Combination of DCE-MRI and NME-DWI via Deep Neural Network for Predicting Breast Cancer Molecular Subtypes.

BACKGROUND: To explore whether the combination of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) and nonmono-exponential (NME) model-based diffusion-weighted imaging (DWI) via deep neural network (DNN) can improve the prediction of breast cancer molecular subtypes compared to either imaging technique used alone. PATIENTS AND METHODS: This prospective study examined 480 breast cancers in 475 patients undergoing DCE-MRI and NME-DWI at 3.0 T. Breast cancers were classified as follows: human epidermal growth factor receptor 2 enriched (HER2-enriched), luminal A, luminal B (HER2-), luminal B (HER2+), and triple-negative subtypes. A total of 20% cases were withheld as an independent test dataset, and the remaining cases were used to train DNN with an 80% to 20% training-validation split and 5-fold cross-validation. The diagnostic accuracies of DNN in 5-way subtype classification between the DCE-MRI, NME-DWI, and their combined multiparametric-MRI datasets were compared using analysis of variance with least significant difference posthoc test. Areas under the receiver-operating characteristic curves were calculated to assess the performances of DNN in binary subtype classification between the 3 datasets. RESULTS: The 5-way classification accuracies of DNN on both DCE-MRI (0.71) and NME-DWI (0.64) were significantly lower (P < .05) than on multiparametric-MRI (0.76), while on DCE-MRI was significantly higher (P < .05) than on NME-DWI. The comparative results of binary classification between the 3 datasets were consistent with the 5-way classification. CONCLUSION: The combination of DCE-MRI and NME-DWI via DNN achieved a significant improvement in breast cancer molecular subtype prediction compared to either imaging technique used alone. Additionally, DCE-MRI outperformed NME-DWI in differentiating subtypes.

A Channel-Dimensional Feature-Reconstructed Deep Learning Model for Predicting Breast Cancer Molecular Subtypes on Overall b-Value Diffusion-Weighted MRI.

BACKGROUND: Dynamic contrast-enhanced (DCE) MRI commonly outperforms diffusion-weighted (DW) MRI in breast cancer discrimination. However, the side effects of contrast agents limit the use of DCE-MRI, particularly in patients with chronic kidney disease. PURPOSE: To develop a novel deep learning model to fully exploit the potential of overall b-value DW-MRI without the need for a contrast agent in predicting breast cancer molecular subtypes and to evaluate its performance in comparison with DCE-MRI. STUDY TYPE: Prospective. SUBJECTS: 486 female breast cancer patients (training/validation/test: 64%/16%/20%). FIELD STRENGTH/SEQUENCE: 3.0 T/DW-MRI (13 b-values) and DCE-MRI (one precontrast and five postcontrast phases). ASSESSMENT: The breast cancers were divided into four subtypes: luminal A, luminal B, HER2+, and triple negative. A channel-dimensional feature-reconstructed (CDFR) deep neural network (DNN) was proposed to predict these subtypes using pathological diagnosis as the reference standard. Additionally, a non-CDFR DNN (NCDFR-DNN) was built for comparative purposes. A mixture ensemble DNN (ME-DNN) integrating two CDFR-DNNs was constructed to identify subtypes on multiparametric MRI (MP-MRI) combing DW-MRI and DCE-MRI. STATISTICAL TESTS: Model performance was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Model comparisons were performed using the one-way analysis of variance with least significant difference post hoc test and the DeLong test. P < 0.05 was considered significant. RESULTS: The CDFR-DNN (accuracies, 0.79 ~ 0.80; AUCs, 0.93 ~ 0.94) demonstrated significantly improved predictive performance than the NCDFR-DNN (accuracies, 0.76 ~ 0.78; AUCs, 0.92 ~ 0.93) on DW-MRI. Utilizing the CDFR-DNN, DW-MRI attained the predictive performance equal (P = 0.065 ~ 1.000) to DCE-MRI (accuracies, 0.79 ~ 0.80; AUCs, 0.93 ~ 0.95). The predictive performance of the ME-DNN on MP-MRI (accuracies, 0.85 ~ 0.87; AUCs, 0.96 ~ 0.97) was superior to those of both the CDFR-DNN and NCDFR-DNN on either DW-MRI or DCE-MRI. DATA CONCLUSION: The CDFR-DNN enabled overall b-value DW-MRI to achieve the predictive performance comparable to DCE-MRI. MP-MRI outperformed DW-MRI and DCE-MRI in subtype prediction. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 1.

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.

BACKGROUND: 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. PURPOSE: 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. STUDY TYPE: Prospective. POPULATION: A total of 477 female patients with 483 breast cancers (5-fold cross-validation: training/validation, 80%/20%). FIELD STRENGTH/SEQUENCE: A 3.0 T/DCE-MRI (6 dynamic frames) and NME-DWI (13 b values). ASSESSMENT: 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. STATISTICAL TESTS: 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. RESULTS: 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). DATA CONCLUSION: 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. EVIDENCE LEVEL: 2. TECHNICAL EFFICACY: Stage 2.

An Unsupervised Deep Learning Approach for Dynamic-Exponential Intravoxel Incoherent Motion MRI Modeling and Parameter Estimation in the Liver.

BACKGROUND: Dynamic-exponential intravoxel incoherent motion (IVIM) imaging is a potential technique for prediction, monitoring, and differential diagnosis of hepatic diseases, especially liver tumors. However, the use of such technique at voxel level is still limited. PURPOSE: To develop an unsupervised deep learning approach for voxel-wise dynamic-exponential IVIM modeling and parameter estimation in the liver. STUDY TYPE: Prospective. POPULATION: Ten healthy subjects (4 males; age 28 ± 6 years). FIELD STRENGTH/SEQUENCE: Single-shot spin-echo echo planar imaging (SE-EPI) sequence with monopolar diffusion-encoding gradients (12 b-values, 0-800 seconds/mm2 ) at 3.0 T. ASSESSMENT: The proposed deep neural network (DNN) was separately trained on simulated and in vivo hepatic IVIM datasets. The trained networks were compared to the approach combining least squares with Akaike information criterion (LSQ-AIC) in terms of dynamic-exponential modeling accuracy, inter-subject coefficients of variation (CVs), and fitting residuals on the simulated subsets and regions of interest (ROIs) in the left and right liver lobes. The ROIs were delineated by a radiologist (H.-X.Z.) with 7 years of experience in MRI reading. STATISTICAL TESTS: Comparisons between approaches were performed with a paired t-test (normality) or a Wilcoxon rank-sum test (nonnormality). P < 0.05 was considered statistically significant. RESULTS: In simulations, DNN gave significantly higher accuracy (91.6%-95.5%) for identification of bi-exponential decays with respect to LSQ-AIC (79.7%-86.8%). For tri-exponential identification, DNN was also superior to LSQ-AIC despite not reaching a significant level (P = 0.08). Additionally, DNN always yielded comparatively low root-mean-square error for estimated parameters. For the in vivo IVIM measurements, inter-subject CVs (0.011-0.150) of DNN were significantly smaller than those (0.049-0.573) of LSQ-AIC. Concerning fitting residuals, there was no significant difference between the two approaches (P = 0.56 and 0.76) in both the simulated and in vivo studies. DATA CONCLUSION: The proposed DNN is recommended for accurate and robust dynamic-exponential modeling and parameter estimation in hepatic IVIM imaging. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 1.

Short-Term Repeatability of in Vivo Cardiac Intravoxel Incoherent Motion Tensor Imaging in Healthy Human Volunteers.

BACKGROUND: Intravoxel incoherent motion (IVIM) tensor imaging is a promising technique for diagnosis and monitoring of cardiovascular diseases. Knowledge about measurement repeatability, however, remains limited. PURPOSE: To evaluate short-term repeatability of IVIM tensor imaging in normal in vivo human hearts. STUDY TYPE: Prospective. POPULATION: Ten healthy subjects without history of heart diseases. FIELD STRENGTH/SEQUENCE: Balanced steady-state free-precession cine sequence and single-shot spin-echo echo planar IVIM tensor imaging sequence (9 b-values, 0-400 seconds/mm2 and six diffusion-encoding directions) at 3.0 T. ASSESSMENT: Subjects were scanned twice with an interval of 15 minutes, leaving the scanner between studies. The signal-to-noise ratio (SNR) was evaluated in anterior, lateral, septal, and inferior segments of the left ventricle wall. Fractional anisotropy (FA), mean diffusivity (MD), mean fraction (MF), and helix angle (HA) in the four segments were independently measured by five radiologists. STATISTICAL TESTS: IVIM tensor indexes were compared between observers using a one-way analysis of variance or between scans using a paired t-test (normal data) or a Wilcoxon rank-sum test (non-normal data). Interobserver agreement and test-retest repeatability were assessed using the intraclass correlation coefficient (ICC), within-subject coefficient of variation (WCV), and Bland-Altman limits of agreements. RESULTS: SNR of inferior segment was significantly lower than the other three segments, and inferior segment was therefore excluded from repeatability analysis. Interobserver repeatability was excellent for all IVIM tensor indexes (ICC: 0.886-0.972; WCV: 0.62%-4.22%). Test-retest repeatability was excellent for MD of the self-diffusion tensor (D) and MF of the perfusion fraction tensor (fp ) (ICC: 0.803-0.888; WCV: 1.42%-9.51%) and moderate for FA and MD of the pseudo-diffusion tensor (D* ) (ICC: 0.487-0.532; WCV: 6.98%-10.89%). FA of D and fp and HA of D presented good test-retest repeatability (ICC: 0.732-0.788; WCV: 3.28%-8.71%). DATA CONCLUSION: The D and fp indexes exhibited satisfactory repeatability, but further efforts were needed to improve repeatability of D* indexes. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 1.

Investigation of intravoxel incoherent motion tensor imaging for the characterization of the in vivo human heart.

PURPOSE: To investigate intravoxel incoherent motion (IVIM) tensor imaging of the in vivo human heart and elucidate whether the estimation of IVIM tensors is affected by the complexity of pseudo-diffusion components in myocardium. METHODS: The cardiac IVIM data of 10 healthy subjects were acquired using a diffusion weighted spin-echo echo-planar imaging sequence along 6 gradient directions with 10 b values (0~400 s/mm2 ). The IVIM data of left ventricle myocardium were fitted to the IVIM tensor model. The complexity of myocardial pseudo-diffusion components was reduced through exclusion of low b values (0 and 5 s/mm2 ) from the IVIM curve-fitting analysis. The fractional anisotropy, mean fraction/mean diffusivity, and Westin measurements of pseudo-diffusion tensors (fp and D*) and self-diffusion tensor (D), as well as the angle between the main eigenvector of fp (or D*) and that of D, were computed and compared before and after excluding low b values. RESULTS: The fractional anisotropy values of fp and D* without low b value participation were significantly higher (P < .001) than those with low b value participation, but an opposite trend was found for the mean fraction/diffusivity values. Besides, after removing low b values, the angle between the main eigenvector of fp (or D*) and that of D became small, and both fp and D* tensors presented significant decrease of spherical components and significant increase of linear components. CONCLUSION: The presence of multiple pseudo-diffusion components in myocardium indeed influences the estimation of IVIM tensors. The IVIM tensor model needs to be further improved to account for the complexity of myocardial microcirculatory network and blood flow.

Non-mono-exponential diffusion models for assessing early response of liver metastases to chemotherapy in colorectal Cancer.

BACKGROUND: Preoperative chemotherapy is becoming standard therapy for liver metastasis from colorectal cancer, so early assessment of treatment response is crucial to make a reasonable therapeutic regimen and avoid overtreatment, especially for patients with severe side effects. The role of three non-mono-exponential diffusion models, such as the kurtosis model, the stretched exponential model and the statistical model, were explored in this study to early assess the response to chemotherapy in patients with liver metastasis from colorectal cancer. METHODS: Thirty-three patients diagnosed as colorectal liver metastasis were evaluated in this study. Diffusion-weighted images with b values (0, 200, 500, 1000, 1500, 2000 s/mm2) were acquired at 3.0 T. The parameters (ADCk, K, DDC,α, Ds and σ) were derived from three non-mono-exponential models (the kurtosis, stretched exponential and statistical models) as well as their corresponding percentage changes before and after chemotherapy. The difference in above parameters between the response and non-response groups were analyzed with independent-samples T-test (normality) and Mann-Whitney U-test (non-normality). Meanwhile, receiver operating characteristic curve (ROC) analyses were performed to assess the response to chemotherapy. RESULTS: Significantly lower values of K (the kurtosis coefficient derived from the kurtosis model) and σ (the width of diffusion coefficient distribution in the statistical model) (P < 0.05) were observed in the respond group before treatment, as well as higher ΔK and Δσ values (P < 0.05) after the first cycle of chemotherapy were also found compared with the non-respond group. ROC analyses showed the K value acquired before treatment had the highest diagnostic performance (0.746) in distinguishing responders from non-responders. Furthermore, the high sensitivity (100%) and accuracy (76.3%) from the K value before treatment was found in assessing the response of colorectal liver metastasis to chemotherapy. CONCLUSIONS: The non-mono-exponential diffusion models may be able to predict early response to chemotherapy in patients with colorectal liver metastasis.

Structure Prior Constrained Estimation of Human Cardiac Diffusion Tensors.

OBJECTIVE: The purpose of this paper is to increase the accuracy of human cardiac diffusion tensor (DT) estimation in diffusion magnetic resonance imaging (dMRI) with a few diffusion gradient directions. METHODS: A structure prior constrained (SPC) method is proposed. The method consists in introducing two regularizers in the conventional nonlinear least squares estimator. The two regularizers penalize the dissimilarity between neighboring DTs and the difference between estimated and prior fiber orientations, respectively. A novel numerical solution is presented to ensure the positive definite estimation. RESULTS: Experiments on ex vivo human cardiac data show that the SPC method is able to well estimate DTs at most voxels, and is superior to state-of-the-art methods in terms of the mean errors of principal eigenvector, second eigenvector, helix angle, transverse angle, fractional anisotropy, and mean diffusivity. CONCLUSION: The SPC method is a practical and reliable alternative to current denoising- or regularization-based methods for the estimation of human cardiac DT. SIGNIFICANCE: The SPC method is able to accurately estimate human cardiac DTs in dMRI with a few diffusion gradient directions.

Evaluation of non-monoexponential diffusion models for hepatocellular carcinoma using b values up to 2000 s/mm2 : A short-term repeatability study.

BACKGROUND: Non-monoexponential diffusion models are being used increasingly for the characterization and curative effect evaluation of hepatocellular carcinoma (HCC). But the fitting quality of the models and the repeatability of their parameters have not been assessed for HCC. PURPOSE: To evaluate kurtosis, stretched exponential, and statistical models for diffusion-weighted imaging (DWI) of HCC, using b-values up to 2000 s/mm2 , in terms of fitting quality and repeatability. STUDY TYPE: Prospective. POPULATION: Eighteen patients with HCC. FIELD STRENGTH/SEQUENCE: Conventional and DW images (b = 0, 200, 500, 1000, 1500, 2000 s/mm2 ) were acquired at 3.0T. ASSESSMENT: The parameters of the kurtosis, stretched exponential, and statistical models were calculated on regions of interest (ROIs) of each lesion. STATISTICAL TESTS: The fitting quality was evaluated through comparing the fitting residuals produced on the average data of ROI between different models using a paired t-test or Wilcoxon rank-sum test. Repeatability of the fitted parameters at the median values on the voxelwise data of ROI was assessed using the within coefficient of variation (WCV), the intraclass correlation coefficient (ICC), and the 95% Bland-Altman limits of agreements (BA-LA). The repeatability was divided into four levels: excellent, good, acceptable, and poor, referring to the values of ICC and WCV. RESULTS: Among three models, the stretched exponential model provided the best fit to HCC (P < 0.05), whereas the statistical model produced the largest fitting residuals (P < 0.05). The repeatability of K from the kurtosis model was excellent (ICC 0.915; WCV 8.79%), while the distributed diffusion coefficient (DDC) from the stretched model was just acceptable (ICC 0.477; WCV 27.83%). The repeatability was good for other diffusion-related parameters. DATA CONCLUSION: Considering the model fit and repeatability, the kurtosis and stretched exponential models are the preferred models for the description of the DW signals of HCC with respect to the statistical model. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:297-304.

Determination of Hepatocellular Carcinoma and Characterization of Hepatic Focal Lesions with Adaptive Multi-Exponential Intravoxel Incoherent Motion Model.

PURPOSE: To distinguish hepatocellular carcinoma (HCC) from other types of hepatic lesions with the adaptive multi-exponential IVIM model. METHODS: 94 hepatic focal lesions, including 38 HCC, 16 metastasis, 12 focal nodular hyperplasia, 13 cholangiocarcinoma, and 15 hemangioma, were examined in this study. Diffusion-weighted images were acquired with 13 b values (b = 0, 3, …, 500 s/mm2) to measure the adaptive multi-exponential IVIM parameters, namely, pure diffusion coefficient (D), diffusion fraction (fd), pseudo-diffusion coefficient (Di*) and perfusion-related diffusion fraction (fi) of the ith perfusion component. Comparison of the parameters of and their diagnostic performance was determined using Mann-Whitney U test, independent-sample t test, one-way analysis of variance, Z test and receiver-operating characteristic analysis. RESULTS: D, D1* and D2* presented significantly difference between HCCs and other hepatic lesions, whereas fd, f1 and f2 did not show statistical differences. In the differential diagnosis of HCCs from other hepatic lesions, D2* (AUC, 0.927) provided best diagnostic performance among all parameters. Additionally, the number of exponential terms in the model was also an important indicator for distinguishing HCCs from other hepatic lesions. In the benign and malignant analysis, D gave the greatest AUC values, 0.895 or 0.853, for differentiation between malignant and benign lesions with three or two exponential terms. Most parameters were not significantly different between hypovascular and hypervascular lesions. For multiple comparisons, significant differences of D, D1* or D2* were found between certain lesion types. CONCLUSION: The adaptive multi-exponential IVIM model was useful and reliable to distinguish HCC from other hepatic lesions.

Effect of multiple perfusion components on pseudo-diffusion coefficient in intravoxel incoherent motion imaging.

The aim of this work was to investigate the effect of multiple perfusion components on the pseudo-diffusion coefficient D * in the bi-exponential intravoxel incoherent motion (IVIM) model. Simulations were first performed to examine how the presence of multiple perfusion components influences D *. The real data of livers (n = 31), spleens (n = 31) and kidneys (n = 31) of 31 volunteers was then acquired using DWI for in vivo study and the number of perfusion components in these tissues was determined together with their perfusion fraction and D *, using an adaptive multi-exponential IVIM model. Finally, the bi-exponential model was applied to the real data and the mean, standard variance and coefficient of variation of D * as well as the fitting residual were calculated over the 31 volunteers for each of the three tissues and compared between them. The results of both the simulations and the in vivo study showed that, for the bi-exponential IVIM model, both the variance of D * and the fitting residual tended to increase when the number of perfusion components was increased or when the difference between perfusion components became large. In addition, it was found that the kidney presented the fewest perfusion components among the three tissues. The present study demonstrated that multi-component perfusion is a main factor that causes high variance of D * and the bi-exponential model should be used only when the tissues under investigation have few perfusion components, for example the kidney.

Generalization of intravoxel incoherent motion model by introducing the notion of continuous pseudodiffusion variable.

PURPOSE: A generalized intravoxel incoherent motion (IVIM) model, called the GIVIM, was proposed to better account for complex perfusion present in the tissues having various vessels and flow regimes, such as the liver. THEORY AND METHODS: The notions of continuous pseudodiffusion variable as well as perfusion fraction density function were introduced to describe the presence of multiple perfusion components in a voxel. The mean and standard deviation of Gaussian perfusion fraction density function were then used to define two new parameters, the mean pseudodiffusivity ( D¯) and pseudodiffusion dispersion (σ). The GIVIM model was evaluated by testing whether or not it can reflect hepatic perfusion difference caused by flow-compensated imaging sequences having different diffusion times. Also, D¯ was compared with D* in the standard IVIM model. RESULTS: The values of both D* and D¯ decreased after flow compensation and further decreased when shortening diffusion time. D¯ exhibited reduced variance in comparison with D*. In addition, σ also showed its sensitivity to hepatic perfusion difference caused by the flow-compensated imaging sequences. CONCLUSION: The GIVIM model has the ability to better describe multicomponent perfusion without lengthening acquisition time and knowing in advance the number and/or the variety of perfusion components. Magn Reson Med 76:1594-1603, 2016. © 2015 International Society for Magnetic Resonance in Medicine.