A Deep Learning Decision Support Tool to Improve Risk Stratification and Reduce Unnecessary Biopsies in BI-RADS 4 Mammograms
Authors:
- Chika F. EzeanaCEChika F. Ezeana
- Tiancheng HeTHTiancheng He
- Tejal A. PatelTPTejal A. Patel
- Virginia KaklamaniVKVirginia Kaklamani
- Maryam ElmiMEMaryam Elmi
- Erika BrigmonEBErika Brigmon
- Pamela M. OttoPOPamela M. Otto
- Kenneth A. KistKKKenneth A. Kist
- Heather SpeckHSHeather Speck
- Lin WangLWLin Wang
- Joe EnsorJEJoe Ensor
- Ya-Chen T. ShihYSYa-Chen T. Shih
Open Access
- 1 November 2023
- journal article
- research article
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 5 (6) , e220259
Abstract
To evaluate the performance of a biopsy decision support algorithmic model, the intelligent-augmented breast cancer risk calculator (iBRISK), on a multicenter patient dataset. iBRISK was previously developed by applying deep learning to clinical risk factors and mammographic descriptors from 9700 patient records at the primary institution and validated using another 1078 patients. All patients were seen from March 2006 to December 2016. In this multicenter study, iBRISK was further assessed on an independent, retrospective dataset (January 2015–June 2019) from three major health care institutions in Texas, with Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions. Data were dichotomized and trichotomized to measure precision in risk stratification and probability of malignancy (POM) estimation. iBRISK score was also evaluated as a continuous predictor of malignancy, and cost savings analysis was performed. The iBRISK model's accuracy was 89.5%, area under the receiver operating characteristic curve (AUC) was 0.93 (95% CI: 0.92, 0.95), sensitivity was 100%, and specificity was 81%. A total of 4209 women (median age, 56 years [IQR, 45–65 years]) were included in the multicenter dataset. Only two of 1228 patients (0.16%) in the “low” POM group had malignant lesions, while in the “high” POM group, the malignancy rate was 85.9%. iBRISK score as a continuous predictor of malignancy yielded an AUC of 0.97 (95% CI: 0.97, 0.98). Estimated potential cost savings were more than $420 million. iBRISK demonstrated high sensitivity in the malignancy prediction of BI-RADS 4 lesions. iBRISK may safely obviate biopsies in up to 50% of patients in low or moderate POM groups and reduce biopsy-associated costs. Keywords: Mammography, Breast, Oncology, Biopsy/Needle Aspiration, Radiomics, Precision Mammography, AI-augmented Biopsy Decision Support Tool, Breast Cancer Risk Calculator, BI-RADS 4 Mammography Risk Stratification, Overbiopsy Reduction, Probability of Malignancy (POM) Assessment, Biopsy-based Positive Predictive Value (PPV3) Supplemental material is available for this article. Published under a CC BY 4.0 license. See also the commentary by McDonald and Conant in this issue.Keywords
This publication has 39 references indexed in Scilit:
- Nation-wide data on screening performance during the transition to digital mammography: Observations in 6 million screensEuropean Journal of Cancer, 2013
- Accuracy and Value of Breast Ultrasound for Primary Imaging Evaluation of Symptomatic Women 30-39 Years of AgeAmerican Journal of Roentgenology, 2012
- Inter- and intraradiologist variability in the BI-RADS assessment and breast density categories for screening mammogramsBritish Journal of Radiology, 2012
- Microenvironmental Regulation of Epithelial–Mesenchymal Transitions in CancerCancer Research, 2012
- Symptom Distress Associated with Biopsy in Women with Suspect Breast LesionsISRN Oncology, 2012
- A Novel Method of Transcriptional Response Analysis to Facilitate Drug Repositioning for Cancer TherapyCancer Research, 2012
- Practice Bulletin No. 122: Breast Cancer ScreeningObstetrics & Gynecology, 2011
- Positive Predictive Value of Mammography: Comparison of Interpretations of Screening and Diagnostic Images by the Same Radiologist and by Different RadiologistsAmerican Journal of Roentgenology, 2010
- The Positive Predictive Value of BI-RADS Microcalcification Descriptors and Final Assessment CategoriesAmerican Journal of Roentgenology, 2010
- Nonpalpable breast cancer: Needle-localized biopsy for diagnosis and considerations for treatmentThe American Journal of Surgery, 1986