Nathaniel Braman1, Prateek Prasanna1, Donna Plecha2, Hannah Gilmore2, Lyndsay Harris2, Kristy Miskimen1, Tao Wan3, Vinay Varadan1, and Anant Madabhushi1
1Case Western Reserve University, Cleveland, OH, United States, 2University Hospitals, Cleveland, OH, United States, 3Beihang University, Beijing, China, People's Republic of
In this work, we
report preliminary success in the prediction of TP53 mutational status in breast cancer from
DCE-MRI using a computer-extracted radiogenomic descriptor of multi-scale disorder, Co-occurrence of Local
Anisotropic Gradient Orientations (CoLlAGe). A set of 8 distinguishing CoLlAGe features yielded accuracy of 78% in predicting TP53 mutational status and outperformed standard DCE-MRI pharmacokinetic parameters in an unsupervised hierarchical clustering. A non-invasive means of discerning TP53 mutational
status may allow clinicians to more easily determine prognosis, assess treatment
response, and inform treatment strategy.