From the Division of Breast Imaging, Department of Radiology, Massachusetts General Hospital/Harvard Medical School, 55 Fruit St, WAC 240, Boston, MA 02114 (M.B., C.D.L.); and Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Mass (R.B., A.B.Y., N.J.L., L.Y.).
Radiology. 2018 Mar;286(3):810-818. doi: 10.1148/radiol.2017170549. Epub 2017 Oct 17.
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.
目的 开发一种机器学习模型，以区分需要手术切除的经影像引导针活检诊断为高危乳腺病变（HRL）与在手术时升级为癌症风险较低的 HRL，后者可进行监测。
材料与方法 本研究回顾性分析了 2006 年 6 月至 2015 年 4 月期间经活检证实为 HRL 且行手术或至少 2 年影像学随访的连续患者。建立了一个随机森林机器学习模型来识别升级为癌症风险较低的 HRL。该模型使用了传统特征，如年龄和 HRL 组织学结果，以及活检病理报告中的文本特征。
结果 共确定了 1600 例 HRL，癌症升级率为 11.4%（115/1006）。建立了一个机器学习随机森林模型，并用 671 例 HRL 进行训练，并用 335 例 HRL 进行独立测试。最重要的传统特征包括年龄和 HRL 组织学结果（如非典型导管增生）。病理报告中的一个重要文本特征是“严重非典型”。如果将模型归类为升级风险低的所有 HRL 进行监测，而其余 HRL 进行切除，那么 97.4%（37/38）的恶性肿瘤将在手术中诊断，30.6%（91/297）的良性病变手术可以避免。
结论 本研究证明了机器学习模型可用于预测 HRL 升级为癌症的风险。该模型的应用可使不必要的手术减少近三分之一，并有助于指导 HRL 监测与手术切除的临床决策。
