Meeting Banner
Abstract #2315

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

Rahul Mehta1,2, Muge Karaman1,2, Yangyang Bu3,4, Zheng Zhong1,2, Guangyu Dan1,2, Shiwei Wang3,4, Changyu Zhou3,4, Weihong Hu3,4, X. Joe Zhou1,2,5, and Maosheng Xu3,4
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 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here