Meeting Banner
Abstract #1712

Radiomic Characteristics Derived from Diffusion-Weighted Imaging for the Assessment of Breast Cancer Receptor Status and Molecular Subtypes

Doris Leithner1,2, Joao V. Horvat1, Maria Adele Marino1, Daly Avendano1, Sunitha Thakur3, Blanca Bernard-Davila4, Maxine S Jochelson1, Danny F Martinez1, Elizabeth A Morris1, and Katja Pinker1,5

1Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, United States, 2University Hospital Frankfurt, Frankfurt am Main, Germany, 3Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States, 4Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY, United States, 5Medical University of Vienna, Vienna, Austria

To evaluate the diagnostic performance of DWI radiomic signatures for the assessment of breast cancer receptor status and molecular subtypes. Ninety-one patients with breast cancer were included. Lesions were manually segmented on high b-value DWI and propagated to ADC maps. To compare different segmentation approaches a subgroup was directly segmented on the ADC map. Results demonstrate that DWI radiomic signatures enable the assessment of breast cancer receptor status and molecular subtypes with high accuracy. Higher accuracies are achieved when segmentations are performed directly on ADC maps that cancel out T2 shine-through indicating as the preferred approach for radiomic analysis.

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

Join Here