Abstract #2315

Diffusion-Weighted MRI-Based Quantitative Markers for Characterizing Breast Cancer Lesions Using Machine Learning

Rahul Mehta^1,2, Muge Karaman^1,2, Yangyang Bu^3,4, Zheng Zhong^1,2, Guangyu Dan^1,2, Shiwei Wang^3,4, Changyu Zhou^3,4, Weihong Hu^3,4, X. Joe Zhou^1,2,5, and Maosheng Xu^3,4

¹Center for Magnetic Resonance Research, University of Illinois at Chicago, Chicago, IL, United States, ²Department of Bioengineering, University of Illinois at Chicago, Chicago, IL, United States, ³The First Clinical Medical College, Zhejiang Chinese Medical University, Hangzhou, China, ⁴The First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China, ⁵Departments of Radiology and Neurosurgery, University of Illinois at Chicago, Chicago, IL, United States

We investigate the quantitative markers obtained from the parameters of two diffusion-weighted imaging (DWI) models, continuous-time random-walk (CTRW) and intravoxel incoherent motion (IVIM) models, for differentiating malignant and benign breast lesions. The quantitative markers are extracted from the histograms of each parameter, and then the statistical importance of each marker is determined using a feature importance algorithm. Our results show the Gradient Boosted Classifier (GBC) achieves optimal performance using the top quantitative markers. The statistical histogram features from the parameters of CTRW and IVIM models can be used in a GBC to provide a new avenue in breast cancer diagnosis.

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

Join Here