Search Results (264)

Background/Objectives: To investigate and develop a non-invasive parametric radiomics model derived from dynamic contrast-enhanced MRI (DCE-MRI) time-intensity curve (TIC) kinetics for predicting breast cancer molecular subtypes (HR+/HER2−, HER2+ and triple-negative breast cancer). Methods: This multicenter retrospective study enrolled 935 female patients with histologically confirmed breast cancer who underwent pretreatment breast DCE-MRI from August 2017 to July 2022. Based on the wash-in rate (WIR) and the area under the TIC, the original multiphase DCE-MRI images were converted into two types of parametric images. Radiomics features were extracted from TIC-WIR and TIC-Area images and analyzed using low variance filtering, the elimination of highly correlated features, and the least absolute shrinkage and selection operator regression. The categorical boosting algorithm was employed to develop multiclass prediction models for breast cancer molecular subtyping. A TIC-Combined model was further established by integrating the calibrated probability outputs of the TIC-WIR and TIC-Area models using a decision-level fusion strategy. The discrimination, calibration, and interpretability of the models were evaluated in the study datasets. Results: The TIC-Combined model achieved superior predictive performance in both the internal validation set (micro-average AUC: 0.79, macro-average AUC: 0.77) and the external validation set (micro-average AUC: 0.77, macro-average AUC: 0.75). For subtype-specific classification by the TIC-Combined model, the highest one-vs-rest AUCs were 0.81 for triple-negative breast cancer in the internal validation set and 0.76 for HER2+ breast cancer in the external validation set. The TIC-Combined model also showed good calibration and high interpretability which ensured reliable predictions and provided clear insights into feature importance. Conclusions: Interpretable parametric radiomics from TIC-derived parametric maps links kinetic features to molecular phenotypes, enabling accurate and non-invasive classification of breast cancer molecular subtypes. Full article

Background: The accurate prediction of response to neoadjuvant therapy (NAT) is crucial for optimizing breast cancer management. Conventional breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) radiomics typically relies on single post-contrast phases and may not fully capture temporal enhancement patterns related to tumor heterogeneity. This study evaluated a machine learning model based on time-dependent radiomic features extracted from pre-treatment DCE-MRI for predicting NAT response in breast cancer patients. Methods: Breast DCE-MRI examinations of women scheduled for NAT, acquired on 1.5 T scanners from three different vendors, were retrospectively collected from two centers. Tumors were automatically segmented on the third post-contrast DCE image using a 3D nnUNet model trained on 30 lesions. All DCE phases were registered to the reference image, and radiomic features were extracted from a consistent tumor region of interest across all phases. Time-dependent radiomic features were computed using linear regression modeling of feature evolution over time. A random forest classifier integrating static and time-dependent radiomic features was developed to predict pathological complete response (pCR), partial response (pPR), and non-response (pNR). Model performance was evaluated using internal validation (Center 1) and an independent external test cohort (Center 2). Results: A total of 212 patients were included (173 from Center 1 and 39 from Center 2), comprising 103 pCR, 103 pPR and 6 pNR cases. Among 759 extracted features, 30 showed significant differences across response groups. Several time-dependent texture features related to intratumoral heterogeneity were significantly associated with pNR. The model achieved AUC values of 0.80, 0.81, and 0.95 in the internal validation cohort and 0.75, 0.74, and 0.86 in the external test cohort for predicting pCR, pPR, and pNR, respectively. Conclusions: Time-dependent radiomic features derived from pre-treatment breast DCE-MRI enable the accurate prediction of response to NAT, with particularly strong performance in identifying non-responders. This approach may support imaging-based risk stratification and contribute to more personalized treatment. Full article

Background/Objectives: Preoperative discrimination between tumor deposits (TDs) and lymph node metastases (LNMs) in rectal cancer on MRI is clinically critical but remains challenging. Methods: A systematic review following PRISMA guidelines was conducted, including studies using MRI to differentiate TDs from LNMs with histopathology as reference. Performance metrics such as AUC, sensitivity, and specificity were extracted. Results: Four retrospective studies (n = 344 patients) were included. Morphology-based MRI showed moderate diagnostic accuracy (AUC 0.72–0.76), whereas DCE-MRI and radiomics models demonstrated improved performance (AUC up to 0.86). Combined multiparametric approaches integrating DWI, DCE, and radiomics yielded the highest discriminative values. Conclusions: MRI-based multiparametric models improve discrimination between TDs and LNMs in rectal cancer. Integration of functional and morphologic features may enhance staging precision and guide therapy planning. Full article

Objectives: To explore if MRI can monitor treatment and predict outcome in patients with human epidermal growth factor 2 (HER2)-negative breast cancer receiving neoadjuvant chemotherapy (NACT) with or without bevacizumab. Methods: Multiparametric MRI was performed at baseline and after 12 and 25 weeks of NACT. MRI assessment included tumour size, apparent diffusion coefficient (ADC) from diffusion-weighted imaging (DWI), and signal intensity–time curves and vascular volume transfer constant (K^TRANS) from dynamic contrast-enhanced MRI (DCE). The reference standards were pathological complete response (pCR) at the time of surgery, and 10-year recurrence-free survival. Receiver operating characteristics analyses were performed to assess the predictive value of the MRI parameters. MRI findings and outcomes were compared between the treatment groups. Results: Seventy women were included from November 2008 to July 2012, with a median age of 49.5 years and median tumour diameter of 47 mm. Fourteen patients (20.0%) achieved pCR, while eleven (15.7%) had recurrence during the 10-year follow-up. The treatment significantly reduced tumour size, increased ADC, decreased K^TRANS, and shifted the signal intensity–time curves towards more benign shapes. The DCE parameters changed significantly more in the bevacizumab group. In the bevacizumab group, baseline K^TRANS predicted pCR (Area under curve (AUC) = 0.73), but the difference in pCR-rates between the treatment groups was not significant (p = 0.07). Only tumour size and shrinkage at 12 weeks predicted pCR (AUC = 0.71–0.85) regardless of size measuring method. No MRI parameters predicted survival. Conclusions: All MRI parameters reflected treatment response, but no parameter predicted survival or benefit from adding bevacizumab to chemotherapy. Full article

Dynamic contrast-enhancement (DCE) modality of MRI is typically considered secondary in prostate cancer (PCa) diagnostics, due to the common interpretation that its diagnostic power is lower than that of other modalities like T2-weighted (T2W) or diffusion-weighted imaging (DWI). To challenge this paradigm, this study introduces a novel concept of a difference map, which relies exclusively on DCE-MRI for the localization of peripheral zone prostate cancer using functional data analysis-based (FDA) signal processing. The proposed workflow uses discrete voxel-level DCE time–signal curves that are transformed into a continuous functional form. First-order derivatives are then used to determine patient-specific time points of greatest enhancement change that adapt to the intrinsic characteristics of each patient, producing diffmaps that highlight regions with pronounced enhancement dynamics, indicative of malignancy. A subsequent normalization step accounts for inter-patient variability, enabling consistent interpretation across subjects and probabilistic PCa localization. The approach is validated on a curated dataset of 20 patients. Evaluation of eight workflow variants is performed using weighted log loss, the best variant achieving a mean log loss of 0.578. This study demonstrates the feasibility and effectiveness of a single-modality, automated, and interpretable approach for peripheral prostate cancer localization based solely on DCE-MRI. Full article

Background and Objectives: Accurate breast tumor segmentation in dynamic contrast-enhanced MRI (DCE-MRI) is crucial for treatment planning, therapy monitoring, and quantitative studies of breast cancer response. However, deep learning models often have worse performance when applied to new hospitals because scanner hardware, acquisition protocols, and patient populations differ from those in the training data. This study investigates how such center-related domain shift affects automated breast DCE-MRI tumor segmentation on the multi-center MAMA-MIA dataset. Methods: We trained a standard 3D U-Net for primary tumor segmentation under two evaluation settings. First, we constructed a random patient-wise split that mixes cases from the three main MAMA-MIA center groups (ISPY2, DUKE, NACT) and used this as an in-distribution reference. Second, we designed a balanced leave-one-center-out cross-validation (LoCoCV) protocol in which each center is held out in turn, while training, validation, and test sets are matched in size across folds. Performance was assessed using the Dice similarity coefficient, 95th percentile Hausdorff distance (HD95), sensitivity, specificity, and related overlap measures. Results: On the mixed-center random split, the best three-channel model achieved a mean Dice of about 0.68 and a mean HD95 of about 19.7 mm on the held-out test set, indicating good volumetric overlap and boundary accuracy when training and test distributions match. Under balanced LoCoCV, the one-channel model reached a mean Dice of about 0.45 and a mean HD95 of about 41 mm on unseen centers, with similar averages for the three-channel variant. Compared with the random split baseline, Dice and sensitivity decreased, while HD95 nearly doubled, showing that boundary errors become larger and segmentations less reliable when the model is applied to new centers. Conclusions: A model that performs well on mixed-center random splits can still suffer a substantial loss of accuracy on completely unseen institutions. The balanced LoCoCV design makes this out-of-distribution penalty visible by separating center-related effects from sample size effects. These findings highlight the need for robust multi-center training strategies and explicit cross-center validation before deploying breast DCE-MRI segmentation models in clinical practice. Full article

Background/Objectives: Preoperative differentiation between oral squamous cell carcinoma (SCC) and minor salivary gland carcinoma (SGC) remains clinically challenging due to overlapping imaging characteristics. This study aimed to develop a diagnostic model based on quantitative dynamic contrast-enhanced MRI (qDCE-MRI) parameters to distinguish SCC from SGC prior to surgery. Methods: Patients with histopathologic confirmed SCC or minor SGC who underwent preoperative 3.0T qDCE-MRI were recruited. Clinical characteristics and pharmacokinetic parameters, including volume transfer constant (K^trans), reverse reflux rate constant (K_ep), volume fraction of extravascular extracellular space (V_e), plasma volume fraction (V_p), time to peak (TTP), maximum concentration (MAXConc), maximal slope (MAXSlope), and area under the concentration-time curve (AUCt), along with the apparent diffusion coefficient (ADC), were extracted. Univariate and multivariable logistic regression analyses were performed to identify independent discriminators. Diagnostic performance was assessed using receiver operating characteristic analysis, and model comparisons were conducted with the DeLong test. Interobserver agreement was evaluated using intraclass correlation coefficients (ICC). Results: All qDCE-MRI parameters demonstrated excellent interobserver agreement (ICC range, 0.82–0.94). Multivariable analysis identified K_ep (OR = 2620.172, p = 0.001), maximal slope (OR = 1.715, p = 0.024), and tumor location (OR = 5.561, p = 0.027) as independent predictors. The qDCE-MRI model achieved superior diagnostic performance compared with the clinical model (AUC: 0.945 vs. 0.747; p = 0.012). Conclusions: A qDCE-MRI–based model incorporating K_ep and MAXSlope was shown to provide excellent accuracy for preoperative differentiation between oral SCC and minor SGC. Full article

Glioblastoma (GBM) remains one of the most treatment-resistant human malignancies, largely due to the interplay between disrupted fluid dynamics, immune evasion, and the structural complexity of the tumor microenvironment; in addition to these, treatment resistance is also driven by intratumoral heterogeneity, glioma stem cell persistence, hypoxia-induced metabolic and epigenetic plasticity, adaptive oncogenic signaling, and profound immunosuppression within the tumor microenvironment. Emerging evidence shows that dysfunction of the glymphatic system, mislocalization of aquaporin-4, and increased intracranial pressure compromise cerebrospinal fluid–interstitial fluid exchange and impair antigen drainage to meningeal lymphatics, thereby weakening immunosurveillance. GBM simultaneously remodels the blood–brain barrier into a heterogeneous and permeable blood–tumor barrier that restricts uniform drug penetration yet enables tumor progression. These alterations intersect with profound immunosuppression mediated by pericytes, tumor-associated macrophages, and hypoxic niches. Advances in imaging, including DCE-MRI, DTI-ALPS, CSF-tracing PET, and elastography, now allow in vivo characterization of glymphatic function and interstitial flow. Therapeutic strategies targeting the fluid-immune interface are rapidly expanding, including convection-enhanced delivery, intrathecal and intranasal approaches, focused ultrasound, nanoparticle systems, and lymphatic-modulating immunotherapies such as VEGF-C and STING agonists. Integrating barrier modulation with immunotherapy and nanomedicine holds promise for overcoming treatment resistance. Our review synthesizes the mechanistic, microenvironmental, and translational advances that position the glymphatic–immune axis as a new frontier in glioblastoma research. Full article

Background/Objectives: Early and accurate characterization of endometrial cancer (EC) is crucial for patient management, but current imaging modalities lack in diagnostic accuracy and ability to assess molecular profiles. The aim of this study is to evaluate hybrid [¹⁸F]FDG PET/MRI’s diagnostic accuracy in EC staging and role in predicting tumor aggressiveness, molecular characterization, and recurrence. Methods: A prospective study (ClinicalTrials.gov, ID:NCT04212910) evaluating EC patients undergoing [¹⁸F]FDG PET/MRI before surgery (2018–2024). Histology, immunohistochemistry, and patients’ follow-up (mean FU time: 3.13y) were used as the reference standard. [¹⁸F]FDG PET/MRI, PET only, and MRI only were independently reviewed to assess the diagnostic accuracy (ACC), sensitivity (SN), specificity (SP), and positive/negative predictive value (PPV, NPV). Imaging parameters were extracted from [¹⁸F]FDG PET and pcT1w, T2w, DWI, and DCE MRI. Spearman’s correlations, Fisher’s exact test, ROC-AUC analysis, Kaplan–Meier survival curves, log-rank tests and Cox proportional hazards models were applied. Results: Eighty participants with primary EC (median age 63 ± 12 years) were enrolled, with 17% showing LN involvement. [¹⁸F]FDG PET/MRI provided ACC = 98.75%, SN = 98.75%, and PPV = 100% for primary tumor detection, and ACC = 92.41%, SN = 84.62%, SP = 93.94%, PPV = 73.33%, and NPV = 96.88% for LN detection. PET/MRI parameters predicted LN involvement (AUC = 79.49%), deep myometrial invasion (79.78%), lymphovascular space invasion (82.00%), p53abn (71.47%), MMRd (74.51%), relapse (82.00%), and postoperative administration of adjuvant therapy (79.64%). Patients with a tumor cranio-caudal diameter ≥ 43 mm and MTV ≥ 13.5 cm³ showed increased probabilities of recurrence (p < 0.001). Conclusions: [¹⁸F]FDG PET/MR showed exceptional accuracy in EC primary tumor and LN detection. Derived parameters demonstrated potential ability in defining features of aggressiveness, molecular alterations, and tumor recurrence. Full article

Background/Objectives: The tumor microenvironment (TME) of pancreatic ductal adenocarcinoma (PDAC) is characterized by an enriched stroma, hampering the effectiveness of therapy. This co-clinical study aimed to (1) provide insight into early post-treatment changes in the TME using multiparametric magnetic resonance imaging (mpMRI)-derived quantitative imaging biomarkers (QIBs) in a preclinical PDAC model treated with radiotherapy and correlate these QIBs with histology; (2) evaluate the feasibility of obtaining these QIBs in patients with PDAC using clinically approved mpMRI data acquisitions. Methods: Athymic mice (n = 12) at pre- and post-treatment as well as patients with PDAC (n = 11) at pre-treatment underwent mpMRI including diffusion-weighted (DW) and dynamic contrast-enhanced (DCE) data acquisition sequences. DW and DCE data were analyzed using monoexponential and extended Tofts models, respectively. DeepLIIF quantified the total percentage (%) of tumor cells in hematoxylin and eosin (H&E)-stained tissues from athymic mice. Spearman correlation and Wilcoxon signed rank tests were performed for statistical analysis. Results: In the preclinical PDAC model, mean pre- and post-treatment ADC and K^trans values differed significantly (p < 0.01), changing by 20.50% and 20.41%, respectively, and the median total tumor cells quantified by DeepLIIF was 24% (range: 15–53%). Post-treatment ADC values and relative change in v_e (rΔv_e) showed a significant negative correlation with total tumor cells (ρ = −0.77, p < 0.014 for ADC and ρ = −0.77, p = 0.009 for rΔv_e). In patients with PDAC, pre-treatment mean ADC and K^trans values were 1.76 × 10⁻³ (mm²/s) and 0.24 (min⁻¹), respectively. Conclusions: QIBs in both preclinical and clinical settings underscore their potential for future co-clinical research to evaluate emerging drug combinations targeting both tumor and stroma. Full article

Background: The role of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in detecting soft-tissue sarcoma (STS) local recurrence (LR) following therapeutic intervention was evaluated. Method: PubMed, Embase, and Scopus were systematically searched from January 1990 to 1 February 2024 for studies evaluating DCE-MRI for LR detection in histologically confirmed STS following surgery. Two independent reviewers screened studies and extracted data, and a bivariate diagnostic test accuracy meta-analysis was performed to estimate pooled sensitivity, specificity, and the area under the summary receiver operating characteristic (SROC) curve. Results: Six studies, including 309 patients (110 with LR and 199 without LR), met the inclusion criteria. Across studies, DCE-MRI qualitative features (such as early rapid arterial enhancement and malignant time–intensity curves) and quantitative or semiquantitative parameters (such as volume transfer constants [Ktrans and Kep], initial area under the curve [iAUC], and relative plasma flow [rPF]) consistently differentiated LR from post-treatment change. When DCE-MRI parameters were added to conventional MRI, the pooled sensitivity and specificity for LR detection were 98% and 83%, respectively, with an SROC area under the curve of 0.94, indicating high overall diagnostic accuracy. Conclusions: DCE-MRI increases the accuracy of LR detection when combined with conventional MRI and offers a higher specificity and sensitivity in distinguishing LR from post-surgical changes, which support consideration of adding DCE-MRI when LR is suspected; prospective standardized studies are warranted. Full article

Ultrasound-stimulated microbubble (USMB) therapy, in combination with radiotherapy (XRT), represents a promising approach to enhancing the efficacy of conventional cancer treatments by targeting tumor vasculature. Recent preclinical studies using MRI-guided focused ultrasound have demonstrated that USMB enhances radiation effects in tumor blood vessels, resulting in significantly greater tumor cell death than radiation alone. Dynamic contrast-enhanced MRI (DCE-MRI) has been instrumental in this methodology in mapping tumor perfusion heterogeneity, allowing for precise targeting of additional USMB and XRT to specific vascular regions. This study employed four advanced texture analysis methods, GLCM, GLDM, GLSZM, and NGTDM, to quantitatively assess changes in the cellular structure of prostate tumors following different treatments, including combinations of USMB and XRT targeted to low- and high-perfusion regions. Texture features, particularly those derived from GLCM, GLDM, and GLSZM, revealed significant differences in cell structure patterns across treatment groups. The GLSZM methodology was identified as the most sensitive method for detecting treatment-induced structural changes, effectively identifying regions of necrosis and varied stages of cell death. Texture-derivative analyses further highlighted intra-tumoral heterogeneity, especially in response to additional USMB + XRT treatments. These results align with findings in other tissue models, underscoring the value of texture analysis for monitoring treatment response. Full article

Background: Interstitial myocardial fibrosis is a crucial pathological feature of many cardiovascular disorders. Myocardial fibrosis resulting in extracellular volume (ECV) expansion can be quantified via cardiac MRI (CMR) with T₁ mapping before and after minimally invasive gadolinium (Gd) contrast agent administration. However, longitudinal repetitive ECV measurements are challenging in rodents due to the prolonged scan time with cardiac and respiratory gating that is required for conventional T₁ mapping and the invasive nature of the rodent intravenous lines. Methods: To address these challenges, the objective of this study is to establish a fast, free-breathing, and gating-free ECV procedure using a minimally invasive subcutaneous catheter for in-scanner Gd administration that can allow longitudinal repetitive ECV evaluations in rodent models. This is achieved by the (1) IntraGate sequence for free-breathing, gating-free cardiac imaging; (2) minimally invasive subcutaneous in-scanner Gd administration; and (3) fast T₁ mapping with a varied flip angle (VFA) in conjunction with (4) triple jugular vein blood T₁ normalization. Additionally, full cine CMR (multi-slice short-axis, long-axis 2-chamber, and long-axis 4-chamber) was acquired during the waiting period to assess comprehensive cardiac function and strain. Results: We successfully established a minimally invasive fast ECV quantification protocol to enable longitudinal repetitive ECV quantifications in rodents. Minimally invasive subcutaneous Gd bolus administration induced a reasonable dynamic contrast enhancement (DCE) time course, reaching a steady state in ~20 min for stable T₁ quantification. The free-breathing gating-free VFA T₁ quantification scheme allows for rapid cardiac (~2.5 min) and jugular vein (49 s) T₁ quantification with no motion artifacts. The triple jugular vein T₁ acquisitions (1 pre-contrast and 2 post-contrast) immediately flanking the heart T₁ acquisitions enable accurate myocardial ECV quantification. Our data demonstrated that left-ventricular myocardial ECV quantification was highly reproducible with repeated scans, and the ECV values (0.25) are comparable to reported ranges among humans and rodents. This protocol was successfully applied to the ischemia–reperfusion injury model to detect myocardial fibrosis, which was validated by histopathology. Conclusions: We established a simple, fast, minimally invasive, and robust CMR protocol in rodents that can enable longitudinal repetitive ECV quantification for cardiovascular disease progression. It can be used to monitor disease regression with interventions. Full article

Background: The Vesical Imaging-Reporting and Data System (VI-RADS) has limited diagnostic accuracy in distinguishing non-muscle-invasive bladder cancer (NMIBC) within VI-RADS categories 2 and 3, despite its value for overall NMIBC assessment. Dynamic contrast-enhanced MRI (DCE-MRI), which reflects tumor vascularity, holds promise for improving these challenging cases but remains underutilized due to unexploited spatiotemporal information. Methods: We developed a deep learning model to comprehensively quantify spatiotemporal features from multiphase DCE-MRI in 184 patients with VI-RADS 2 or 3 (training: n = 115, validation: n = 20, testing: n = 49). The model integrated multiscale feature extraction and contextual attention mechanisms to enhance diagnostic performance. Results: The model outperformed established benchmarks (e.g., VGG, ResNet) and the conventional VI-RADS ≤ 2 threshold (sensitivity: 0.67 for NMIBC), achieving a sensitivity of 0.90 (95% CI: 0.81–0.96) for NMIBC and an area under the curve (AUC) of 0.82 (95% CI: 0.75–0.89) for overall classification. Visualizations confirmed its ability to identify key spatiotemporal patterns linked to muscle invasion. Conclusions: By leveraging comprehensive spatiotemporal information from DCE-MRI, our deep learning model significantly improves NMIBC diagnosis in VI-RADS 2/3 cases, offering a clinically valuable tool to address the limitations of current VI-RADS assessment. Full article

Background/Objectives: Segmental non-mass enhancement (NME) is the breast MRI distribution pattern with the highest positive predictive value (PPV) for malignancy. Despite its diagnostic relevance, its imaging characteristics have rarely been examined in isolation, leaving uncertainty in clinical practice. This multicenter retrospective cohort study aimed to evaluate multiparametric MRI features—including internal enhancement pattern, dynamic contrast-enhanced (DCE) kinetics, and diffusion restriction—in segmental NME to identify malignancy predictors. Methods: This retrospective cohort review included 14,834 breast MRI reports from five institutions (September 2017–February 2024), identifying 103 women (mean age, 44.4 ± 9.9 years) with segmental NME (70 malignant, 33 benign). MRI was performed at 1.5 T or 3 T using standardized protocols. Two breast radiologists, blinded to pathology, assessed internal enhancement, DCE kinetics, diffusion restriction, and short tau inversion recovery (STIR) features according to BI-RADS. Statistical analyses included chi-square/Fisher’s tests and logistic regression. Results: Clustered ring enhancement (CRE) was significantly associated with malignancy (p = 0.004). Fast initial-phase enhancement (p < 0.001) and delayed-phase washout (p = 0.011) also correlated with malignancy. On multivariate analysis, fast initial-phase enhancement remained an independent predictor (odds ratio [OR] = 5.133, p = 0.031), whereas slow enhancement predicted benignity (OR = 0.194, p = 0.020). Histologies included ductal carcinoma in situ, invasive ductal carcinoma, granulomatous mastitis, and benign hyperplastic lesions. Conclusions: This study, focusing exclusively on segmental NME, identifies CRE, fast initial-phase enhancement, and washout kinetics as reliable imaging biomarkers. Incorporating these features into breast MRI interpretation may improve diagnostic accuracy, risk stratification, and management decisions. Full article