High-Risk Breast Lesions: A Machine Learning Model to Predict Pathologic Upgrade and Reduce Unnecessary Surgical Excision

Abstract

Purpose 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. Materials and Methods 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. Results 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. Conclusion 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, 2017.

Human factors challenges for the safe use of artificial intelligence in patient care

“…It is common to find claims that pit the performance of, for example, a DNN against that of clinicians at undertaking a well-defined and narrow task. Examples include identification of skin cancer,7 identification of high-risk breast lesions not requiring surgical excision8 and detection of diabetic retinopathy 9. These studies have shown that AI systems often outperform humans at such tasks.…”

Artificial intelligence in radiology: the ecosystem essential to improving patient care

“…In addition, AI can be used to procure prognostic information in breast imaging. Many women with biopsy-proven high-risk breast lesions undergo surgical excision while only 11% of them are upgraded to cancer [33]. Integrating multiple complex features of patient data through a machine learning model can be used to identify women at low risk for upgrade to cancer and decrease unnecessary surgery by 30% [33].…”

“…Many women with biopsy-proven high-risk breast lesions undergo surgical excision while only 11% of them are upgraded to cancer [33]. Integrating multiple complex features of patient data through a machine learning model can be used to identify women at low risk for upgrade to cancer and decrease unnecessary surgery by 30% [33]. Furthermore, radiomics can lead to the discovery of predictive imaging phenotypes of breast cancer that can be used to inform clinicians on treatment response and prognosis.…”

Simultaneous spatiotemporal tracking and oxygen sensing of transient implants in vivo using hot-spot MRI and machine learning

“…Of relevance, machine-learning techniques have been widely used to automate tasks in our daily life and, more recently, to facilitate computerized decision making and knowledge acquisition informed by a vast amount of data (54). In the field of biomedical imaging and medical diagnostics, intelligent algorithms are able to review thousands of images and extract high-level information, such as the presence of disease, in an automated way and at a competitive success rate to that of a human observer (55,56).…”