program to assess the quality of outpatient imaging efficiency (OIE). In this study, trends in hospital performance on these national hospital OIE measures a year after inception and public reporting were described. An observational trend analysis was conducted using 2013-2019 data from CMS 6 OIE measures. The trend analysis of metric scores indicates year-to-year variability in all 6 OIE variables. The reporting of these measures appears to have effectively improved the efficiency of most of the measures since the inception of the program.

show abstract

“…(see Figures 6 and 7 and Table 3). Recall Rate (i.e., the percentage of mammograms that were reported to have abnormal findings) and PPV (i.e., the percentage of women recalled for further tests who have cancer) are important clinical metrics within breast cancer screening (e.g., Norsuddin et al, 2015;Rauscher et al, 2021;Taylor-Phillips et al, 2024) and were calculated as follows, in which TP stands for True Positive, FP stands for False Positive (false alarms), TN stands for True Negative and FN stands for False Negative:…”

Section: Miss Errorsmentioning

confidence: 99%

The Message Matters: Changes to Binary Computer Aided Detection Recommendations Affect Cancer Detection in Low Prevalence Search

Patterson,

Kunar

2024

Preprint

View full text Add to dashboard Cite

Computer Aided Detection (CAD) has been used to help readers find cancers in mammograms. Although these automated systems have been shown to help cancer detection when accurate, the presence of CAD also leads to an over-reliance effect where miss errors and false alarms increase when the CAD system fails. Previous research investigated CAD systems which overlayed salient exogenous cues onto the image to highlight suspicious areas. These salient cues capture attention which may exacerbate the over-reliance effect. Furthermore, overlaying CAD cues directly on the mammogram occludes sections of breast tissue which may disrupt global statistics useful for cancer detection. In this study we investigated whether an over-reliance effect occurred with a binary CAD system, which instead of overlaying a CAD cue onto the mammogram, reported a message alongside the mammogram indicating the possible presence of a cancer. We manipulated the certainty of the message and whether it was presented only to indicate the presence of a cancer, or whether a message was displayed on every mammogram to state whether a cancer was present or absent. The results showed that although an over-reliance effect still occurred with binary CAD systems miss errors were reduced when the CAD message was more definitive and only presented to alert readers of a possible cancer.

show abstract

The “Sweet Spot” Revisited: Optimal Recall Rates for Cancer Detection With 2D and 3D Digital Screening Mammography in the Metro Chicago Breast Cancer Registry

Cited by 16 publications

References 22 publications

Comparative Clinical Evaluation of 3 Artificial Intelligence Algorithms for Breast Cancer Screening with Mammography

Comparative Clinical Evaluation of 3 Artificial Intelligence Algorithms for Breast Cancer Screening with Mammography

Observational Trends in Publicly Reported Quality Measures of Hospital Outpatient Quality Reporting Program, 2013-2019

The Message Matters: Changes to Binary Computer Aided Detection Recommendations Affect Cancer Detection in Low Prevalence Search

Contact Info

Product

Resources

About