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.

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.

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.

Optimizing pseudo-spiral sampling for abdominal DCE MRI using a digital anthropomorphic phantom.

PURPOSE: For reliable DCE MRI parameter estimation, k-space undersampling is essential to meet resolution, coverage, and signal-to-noise requirements. Pseudo-spiral (PS) sampling achieves this by sampling k-space on a Cartesian grid following a spiral trajectory. The goal was to optimize PS k-space sampling patterns for abdomin al DCE MRI. METHODS: The optimal PS k-space sampling pattern was determined using an anthropomorphic digital phantom. Contrast agent inflow was simulated in the liver, spleen, pancreas, and pancreatic ductal adenocarcinoma (PDAC). A total of 704 variable sampling and reconstruction approaches were created using three algorithms using different parametrizations to control sampling density, halfscan and compressed sensing regularization. The sampling patterns were evaluated based on image quality scores and the accuracy and precision of the DCE pharmacokinetic parameters. The best and worst strategies were assessed in vivo in five healthy volunteers without contrast agent administration. The best strategy was tested in a DCE scan of a PDAC patient. RESULTS: The best PS reconstruction was found to be PS-diffuse based, with quadratic distribution of readouts on a spiral, without random shuffling, halfscan factor of 0.8, and total variation regularization of 0.05 in the spatial and temporal domains. The best scoring strategy showed sharper images with less prominent artifacts in healthy volunteers compared to the worst strategy. Our suggested DCE sampling strategy also showed high quality DCE images in the PDAC patient. CONCLUSION: Using an anthropomorphic digital phantom, we identified an optimal PS sampling strategy for abdominal DCE MRI, and demonstrated feasibility in a PDAC patient.

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.

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.

Deep Learning Radiomics Model of Dynamic Contrast-Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma.

BACKGROUND: Vessels encapsulating tumor cluster (VETC) is a critical prognostic factor and therapeutic predictor of hepatocellular carcinoma (HCC). However, noninvasive evaluation of VETC remains challenging. PURPOSE: To develop and validate a deep learning radiomic (DLR) model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of VETC and prognosis of HCC. STUDY TYPE: Retrospective. POPULATION: A total of 221 patients with histologically confirmed HCC and stratified this cohort into training set (n = 154) and time-independent validation set (n = 67). FIELD STRENGTH/SEQUENCE: A 1.5 T and 3.0 T; DCE imaging with T1-weighted three-dimensional fast spoiled gradient echo. ASSESSMENT: Histological specimens were used to evaluate VETC status. VETC+ cases had a visible pattern (≥5% tumor area), while cases without any pattern were VETC-. The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI and reproducibility of segmentation was evaluated. Deep neural network and machine learning (ML) classifiers (logistic regression, decision tree, random forest, SVM, KNN, and Bayes) were used to develop nine DLR, 54 ML and clinical-radiological (CR) models based on AP, PP, and DP of DCE-MRI for evaluating VETC status and association with recurrence. STATISTICAL TESTS: The Fleiss kappa, intraclass correlation coefficient, receiver operating characteristic curve, area under the curve (AUC), Delong test and Kaplan-Meier survival analysis. P value <0.05 was considered as statistical significance. RESULTS: Pathological VETC+ were confirmed in 68 patients (training set: 46, validation set: 22). In the validation set, DLR model based on peritumor PP (peri-PP) phase had the best performance (AUC: 0.844) in comparison to CR (AUC: 0.591) and ML (AUC: 0.672) models. Significant differences in recurrence rates between peri-PP DLR model-predicted VETC+ and VETC- status were found. DATA CONCLUSIONS: The DLR model provides a noninvasive method to discriminate VETC status and prognosis of HCC patients preoperatively. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 2.

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.

Magnetic Resonance Imaging of Lung Perfusion.

"Lung perfusion" in the context of imaging conventionally refers to the delivery of blood to the pulmonary capillary bed through the pulmonary arteries originating from the right ventricle required for oxygenation. The most important physiological mechanism in the context of imaging is the so-called hypoxic pulmonary vasoconstriction (HPV, also known as "Euler-Liljestrand-Reflex"), which couples lung perfusion to lung ventilation. In obstructive airway diseases such as asthma, chronic-obstructive pulmonary disease (COPD), cystic fibrosis (CF), and asthma, HPV downregulates pulmonary perfusion in order to redistribute blood flow to functional lung areas in order to conserve optimal oxygenation. Imaging of lung perfusion can be seen as a reflection of lung ventilation in obstructive airway diseases. Other conditions that primarily affect lung perfusion are pulmonary vascular diseases, pulmonary hypertension, or (chronic) pulmonary embolism, which also lead to inhomogeneity in pulmonary capillary blood distribution. Several magnetic resonance imaging (MRI) techniques either dependent on exogenous contrast materials, exploiting periodical lung signal variations with cardiac action, or relying on intrinsic lung voxel attributes have been demonstrated to visualize lung perfusion. Additional post-processing may add temporal information and provide quantitative information related to blood flow. The most widely used and robust technique, dynamic-contrast enhanced MRI, is available in clinical routine assessment of COPD, CF, and pulmonary vascular disease. Non-contrast techniques are important research tools currently requiring clinical validation and cross-correlation in the absence of a viable standard of reference. First data on many of these techniques in the context of observational studies assessing therapy effects have just become available. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 5.

Myocardial Blood Flow Determination From Contrast-Free Magnetic Resonance Imaging Quantification of Coronary Sinus Flow.

BACKGROUND: Determination of myocardial blood flow (MBF) with MRI is usually performed with dynamic contrast enhanced imaging (MBFDCE ). MBF can also be determined from coronary sinus blood flow (MBFCS ), which has the advantage of being a noncontrast technique. However, comparative studies of MBFDCE and MBFCS in large cohorts are lacking. PURPOSE: To compare MBFCS and MBFDCE in a large cohort. STUDY TYPE: Prospective, sequence-comparison study. POPULATION: 147 patients with type 2 diabetes mellitus (age: 56+/-12 years; 106 male; diabetes duration: 12.9+/-8.1 years), and 25 age-matched controls. FIELD STRENGTH/SEQUENCES: 1.5 Tesla scanner. Saturation recovery sequence for MBFDCE vs. phase-contrast gradient-echo pulse sequence (free-breathing) for MBFCS . ASSESSMENT: MBFDCE and MBFCS were determined at rest and during coronary dilatation achieved by administration of adenosine at 140 µg/kg/min. Myocardial perfusion reserve (MPR) was calculated as the stress/rest ratio of MBF values. Coronary sinus flow was determined twice in the same imaging session for repeatability assessment. STATISTICAL TESTS: Agreement between MBFDCE and MBFCS was assessed with Bland and Altman's technique. Repeatability was determined from single-rater random intraclass and repeatability coefficients. RESULTS: Rest and stress flows, including both MBFDCE and MBFCS values, ranged from 33 to 146 mL/min/100 g and 92 to 501 mL/min/100 g, respectively. Intraclass and repeatability coefficients for MBFCS were 0.95 (CI 0.90; 0.95) and 5 mL/min/100 g. In Bland-Altman analysis, mean bias at rest was -1.1 mL/min/100 g (CI -3.1; 0.9) with limits of agreement of -27 and 24.8 mL/min/100 g. Mean bias at stress was 6.3 mL/min/100 g (CI -1.1; 14.1) with limits of agreement of -86.9 and 99.9. Mean bias of MPR was 0.11 (CI: -0.02; 0.23) with limits of agreement of -1.43 and 1.64. CONCLUSION: MBF may be determined from coronary sinus blood flow, with acceptable bias, but relatively large limits of agreement, against the reference of MBFDCE . LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY STAGE: 2.

Predicting intraoperative hemorrhage during curettage treatment of cesarean scar pregnancy using free-breathing GRASP DCE-MRI.

OBJECTIVE: To explore the feasibility of the golden-angle radial sparse parallel (GRASP) dynamic magnetic resonance imaging (MRI) technique in predicting the intraoperative bleeding risk of scar pregnancy. METHODS: A total of 49 patients with cesarean scar pregnancy (CSP) who underwent curettage and GRASP-MRI imaging were retrospectively selected between January 2021 and July 2022. The pharmacokinetic parameters, including Wash-in, Wash-out, time to peck (TTP), initial area under the curve (iAUC), the transfer rate constant (Ktrans), constant flow rate (Kep), and volume of extracellular space (Ve), were calculated. The amount of intraoperative bleeding was recorded by a gynecologist who performed surgery, after which patients were divided into non-hemorrhage (blood loss ≤ 200 mL) and hemorrhage (blood loss > 200 mL) groups. The measured pharmacokinetic parameters were statistically compared using the t-test or Mann-Whitney U test with a significant level set to be p < 0.05. The receiver operating characteristic (ROC) curve was constructed, and the area under the curve (AUC) was calculated to evaluate each parameter's capability in intraoperative hemorrhage subgroup classification. RESULTS: Twenty patients had intraoperative hemorrhage (blood loss > 200 mL) during curettage. The hemorrhage group had larger Wash-in, iAUC, Ktrans, Ve, and shorter TTP than the non-hemorrhage group (all P > 0.05). Wash-in had the highest AUC value (0.90), while Ktrans had the lowest value (0.67). Wash-out and Kep were not significantly different between the two groups. CONCLUSION: GRASP DCE-MRI has the potential to forecast intraoperative hemorrhage during curettage treatment of CSP, with Wash-in exhibiting the highest predictive performance. This data holds promise for advancing personalized treatment. However, further study is required to compare its effectiveness with other risk factors identified through anatomical MRI and ultrasound.

Predictive value of triple negative breast cancer based on DCE-MRI multi-phase full-volume ROI clinical radiomics model.

BACKGROUND: Since no studies compared the value of radiomics features of distinct phases of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting triple-negative breast cancer (TNBC). PURPOSE: To identify the optimal phase of DCE-MRI for diagnosing TNBC and, in combination with clinical factors, to develop a clinical-radiomics model to well predict TNBC. MATERIAL AND METHODS: This retrospective study included 158 patients with pathology-confirmed breast cancer, including 38 cases of TNBC. The patients were randomly divided into the training and validation set (7:3). Eight radiomics models were built based on eight DCE-MR phases, and their performances were evaluated using receiver operating characteristic curve (ROC) and DeLong's test. The Radscore derived from the best radiomics model was integrated with independent clinical risk factors to construct a clinical-radiomics predictive model, and evaluate its performance using ROC analysis, calibration, and decision curve analyses. RESULTS: WHO classification, margin, and T2-weighted (T2W) imaging signals were significantly correlated with TNBC and independent risk factors for TNBC (P<0.05). The clinical model yielded areas under the curve (AUCs) of 0.867 and 0.843 in the training and validation sets, respectively. The radiomics model based on DCEphase7 achieved the highest efficacy, with an AUC of 0.818 and 0.777. The AUC of the clinical-radiomics model was 0.936 and 0.886 in the training and validation sets, respectively. The decision curve showed the clinical utility of the clinical-radiomics model. CONCLUSION: The radiomics features of DCE-MRI had the potential to predict TNBC and could improve the performance of clinical risk factors for preoperative personalized prediction of TNBC.

Comparison of lung lesion assessment using free-breathing dynamic contrast-enhanced 1.5-T MRI with a golden-angle radial stack-of-stars VIBE sequence and CT.

BACKGROUND: Few studies have investigated the feasibility of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using a free-breathing golden-angle radial stack-of-stars volume-interpolated breath-hold examination (FB radial VIBE) sequence in the lung. PURPOSE: To investigate whether DCE-MRI using the FB radial VIBE sequence can assess morphological and kinetic parameters in patients with pulmonary lesions, with computed tomography (CT) as the reference. MATERIAL AND METHODS: In total, 43 patients (30 men; mean age = 64 years) with one lesion each were prospectively enrolled. Morphological and kinetic features on MRI were calculated. The diagnostic performance of morphological MR features was evaluated using a receiver operating characteristic (ROC) curve. Kinetic features were compared among subgroups based on histopathological subtype, lesion size, and lymph node metastasis. RESULTS: The maximum diameter was not significantly different between CT and MRI (3.66 ± 1.62 cm vs. 3.64 ± 1.72 cm; P = 0.663). Spiculation, lobulation, cavitation or bubble-like areas of low attenuation, and lymph node enlargement had an area under the ROC curve (AUC) >0.9, while pleural indentation yielded an AUC of 0.788. The lung cancer group had significantly lower Ktrans, Ve, and initial AUC values than the other cause inflammation group (0.203, 0.158, and 0.589 vs. 0.597, 0.385, and 1.626; P < 0.05) but significantly higher values than the tuberculosis group (P < 0.05). CONCLUSION: Morphology features derived from FB radial VIBE have high correlations with CT, and kinetic analyses show significant differences between benign and malignant lesions. DCE-MRI with FB radial VIBE could serve as a complementary quantification tool to CT for radiation-free assessments of lung lesions.

Reproducibility and reliability of pancreatic pharmacokinetic parameters derived from dynamic contrast-enhanced magnetic resonance imaging.

BACKGROUND: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) with an extended Tofts linear (ETL) model for tissue and tumor evaluation has been established, but its effectiveness in evaluating the pancreas remains uncertain. PURPOSE: To understand the pharmacokinetics of normal pancreas and serve as a reference for future studies of pancreatic diseases. MATERIAL AND METHODS: Pancreatic pharmacokinetic parameters of 54 volunteers were calculated using DCE-MRI with the ETL model. First, intra- and inter-observer reliability was assessed through the use of the intra-class correlation coefficient (ICC) and coefficient of variation (CoV). Second, a subgroup analysis of the pancreatic DCE-MRI pharmacokinetic parameters was carried out by dividing the 54 individuals into three groups based on the pancreatic region, three groups based on age, and two groups based on sex. RESULTS: There was excellent agreement and low variability of intra- and inter-observer to pancreatic DCE-MRI pharmacokinetic parameters. The intra- and inter-observer ICCs of Ktrans, kep, ve, and vp were 0.971, 0.952, 0.959, 0.944 and 0.947, 0.911, 0.978, 0.917, respectively. The intra- and inter-observer CoVs of Ktrans, kep, ve, vp were 9.98%, 5.99%, 6.47%, 4.76% and 10.15%, 5.22%, 6.28%, 5.40%, respectively. Only the pancreatic ve of the older group was higher than that of the young and middle-aged groups (P = 0.042, 0.001), and the vp of the pancreatic head was higher than that of the pancreatic body and tail (P = 0.014, 0.043). CONCLUSION: The application of DCE-MRI with an ETL model provides a reliable, robust, and reproducible means of non-invasively quantifying pancreatic pharmacokinetic parameters.

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.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in differentiation of soft tissue sarcoma from benign lesions: a systematic review of literature.

OBJECTIVE: To systematically review the literature assessing the role of Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) in the differentiation of soft tissue sarcomas from benign lesions. MATERIALS AND METHODS: A comprehensive literature search was performed with the following keywords: multiparametric magnetic resonance imaging, DCE-MR perfusion, soft tissue, sarcoma, and neoplasm. Original studies evaluating the role of DCE-MRI for differentiating benign soft-tissue lesions from soft-tissue sarcomas were included. RESULTS: Eighteen studies with a total of 965 imaging examinations were identified. Ten of twelve studies evaluating qualitative parameters reported improvement in discriminative power. One of the evaluated qualitative parameters was time-intensity curves (TIC), and malignant curves (TIC III, IV) were found in 74% of sarcomas versus 26.5% benign lesions. Six of seven studies that used the semiquantitative approach found it relatively beneficial. Four studies assessed quantitative parameters including Ktrans (contrast transit from the vascular compartment to the interstitial compartment), Kep (contrast return to the vascular compartment), and Ve (the volume fraction of the extracellular extravascular space) in addition to other parameters. All found Ktrans, and 3 studies found Kep to be significantly different between sarcomas and benign lesions. The values for Ve were variable. Additionally, eight studies assessed diffusion-weighted imaging (DWI), and 6 of them found it useful. CONCLUSION: Of different DCE-MRI approaches, qualitative parameters showed the best evidence in increasing the diagnostic performance of MRI. Semiquantitative and quantitative approaches seemed to improve the discriminative power of MRI, but which parameters and to what extent is still unclear and needs further investigation.

A comprehensive MRI analysis of osteoid osteomas in patients with diverse radiological features across various regions.

BACKGROUND: Magnetic resonance imaging (MRI), which does not involve ionizing radiation, is the preferred imaging modality for diagnosing osteoid osteoma (OO), an ailment more common in children and young adults. PURPOSE: This study aims to perform a literature review and delineate the MRI findings of OO lesions in patients exhibiting varying radiological features across different regions. MATERIALS AND METHODS: A retrospective study included 63 patients diagnosed with OO through MRI, assessed independently by two blinded radiologists using both standard and dynamic contrast-enhanced MRI techniques. After excluding 7 patients with prior biopsy, surgery, or RFA, the study included 56 patients with 57 lesions. RESULTS: Of 57 lesions evaluated, 50 were in long, and 7 in flat bones. One patient presented with two separate nidi within the intertrochanteric region. Most of the lesions, 49 (86%), were extra-articular, while 8 (14%) were intra-articular. The nidus was intracortical in 45 (78.9%) patients, intramedullary in 5 (8.8%), subperiosteal in 5 (8.8%), and endosteal in 2 (3.5%). Average nidus diameter was 7.02 ± 2.64 mm (3-12.6 mm). Central nidal calcification was present in 68.4% (n = 39) cases. Contrast enhancement was intense at 90.5%, moderate at 9.5%. Reactive sclerosis around the nidus was severe (50.9%), moderate (22.8%), and mild (26.3%). Bone marrow edema was severe (70.2%), moderate (14.0%), and mild (15.8%). Soft tissue edema was identified in 77.2% of all lesions. CONCLUSION: To minimize delays in diagnosis and treatment, radiologists should become acquainted with the typical OO MRI findings and the atypical MRI findings that might be mistaken for other conditions.

Deep learning applications to breast cancer detection by magnetic resonance imaging: a literature review.

Deep learning analysis of radiological images has the potential to improve diagnostic accuracy of breast cancer, ultimately leading to better patient outcomes. This paper systematically reviewed the current literature on deep learning detection of breast cancer based on magnetic resonance imaging (MRI). The literature search was performed from 2015 to Dec 31, 2022, using Pubmed. Other database included Semantic Scholar, ACM Digital Library, Google search, Google Scholar, and pre-print depositories (such as Research Square). Articles that were not deep learning (such as texture analysis) were excluded. PRISMA guidelines for reporting were used. We analyzed different deep learning algorithms, methods of analysis, experimental design, MRI image types, types of ground truths, sample sizes, numbers of benign and malignant lesions, and performance in the literature. We discussed lessons learned, challenges to broad deployment in clinical practice and suggested future research directions.

Multimodal prediction of neoadjuvant treatment outcome by serial FDG PET and MRI in women with locally advanced breast cancer.

PURPOSE: To investigate combined MRI and 18F-FDG PET for assessing breast tumor metabolism/perfusion mismatch and predicting pathological response and recurrence-free survival (RFS) in women treated for breast cancer. METHODS: Patients undergoing neoadjuvant chemotherapy (NAC) for locally-advanced breast cancer were imaged at three timepoints (pre, mid, and post-NAC), prior to surgery. Imaging included diffusion-weighted and dynamic contrast-enhanced (DCE-) MRI and quantitative 18F-FDG PET. Tumor imaging measures included apparent diffusion coefficient, peak percent enhancement (PE), peak signal enhancement ratio (SER), functional tumor volume, and washout volume on MRI and standardized uptake value (SUVmax), glucose delivery (K1) and FDG metabolic rate (MRFDG) on PET, with percentage changes from baseline calculated at mid- and post-NAC. Associations of imaging measures with pathological response (residual cancer burden [RCB] 0/I vs. II/III) and RFS were evaluated. RESULTS: Thirty-five patients with stage II/III invasive breast cancer were enrolled in the prospective study (median age: 43, range: 31-66 years, RCB 0/I: N = 11/35, 31%). Baseline imaging metrics were not significantly associated with pathologic response or RFS (p > 0.05). Greater mid-treatment decreases in peak PE, along with greater post-treatment decreases in several DCE-MRI and 18F-FDG PET measures were associated with RCB 0/I after NAC (p < 0.05). Additionally, greater mid- and post-treatment decreases in DCE-MRI (peak SER, washout volume) and 18F-FDG PET (K1) were predictive of prolonged RFS. Mid-treatment decreases in metabolism/perfusion ratios (MRFDG/peak PE, MRFDG/peak SER) were associated with improved RFS. CONCLUSION: Mid-treatment changes in both PET and MRI measures were predictive of RCB status and RFS following NAC. Specifically, our results indicate a complementary relationship between DCE-MRI and 18F-FDG PET metrics and potential value of metabolism/perfusion mismatch as a marker of patient outcome.

GRASPNET: Fast spatiotemporal deep learning reconstruction of golden-angle radial data for free-breathing dynamic contrast-enhanced magnetic resonance imaging.

The purpose of the current study was to develop a deep learning technique called Golden-angle RAdial Sparse Parallel Network (GRASPnet) for fast reconstruction of dynamic contrast-enhanced 4D MRI acquired with golden-angle radial k-space trajectories. GRASPnet operates in the image-time space and does not use explicit data consistency to minimize the reconstruction time. Three different network architectures were developed: (1) GRASPnet-2D: 2D convolutional kernels (x,y) and coil and contrast dimensions collapsed into a single combined dimension; (2) GRASPnet-3D: 3D kernels (x,y,t); and (3) GRASPnet-2D + time: two 3D kernels to first exploit spatial correlations (x,y,1) followed by temporal correlations (1,1,t). The networks were trained using iterative GRASP reconstruction as the reference. Free-breathing 3D abdominal imaging with contrast injection was performed on 33 patients with liver lesions using a T1-weighted golden-angle stack-of-stars pulse sequence. Ten datasets were used for testing. The three GRASPnet architectures were compared with iterative GRASP results using quantitative and qualitative analysis, including impressions from two body radiologists. The three GRASPnet techniques reduced the reconstruction time to about 13 s with similar results with respect to iterative GRASP. Among the GRASPnet techniques, GRASPnet-2D + time compared favorably in the quantitative analysis. Spatiotemporal deep learning enables reconstruction of dynamic 4D contrast-enhanced images in a few seconds, which would facilitate translation to clinical practice of compressed sensing methods that are currently limited by long reconstruction times.