Radiomic Analysis of Pharmacokinetic Heterogeneity Within Tumor Based on the Unsupervised Decomposition of Dynamic Contrast-Enhanced MRI for Predicting Histological Characteristics of Breast Cancer.

Breast tumor heterogeneity is associated with histological characteristics. However, pharmacokinetic (PK) heterogeneity within tumor might merit further exploration. To enhance the predictive power of molecular subtypes, Ki-67, and tumor grade by analyzing PK heterogeneity within tumor based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Retrospective. Two hundred and eight biopsy-proven breast cancer patients, randomly divided into a training cohort (N = 144) and a testing cohort (N = 64). T1 -weighted DCE-MRI at 3.0 T. A convex analysis of mixtures-compartmental modeling decomposition method was used to estimate the PK parameter (i.e., the volume transfer constant Ktrans ) in tumor subregions with distinct physiological kinetic patterns, including fast-flow kinetics, slow-flow kinetics, and plasma input. Radiomic features based on the PK parameter were calculated from each tumor subregion. The training cohort was used to build random forest classifiers based on the optimal features determined by the 5-fold cross-validation method. The performance was assessed on the testing cohort using the area under the receiver operating characteristic curve (AUC). The AUCs derived from the tumor subregion-based PK parameter were compared with those of the original images of the entire tumor using the DeLong test. A P-value of <0.05 was considered statistically significant. The tumor subregion-based PK parameter, which yielded the highest AUCs of 0.8782, 0.7568, 0.7019, 0.7963, 0.8080, and 0.7375 for luminal A, luminal B, basal-like, human epidermal growth factor receptor 2, Ki-67, and tumor grade, respectively, obtained better diagnostic performance than the original images in the entire tumor (highest AUCs = 0.8612, 0.6191, 0.5593, 0.7704, 0.7494, and 0.6261, respectively). In particular, statistically significant improvement in the diagnostic performance was obtained for luminal B. Radiomic analysis of PK heterogeneity within tumor can enhance the predictive performance of radiomic models compared with that of the entire tumor. 4 TECHNICAL EFFICACY STAGE: 3.

Zhang L ，Fan M ，Wang S ，Xu M ，Li L ... -  《-》

DCE-MRI texture analysis with tumor subregion partitioning for predicting Ki-67 status of estrogen receptor-positive breast cancers.

Breast tumor heterogeneity is related to risk factors that lead to worse prognosis, yet such heterogeneity has not been well studied. To predict the Ki-67 status of estrogen receptor (ER)-positive breast cancer patients via analysis of tumor heterogeneity with subgroup identification based on patterns of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Retrospective study. Seventy-seven breast cancer patients with ER-positive breast cancer were investigated, of whom 51 had low Ki-67 expression. T1 -weighted 3.0T DCE-MR images. Each tumor was partitioned into multiple subregions using three methods based on patterns of dynamic enhancement: 1) time to peak (TTP), 2) peak enhancement rate (PER), and 3) kinetic pattern clustering (KPC). In each tumor subregion, 18 texture features were computed. Univariate and multivariate logistic regression analyses were performed using a leave-one-out-based cross-validation (LOOCV) method. The partitioning results were compared with the same feature extraction methods across the whole tumor. In the univariate analysis, the best-performing feature was the texture statistic of sum variance in the tumor subregion with early TTP for differentiating between patients with high and low Ki-67 expression (area under the receiver operating characteristic curves, AUC = 0.748). Multivariate analysis showed that features from the tumor subregion associated with early TTP yielded the highest performance (AUC = 0.807) among the subregions for predicting the Ki-67 status. Among all regions, the tumor area with high PER at a precontrast MR image achieved the highest performance (AUC = 0.722), while the subregion that exhibited the highest overall enhancement rate based on KPC had an AUC of 0.731. These three models based on intratumoral texture analysis significantly (P < 0.01) outperformed the model using features from the whole tumor (AUC = 0.59). Texture analysis of intratumoral heterogeneity has the potential to serve as a valuable clinical marker to enhance the prediction of breast cancer prognosis. 4 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2017.

Fan M ，Cheng H ，Zhang P ，Gao X ，Zhang J ，Shao G ，Li L ... -  《-》

Radiomic analysis of imaging heterogeneity in tumours and the surrounding parenchyma based on unsupervised decomposition of DCE-MRI for predicting molecular subtypes of breast cancer.

Fan M ，Zhang P ，Wang Y ，Peng W ，Wang S ，Gao X ，Xu M ，Li L ... -  《-》

Efficient estimation of pharmacokinetic parameters from breast dynamic contrast-enhanced MRI based on a convolutional neural network for predicting molecular subtypes.

Objective. Tracer kinetic models allow for estimating pharmacokinetic (PK) parameters, which are related to pathological characteristics, from breast dynamic contrast-enhanced magnetic resonance imaging. However, existing tracer kinetic models subject to inaccuracy are time-consuming for PK parameters estimation. This study aimed to accurately and efficiently estimate PK parameters for predicting molecular subtypes based on convolutional neural network (CNN).Approach. A CNN integrating global and local features (GL-CNN) was trained using synthetic data where known PK parameters map was used as the ground truth, and subsequently used to directly estimate PK parameters (volume transfer constantKtransand flux rate constantKep) map. The accuracy assessed by the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and concordance correlation coefficient (CCC) was compared between the GL-CNN and Tofts-based PK parameters in synthetic data. Radiomic features were calculated from the PK parameters map in 208 breast tumors. A random forest classifier was constructed to predict molecular subtypes using a discovery cohort (n= 144). The diagnostic performance evaluated on a validation cohort (n= 64) using the area under the receiver operating characteristic curve (AUC) was compared between the GL-CNN and Tofts-based PK parameters.Main results. The average PSNR (48.8884), SSIM (0.9995), and CCC (0.9995) between the GL-CNN-basedKtransmap and ground truth were significantly higher than those between the Tofts-basedKtransmap and ground truth. The GL-CNN-basedKtransobtained significantly better diagnostic performance (AUCs = 0.7658 and 0.8528) than the Tofts-basedKtransfor luminal B and HER2 tumors. The GL-CNN method accelerated the computation by speed approximately 79 times compared to the Tofts method for the whole breast of all patients.Significance. Our results indicate that the GL-CNN method can be used to accurately and efficiently estimate PK parameters for predicting molecular subtypes.

Zhang L ，Fan M ，Li L 《-》

Comparison of Dynamic Contrast-Enhanced MRI and Non-Mono-Exponential Model-Based Diffusion-Weighted Imaging for the Prediction of Prognostic Biomarkers and Molecular Subtypes of Breast Cancer Based on Radiomics.

Dynamic contrast-enhanced (DCE) MRI and non-mono-exponential model-based diffusion-weighted imaging (NME-DWI) that does not require contrast agent can both characterize breast cancer. However, which technique is superior remains unclear. To compare the performances of DCE-MRI, NME-DWI and their combination as multiparametric MRI (MP-MRI) in the prediction of breast cancer prognostic biomarkers and molecular subtypes based on radiomics. Prospective. A total of 477 female patients with 483 breast cancers (5-fold cross-validation: training/validation, 80%/20%). A 3.0 T/DCE-MRI (6 dynamic frames) and NME-DWI (13 b values). After data preprocessing, high-throughput features were extracted from each tumor volume of interest, and optimal features were selected using recursive feature elimination method. To identify ER+ vs. ER-, PR+ vs. PR-, HER2+ vs. HER2-, Ki-67+ vs. Ki-67-, luminal A/B vs. nonluminal A/B, and triple negative (TN) vs. non-TN, the following models were implemented: random forest, adaptive boosting, support vector machine, linear discriminant analysis, and logistic regression. Student's t, chi-square, and Fisher's exact tests were applied on clinical characteristics to confirm whether significant differences exist between different statuses (±) of prognostic biomarkers or molecular subtypes. The model performances were compared between the DCE-MRI, NME-DWI, and MP-MRI datasets using the area under the receiver-operating characteristic curve (AUC) and the DeLong test. P < 0.05 was considered significant. With few exceptions, no significant differences (P = 0.062-0.984) were observed in the AUCs of models for six classification tasks between the DCE-MRI (AUC = 0.62-0.87) and NME-DWI (AUC = 0.62-0.91) datasets, while the model performances on the two imaging datasets were significantly poorer than on the MP-MRI dataset (AUC = 0.68-0.93). Additionally, the random forest and adaptive boosting models (AUC = 0.62-0.93) outperformed other three models (AUC = 0.62-0.90). NME-DWI was comparable with DCE-MRI in predictive performance and could be used as an alternative technique. Besides, MP-MRI demonstrated significantly higher AUCs than either DCE-MRI or NME-DWI. 2. Stage 2.

Zhang L ，Zhou XX ，Liu L ，Liu AY ，Zhao WJ ，Zhang HX ，Zhu YM ，Kuai ZX ... -  《-》