High-Risk Breast Lesions: A Machine Learning Model to Predict Pathologic Upgrade and Reduce Unnecessary Surgical Excision
- 1 March 2018
- journal article
- research article
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 286 (3), 810-818
- https://doi.org/10.1148/radiol.2017170549
Abstract
To develop a machine learning model that allows high-risk breast lesions (HRLs) diagnosed with image-guided needle biopsy that require surgical excision to be distinguished from HRLs that are at low risk for upgrade to cancer at surgery and thus could be surveilled. Consecutive patients with biopsy-proven HRLs who underwent surgery or at least 2 years of imaging follow-up from June 2006 to April 2015 were identified. A random forest machine learning model was developed to identify HRLs at low risk for upgrade to cancer. Traditional features such as age and HRL histologic results were used in the model, as were text features from the biopsy pathologic report. One thousand six HRLs were identified, with a cancer upgrade rate of 11.4% (115 of 1006). A machine learning random forest model was developed with 671 HRLs and tested with an independent set of 335 HRLs. Among the most important traditional features were age and HRL histologic results (eg, atypical ductal hyperplasia). An important text feature from the pathologic reports was “severely atypical.” Instead of surgical excision of all HRLs, if those categorized with the model to be at low risk for upgrade were surveilled and the remainder were excised, then 97.4% (37 of 38) of malignancies would have been diagnosed at surgery, and 30.6% (91 of 297) of surgeries of benign lesions could have been avoided. This study provides proof of concept that a machine learning model can be applied to predict the risk of upgrade of HRLs to cancer. Use of this model could decrease unnecessary surgery by nearly one-third and could help guide clinical decision making with regard to surveillance versus surgical excision of HRLs. © RSNA, 2017This publication has 34 references indexed in Scilit:
- Harms of Breast Cancer Screening: Systematic Review to Update the 2009 U.S. Preventive Services Task Force RecommendationAnnals of Internal Medicine, 2016
- Benefits and Harms of Breast Cancer ScreeningJAMA, 2015
- Trends in breast biopsy pathology diagnoses among women undergoing mammography in the United States: A report from the Breast Cancer Surveillance ConsortiumCancer, 2015
- Multidisciplinary Considerations in the Management of High-Risk Breast LesionsAmerican Journal of Roentgenology, 2012
- Excision of High-Risk Breast Lesions on Needle Biopsy: Is There a Standard of Core?American Journal of Roentgenology, 2009
- Frequency and Upgrade Rates of Atypical Ductal Hyperplasia Diagnosed at Stereotactic Vacuum-Assisted Breast Biopsy: 9-Versus 11-GaugeAmerican Journal of Roentgenology, 2009
- Is surgical biopsy mandatory in case of atypical ductal hyperplasia on 11-gauge core needle biopsy? a retrospective study of 300 patientsThe American Journal of Surgery, 2008
- Lobular Neoplasia at Percutaneous Breast Biopsy: Variables Associated with Carcinoma at Surgical ExcisionAmerican Journal of Roentgenology, 2008
- Breast cancer screening with mammography: overview of Swedish randomised trialsThe Lancet, 1993
- REDUCTION IN MORTALITY FROM BREAST CANCER AFTER MASS SCREENING WITH MAMMOGRAPHYThe Lancet, 1985