Search Results (838)

Background: Locally advanced cervical cancer (LACC) represents a significant challenge in oncology, requiring accurate assessment of local extent and metastatic spread. Multiparametric magnetic resonance imaging (mpMRI) has assumed a central role in the loco-regional characterization of the tumor due to its high soft-tissue resolution and the ability to integrate functional information. Objectives: In this narrative review, we explore the use of mpMRI in the diagnosis, staging, and treatment response of LACC, comparing its performance with that of PET/CT, which remains complementary for remote staging. The potential of whole-body magnetic resonance imaging (WB-MRI) and hybrid PET/MRI techniques is also analyzed, as well as the emerging applications of radiomics and artificial intelligence. The paper also discusses technical limitations, interpretative variability, and the importance of protocol standardization. The goal is to provide an updated and translational summary of imaging in LACC, with implications for clinical practice and future research. Methods: Prospective and retrospective studies, systematic reviews, and meta-analyses on adult patients with cervical cancer were included. Results: Fifty-two studies were included. MRI demonstrated a sensitivity and specificity greater than 80% for parametrial and bladder invasion, but limited sensitivity (45–60%) for lymph node disease, lower than PET/CT. Multiparametric MRI was useful in early prediction of response to chemotherapy and radiotherapy and in distinguishing residual disease from fibrosis. The integration of MRI into Image-Guided Adaptive Brachytherapy (IGABT) resulted in improved oncological outcomes and reduced toxicity. The applications of radiomics and AI demonstrated enormous potential in predicting therapeutic response and lymph node status in the MRI study, but multicenter validation is still needed. Conclusions: MRI is the cornerstone of the local–regional staging of advanced cervical cancer; it has become an essential and crucial tool in treatment planning. Its use, combined with PET/CT for lymph node assessment and metastatic disease staging, is now the standard of care. Future prospects include the use of whole-body MRI and the development of predictive models based on radiomics and artificial intelligence. Full article

UAV object detection is still difficult to achieve due to large-scale variation, dense small objects, a complicated background, and resource constraints from onboard computing. To solve these problems, we develop a diffusion-enhanced detection network, DL-DEIM, tailored for aerial images. The proposed scheme generalizes the DEIM baseline across three orthogonal axes. First, we propose a lightweight backbone network called DCFNet, which utilizes a DRFD module and a FasterC3k2 module to maintain spatial information and reduce computational complexity. Second, we propose a LFDPN module, which can conduct bidirectional multi-scale fusion via frequency-spatial self-attention and deep feature refinement and largely enhance cross-scale contextual propagation for small objects. Third, we propose LAWDown, an adaptive-content-aware downsampling to preserve the discriminative representation with higher accuracy at lower resolutions, which can effectively capture the spatially-variant weights and group channel interactions. On the VisDrone2019 dataset, DL-DEIM achieves a mAP@0.5 of 34.9% and a mAP@0.5:0.95 of 20.0%, outperforming the DEIM baseline by +4.6% and +2.9%, respectively. The model maintains real-time inference speed (356 FPS) with only 4.64 M parameters and 11.73 GFLOPs. Ablation studies validate the fact that DCFNet, LFDPN, and LAWDown collaboratively contribute to the accuracy and efficiency. Visualizations also display clustered and better localized activation in crowded scenes. These results show that DL-DEIM achieves a good tradeoff between detection probability and computation burden and it can be used in practice on resource-limited UAV systems. Full article

Objectives: The potential use of electron density (ED) and effective atomic number (Zeff) derived from dual-energy computed tomography (DECT) as novel quantitative imaging biomarkers for differentiating malignant brain tumors was investigated. Methods: Data pertaining to 136 patients with a pathological diagnosis of brain metastasis (BM), glioblastoma, and primary central nervous system lymphoma (PCNSL) were retrospectively reviewed. The 10th percentile, mean and 90th percentile values of conventional 120-kVp CT value (CTconv), ED, Zeff, and relative apparent diffusion coefficient derived from diffusion-weighted magnetic resonance imaging (rADC: ADC of lesion divided by ADC of normal-appearing white matter) within the contrast-enhanced tumor region were compared across the three groups. Furthermore, machine learning (ML)-based diagnostic models were developed to maximize diagnostic performance for each tumor classification using the indices of DECT parameters and rADC. Machine learning models were developed using the AutoGluon-Tabular framework with rigorous patient-level data splitting into training (60%), validation (20%), and independent test sets (20%). Results: The 10th percentile of Zeff was significantly higher in glioblastomas than in BMs (p = 0.02), and it was the only index with a significant difference between BMs and glioblastomas. In the comparisons including PCNSLs, all indices of CTconv, Zeff, and rADC exhibited significant differences (p < 0.001–0.02). DECT-based ML models exhibited high area under the receiver operating characteristic curves (AUC) for all pairwise differentiations (BMs vs. Glioblastomas: AUC = 0.83; BMs vs. PCNSLs: AUC = 0.91; Glioblastomas vs. PCNSLs: AUC = 0.82). Combined models of DECT and rADC demonstrated excellent diagnostic performance between BMs and PCNSLs (AUC = 1) and between Glioblastomas and PCNSLs (AUC = 0.93). Conclusion: This study suggested the potential of DECT-derived ED and Zeff as novel quantitative imaging biomarkers for differentiating malignant brain tumors. Full article

A 70-year-old Japanese woman with longstanding hearing loss and asthma developed floating sensations, left finger numbness, and postural instability one day after influenza vaccination, leading to hospital admission. Neurological examinations showed hearing loss, hyperreflexia, left-predominant ataxia, bilateral mild bathyanesthesia, and inability to tandem gait. Cerebrospinal fluid (CSF) analysis showed no pleocytosis or malignant cells, but revealed positive oligoclonal bands and elevated myelin basic protein. Despite no contrast agent use due to asthma, brain magnetic resonance imaging (MRI) revealed pontine hyperintensities on diffusion-weighted imaging (DWI) and T2-fluid attenuated inversion recovery (T2-FLAIR) sequences, along with hyperperfusion on arterial spin labeling (ASL) imaging. Serum anti-aquaporin-4 antibodies (AQP4-Ab) were negative by ELISA. Given the temporal proximity to vaccination and elevated demyelination markers, brainstem-type acute disseminated encephalomyelitis (ADEM) was initially suspected. Symptoms nearly resolved after two cycles of methylprednisolone pulse therapy. Notably, hyperperfusion gradually improved on ASL imaging. Post-discharge, a cell-based assay confirmed the diagnosis of neuromyelitis optica spectrum disorder (NMOSD) by detecting positive anti-AQP4-Ab. She has been relapse-free for about a year without any immunosuppressants or biologics. Although contrast-enhanced MRI remains the gold standard modality for lesion evaluation due to its high sensitivity, hyperperfusion on ASL may provide a useful alternative in patients for whom contrast agents are contraindicated, such as those with asthma or impaired renal function. Full article

Background: Whole-body magnetic resonance imaging (WB-MRI) is incorporated into international guidelines and recommendations for imaging patients with multiple myeloma. The aim of this study was to investigate inter-observer agreement of radiologists with different levels of expertise in reporting whole-body MRI performed along MY-RADS criteria in myeloma at baseline and in evaluating response to therapy to better certify the use of these criteria. Methods: A total of 52 patients with symptomatic myeloma at first presentation (47) or relapse (5) and planned for a new line of therapy were included. All patients completed baseline whole-body MRI within 1 month prior to starting treatment. A total of 25 patients were evaluated with WB-MRI within 1 month after therapy. Each scan was reported independently by three radiologists using MY-RADS. Differences in observer scores were compared using analysis of variance (ANOVA), and inter-observer agreement was assessed using the intra-class correlation coefficient (ICC). Results: Interobserver agreement was excellent for all anatomic regions (> 0.81), both at baseline and at follow-up. Quantitative MRI analysis demonstrated that there was no significant difference in mean observer scores for the whole skeleton, and ICC demonstrated excellent inter-observer agreement at 0.9197 for ROI dimension, 0.94 for ADC values, and 0.98 for rFF%. Conclusion: MY RADS has excellent inter-observer agreement in reporting symptomatic myeloma at baseline and follow-up after therapy. In our study, there was no discrepancy between skeletal regions, highlighting specific areas of difficulty. Full article

Background: This study aims to evaluate the contribution of clinical and radiomic features to machine learning-based models for survival prediction in patients with locally advanced cervical cancer. Methods: Clinical and radiomic data from 161 patients were retrospectively collected from a single center. Radiomic features were obtained from contrast-enhanced magnetic resonance imaging (MRI) T1-weighted (T1W), T2-weighted (T2W), and diffusion-weighted (DWI) sequences. After data cleaning, feature engineering, and scaling, survival prediction models were created using the CatBoost algorithm with different data combinations (clinical, clinical + T1W, clinical + T2W, clinical + DWI). The performance of the models was evaluated using test accuracy, precision, recall, F1-score, ROC curve, and Bland–Altman analysis. Results: Models using both clinical and radiomic features showed significant improvements in accuracy and F1-score compared to models based solely on clinical data. In particular, the CatBoost_CLI + T2W_DMFS model achieved the best performance, with a test accuracy of 92.31% and an F1-score of 88.62 for distant metastasis-free survival prediction. ROC and Bland–Altman analyses further demonstrated that this model has high discriminative power and prediction consistency. Conclusions: The CatBoost algorithm shows high accuracy and reliability for survival prediction in locally advanced cervical cancer when clinical and radiomic features are combined. The addition of radiomics data significantly improves model performance. Full article

Objectives: This exploratory preclinical study aimed to compare the correlations of apparent diffusion coefficient (ADC) and native T1 mapping histogram features with tumor cell proliferation, microvessel density (MVD), and extracellular matrix composition in neuroblastoma xenografts. Methods: Neuroblastoma xenografts (n = 42) were established by subcutaneously injecting three MYCN-amplified/non-amplified human neuroblastoma cell lines (IMR-32, SK-N-BE(2), and SH-SY5Y; n = 14 per group) into female immunodeficient BALB/c-nude mice. Once tumors reached a diameter within the range of 12–15 mm, native T1 mapping and diffusion-weighted imaging were performed using a 3.0T clinical MRI scanner. Tumor cell proliferation and MVD were assessed via immunohistochemical Ki-67 staining and CD31 staining, respectively. Collagen fibers were visualized using Masson staining to calculate the collagen volume fraction (CVF). Pearson correlation coefficients with false discovery rate (FDR) correction were used to evaluate their associations. Results: Significant negative correlations were observed between Ki-67 expression and multiple ADC values after FDR correction, including ADC_10Percentile (r = −0.397, adjusted p = 0.032), ADC_90Percentile (r = −0.394, adjusted p = 0.032), ADC_maximum (r = −0.362, adjusted p = 0.048), ADC_mean (r = −0.421, adjusted p = 0.032), ADC_median (r = −0.422, adjusted p = 0.032), ADC_minimum (r = −0.390, adjusted p = 0.032), and ADC_{rootmeansquared} (r = −0.419, adjusted p = 0.032). In contrast, multiple T1 mapping features showed significant positive correlations with CVF (adjusted p < 0.05). Conclusions: ADC and T1 mapping provide complementary insights into tumor proliferation and extracellular matrix composition in neuroblastoma. These preclinical findings support further research to validate their potential clinical utility. Full article

Background: Hemorrhagic transformation (HT) is a major complication of endovascular thrombectomy (EVT) for acute ischemic stroke (AIS). Objectives: To investigate the factors as sociated with HT in patients with successful recanalization and examine the impact of collateral status (CS) on ischemic progression and outcomes. Methods: We retrospectively analyzed patients with AIS with successful recanalization (modified treatment in cerebral infarction (mTICI) 2B-3) who underwent dual-energy CT (DECT) within 24 h and MRI within 10 days post-EVT. Patients with posterior circulation stroke, missing multiphase CT angiography (CTA) collateral scores, or missing 3-month modified ranking scale scores were excluded from the study. Results: Among the 86 patients, those with HT had a significantly lower proportion of 3-month excellent outcomes and worse imaging scores, including non-contrast CT (NCCT)-Alberta Stroke Program Early CT Score (ASPECTS), virtual non-contrast (VNC)-ASPECTS, and diffusion-weighted imaging (DWI)-ASPECTS. Patients with HT with poor CS had a significantly lower proportion of 3-month excellent outcomes, poorer post-EVT National Institutes of Health Stroke Scale (NIHSS) score, worse imaging scores, including VNC-ASPECTS, and DWI-ASPECTS. In the predictive factor analysis, post-EVT NIHSS and VNC-ASPECTS scores were significantly associated with 3-month excellent functional outcomes (modified Rankin Scale (mRS) 0-1). Conclusions: In patients with successfully recanalized AIS, HT with poor CS was associated with poorer functional outcomes and worse imaging scores, and a 24 h combined measure (post-EVT NIHSS and DECT VNC-ASPECT) show promise for early risk stratification; prospective external validation is warranted before routine use. Full article

Background/Objectives: Crohn’s disease (CD) requires precise, noninvasive monitoring to guide therapy and support treat-to-target management. Magnetic resonance enterography (MRE), particularly diffusion-weighted imaging (DWI), is the preferred cross-sectional technique for assessing small-bowel inflammation. Indices such as the Magnetic Resonance Index of Activity (MaRIA) and its diffusion-weighted variant (DWI MaRIA) are widely used for grading disease activity. This study evaluated whether unsupervised clustering of MRI-derived features can complement these indices by providing more coherent and biologically grounded stratification of disease activity. Materials and Methods: Fifty patients with histologically confirmed CD underwent 1.5 T MRE. Of 349 bowel segments, 84 were pathological and classified using literature-based thresholds (MaRIA, DWI MaRIA) and unsupervised clustering. Differences between inactive, active, and severe disease were analyzed using multivariate analysis of variance (MANOVA), analysis of variance (ANOVA), and t-tests. Mahalanobis distances were calculated to quantify and compare separation between categories. Results: Using MaRIA thresholds, 5, 16, and 63 segments were classified as inactive, active, and severe (Mahalanobis distances 2.60, 4.95, 4.12). Clustering redistributed them into 22, 37, and 25 (9.26, 24.22, 15.27). For DWI MaRIA, 21, 14, and 49 segments were identified under thresholds (3.59, 5.72, 2.85) versus 21, 37, and 26 with clustering (7.40, 16.35, 9.41). Wall thickness dominated cluster-derived separation, supported by diffusion metrics and the apparent diffusion coefficient (ADC). Conclusions: Cluster-derived classification yielded clearer and more biologically consistent separation of disease-activity groups than fixed thresholds, emphasizing its potential to refine boundary definition, enhance MRI-based assessment, and inform future AI-driven diagnostic modeling. Full article

Background: Obesity is a known risk factor for neurodegenerative diseases, potentially due to impaired clearance of brain waste through the glymphatic system. While the association between obesity and brain dysfunction has been widely studied in populations with neurological conditions, it remains unclear whether glymphatic system function is already reduced in neurologically healthy individuals with obesity. This study aimed to investigate whether glymphatic system function, measured via the diffusion tensor image (DTI) analysis along the perivascular space (DTI-ALPS) index, differs according to obesity status in neurologically healthy adults. Methods: We retrospectively analyzed brain DTI data from 62 neurologically healthy participants stratified into underweight (<18.5 kg/m²), normal weight (BMI ≥ 18.5 and <23.0 kg/m²), overweight (BMI ≥ 23.0 and <25.0 kg/m²), and obese (≥25.0 kg/m²) groups based on the World Health Organization Asia-Pacific body mass index (BMI) criteria. Group differences were examined using Mann–Whitney U tests and analysis of covariance, after adjusting for age. Results: Participants with obesity had significantly lower DTI-ALPS index values (1.262 ± 0.150) compared to those in the normal weight (1.405 ± 0.168, p = 0.048) and overweight (1.423 ± 0.195, p = 0.029) categories, even after adjusting for age. The DTI-ALPS index was also significantly reduced in participants with obesity compared to participants in the BMI < 25 kg/m² group (1.410 ± 0.176, p = 0.015). Conclusions: This study provides the first evidence that obesity is linked to reduced glymphatic system function, as reflected by lower DTI-ALPS index in neurologically healthy adults. These findings underscore the importance of maintaining a healthy body weight to preserve brain waste clearance mechanisms and may offer insights into early vulnerability to neurodegenerative changes. Full article

Background/Objectives: We provide a framework for determining how far into the future the spatiotemporal dynamics of tumor growth can be accurately predicted using routinely available magnetic resonance imaging (MRI) data. Our analysis is applied to a coupled set of reaction-diffusion equations describing the spatiotemporal development of tumor cellularity and vascularity, initialized and constrained with diffusion-weighted (DW) and dynamic contrast-enhanced (DCE) MRI data, respectively. Methods: Motivated by experimentally acquired murine glioma data, the rat brain serves as the computational domain within which we seed an in silico tumor. We generate a set of 13 virtual tumors defined by different combinations of model parameters. The first parameter combination was selected as it generated a tumor with a necrotic core during our simulated ten-day experiment. We then tested 12 additional parameter combinations to study a range of high and low tumor cell proliferation and diffusion values. Each tumor is grown for ten days via our model system to establish “ground truth” spatiotemporal tumor dynamics with an infinite signal-to-noise ratio (SNR). We then systematically reduce the quality of the imaging data by decreasing the SNR, downsampling the spatial resolution (SR), and decreasing the sampling frequency, our proxy for reduced temporal resolution (TR). With each decrement in image quality, we assess the accuracy of the calibration and subsequent prediction by comparing it to the corresponding ground truth data using the concordance correlation coefficient (CCC) for both tumor and vasculature volume fractions, as well as the Dice similarity coefficient for tumor volume fraction. Results: All tumor CCC and Dice scores for each of the 13 virtual tumors are >0.9 regardless of the SNR/SR/TR combination. Vasculature CCC scores with any SR/TR combination are >0.9 provided the SNR ≥ 80 for all virtual tumors; for the special case of high-proliferating tumors (i.e., proliferation > 0.0263 day⁻¹), any SR/TR combination yields CCC and Dice scores > 0.9 provided the SNR ≥ 40. Conclusions: Our systematic evaluation demonstrates that reaction-diffusion models can maintain acceptable longitudinal prediction accuracy—especially for tumor predictions—despite limitations in the quality and quantity of experimental data. Full article

Background: Ovarian cancer remains a major contributor to cancer-related morbidity and mortality worldwide. Primary cytoreductive surgery is the cornerstone of treatment, and accurate preoperative assessment of tumor resectability is critical to guiding optimal therapeutic strategies in patients with advanced tubo-ovarian cancer. Methods: A narrative review about the role of ultrasound for assessing tumor spread and prediction of tumor resectability was performed. Results: The ISAAC study represents the largest prospective multicenter trial to date comparing the diagnostic performance of ultrasound (US), computed tomography (CT), and whole-body diffusion-weighted magnetic resonance imaging (WB-DWI/MRI) in predicting non-resectability, using surgical and histopathological findings as the reference standard. Key strengths of the study include the use of standardized imaging and intraoperative reporting protocols across ESGO-accredited high-volume oncologic centers. All three imaging modalities were performed within four weeks prior to surgery by independent, blinded expert operators. US demonstrated diagnostic accuracy comparable to that of CT and WB-DWI/MRI. The study also defined modality-specific thresholds for the Peritoneal Cancer Index (PCI) and Predictive Index Value (PIV), offering quantitative tools to support surgical decision-making. A noteworthy secondary finding was patient preference: in a cohort of 144 participants who underwent all three imaging modalities, nearly half preferred US, while WB-DWI/MRI was the least favored due to discomfort and examination duration. Conclusions: The ISAAC study represents a significant advancement in imaging-based prediction of surgical non-resectability in tubo-ovarian cancer. Its findings suggest that, in expert hands, ultrasound can match or even surpass cross-sectional imaging for preoperative staging, supporting its integration into routine clinical practice, particularly in resource-constrained settings. Full article

Background: Despite effective antiretroviral therapy, HIV-associated neurocognitive disorders (HANDs) remain prevalent, highlighting the need for sensitive biomarkers of early brain alterations. Trace-weighted diffusion spectroscopic imaging offers a non-invasive means to assess microstructural changes in brain metabolites in a single shot by measuring apparent diffusion coefficients (ADCs) of total N-acetylaspartate (tNAA), total creatine (tCr), total choline (tCho), and water. Methods: In this study, we used trace-weighted single-shot diffusion-weighted radial echo-planar spectroscopic imaging (DW-RESPI) to investigate metabolite diffusion and relative concentrations in the brains of people living with HIV (PLWH). Using a 3T MRI scanner, we studied 16 PLWH and 15 healthy controls (HCs), and we collected two sets of data with low and high b-values from which metabolite ADCs were computed. Metabolite ratios were derived from the low b-value spectra. A brief neuropsychological assessment evaluated attention, executive function, and memory in a subset of subjects. Cognitive and affective performance was quantified using domain-specific deficit scores, as well as depression and anxiety assessments, offering a comprehensive evaluation of neurobehavioral function. In the male subgroup (N = 15) of PLWH, we calculated the correlations between ADC values and neuropsychological domain scores. Results: tNAA, tCr, tCho, and water ADC values were significantly elevated in multiple gray and white matter regions in PLWH compared to HC, with the most pronounced differences observed in the superior precuneus, anterior cingulate cortex, and corona radiata. Notably, regional ADC values and metabolite ratios showed significant correlations with neuropsychological domain scores. Conclusions: These findings indicate the potential of metabolite and water diffusion metrics as biomarkers for HIV-associated microstructural brain alterations and cognitive impairment. However, the small sample size and preliminary nature of this data warrant further investigation to validate these findings. Full article

Background/Objectives: To evaluate whether incorporating both diffusion-weighted imaging (DWI) and perfusion-weighted imaging (PWI) in pituitary MRI examinations improves differential diagnosis by providing additional diagnostic value. Methods: A retrospective analysis was performed on 88 patients with histologically confirmed sellar or parasellar tumors who underwent 1.5T MRI with DWI and dynamic susceptibility contrast PWI (DSC-PWI) between October 2007 and April 2023. DWI parameters included minimum apparent diffusion coefficient (ADCmin) and relative ADCmin (rADCmin). PWI parameters included mean and maximum relative cerebral blood volume (rCBV, rCBVmax) and relative peak height (rPH, rPHmax), normalized to white matter. Tumor regions of interest were manually segmented, excluding calcified or hemorrhagic areas. Group comparisons and ROC analyses assessed diagnostic performance of individual and combined parameters. Results: Significant differences in diffusion and perfusion metrics were observed among the five tumor types. The combined analysis of DWI and PWI improved diagnostic accuracy in selected comparisons. The greatest benefit occurred in distinguishing meningiomas from solid non-functional pituitary adenomas (pituitary neuroendocrine tumors-PitNET), where the combination of ADCmin and rPHmax yielded an AUC of 0.818, sensitivity of 88%, and specificity of 76%, exceeding the performance of either parameter alone. In other comparisons, including meningiomas versus invasive PitNETs and adamantinomatous craniopharyngiomas, combined analysis did not substantially improve accuracy when single parameters, particularly rCBVmax (AUC = 0.995), already demonstrated excellent performance. Conclusions: Integration of DWI and PWI into pituitary MRI protocols enhances diagnostic performance in selected tumor groups. The additive value is context-dependent, supporting the tailored application of these sequences in the evaluation of sellar and parasellar tumors. Full article

Background/Objectives: Ulcerative Colitis (UC) lacks longitudinal visual data, which limits both disease progression modeling and the effectiveness of computer-aided diagnosis systems. These systems are further constrained by sparse intermediate disease stages and the discrete nature of the Mayo Endoscopic Score (MES). Meanwhile, synthetic image generation has made significant advances. In this paper, we propose novel ordinal embedding architectures for conditional diffusion models to generate realistic UC progression sequences from cross-sectional endoscopic images. Methods: By adapting Stable Diffusion v1.4 with two specialized ordinal embeddings (Basic Ordinal Embedder using linear interpolation and Additive Ordinal Embedder modeling cumulative pathological features), our framework converts discrete MES categories into continuous progression representations. Results: The Additive Ordinal Embedder outperforms alternatives, achieving superior distributional alignment (CMMD 0.4137, recall 0.6331) and disease consistency comparable to real data (Quadratic Weighted Kappa 0.8425, UMAP Silhouette Score 0.0571). The generated sequences exhibit smooth transitions between severity levels while maintaining anatomical fidelity. Conclusions: This work establishes a foundation for transforming static medical datasets into dynamic progression models and demonstrates that ordinal-aware embeddings can effectively capture disease severity relationships, enabling synthesis of underrepresented intermediate stages. These advances support applications in medical education, diagnosis, and synthetic data generation. Full article