Meeting Banner
Abstract #0598

Unsupervised Hierarchical Clustering of PET/MRI Radiomics Features Might Be Helpful to Predict Response to Neoadjuvant Chemotherapy of Breast Cancer

Cindy Xue1, Jing Yuan1, Victor Ai2, Helen HL Chan2, and Gladys Lo2

1Medical Physicist and Research Department, Hong Kong Sanatorium and Hospital, Hong Kong, Hong Kong, 2Department of Diagnostic and Interventional Radiology, Hong Kong Sanatorium and Hospital, Hong Kong, Hong Kong

Radiomics has been studied as imaging biomarker for quantifying tumor characteristics non-invasively. In this study, we sought to evaluate the relationship between radiomics features of PET/MRI and its response towards neo-adjuvant chemotherapy (NAC). 26 females with newly diagnosed breast cancer underwent PET/MRI. Radiomics features were extracted from the PET/MRI images. Using the radiomics features, the group was then subdivided into three groups using unsupervised clustering. Different pathology response towards NAC was found among the groups, hence, showing there might be some associations among PET/MRI radiomics features and pathology response to NAC in breast cancer.

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

Join Here