Dynamic Contrast-enhanced Magnetic Resonance Imaging Data Research Articles

Kinetic Heterogeneity Improves the Specificity of Dynamic Enhanced MRI in Differentiating Benign and Malignant Breast Tumours

To investigate whether kinetic heterogeneity in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) improves the specificity of breast cancer (BC) diagnosis. The DCE-MRI data of patients with benign breast tumours and BC from June 2020 to July 2022 were retrospectively evaluated. MATLAB and SPM were used to determine six major kinetic parameters: peak, enhancement volume, heterogeneity, as well as persistent, plateau, and washout proportions. Continuous variables were compared using the Student's t-test or Mann-Whitney U tests, and categorical variables were compared using the chi-square or Fisher's exact tests. Receiver operating characteristic curves were plotted. The intraclass correlation coefficient (ICC) was used to evaluate agreement between the two observers. Multivariate logistic regression analysis was conducted to calculate the odds ratios (ORs) with 95% confidence intervals (CIs) for the association between benign and malignant breast tumours. In total, 147 patients (mean age, 47 years old) were included in the study, 76 of whom had BC. Data analysis by the two observers showed good consistency in the peak, enhancement volume, persistent proportion, plateau proportion, washout proportion, and heterogeneity, with ICCs of 0.865, 0.988, 0.906, 0.940, 0.740, and 0.867, respectively (p<0.001). In the DCE kinetic analysis, differences in all the six kinetic parameters were statistically significant (p<0.05). The area under the curve for heterogeneity was 0.92 (95% CI:0.88,0.97), and the sensitivity and specificity were 0.895 and 0.845, respectively. Multivariate logistic regression analysis showed that heterogeneity was an independent predictor of BC comparedtobenign breast tumours (OR=2.020; 95% CI:1.316, 3.100; p=0.001). The kinetic heterogeneity of DCE-MRI can effectively distinguish between benign and malignant breast tumours and improve the specificity of BC diagnosis.

Alteration in Microcirculation With Osteonecrosis of the Femoral Head: A Study of Dynamic Contrast-Enhanced MRI.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is commonly used in clinical practice to detect tumor blood supply, and it has recently been applied to assess skeletal vasculature. In this study, we retrospectively analyzed DCE-MRI data from 37 patients with osteonecrosis of the femoral head to evaluate alterations in microvascular circulation of the femoral head. Time-intensity curves (TICs) in the region of interest were classified into different lesion stages. In the greater trochanter area, extracellular space volume per unit volume of tissue was significantly higher in Association Research Circulation Osseous (ARCO) stage III than in ARCO stage II (P<.05 and power ≥ 0.8), while other parameters showed no statistical difference (P>.05 and/or power < 0.8). In the necrotic area, contrast enhancement ratio and maximum slope of increase were significantly lower in ARCO stage III than in ARCO stage II (P<.05 and power ≥ 0.8), while other parameters showed no statistical difference (P>.05 and/or power < 0.8). In the repair reaction area, all parameters were significantly higher in ARCO stage III than in ARCO stage II (P<.05 and power ≥ 0.8). TIC classification showed that the greater trochanter area mainly exhibited type C (plateau type), the necrotic area mainly exhibited type B (out-flow type), and the repair reaction area mainly exhibited type A (inflow type). We believe that the exchange capacity of the vessels has a much greater impact on femoral head necrosis than the number of vessels, while the generation of the repair area greatly affects the prognosis of femoral head necrosis. These findings suggest that DCE-MRI can provide a good assessment of osteonecrosis of the femoral head perfusion and can serve as a new reference for clinical treatment decisions. [Orthopedics. 2024;47(2):e73-e78.].

Multiparametric MRI for Staging of Bowel Inflammatory Activity in Crohn's Disease with MUSE-IVIM and DCE-MRI: A Preliminary Study

To investigate if the combination of multishot diffusion imaging-based multiplexed sensitivity encoding intravoxel incoherent motion (MUSE-IVIM) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is feasible for staging Crohn's disease (CD) activity. A total of 65 CD patients were enrolled and analyzed in this retrospective study. The simplified endoscopic score for Crohn's disease (SES-CD) and magnetic resonance index of activity (MaRIA) were used as the reference. The MUSE-IVIM and DCE-MRI data were acquired at 3.0-T MRI scanner and processed by two radiologists. Three MUSE-IVIM parameters: fast apparent diffusion coefficient (ADCfast), slow apparent diffusion coefficient (ADCslow), and the fractional perfusion (Fraction of ADCfast), as well as four DCE-MRI parameters: volume transfer constant (Ktrans), rate constant (Kep), extravascular extracellular volume fraction (Ve), and plasma volume fraction (Vp) were generated. Intraclass correlation coefficient (ICC), non-parametric test (Kruskal-Wallis H and Mann-Whitney U), logistic regression, receiver operating characteristic analysis, Delong test, and Spearman's correlation test were performed. According to SES-CD, 116 ileocolonic segments with CD lesions were identified as: inactive, mild, and moderate to severe. With multivariable logistic regression analysis, ADCfast (p<0.001), Fraction of ADCfast (p=0.005), Ktrans (p<0.001) and Kep (p=0.003) were identified as significant factors for differentiating among the three groups. Binary logistic analyses identified ADCfast (p=0.001), Ktrans (p=0.014), and Kep (p=0.029) as independent predictors for the active status. The combination of ADCfast, Ktrans, and Kep performed better than MaRIA score (p=0.028), for differentiating inactive and active status. MaRIA score was positively correlated with ADCfast (p<0.001), Ktrans (p<0.001), Kep (p<0.001), and Ve (p=0.001), however, negatively correlated with Fraction of ADCfast (p<0.001). The combination of MUSE-IVIM and DCE-MRI has been demonstrated to accurately stage inflammatory activity in CD.

Quantitative pharmacokinetic parameter Ktrans map assists in regional segmentation of nasopharyngeal carcinoma in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)

Accurate segmentation of nasopharyngeal carcinoma (NPC) lesion areas from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) facilitates subsequent diagnostic and prognostic workups. However, in previous studies, little consideration has been given to incorporating the pharmacokinetic feature Ktrans as auxiliary information for segmenting NPC in DCE-MRI. Therefore, this paper proposes the use of a pharmacokinetic extended Tofts and Kermode (ETK) model to obtain the Ktrans feature from DCE-MRI and combine it with MRI images for nasopharyngeal tumor segmentation. Additionally, this paper proposes a multi-input branch residual U-Net (MBRU-Net) model that effectively fuses DCE-MRI features and Ktrans features. The effectiveness of the multibranch network is validated by comparing MBRU-Net with ResU-Net with DCE-MRI + Ktrans data. Additionally, different models are trained with DCE-MRI and DCE-MRI + Ktrans data separately and compared to validate the effectiveness of multimodal data using the Dice coefficient. Our proposed MBRU-Net achieves the best Dice in this study (67.39 ± 15.79%), higher than ResU-Net's Dice (65.57 ± 17.52) based on DCE-MRI and Ktrans data. U-Net, SegNet, R2U-Net, and ResU-Net achieve better results in terms of segmenting tumor regions with DCE-MRI + Ktrans data than those of the corresponding models with DCE-MRI data alone, where U-Net has the best performance (DCE-MRI + Ktrans: DCE-MRI = 66.31 ± 17.80%: 61.10 ± 24.14%). The results show that it is beneficial to add a pharmacokinetic parametric (Ktrans) map as prior information to the conventional anatomical MRI-based segmentation task, and multibranch network structures perform better than single-branch network structures in terms of NPC segmentation.

Dynamic contrast-enhanced MRI radiomics model predicts epidermal growth factor receptor amplification in glioblastoma, IDH-wildtype.

To develop and validate a dynamic contrast-enhanced (DCE) MRI-based radiomics model to predict epidermal growth factor receptor (EGFR) amplification in patients with glioblastoma, isocitrate dehydrogenase (IDH) wildtype. Patients with pathologically confirmed glioblastoma, IDH wildtype, from January 2015 to December 2020, with an EGFR amplification status, were included. Patients who did not undergo DCE or conventional brain MRI were excluded. Patients were categorized into training and test sets by a ratio of 7:3. DCE MRI data were used to generate volume transfer constant (Ktrans) and extracellular volume fraction (Ve) maps. Ktrans, Ve, and conventional MRI were then used to extract the radiomics features, from which the prediction models for EGFR amplification status were developed and validated. A total of 190 patients (mean age, 59.9; male, 55.3%), divided into training (n = 133) and test (n = 57) sets, were enrolled. In the test set, the radiomics model using the Ktrans map exhibited the highest area under the receiver operating characteristic curve (AUROC), 0.80 (95% confidence interval [CI], 0.65-0.95). The AUROC for the Ve map-based and conventional MRI-based models were 0.74 (95% CI, 0.58-0.90) and 0.76 (95% CI, 0.61-0.91). The DCE MRI-based radiomics model that predicts EGFR amplification in glioblastoma, IDH wildtype, was developed and validated. The MRI-based radiomics model using the Ktrans map has higher AUROC than conventional MRI.

Improving measurement of blood-brain barrier permeability with reduced scan time using deep-learning-derived capillary input function

PurposeIn Dynamic contrast-enhanced MRI (DCE-MRI), Arterial Input Function (AIF) has been shown to be a significant contributor to uncertainty in the estimation of kinetic parameters. This study is to assess the feasibility of using a deep learning network to estimate local Capillary Input Function (CIF) to estimate blood-brain barrier (BBB) permeability, while reducing the required scan time. Materials and MethodA total of 13 healthy subjects (younger (<40 y/o): 8, older (> 67 y/o): 5) were recruited and underwent 25-min DCE-MRI scans. The 25 min data were retrospectively truncated to 10 min to simulate a reduced scan time of 10 min. A deep learning network was trained to predict the CIF using simulated tissue contrast dynamics with two vascular transport models. The BBB permeability (PS) was measured using 3 methods: (i) Ca-25min, using DCE-MRI data of 25 min with individually sampled AIF (Ca); (ii) Ca-10min, using truncated 10min data with AIF (Ca); and (iii) Cp-10min, using truncated 10 min data with CIF (Cp). The PS estimates from the Ca-25min method were used as reference standard values to assess the accuracy of the Ca-10min and Cp-10min methods in estimating the PS values. ResultsWhen compared to the reference method(Ca-25min), the Ca-10min and Cp-10min methods resulted in an overestimation of PS by 217 ± 241 % and 48.0 ± 30.2 %, respectively. The Bland Altman analysis showed that the mean difference from the reference was 8.85 ± 1.78 (x10−4 min−1) with the Ca-10min, while it was reduced to 1.63 ± 2.25 (x10−4 min−1) with the Cp-10min, resulting in an average reduction of 81%. The limits of agreement also reduced by up to 39.2% with the Cp-10min. We found a 75% increase of BBB permeability in the gray matter and a 35% increase in the white matter, when comparing the older group to the younger group. ConclusionsWe demonstrated the feasibility of estimating the capillary-level input functions using a deep learning network. We also showed that this method can be used to estimate subtle age-related changes in BBB permeability with reduced scan time, without compromising accuracy. Moreover, the trained deep learning network can automatically select CIF, reducing the potential uncertainty resulting from manual user-intervention.

The therapeutic utility of combining dynamic contrast-enhanced magnetic resonance imaging with arterial spin labeling in the staging of nasopharyngeal carcinoma

BackgroundTo research the pathological and clinical staging uses of arterial spin labeling (ASL) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).Materials and methods64 newly diagnosed nasopharyngeal carcinoma (NPC) patients were enrolled from December 2020 to January 2022, and 3.0 T MRI (Discovery 750W, GE Healthcare, USA) were used for ASL and DCE-MRI scans. The DCE-MRI and ASL raw data were processed post-acquisition on the GE image processing workstation (GE Healthcare, ADW 4.7, USA). The volume transfer constant (Ktrans), blood flow (BF), and accompanying pseudo-color images were generated automatically. Draw the region of interest (ROIs), and the Ktrans and BF values for each ROI were recorded separately. Based on pathological information and the most recent AJCC staging criteria, patients were divided into low T stage groups = T1–2 and high T stage groups = T3–4, low N stage groups = N0–1 and high N stage groups = N2–3, and low AJCC stage group = stage I–II and high AJCC stage group = stage III–IV. The association between the Ktranst and BF parameters and the T, N, and AJCC stages was compared using an independent sample t-test. Using a receiver operating characteristic (ROC) curve, the sensitivity, specificity, and AUC of Ktranst, BFt, and their combined use in T and AJCC staging of NPC were investigated and assessed.ResultThe tumor-BF (BFt) (t = − 4.905, P < 0.001) and tumor-Ktrans (Ktranst) (t = − 3.113, P = 0.003) in the high T stage group were significantly higher than those in the low T stage group. The Ktranst in the high N stage group was significantly higher than that in the low N stage group (t = − 2.071, P = 0.042). The BFt (t = − 3.949, P < 0.001) and Ktranst (t = − 4.467, P < 0.001) in the high AJCC stage group were significantly higher than those in the low AJCC stage group. BFt was moderately positively correlated with the T stage (r = 0.529, P < 0.001) and AJCC stage (r = 0.445, P < 0.001). Ktranst was moderately positively correlated with T staging (r = 0.368), N staging (r = 0.254), and AJCC staging (r = 0.411). There was also a positive correlation between BF and Ktrans in gross tumor volume (GTV) (r = 0.540, P < 0.001), parotid (r = 0.323, P < 0.009) and lateral pterygoid muscle (r = 0.445, P < 0.001). The sensitivity of the combined application of Ktranst and BFt for AJCC staging increased from 76.5 and 78.4 to 86.3%, and the AUC value increased from 0.795 and 0.819 to 0.843, respectively.ConclusionCombining Ktrans and BF measures may make it possible to identify the clinical stages in NPC patients.

Persistent Peri-Ablation Blood-Brain Barrier Opening After Laser Interstitial Thermal Therapy for Brain Tumors.

Purpose Laser interstitial thermal therapy (LITT) is a minimally invasive, image-guided, cytoreductive procedure to treat recurrent glioblastoma. This study implemented dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) methods and employed a model selection paradigm to localize and quantify post-LITT blood-brain barrier (BBB) permeability in the ablation vicinity. Serum levels of neuron-specific enolase (NSE), a peripheral marker of increased BBB permeability, were measured. Methods Seventeen patients were enrolled in the study. Using an enzyme-linked immunosorbent assay, serum NSE was measured preoperatively, 24 hours postoperatively, and at two, eight, 12, and 16 weeks postoperatively, depending on postoperative adjuvant treatment. Of the 17 patients, four had longitudinal DCE-MRI data available, from which blood-to-brain forward volumetric transfer constant (Ktrans) data were assessed. Imaging was performed preoperatively, 24 hours postoperatively, and between two and eight weeks postoperatively. Results Serum NSE increased at 24 hours following ablation (p=0.04), peaked at two weeks, and returned to baseline by eight weeks postoperatively. Ktrans was found to be elevated in the peri-ablation periphery 24 hours after the procedure. This increase persisted for two weeks. Conclusion Following the LITT procedure, serum NSE levels and peri-ablation Ktrans estimated from DCE-MRI demonstrated increases during the first two weeks after ablation, suggesting transiently increased BBB permeability.

Diagnostic efficacy of diffusion-weighted imaging and semiquantitative and quantitative dynamic contrast-enhanced magnetic resonance imaging in salivary gland tumors.

Increased use of functional magnetic resonance imaging (MRI) methods such as diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI consisting of sequential contrast series, allows us to obtain more information on the microstructure, cellularity, interstitial distance, and vascularity of tumors, which has increased the discrimination power for benign and malignant salivary gland tumors (SGTs). In the last few years, quantitative DCE MRI data containing T1 perfusion parameters (Ktrans, Kep and Ve), were reported to contribute to the differentiation of benign or malignant subtypes in SGTs. To evaluate the diagnostic efficacy of DWI and semiquantitative and quantitative perfusion MRI parameters in SGTs. Diffusion MRI [apparent diffusion coefficient (ADC) value] with a 1.5 T MR machine, semiquantitative perfusion MRI [time intensity curve (TIC) pattern], and quantitative perfusion MRI examinations (Ktrans, Kep and Ve) of 73 tumors in 67 patients with histopathological diagnosis performed from 2017 to 2021 were retrospectively evaluated. In the ADC value and semiquantitative perfusion MRI measurements, cystic components of the tumors were not considered, and the region of interest (ROI) was manually placed through the widest axial section of the tumor. TIC patterns were divided into four groups: Type A = Tpeak > 120 s; type B = Tpeak ≤ 120 s, washout ratio (WR) ≥ 30%; type C = Tpeak ≤ 120 s, WR < 30%; and type D = flat TIC. For the quantitative perfusion MRI analysis, a 3D ROI was placed in the largest solid component of the tumor, and the Ktrans, Kep and Ve values were automatically generated. The majority of SGTs were located in the parotid glands (86.3%). Of all the SGTs, 68.5% were benign and 31.5% were malignant. Significant differences were found for ADC values among pleomorphic adenomas (PMAs), Warthin's tumors (WTs), and malignant tumors (MTs) (P < 0.001). PMAs had type A and WTs had type B TIC pattern while the vast majority of MTs and other benign tumors (OBTs) (54.5% and 45.5%, respectively) displayed type C TIC pattern. PMAs showed no washout, while the highest mean WR was observed in WTs (59% ± 11%). Ktrans values of PMAs, WTs, OBTs, and MTs were not significantly different. Kep values of PMAs and WTs were significantly different from those of OBTs and MTs. Mean Ve value of WTs was significantly different from those of PMAs, OBTs, and MTs (P < 0.001). The use of quantitative DCE parameters along with diffusion MRI and semiquantitative contrast-enhanced MRI in SGTs could improve the diagnostic accuracy.

Deep learning radiomic analysis of DCE-MRI combined with clinical characteristics predicts pathological complete response to neoadjuvant chemotherapy in breast cancer.

The aim of this study was to develop and validate a deep learning-based radiomic (DLR) model combined with clinical characteristics for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. For early prediction of pCR, the DLR model was based on pre-treatment and early treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data. This retrospective study included 95 women (mean age, 48.1 years; range, 29-77 years) who underwent DCE-MRI before (pre-treatment) and after two or three cycles of NAC (early treatment) from 2018 to 2021. The patients in this study were randomly divided into a training cohort (n=67) and a validation cohort (n=28) at a ratio of 7:3. Deep learning and handcrafted features were extracted from pre- and early treatment DCE-MRI contoured lesions. These features contribute to the construction of radiomic signature RS1 and RS2 representing information from different periods. Mutual information and least absolute shrinkage and selection operator regression were used for feature selection. A combined model was then developed based on the DCE-MRI features and clinical characteristics. The performance of the models was assessed using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test. The overall pCR rate was 25.3% (24/95). One radiomic feature and three deep learning features in RS1, five radiomic features and 11 deep learning features in RS2, and five clinical characteristics remained in the feature selection. The performance of the DLR model combining pre- and early treatment information (AUC=0.900) was better than that of RS1 (AUC=0.644, P=0.068) and slightly higher that of RS2 (AUC=0.888, P=0.604) in the validation cohort. The combined model including pre- and early treatment information and clinical characteristics showed the best ability with an AUC of 0.925 in the validation cohort. The combined model integrating pre-treatment, early treatment DCE-MRI data, and clinical characteristics showed good performance in predicting pCR to NAC in patients with breast cancer. Early treatment DCE-MRI and clinical characteristics may play an important role in evaluating the outcomes of NAC by predicting pCR.

An Investigation into Race Bias in Random Forest Models Based on Breast DCE-MRI Derived Radiomics Features.

Recent research has shown that artificial intelligence (AI) models can exhibit bias in performance when trained using data that are imbalanced by protected attribute(s). Most work to date has focused on deep learning models, but classical AI techniques that make use of hand-crafted features may also be susceptible to such bias. In this paper we investigate the potential for race bias in random forest (RF) models trained using radiomics features. Our application is prediction of tumour molecular subtype from dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) of breast cancer patients. Our results show that radiomics features derived from DCE-MRI data do contain race-identifiable information, and that RF models can be trained to predict White and Black race from these data with 60-70% accuracy, depending on the subset of features used. Furthermore, RF models trained to predict tumour molecular subtype using race-imbalanced data seem to produce biased behaviour, exhibiting better performance on test data from the race on which they were trained.

Ktrans Calculation Using Reference Method Corrected Native T10 for Breast Cancer Diagnosis.

The objective of the study is to use multiple tube phantoms to generate correction factor at different spatial locations for each breast coil cuff to correct the native T10 value in the corresponding spatial location of the breast lesion. The corrected T10 value was used to compute Ktrans and analyze its diagnostic accuracy in the classification of target condition, i.e., breast tumors into malignant and benign. Both in vitro phantom study (external reference) and patient's studies were acquired on simultaneous positron emission tomography/magnetic resonance imaging (PET/MRI) Biograph molecular magnetic resonance (mMR) system using 4 channel mMR breast coil. The spatial correction factors derived using multiple tube phantom were used for a retrospective analysis of dynamic contrast-enhanced (DCE) MRI data of 39 patients with a mean age of 50 years (31-77 years) having 51 enhancing breast lesions. Corrected and non-corrected receiver operating characteristic (ROC) curve analysis revealed a mean Ktrans value of 0.64 min-1 and 0.60 min-1, respectively. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and overall accuracy for non-corrected data were 86.21%, 81.82%, 86.20%, 81.81%, and 84.31%, respectively, and for corrected data were 93.10%, 86.36%, 90%, 90.47%, and 90.20% respectively. The area under curve (AUC) of corrected data was improved to 0.959 (95% confidence interval [CI] 0.862-0.994) from 0.824 (95% CI 0.694-0.918) of non-corrected data, and for NPV, it was improved to 90.47% from 81.81%, respectively. T10 values were normalized using multiple tube phantom which was used for computation of Ktrans. We found significant improvement in the diagnostic accuracy of corrected Ktrans values that results in better characterization of breast lesions.

Variational Approach for Joint Kidney Segmentation and Registration from DCE-MRI Using Fuzzy Clustering with Shape Priors.

The dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technique has great potential in the diagnosis, therapy, and follow-up of patients with chronic kidney disease (CKD). Towards that end, precise kidney segmentation from DCE-MRI data becomes a prerequisite processing step. Exploiting the useful information about the kidney's shape in this step mandates a registration operation beforehand to relate the shape model coordinates to those of the image to be segmented. Imprecise alignment of the shape model induces errors in the segmentation results. In this paper, we propose a new variational formulation to jointly segment and register DCE-MRI kidney images based on fuzzy c-means clustering embedded within a level-set (LSet) method. The image pixels' fuzzy memberships and the spatial registration parameters are simultaneously updated in each evolution step to direct the LSet contour toward the target kidney. Results on real medical datasets of 45 subjects demonstrate the superior performance of the proposed approach, reporting a Dice similarity coefficient of 0.94 ± 0.03, Intersection-over-Union of 0.89 ± 0.05, and 2.2 ± 2.3 in 95-percentile of Hausdorff distance. Extensive experiments show that our approach outperforms several state-of-the-art LSet-based methods as well as two UNet-based deep neural models trained for the same task in terms of accuracy and consistency.

Predicting hormone receptors and PAM50 subtypes of breast cancer from multi-scale lesion images of DCE-MRI with transfer learning technique

BackgroundThe recent development of artificial intelligence (AI) technologies coupled with medical imaging data has gained considerable attention, and offers a non-invasive approach for cancer diagnosis and prognosis. In this context, improved breast cancer (BC) molecular characteristics assessment models are foreseen to enable personalized strategies with better clinical outcomes compared to existing screening strategies. And it is a promising approach to developing models for hormone receptors (HR) and subtypes of BC patients from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data. MethodsIn this institutional review board-approved study, 174 BC patients with both DCE-MRI and RNA-seq data in the local database were analyzed. Slice images from tumor lesions and multi-scale peri-tumor regions were used as model inputs, and five representative pre-trained transfer learning (TF) networks, such as Inception-v3 and Xception, were employed to establish prediction models. A comprehensive analysis was performed using five-fold cross-validation to avoid overfitting, and accuracy (ACC) and area under the receiver operating characteristic curve (AUROC) to evaluate model performance. ResultsXception achieved the superior results when using solely tumor regions, with highest AUROCs of 0.844 (95% CI: [0.841, 0.847]) and 0.784 (95% CI: [0.781, 0.788]) for estrogen receptor (ER) and progesterone receptor (PR), respectively, and best ACC of 0.467 (95% CI: [0.462, 0.470]) for PAM50 subtypes. A significant improvement in the model performance was observed when images of the peri-tumor region were included, with optimal results achieved using images of the tumor and the 10 mm peri-tumor regions. Xception-based TF models performed most effectively in predicting ER and PR statuses, with the AUROCs were 0.942 (95% CI: [0.940, 0.944]) and 0.920 (95% CI: [0.917, 0.922]), respectively, whereas for PAM50 subtypes, the Inception-v3-based network yielded the highest ACC as 0.742 (95% CI: [0.738, 0.746]). ConclusionsTransfer learning analysis based on DCE-MRI data of tumor and peri-tumor regions was helpful to the non-invasive assessment of molecular characteristics of BC.

Self-gated, dynamic contrast-enhanced magnetic resonance imaging with compressed-sensing reconstruction for evaluating endothelial permeability in the aortic root of atherosclerotic mice.

High-risk atherosclerotic plaques are characterized by active inflammation and abundant leaky microvessels. We present a self-gated, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) acquisition with compressed sensing reconstruction and apply it to assess longitudinal changes in endothelial permeability in the aortic root of Apoe-/- atherosclerotic mice during natural disease progression. Twenty-four, 8-week-old, female Apoe-/- mice were divided into four groups (n = 6 each) and imaged with self-gated DCE-MRI at 4, 8, 12, and 16 weeks after high-fatdiet initiation, and then euthanized for CD68 immunohistochemistry for macrophages. Eight additional mice were kept on a high-fat diet and imaged longitudinally at the same time points. Aortic-root pseudo-concentration curves were analyzed using a validated piecewise linear model. Contrast agent wash-in and washout slopes (b1 and b2 ) were measured as surrogates of aortic root endothelial permeability and compared with macrophage density by immunohistochemistry. b2 , indicating contrast agent washout, was significantly higher in mice kept on an high-fat diet for longer periods of time (p= 0.03). Group comparison revealed significant differences between mice on a high-fat diet for 4 versus 16 weeks (p= 0.03). Macrophage density also significantly increased with diet duration (p= 0.009). Spearman correlation between b2 from DCE-MRI and macrophage density indicated a weak relationship between the two parameters (r = 0.28, p= 0.20). Validated piecewise linear modeling of the DCE-MRI data showed that the aortic root contrast agent washout rate is significantly different during disease progression. Further development of this technique from a single-slice to a 3D acquisition may enable better investigation of the relationship between in vivo imaging of endothelial permeability and atherosclerotic plaques' genetic, molecular, and cellular makeup in this important model of disease.

Radiogenomics analysis reveals the associations of dynamic contrast-enhanced-MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer.

BackgroundTo investigate reliable associations between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and gene expression characteristics in breast cancer (BC) and to develop and validate classifiers for predicting PAM50 subtypes and prognosis from DCE-MRI non-invasively.MethodsTwo radiogenomics cohorts with paired DCE-MRI and RNA-sequencing (RNA-seq) data were collected from local and public databases and divided into discovery (n = 174) and validation cohorts (n = 72). Six external datasets (n = 1,443) were used for prognostic validation. Spatial–temporal features of DCE-MRI were extracted, normalized properly, and associated with gene expression to identify the imaging features that can indicate subtypes and prognosis.ResultsExpression of genes including RBP4, MYBL2, and LINC00993 correlated significantly with DCE-MRI features (q-value < 0.05). Importantly, genes in the cell cycle pathway exhibited a significant association with imaging features (p-value < 0.001). With eight imaging-associated genes (CHEK1, TTK, CDC45, BUB1B, PLK1, E2F1, CDC20, and CDC25A), we developed a radiogenomics prognostic signature that can distinguish BC outcomes in multiple datasets well. High expression of the signature indicated a poor prognosis (p-values < 0.01). Based on DCE-MRI features, we established classifiers to predict BC clinical receptors, PAM50 subtypes, and prognostic gene sets. The imaging-based machine learning classifiers performed well in the independent dataset (areas under the receiver operating characteristic curve (AUCs) of 0.8361, 0.809, 0.7742, and 0.7277 for estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2)-enriched, basal-like, and obtained radiogenomics signature). Furthermore, we developed a prognostic model directly using DCE-MRI features (p-value < 0.0001).ConclusionsOur results identified the DCE-MRI features that are robust and associated with the gene expression in BC and displayed the possibility of using the features to predict clinical receptors and PAM50 subtypes and to indicate BC prognosis.

Improving automatic liver tumor segmentation in late-phase MRI using multi-model training and 3D convolutional neural networks

Automatic liver tumor segmentation can facilitate the planning of liver interventions. For diagnosis of hepatocellular carcinoma, dynamic contrast-enhanced MRI (DCE-MRI) can yield a higher sensitivity than contrast-enhanced CT. However, most studies on automatic liver lesion segmentation have focused on CT. In this study, we present a deep learning-based approach for liver tumor segmentation in the late hepatocellular phase of DCE-MRI, using an anisotropic 3D U-Net architecture and a multi-model training strategy. The 3D architecture improves the segmentation performance compared to a previous study using a 2D U-Net (mean Dice 0.70 vs. 0.65). A further significant improvement is achieved by a multi-model training approach (0.74), which is close to the inter-rater agreement (0.78). A qualitative expert rating of the automatically generated contours confirms the benefit of the multi-model training strategy, with 66 % of contours rated as good or very good, compared to only 43 % when performing a single training. The lesion detection performance with a mean F1-score of 0.59 is inferior to human raters (0.76). Overall, this study shows that correctly detected liver lesions in late-phase DCE-MRI data can be automatically segmented with high accuracy, but the detection, in particular of smaller lesions, can still be improved.

Comparison of diffusion kurtosis imaging and dynamic contrast enhanced MRI in prediction of prognostic factors and molecular subtypes in patients with breast cancer

PurposeTo explore the clinical value of diffusional kurtosis imaging (DKI) and dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) for predicting genotypes and prognostic factors of breast cancer. Materials and methodsA total of 130 female patients with pathologically-confirmed breast cancer and DKI and DCE-MRI data were reviewed retrospectively. Two radiologists independently evaluated mean diffusivity (MD) and mean kurtosis (MK) for the DKI model and volume transfer constant (Ktrans), reverse rate constant (Kep), and extracellular extravascular volume ratio (Ve) for the DCE-MRI model for post-processing analyses. Receiver operating characteristic (ROC) curves were used to analyse the diagnostic efficacies. ResultsMK, Ktrans, and Kep values were significantly higher in the high-grade Nottingham prognostic index (NPI) group (NPI ≥ 3.4) than in the low-grade NPI group (NPI < 3.4) (p < 0.01). The Ktrans had significantly greater area under ROC curve (AUC) than Kep and MK in predicting the NPI (p = 0.038 and 0.0217, respectively). Higher Ktrans, Kep, and MK values were observed in the high Ki-67 expression (≥14%) group than in the low Ki-67 expression (<14%) group (p < 0.05). Moreover, the MK value had better diagnostic performance than the Ktrans and Kep values in identifying Ki-67 expression status (p = 0.0097 and 0.0008, respectively). The combined model (MD + MK + Ktrans + Ve) had a significantly higher AUC than the single parameters for differentiating between luminal A/B and non-luminal subtypes (p = 0.003, < 0.001, 0.001, and < 0.001, respectively). The Human epidermal growth factor receptor 2-positive group had higher MD and Ve values than the other subtype groups (p < 0.05), and the Ve had a sensitivity of 100%. Moreover, the Ve AUC was significantly higher than that for MD in the identification of the triple-negative subtype (p = 0.048). ConclusionKtrans of DCE-MRI and MK of DKI demonstrated good diagnostic performance in predicting the prognostic factors of breast cancer. Additionally, the combination of the DCE-MRI and DKI models can improve the efficiency of predicting breast cancer genotypes.

Consideration of transmembrane water exchange in pharmacokinetic model significantly improves the accuracy of DCE-MRI in estimating cellular density: A pilot study in glioblastoma multiforme

Transmembrane water exchange (TWE) including transcytolemmal water exchange and transvascular water exchange is involved in many in vivo measurements and makes different contributions to the measuring results. In this study, we focus on the potential influence of TWE on the cell density parameter, intracellular water mole fraction pi, derived by dynamic contrast enhanced-magnetic resonance imaging (DCE-MRI) which has been reported as a technique to characterize perfusion and vascularization of tissues, but its accuracy in measuring cell density (or interstitial space) has been questioned. Sixteen patients with glioblastoma multiforme (GBM) were enrolled since GBM shows strong intratumor heterogeneity in both cell density and TWE. All the subjects were collected with DCE-MRI and apparent diffusion coefficient (ADC) map. The latter was considered as a valid surrogate of cell density. Extended Tofts (eTofts) model considering TWE as infinitely large variables and shutter-speed model (SSM) considering TWE as finite ones were used to fit DCE-MRI data. Monte Carlo (MC) and finite difference (FD) methods were used to simulate the influence of TWE on DCE-MRI-derived pi and ADC, respectively. The eTofts model shows a significant overestimation of pi in comparison with SSM in GBM (P < 0.001), which is in accordance with MC simulations, and this overestimation shows dependence on the intra-to-extracellular water exchange rate constant (kio). Significant negative correlations between ADC and SSM-derived pi were found in both voxel-wise analyses (t-test P < 0.001, average r = −0.74) and inter-subject comparisons (r = −0.63, P = 0.009). But no consistent voxel-wise correlations (P > 0.05) and a weaker inter-subject negative correlation (r = −0.56, P = 0.02) were found between ADC and eTofts-derived pi. Further experimental and FD results revealed that kio made a limited contribution to ADC values in the physiological kio range in GBM, supporting ADC as a valid biomarker of cell density. These results suggest that the DCE-MRI pharmacokinetic shutter-speed model could significantly improve its accuracy in cell density estimation because of the considering transmembrane water exchange.

Application of Multimodal Fusion Technology in Image Analysis of Pretreatment Examination of Patients with Spinal Injury.

As one of the most common imaging screening techniques for spinal injuries, MRI is of great significance for the pretreatment examination of patients with spinal injuries. With rapid iterative update of imaging technology, imaging techniques such as diffusion weighted magnetic resonance imaging (DWI), dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), and magnetic resonance spectroscopy are frequently used in the clinical diagnosis of spinal injuries. Multimodal medical image fusion technology can obtain richer lesion information by combining medical images in multiple modalities. Aiming at the two modalities of DCE-MRI and DWI images under MRI images of spinal injuries, by fusing the image data under the two modalities, more abundant lesion information can be obtained to diagnose spinal injuries. The research content includes the following: (1) A registration study based on DCE-MRI and DWI image data. To improve registration accuracy, a registration method is used, and VGG-16 network structure is selected as the basic registration network structure. An iterative VGG-16 network framework is proposed to realize the registration of DWI and DCE-MRI images. The experimental results show that the iterative VGG-16 network structure is more suitable for the registration of DWI and DCE-MRI image data. (2) Based on the fusion research of DCE-MRI and DWI image data. For the registered DCE-MRI and DWI images, this paper uses a fusion method combining feature level and decision level to classify spine images. The simple classifier decision tree, SVM, and KNN were used to predict the damage diagnosis classification of DCE-MRI and DWI images, respectively. By comparing and analyzing the classification results of the experiments, the performance of multimodal image fusion in the auxiliary diagnosis of spinal injuries was evaluated.