Fully automated tumor localization and segmentation in breast DCEMRI using deep learning and kinetic prior

摘要

Breast magnetic resonance imaging (MRI) plays an important role in high-risk breast cancer screening, clinical problemsolving,and imaging-based outcome prediction. Breast tumor segmentation in MRI is an essential step for quantitativeradiomics analysis, where automated and accurate tumor segmentation is needed but very challenging. Automated breasttumor segmentation methods have been proposed and can achieve promising results. However, these methods still needa pre-defined a region of interest (ROI) before performing segmentation, which makes them hard to run fullyautomatically. In this paper, we investigated automated localization and segmentation method for breast tumor in breastDynamic Contrast-Enhanced MRI (DCE-MRI) scans. The proposed method takes advantage of kinetic prior and deeplearning for automatic tumor localization and segmentation. We implemented our method and evaluated its performanceon a dataset consisting of 74 breast MR images. We quantitatively evaluated the proposed method by comparing thesegmentation with the manual annotation from an expert radiologist. Experimental results showed that the automatedbreast tumor segmentation method exhibits promising performance with an average Dice Coefficient of 0.89±0.06.