Deep Super-resolution Network on Diffusion Weighted Imaging for Improving Prediction of Histological Grade in Breast Cancer

摘要

In many medical image applications, high-resolution images are needed to facilitate early diagnosis. However, due totechnical limitations, it may not be easy to obtain an image with ideal resolution especially for the diffusion weightedimaging (DWI). Super-resolution (SR) technology is developed to solve this problem by generating high-resolution (HR)images from low-resolution (LR) images. The purpose of this study is to obtain the SR-DWI from the original LR imagethrough deep super-resolution network. The effectiveness of the SR image is assessed by radiomic analysis in predictingthe histological grade of breast cancer. To this end, a dataset of 144 breast cancer cases were collected, including 83 caseswho diagnosed as high-grade malignant (Grade 3) breast cancer, and 61 who were median-grade malignant (Grade 2). Foreach case, the dynamic enhanced magnetic resonance imaging (DCE-MRI), and the apparent diffusion coefficients (ADC)map derived from DWI were obtained. Lesion segmentation was performed on each of the original ADC and the SR-ADC,in which 30 texture and 10 statistical features were extracted. Deep SR model was established by an end-to-end trainingfrom the LR DCE-MRI and the HR counterparts and was applied to the ADC images to obtain SR-ADCs. Univariate andmultivariate logistic regression classifier was implemented to evaluate the performance of the individual feature andcollective features, respectively. The model performance was evaluated by the area under the curve (AUC) under leaveone-out cross-validation (LOOCV). For the individual feature analysis, the performance in terms of AUC was significantlybetter based on the SR-ADC image than that based on the original ADC image. For multivariate analysis, the classifierperformance in terms of AUCs were 0.848±0.061 and 0.878±0.051 for the original ADC and the SR ADC, respectively.The results suggested that the enhanced resolution of ADC image had the potential to more accurately predict histologicalgrade in breast cancer.