Abstract #2129

Using Natural Language Processing to Explore the Correlation of Breast MR Findings and BI-RADS classification

Yuan Jiang¹, Yi Liu¹, Yahui Shi², Zuofeng Li², Juan Wei², and Xiaoying Wang¹

¹Radiology, Peking University First Hospital, Beijing, People's Republic of China, ²Philips Research China, Shanghai, People's Republic of China

The decision tree trained on MR descriptions by natural language processing (NLP) method shows desirable capability in identifying the high-risk BI-RADS 5-6 class.From the decision path, we identify the key indicators to distinguish BI-RADS 5-6 from the relatively low-risk classes. And the inner heterogeneity of BI-RADS 4 cases makes it difficult to build a general model for this class.

This abstract and the presentation materials are available to members only; a login is required.

Join Here