Probabilistic Nested Model Selection in Pharmacokinetic Analysis of DCE-MRI Data in Animal Model of Cerebral Tumor.

Purpose: Best current practice in the analysis of dynamic contrast enhanced (DCE)-MRI is to employ a voxel-by-voxel model selection from a hierarchy of nested models. This nested model selection (NMS) assumes that the observed time-trace of contrast-agent (CA) concentration within a voxel, corresponds to a singular physiologically nested model. However, admixtures of different models may exist within a voxel's CA time-trace. This study introduces an unsupervised feature engineering technique (Kohonen-Self-Organizing-Map (K-SOM)) to estimate the voxel-wise probability of each nested model. Methods: Sixty-six immune-compromised-RNU rats were implanted with human U-251N cancer cells, and DCE-MRI data were acquired from all the rat brains. The time-trace of change in the longitudinalrelaxivity Δ R 1 for all animals' brain voxels was calculated. DCE-MRI pharmacokinetic (PK) analysis was performed using NMS to estimate three model regions: Model-1: normal vasculature without leakage, Model-2: tumor tissues with leakage without back-flux to the vasculature, Model-3: tumor vessels with leakage and back-flux. Approximately two hundred thirty thousand (229,314) normalized Δ R 1 profiles of animals' brain voxels along with their NMS results were used to build a K-SOM (topology-size: 8×8, with competitive-learning algorithm) and probability map of each model. K-fold nested-cross-validation (NCV, k=10) was used to evaluate the performance of the K-SOM probabilistic-NMS (PNMS) technique against the NMS technique. Results: The K-SOM PNMS's estimation for the leaky tumor regions were strongly similar (Dice-Similarity-Coefficient, DSC=0.774 [CI: 0.731-0.823], and 0.866 [CI: 0.828-0.912] for Models 2 and 3, respectively) to their respective NMS regions. The mean-percent-differences (MPDs, NCV, k=10) for the estimated permeability parameters by the two techniques were: -28%, +18%, and +24%, for v p , K trans , and v e , respectively. The KSOM-PNMS technique produced microvasculature parameters and NMS regions less impacted by the arterial-input-function dispersion effect. Conclusion: This study introduces an unsupervised model-averaging technique (K-SOM) to estimate the contribution of different nested-models in PK analysis and provides a faster estimate of permeability parameters.

Differentiation between primary central nervous system lymphomas and gliomas according to pharmacokinetic parameters derived from dynamic contrast-enhanced magnetic resonance imaging.

Purpose: It is difficult to differentiate between primary central nervous system lymphoma and primary glioblastoma due to their similar MRI findings. This study aimed to assess whether pharmacokinetic parameters derived from dynamic contrast-enhanced MRI could provide valuable insights for differentiation. Methods: Seventeen cases of primary central nervous system lymphoma and twenty-one cases of glioblastoma as confirmed by pathology, were retrospectively analyzed. Pharmacokinetic parameters, including Ktrans, Kep, Ve, and the initial area under the Gd concentration curve, were measured from the enhancing tumor parenchyma, peritumoral parenchyma, and contralateral normal parenchyma. Statistical comparisons were made using Mann-Whitney U tests for Ve and Matrix Metallopeptidase-2, while independent samples t-tests were used to compare pharmacokinetic parameters in the mentioned regions and pathological indicators of enhancing tumor parenchyma, such as vascular endothelial growth factor and microvessel density. The pharmacokinetic parameters with statistical differences were evaluated using receiver-operating characteristics analysis. Except for the Wilcoxon rank sum test for Ve, the pharmacokinetic parameters were compared within the enhancing tumor parenchyma, peritumoral parenchyma, and contralateral normal parenchyma of the primary central nervous system lymphomas and glioblastomas using variance analysis and the least-significant difference method. Results: Statistical differences were observed in Ktrans and Kep within the enhancing tumor parenchyma and in Kep within the peritumoral parenchyma between these two tumor types. Differences were also found in Matrix Metallopeptidase-2, vascular endothelial growth factor, and microvessel density within the enhancing tumor parenchyma of these tumors. When compared with the contralateral normal parenchyma, pharmacokinetic parameters within the peritumoral parenchyma and enhancing tumor parenchyma exhibited variations in glioblastoma and primary central nervous system lymphoma, respectively. Moreover, the receiver-operating characteristics analysis showed that the diagnostic efficiency of Kep in the peritumoral parenchyma was notably higher. Conclusion: Pharmacokinetic parameters derived from dynamic contrast-enhanced MRI can differentiate primary central nervous system lymphoma and glioblastoma, especially Kep in the peritumoral parenchyma.

Relative Wash-In Rate in Dynamic Contrast-Enhanced Magnetic Resonance Imaging as a New Prognostic Biomarker for Event-Free Survival in 82 Patients with Osteosarcoma: A Multicenter Study.

BACKGROUND: The decreased perfusion of osteosarcoma in dynamic contrast-enhanced (DCE) MRI, reflecting a good histological response to neoadjuvant chemotherapy, has been described. PURPOSE: In this study, we aim to explore the potential of the relative wash-in rate as a prognostic factor for event-free survival (EFS). METHODS: Skeletal high-grade osteosarcoma patients, treated in two tertiary referral centers between 2005 and 2022, were retrospectively included. The relative wash-in rate (rWIR) was determined with DCE-MRI before, after, or during the second cycle of chemotherapy (pre-resection). A previously determined cut-off was used to categorize patients, where rWIR < 2.3 was considered poor and rWIR ≥ 2.3 a good radiological response. EFS was defined as the time from resection to the first event: local recurrence, new metastases, or tumor-related death. EFS was estimated using Kaplan-Meier's methodology. Multivariate Cox proportional hazard model was used to estimate the effect of histological response and rWIR on EFS, adjusted for traditional prognostic factors. RESULTS: Eighty-two patients (median age: 17 years; IQR: 14-28) were included. The median follow-up duration was 11.8 years (95% CI: 11.0-12.7). During follow-up, 33 events occurred. Poor histological response was not significantly associated with EFS (HR: 1.8; 95% CI: 0.9-3.8), whereas a poor radiological response was associated with a worse EFS (HR: 2.4; 95% CI: 1.1-5.0). In a subpopulation without initial metastases, the binary assessment of rWIR approached statistical significance (HR: 2.3; 95% CI: 1.0-5.2), whereas its continuous evaluation demonstrated a significant association between higher rWIR and improved EFS (HR: 0.7; 95% CI: 0.5-0.9), underlining the effect of response to chemotherapy. The 2- and 5-year EFS for patients with a rWIR ≥ 2.3 were 85% and 75% versus 55% and 50% for patients with a rWIR < 2.3. CONCLUSION: The predicted poor chemo response with MRI (rWIR < 2.3) is associated with shorter EFS even when adjusted for known clinical covariates and shows similar results to histological response evaluation. rWIR is a potential tool for future response-based individualized healthcare in osteosarcoma patients before surgical resection.

The relationship between parameters measured using intravoxel incoherent motion and dynamic contrast-enhanced MRI in patients with breast cancer undergoing neoadjuvant chemotherapy: a longitudinal cohort study.

Purpose: The primary aim of this study was to explore whether intravoxel incoherent motion (IVIM) can offer a contrast-agent-free alternative to dynamic contrast-enhanced (DCE)-MRI for measuring breast tumor perfusion. The secondary aim was to investigate the relationship between tissue diffusion measures from DWI and DCE-MRI measures of the tissue interstitial and extracellular volume fractions. Materials and methods: A total of 108 paired DWI and DCE-MRI scans were acquired at 1.5 T from 40 patients with primary breast cancer (median age: 44.5 years) before and during neoadjuvant chemotherapy (NACT). DWI parameters included apparent diffusion coefficient (ADC), tissue diffusion (Dt), pseudo-diffusion coefficient (Dp), perfused fraction (f), and the product f×Dp (microvascular blood flow). DCE-MRI parameters included blood flow (Fb), blood volume fraction (vb), interstitial volume fraction (ve) and extracellular volume fraction (vd). All were extracted from three tumor regions of interest (whole-tumor, ADC cold-spot, and DCE-MRI hot-spot) at three MRI visits: pre-treatment, after one, and three cycles of NACT. Spearman's rank correlation was used for assessing between-subject correlations (r), while repeated measures correlation was employed to assess within-subject correlations (rrm) across visits between DWI and DCE-MRI parameters in each region. Results: No statistically significant between-subject or within-subject correlation was found between the perfusion parameters estimated by IVIM and DCE-MRI (f versus vb and f×Dp versus Fb; P=0.07-0.81). Significant moderate positive between-subject and within-subject correlations were observed between ADC and ve (r=0.461, rrm=0.597) and between Dt and ve (r=0.405, rrm=0.514) as well as moderate positive within-subject correlations between ADC and vd and between Dt and vd (rrm=0.619 and 0.564, respectively) in the whole-tumor region. Conclusion: No correlations were observed between the perfusion parameters estimated by IVIM and DCE-MRI. This may be attributed to imprecise estimates of fxDp and vb, or an underlying difference in what IVIM and DCE-MRI measure. Care should be taken when interpreting the IVIM parameters (f and f×Dp) as surrogates for those measured using DCE-MRI. However, the moderate positive correlations found between ADC and Dt and the DCE-MRI parameters ve and vd confirms the expectation that as the interstitial and extracellular volume fractions increase, water diffusion increases.

Correlation of Ktrans derived from dynamic contrast-enhanced MRI with treatment response and survival in locally advanced NSCLC patients undergoing induction immunochemotherapy and concurrent chemoradiotherapy.

PURPOSE: This study aimed to investigate the prognostic significance of pretreatment dynamic contrast-enhanced (DCE)-MRI parameters concerning tumor response following induction immunochemotherapy and survival outcomes in patients with locally advanced non-small cell lung cancer (NSCLC) who underwent immunotherapy-based multimodal treatments. MATERIAL AND METHODS: Unresectable stage III NSCLC patients treated by induction immunochemotherapy, concurrent chemoradiotherapy (CCRT) with or without consolidative immunotherapy from two prospective clinical trials were screened. Using the two-compartment Extend Tofts model, the parameters including Ktrans, Kep, Ve, and Vp were calculated from DCE-MRI data. The apparent diffusion coefficient was calculated from diffusion-weighted-MRI data. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to assess the predictive performance of MRI parameters. The Cox regression model was used for univariate and multivariate analysis. RESULTS: 111 unresectable stage III NSCLC patients were enrolled. Patients received two cycles of induction immunochemotherapy and CCRT, with or without consolidative immunotherapy. With the median follow-up of 22.3 months, the median progression-free survival (PFS) and overall survival (OS) were 16.3 and 23.8 months. The multivariate analysis suggested that Eastern Cooperative Oncology Group score, TNM stage and the response to induction immunochemotherapy were significantly related to both PFS and OS. After induction immunochemotherapy, 67 patients (59.8%) achieved complete response or partial response and 44 patients (40.2%) had stable disease or progressive disease. The Ktrans of primary lung tumor before induction immunochemotherapy yielded the best performance in predicting the treatment response, with an AUC of 0.800. Patients were categorized into two groups: high-Ktrans group (n=67, Ktrans＞164.3×10-3/min) and low-Ktrans group (n=44, Ktrans≤164.3×10-3/min) based on the ROC analysis. The high-Ktrans group had a significantly higher objective response rate than the low-Ktrans group (85.1% (57/67) vs 22.7% (10/44), p<0.001). The high-Ktrans group also presented better PFS (median: 21.1 vs 11.3 months, p=0.002) and OS (median: 34.3 vs 15.6 months, p=0.035) than the low-Ktrans group. CONCLUSIONS: Pretreatment Ktrans value emerged as a significant predictor of the early response to induction immunochemotherapy and survival outcomes in unresectable stage III NSCLC patients who underwent immunotherapy-based multimodal treatments. Elevated Ktrans values correlated positively with enhanced treatment response, leading to extended PFS and OS durations.

Explainable Precision Medicine in Breast MRI: A Combined Radiomics and Deep Learning Approach for the Classification of Contrast Agent Uptake.

In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. In accordance with the Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility of such an assessment to inter-reader variability highlights the urgent need for a standardized classification algorithm. In this retrospective study, the first post-contrast subtraction images for 27 healthy female subjects were included. The BPE was classified slice-wise by two expert radiologists. The extraction of radiomic features from segmented BPE was followed by dataset splitting and dimensionality reduction. The latent representations were then utilized as inputs to a deep neural network classifying BPE into BI-RADS classes. The network's predictions were elucidated at the radiomic feature level with Shapley values. The deep neural network achieved a BPE classification accuracy of 84 ± 2% (p-value < 0.00001). Most of the misclassifications involved adjacent classes. Different radiomic features were decisive for the prediction of each BPE class underlying the complexity of the decision boundaries. A highly precise and explainable pipeline for BPE classification was achieved without user- or algorithm-dependent radiomic feature selection.

Artificial Intelligence Quantification of Enhanced Synovium Throughout the Entire Hand in Rheumatoid Arthritis on Dynamic Contrast-Enhanced MRI.

BACKGROUND: Challenges persist in achieving automatic and efficient inflammation quantification using dynamic contrast-enhanced (DCE) MRI in rheumatoid arthritis (RA) patients. PURPOSE: To investigate an automatic artificial intelligence (AI) approach and an optimized dynamic MRI protocol for quantifying disease activity in RA in whole hands while excluding arterial pixels. STUDY TYPE: Retrospective. SUBJECTS: Twelve RA patients underwent DCE-MRI with 27 phases for creating the AI model and tested on images with a variable number of phases from 35 RA patients. FIELD STRENGTH/SEQUENCE: 3.0 T/DCE T1-weighted gradient echo sequence (mDixon, water image). ASSESSMENT: The model was trained with various DCE-MRI time-intensity number of phases. Evaluations were conducted for similarity between AI segmentation and manual outlining in 51 ROIs with synovitis. The relationship between synovial volume via AI segmentation with rheumatoid arthritis magnetic resonance imaging scoring (RAMRIS) across whole hands was then evaluated. The reference standard was determined by an experienced musculoskeletal radiologist. STATISTICAL TEST: Area under the curve (AUC) of receiver operating characteristic (ROC), Dice and Spearman's rank correlation coefficients, and interclass correlation coefficient (ICC). A P-value <0.05 was considered statistically significant. RESULTS: A minimum of 15 phases (acquisition time at least 2.5 minutes) was found to be necessary. AUC ranged from 0.941 ± 0.009 to 0.965 ± 0.009. The Dice score was 0.557-0.615. Spearman's correlation coefficients between the AI model and ground truth were 0.884-0.927 and 0.736-0.831, for joint ROIs and whole hands, respectively. The Spearman's correlation coefficient for the additional test set between the model trained with 15 phases and RAMRIS was 0.768. CONCLUSION: The AI-based classification model effectively identified synovitis pixels while excluding arteries. The optimal performance was achieved with at least 15 phases, providing a quantitative assessment of inflammatory activity in RA while minimizing acquisition time. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Digital reference object toolkit of breast DCE MRI for quantitative evaluation of image reconstruction and analysis methods.

PURPOSE: To develop a digital reference object (DRO) toolkit to generate realistic breast DCE-MRI data for quantitative assessment of image reconstruction and data analysis methods. METHODS: A simulation framework in a form of DRO toolkit has been developed using the ultrafast and conventional breast DCE-MRI data of 53 women with malignant (n = 25) or benign (n = 28) lesions. We segmented five anatomical regions and performed pharmacokinetic analysis to determine the ranges of pharmacokinetic parameters for each segmented region. A database of the segmentations and their pharmacokinetic parameters is included in the DRO toolkit that can generate a large number of realistic breast DCE-MRI data. We provide two potential examples for our DRO toolkit: assessing the accuracy of an image reconstruction method using undersampled simulated radial k-space data and assessing the impact of the B 1 + $$ {\mathrm{B}}_1^{+} $$ field inhomogeneity on estimated parameters. RESULTS: The estimated pharmacokinetic parameters for each region showed agreement with previously reported values. For the assessment of the reconstruction method, it was found that the temporal regularization resulted in significant underestimation of estimated parameters by up to 57% and 10% with the weighting factor λ = 0.1 and 0.01, respectively. We also demonstrated that spatial discrepancy of v p $$ {v}_p $$ and PS $$ \mathrm{PS} $$ increase to about 33% and 51% without correction for B 1 + $$ {\mathrm{B}}_1^{+} $$ field. CONCLUSION: We have developed a DRO toolkit that includes realistic morphology of tumor lesions along with the expected pharmacokinetic parameter ranges. This simulation framework can generate many images for quantitative assessment of DCE-MRI reconstruction and analysis methods.

Applying dynamic contrast-enhanced MRI tracer kinetic models to differentiate benign and malignant soft tissue tumors.

BACKGROUND: To explore the potential of different quantitative dynamic contrast-enhanced (qDCE)-MRI tracer kinetic (TK) models and qDCE parameters in discriminating benign from malignant soft tissue tumors (STTs). METHODS: This research included 92 patients (41females, 51 males; age range 16-86 years, mean age 51.24 years) with STTs. The qDCE parameters (Ktrans, Kep, Ve, Vp, F, PS, MTT and E) for regions of interest of STTs were estimated by using the following TK models: Tofts (TOFTS), Extended Tofts (EXTOFTS), adiabatic tissue homogeneity (ATH), conventional compartmental (CC), and distributed parameter (DP). We established a comprehensive model combining the morphologic features, time-signal intensity curve shape, and optimal qDCE parameters. The capacities to identify benign and malignant STTs was evaluated using the area under the curve (AUC), degree of accuracy, and the analysis of the decision curve. RESULTS: TOFTS-Ktrans, EXTOFTS-Ktrans, EXTOFTS-Vp, CC-Vp and DP-Vp demonstrated good diagnostic performance among the qDCE parameters. Compared with the other TK models, the DP model has a higher AUC and a greater level of accuracy. The comprehensive model (AUC, 0.936, 0.884-0.988) demonstrated superiority in discriminating benign and malignant STTs, outperforming the qDCE models (AUC, 0.899-0.915) and the traditional imaging model (AUC, 0.802, 0.712-0.891) alone. CONCLUSIONS: Various TK models successfully distinguish benign from malignant STTs. The comprehensive model is a noninvasive approach incorporating morphological imaging aspects and qDCE parameters, and shows significant potential for further development.

Comparison of Early Contrast Enhancement Models in Ultrafast Dynamic Contrast-Enhanced Magnetic Resonance Imaging of Prostate Cancer.

Tofts models have failed to produce reliable quantitative markers for prostate cancer. We examined the differences between prostate zones and lesion PI-RADS categories and grade group (GG) using regions of interest drawn in tumor and normal-appearing tissue for a two-compartment uptake (2CU) model (including plasma volume (vp), plasma flow (Fp), permeability surface area product (PS), plasma mean transit time (MTTp), capillary transit time (Tc), extraction fraction (E), and transfer constant (Ktrans)) and exponential (amplitude (A), arrival time (t0), and enhancement rate (α)), sigmoidal (amplitude (A0), center time relative to arrival time (A1 - T0), and slope (A2)), and empirical mathematical models, and time to peak (TTP) parameters fitted to high temporal resolution (1.695 s) DCE-MRI data. In 25 patients with 35 PI-RADS category 3 or higher tumors, we found Fp and α differed between peripheral and transition zones. Parameters Fp, MTTp, Tc, E, α, A1 - T0, and A2 and TTP all showed associations with PI-RADS categories and with GG in the PZ when normal-appearing regions were included in the non-cancer GG. PS and Ktrans were not associated with any PI-RADS category or GG. This pilot study suggests early enhancement parameters derived from ultrafast DCE-MRI may become markers of prostate cancer.

Deep Learning Model for Predicting Proliferative Hepatocellular Carcinoma Using Dynamic Contrast-Enhanced MRI: Implications for Early Recurrence Prediction Following Radical Resection.

RATIONALE AND OBJECTIVES: The proliferative nature of hepatocellular carcinoma (HCC) is closely related to early recurrence following radical resection. This study develops and validates a deep learning (DL) prediction model to distinguish between proliferative and non-proliferative HCCs using dynamic contrast-enhanced MRI (DCE-MRI), aiming to refine preoperative assessments and optimize treatment strategies by assessing early recurrence risk. MATERIALS AND METHODS: In this retrospective study, 355 HCC patients from two Chinese medical centers (April 2018-February 2023) who underwent radical resection were included. Patient data were collected from medical records, imaging databases, and pathology reports. The cohort was divided into a training set (n = 251), an internal test set (n = 62), and external test sets (n = 42). A DL model was developed using DCE-MRI images of primary tumors. Clinical and radiological models were generated from their respective features, and fusion strategies were employed for combined model development. The discriminative abilities of the clinical, radiological, DL, and combined models were extensively analyzed. The performances of these models were evaluated against pathological diagnoses, with independent and fusion DL-based models validated for clinical utility in predicting early recurrence. RESULTS: The DL model, using DCE-MRI, outperformed clinical and radiological feature-based models in predicting proliferative HCC. The area under the curve (AUC) for the DL model was 0.98, 0.89, and 0.83 in the training, internal validation, and external validation sets, respectively. The AUCs for the combined DL and clinical feature models were 0.99, 0.86, and 0.83 in these sets, while the AUCs for the combined DL, clinical, and radiological model were 0.99, 0.87, and 0.8, respectively. Among models predicting early recurrence, the DL plus clinical features model showed superior performance. CONCLUSION: The DL-based DCE-MRI model demonstrated robust performance in predicting proliferative HCC and stratifying patient risk for early postoperative recurrence. As a non-invasive tool, it shows promise in enhancing decision-making for individualized HCC management strategies.

Microvascular disease not type 2 diabetes is associated with increased cortical porosity: A study of cortical bone microstructure and intracortical vessel characteristics.

Introduction: Fracture risk is elevated in type 2 diabetes (T2D) despite normal or even high bone mineral density (BMD). Microvascular disease (MVD) is a diabetic complication, but also associated with other diseases, for example chronic kidney disease. We hypothesize that increased fracture risk in T2D could be due to increased cortical porosity (Ct.Po) driven by expansion of the vascular network in MVD. The purpose of this study was to investigate associations of T2D and MVD with cortical microstructure and intracortical vessel parameters. Methods: The study group consisted of 75 participants (38 with T2D and 37 without T2D). High-resolution peripheral quantitative CT (HR-pQCT) and dynamic contrast-enhanced MRI (DCE-MRI) of the ultra-distal tibia were performed to assess cortical bone and intracortical vessels (outcomes). MVD was defined as ≥1 manifestation including neuropathy, nephropathy, or retinopathy based on clinical exams in all participants. Adjusted means of outcomes were compared between groups with/without T2D or between participants with/without MVD in both groups using linear regression models adjusting for age, sex, BMI, and T2D as applicable. Results: MVD was found in 21 (55 %) participants with T2D and in 9 (24 %) participants without T2D. In T2D, cortical pore diameter (Ct.Po.Dm) and diameter distribution (Ct.Po.Dm.SD) were significantly higher by 14.6 µm (3.6 %, 95 % confidence interval [CI]: 2.70, 26.5 µm, p = 0.017) and by 8.73 µm (4.8 %, CI: 0.79, 16.7 µm, p = 0.032), respectively. In MVD, but not in T2D, cortical porosity was significantly higher by 2.25 % (relative increase = 12.9 %, CI: 0.53, 3.97 %, p = 0.011) and cortical BMD (Ct.BMD) was significantly lower by -43.6 mg/cm3 (2.6 %, CI: -77.4, -9.81 mg/cm3, p = 0.012). In T2D, vessel volume and vessel diameter were significantly higher by 0.02 mm3 (13.3 %, CI: 0.004, 0.04 mm3, p = 0.017) and 15.4 µm (2.9 %, CI: 0.42, 30.4 µm, p = 0.044), respectively. In MVD, vessel density was significantly higher by 0.11 mm-3 (17.8 %, CI: 0.01, 0.21 mm-3, p = 0.033) and vessel volume and diameter were significantly lower by -0.02 mm3 (13.7 %, CI: -0.04, -0.004 mm3, p = 0.015) and - 14.6 µm (2.8 %, CI: -29.1, -0.11 µm, p = 0.048), respectively. Conclusions: The presence of MVD, rather than T2D, was associated with increased cortical porosity. Increased porosity in MVD was coupled with a larger number of smaller vessels, which could indicate upregulation of neovascularization triggered by ischemia. It is unclear why higher variability and average diameters of pores in T2D were accompanied by larger vessels.

18F-FDG Dedicated Breast PET Complementary to Breast MRI for Evaluating Early Response to Neoadjuvant Chemotherapy.

Purpose To compare quantitative measures of tumor metabolism and perfusion using fluorine 18 (18F) fluorodeoxyglucose (FDG) dedicated breast PET (dbPET) and breast dynamic contrast-enhanced (DCE) MRI during early treatment with neoadjuvant chemotherapy (NAC). Materials and Methods Prospectively collected DCE MRI and 18F-FDG dbPET examinations were analyzed at baseline (T0) and after 3 weeks (T1) of NAC in 20 participants with 22 invasive breast cancers. FDG dbPET-derived standardized uptake value (SUV), metabolic tumor volume, and total lesion glycolysis (TLG) and MRI-derived percent enhancement (PE), signal enhancement ratio (SER), and functional tumor volume (FTV) were calculated at both time points. Differences between FDG dbPET and MRI parameters were evaluated after stratifying by receptor status, Ki-67 index, and residual cancer burden. Parameters were compared using Wilcoxon signed rank and Mann-Whitney U tests. Results High Ki-67 tumors had higher baseline SUVmean (difference, 5.1; P = .01) and SUVpeak (difference, 5.5; P = .04). At T1, decreases were observed in FDG dbPET measures (pseudo-median difference T0 minus T1 value [95% CI]) of SUVmax (-6.2 [-10.2, -2.6]; P < .001), SUVmean (-2.6 [-4.9, -1.3]; P < .001), SUVpeak (-4.2 [-6.9, -2.3]; P < .001), and TLG (-29.1 mL3 [-71.4, -6.8]; P = .005) and MRI measures of SERpeak (-1.0 [-1.3, -0.2]; P = .02) and FTV (-11.6 mL3 [-22.2, -1.7]; P = .009). Relative to nonresponsive tumors, responsive tumors showed a difference (95% CI) in percent change in SUVmax of -34.3% (-55.9%, 1.5%; P = .06) and in PEpeak of -42.4% (95% CI: -110.5%, 8.5%; P = .08). Conclusion 18F-FDG dbPET was sensitive to early changes during NAC and provided complementary information to DCE MRI that may be useful for treatment response evaluation. Keywords: Breast, PET, Dynamic Contrast-enhanced MRI Clinical trial registration no. NCT01042379 Supplemental material is available for this article. © RSNA, 2024.

Unpaired deep learning for pharmacokinetic parameter estimation from dynamic contrast-enhanced MRI without AIF measurements.

DCE-MRI provides information about vascular permeability and tissue perfusion through the acquisition of pharmacokinetic parameters. However, traditional methods for estimating these pharmacokinetic parameters involve fitting tracer kinetic models, which often suffer from computational complexity and low accuracy due to noisy arterial input function (AIF) measurements. Although some deep learning approaches have been proposed to tackle these challenges, most existing methods rely on supervised learning that requires paired input DCE-MRI and labeled pharmacokinetic parameter maps. This dependency on labeled data introduces significant time and resource constraints and potential noise in the labels, making supervised learning methods often impractical. To address these limitations, we present a novel unpaired deep learning method for estimating pharmacokinetic parameters and the AIF using a physics-driven CycleGAN approach. Our proposed CycleGAN framework is designed based on the underlying physics model, resulting in a simpler architecture with a single generator and discriminator pair. Crucially, our experimental results indicate that our method does not necessitate separate AIF measurements and produces more reliable pharmacokinetic parameters than other techniques.

Quantitative dynamic contrast-enhanced magnetic resonance imaging in head and neck cancer: A systematic comparison of different modelling approaches.

Background and purpose: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) describes tissue microvasculature and has prognostic and predictive potential in radiotherapy for head and neck cancer (HNC). However, lack in standardization of DCE-MRI hinders comparison of studies and clinical implementation. This study investigated the accuracy and robustness of the population arterial input function (AIF), correlations between pharmacokinetic parameters and their association to T stage and human papillomavirus (HPV) status for HNC. Materials and methods: DCE-MRI was acquired for 44 HNC patients. Population AIFs were calculated with six different approaches. DCE-MRI was analysed in primary and lymph node tumours using Tofts model (TM) with population AIFs and individual AIFs, extended TM (ETM) with individual AIFs, Brix model (BM), and areas under the curve (AUCs). Intraclass correlation, concordance correlation, Pearson correlation and Whitney Mann U test helped examining the robustness and accuracy of population AIF, correlations between DCE-MRI parameters and their association to T stage and HPV status, respectively. Results: The population AIF was robust but differed from individual AIFs. There was significant correlation between KtransTM/ETM and ve, TM/ETM, and KtransTM/ETM and Kep, TM/ETM. ABrix and AUCs correlated for lymph nodes. Kep, Brix correlated with ABrix, KtransTM/ETM and Kep, TM/ETM for primary tumours. Kep, TM significantly decreased with increasing T stage. Both the correlations and the parameters' association to T stage were stronger for HPV negative lesions. Conclusions: Individual AIF was preferred for accurate pharmacokinetic modelling of DCE-MRI. DCE-MRI parameters and their correlations were affected by the lesion type, HPV status and T staging.

A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma.

PURPOSE: This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC). METHODS: 320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis. RESULTS: Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05). CONCLUSIONS: A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer.

Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Contrast-agent-based perfusion MRI code repository and testing framework: ISMRM Open Science Initiative for Perfusion Imaging (OSIPI).

PURPOSE: Software has a substantial impact on quantitative perfusion MRI values. The lack of generally accepted implementations, code sharing and transparent testing reduces reproducibility, hindering the use of perfusion MRI in clinical trials. To address these issues, the ISMRM Open Science Initiative for Perfusion Imaging (OSIPI) aimed to establish a community-led, centralized repository for sharing open-source code for processing contrast-based perfusion imaging, incorporating an open-source testing framework. METHODS: A repository was established on the OSIPI GitHub website. Python was chosen as the target software language. Calls for code contributions were made to OSIPI members, the ISMRM Perfusion Study Group, and publicly via OSIPI websites. An automated unit-testing framework was implemented to evaluate the output of code contributions, including visual representation of the results. RESULTS: The repository hosts 86 implementations of perfusion processing steps contributed by 12 individuals or teams. These cover all core aspects of DCE- and DSC-MRI processing, including multiple implementations of the same functionality. Tests were developed for 52 implementations, covering five analysis steps. For T1 mapping, signal-to-concentration conversion and population AIF functions, different implementations resulted in near-identical output values. For the five pharmacokinetic models tested (Tofts, extended Tofts-Kety, Patlak, two-compartment exchange, and two-compartment uptake), differences in output parameters were observed between contributions. CONCLUSIONS: The OSIPI DCE-DSC code repository represents a novel community-led model for code sharing and testing. The repository facilitates the re-use of existing code and the benchmarking of new code, promoting enhanced reproducibility in quantitative perfusion imaging.

Evaluation of response to neoadjuvant chemotherapy in osteosarcoma using dynamic contrast-enhanced MRI: development and external validation of a model.

OBJECTIVE: To identify which dynamic contrast-enhanced (DCE-)MRI features best predict histological response to neoadjuvant chemotherapy in patients with an osteosarcoma. METHODS: Patients with osteosarcoma who underwent DCE-MRI before and after neoadjuvant chemotherapy prior to resection were retrospectively included at two different centers. Data from the center with the larger cohort (training cohort) was used to identify which method for region-of-interest selection (whole slab or focal area method) and which change in DCE-MRI features (time to enhancement, wash-in rate, maximum relative enhancement and area under the curve) gave the most accurate prediction of histological response. Models were created using logistic regression and cross-validated. The most accurate model was then externally validated using data from the other center (test cohort). RESULTS: Fifty-five (27 poor response) and 30 (19 poor response) patients were included in training and test cohorts, respectively. Intraclass correlation coefficient of relative DCE-MRI features ranged 0.81-0.97 with the whole slab and 0.57-0.85 with the focal area segmentation method. Poor histological response was best predicted with the whole slab segmentation method using a single feature threshold, relative wash-in rate <2.3. Mean accuracy was 0.85 (95%CI: 0.75-0.95), and area under the receiver operating characteristic curve (AUC-index) was 0.93 (95%CI: 0.86-1.00). In external validation, accuracy and AUC-index were 0.80 and 0.80. CONCLUSION: In this study, a relative wash-in rate of <2.3 determined with the whole slab segmentation method predicted histological response to neoadjuvant chemotherapy in osteosarcoma. Consistent performance was observed in an external test cohort.

Improved reliability of perfusion estimation in dynamic susceptibility contrast MRI by using the arterial input function from dynamic contrast enhanced MRI.

The arterial input function (AIF) plays a crucial role in estimating quantitative perfusion properties from dynamic susceptibility contrast (DSC) MRI. An important issue, however, is that measuring the AIF in absolute contrast-agent concentrations is challenging, due to uncertainty in relation to the measured R 2 ∗ -weighted signal, signal depletion at high concentration, and partial-volume effects. A potential solution could be to derive the AIF from separately acquired dynamic contrast enhanced (DCE) MRI data. We aim to compare the AIF determined from DCE MRI with the AIF from DSC MRI, and estimated perfusion coefficients derived from DSC data using a DCE-driven AIF with perfusion coefficients determined using a DSC-based AIF. AIFs were manually selected in branches of the middle cerebral artery (MCA) in both DCE and DSC data in each patient. In addition, a semi-automatic AIF-selection algorithm was applied to the DSC data. The amplitude and full width at half-maximum of the AIFs were compared statistically using the Wilcoxon rank-sum test, applying a 0.05 significance level. Cerebral blood flow (CBF) was derived with different AIF approaches and compared further. The results showed that the AIFs extracted from DSC scans yielded highly variable peaks across arteries within the same patient. The semi-automatic DSC-AIF had significantly narrower width compared with the manual AIFs, and a significantly larger peak than the manual DSC-AIF. Additionally, the DCE-based AIF provided a more stable measurement of relative CBF and absolute CBF values estimated with DCE-AIFs that were compatible with previously reported values. In conclusion, DCE-based AIFs were reproduced significantly better across vessels, showed more realistic profiles, and delivered more stable and reasonable CBF measurements. The DCE-AIF can, therefore, be considered as an alternative AIF source for quantitative perfusion estimations in DSC MRI.