Diagnostics最新文献

Background & Aims: The accurate, noninvasive assessment of hepatic steatosis is essential in living liver donor evaluation, where disease prevalence is low, and donor safety is paramount. This study evaluated commonly used noninvasive diagnostic tools for detecting hepatic steatosis in a real-world donor screening setting. Methods: We analyzed 108 living liver donor candidates (18-53 years) with complete MRI, CT, transient elastography (FibroScan^®), and biochemical data obtained during routine donor evaluation. Hepatic steatosis was defined as an MRI-proton density fat fraction (PDFF) ≥5%, which served as the noninvasive reference standard. Diagnostic performance metrics, receiver operating characteristic (ROC) analyses, and correlations with serum fibrosis indices (FIB-4 and APRI) were assessed. Results: MRI-PDFF identified hepatic steatosis in 21 donors (19.4%). Controlled attenuation parameter (CAP), measured by transient elastography, demonstrated high sensitivity (90.5%) and negative predictive value (97.1%), supporting its role as a rule-out screening tool. CT showed excellent specificity (97.7%) but lower sensitivity (61.9%), consistent with a confirmatory role when MRI is unavailable. Serum fibrosis indices were generally low and did not correlate strongly with imaging-based steatosis. Conclusions: In the low-prevalence setting of living liver donor evaluation, CAP-based transient elastography provides effective noninvasive screening for hepatic steatosis, while MRI-PDFF serves as a confirmatory reference when indicated. These findings support a stepwise, clinically practical diagnostic approach that prioritizes donor safety and workflow efficiency.

Background: Occult lymph node metastasis (OLNM) and depth of invasion (DOI) are key determinants of elective neck dissection in clinically node-negative oral tongue squamous cell carcinoma (OTSCC), yet accurate preoperative risk stratification remains challenging. This study evaluated the diagnostic performance of artificial intelligence (AI)-based predictive models for OLNM and DOI in OTSCC. Methods: A systematic review and meta-analysis were conducted in accordance with PRISMA 2020 guidelines. A structured search of PubMed identified twelve eligible studies, nine of which provided extractable 2 × 2 contingency data for inclusion in the primary bivariate meta-analysis. One additional study modeling DOI-derived pT stage was synthesized narratively. Pooled sensitivity and specificity were estimated using a bivariate random-effects model. Heterogeneity, threshold effects, and publication bias (Deeks' test) were assessed. Methodological quality was evaluated using QUADAS-2 supplemented by an AI-specific methodological appraisal. Results: Across nine studies included in the primary meta-analysis, pooled sensitivity was 0.679 (95% CI: 0.604-0.745) and pooled specificity was 0.762 (95% CI: 0.705-0.811), with a summary AUC of 0.786. Heterogeneity was moderate for sensitivity (I² = 41.8%) and low for specificity (I² = 23.4%), with no significant threshold effect (ρ = -0.117, p = 0.776). No significant publication bias was detected (p = 0.596). Subgroup analyses showed comparable performance between OLNM-specific and general LNM models, whereas deep learning or hybrid approaches demonstrated higher accuracy than traditional machine learning methods. Notably, only one out of nine primary studies incorporated true external validation. Conclusions: AI-based models demonstrate moderate discriminative performance for predicting LNM and DOI in OTSCC and may serve as adjunctive tools in preoperative risk stratification rather than standalone decision-makers. However, the near absence of external validation, limited calibration reporting, and lack of clinician-comparator analyses substantially constrain current clinical translation. Future research should prioritize multi-center prospective validation, systematic calibration and decision-curve analyses, and adherence to TRIPOD-AI and CLAIM reporting standards.

Background: Individuals with type 2 diabetes mellitus (T2DM) are at markedly increased risk of developing coronary heart disease (CHD); however, the generalizability and transportability of existing prediction models remain uncertain. Objective: To identify and evaluate multivariable prognostic models developed to predict CHD in adults with T2DM. Methods: We conducted a PRISMA-guided systematic review and meta-analysis of multivariable prognostic models predicting CHD in T2DM populations. Model characteristics and performance metrics were extracted following the CHARMS and TRIPOD-SRMA frameworks, and pooled discrimination was estimated on the logit-transformed AUC scale using a random-effects model (REML, Hartung-Knapp adjustment). Between-study heterogeneity and 95% prediction intervals were quantified, while risk of bias and applicability were assessed using the PROBAST tool. Results: Thirteen studies encompassing clinical, imaging-based, and omics-augmented models met the inclusion criteria. The pooled AUC was 0.69 (95% CI: 0.66-0.71), with high heterogeneity (I² = 97.4%; τ² = 0.0979) and a wide 95% prediction interval (0.54-0.81). Classical regression-based models demonstrated modest discrimination, whereas machine learning, imaging, and proteomic approaches achieved higher AUC estimates but were frequently constrained by small sample sizes, internal-only validation, and poor calibration reporting. The analysis domain emerged as the principal source of bias in PROBAST evaluations, and applicability issues were most frequent in models requiring advanced imaging or molecular platforms. Conclusions: Prognostic models for CHD in T2DM demonstrate moderate-to-good discrimination but substantial heterogeneity and frequent miscalibration across studies. Their clinical utility depends on rigorous external validation and local recalibration, particularly when incorporating imaging or molecular predictors. Future research should prioritize standardized CHD outcomes, consistent calibration reporting, decision-analytic assessments, and the development of transportable multimodal prediction models across diverse populations.

Objectives: To assess the diagnostic accuracy of a deep learning (DL)-based algorithm for non-invasive computation of fractional flow reserve (FFR-CT) from coronary computed tomography angiography (CCTA) and to evaluate the model's ability to automatically assign cardiovascular risk categories according to the Coronary Artery Disease-Reporting and Data System (CAD-RADS). Materials and Methods: Sixty patients with suspected coronary artery disease who underwent both CCTA and invasive coronary angiography (ICA) were retrospectively included in this multicenter study. Curved multiplanar reconstructions derived from CCTA were analyzed by the deep learning-based model to estimate FFR-CT values and to automatically assign CAD-RADS risk categories. The diagnostic performance of the software for the identification of hemodynamically significant coronary stenoses was evaluated using ICA as the reference standard. Receiver operating characteristic (ROC) curve analysis was performed to determine the area under the curve (AUC), sensitivity, and specificity on both a per-patient and per-vessel basis. Finally, agreement between CAD-RADS risk categories assigned by the DL algorithm and those determined by an expert radiologist was assessed. Results: FFR-CT demonstrated high diagnostic accuracy, with AUC of 0.935, sensitivity of 93.2%, specificity of 93.7%, and excellent agreement with reference standard (k = 0.836) on a per-patient level. Per-vessel diagnostic performance was consistently high across all major coronary arteries, with the left anterior descending artery (LAD) showing the highest accuracy (AUC = 0.932). Automated CAD-RADS classifications generated by the software showed good agreement with those assigned by human (k = 0.765). Conclusions: The DL-based model demonstrated high diagnostic accuracy and represents a promising noninvasive approach for ischemia assessment and cardiovascular risk stratification.

Background/objective: Breast density and cancer risk are key imaging-derived biomarkers, yet their assessment is limited by inter-reader variability and inconsistent reproducibility. This Technical Note evaluates the feasibility of a bifurcated neural network designed to simultaneously predict breast density and a composite cancer risk index, providing a methodological foundation for future integration into contrast-enhanced mammography (CEM) workflows.

Materials and methods: A simulated cohort of 1000 patients was generated to reproduce clinically plausible variability in breast density (Densitanum) and cancer risk (RiskEnum). A multi-output neural network was developed and compared with two baselines: multiple linear regression and a single-output multilayer perceptron (MLP). Performance was assessed using R², mean squared error (MSE), and mean absolute error (MAE). Learned trends were examined for consistency with established physiological and epidemiologic patterns.

Results: Linear regression showed limited explanatory power (R² ≈ 0.144). The single-output MLP improved prediction of the cancer risk index (R² = 0.436; MSE = 9.558). The bifurcated neural network achieved MAE values below 4 for both outputs (2.624 for Densitanum; 3.731 for RiskEnum), demonstrating robust performance and the advantage of simultaneous multi-target prediction. The model reproduced clinically coherent patterns, including the expected age-related decline in breast density.

Conclusions: This simulation-based feasibility study demonstrates that bifurcated neural networks can jointly model correlated breast imaging biomarkers with high internal consistency. The proposed architecture provides a reproducible methodological platform that can be directly tested on real CEM datasets to support future AI-enhanced risk stratification and personalized screening pathways.

Background/Objectives: Macular telangiectasia type 2 (MacTel2) is a progressive parafoveal retinal disorder with emerging evidence supporting broader neurodegenerative and metabolic involvement. Given the vulnerability of cochlear structures to systemic and microvascular stressors, this study aimed to investigate whether MacTel2 is associated with measurable auditory dysfunction. Methods: This prospective case-control study included 42 participants: 21 patients with clinically and multimodally confirmed MacTel2 and 21 age- and sex-matched healthy controls. All participants underwent standardized audiological assessment, including tympanometry, conventional and extended high-frequency pure-tone audiometry (0.5-16 kHz), distortion product otoacoustic emissions (DPOAE; 0.5-8 kHz), and click-evoked auditory brainstem response (ABR). Hearing loss was graded using the World Health Organization (WHO) classification based on PTA4 (0.5, 1, 2, and 4 kHz), and a clinically relevant cutoff of PTA4 > 25 dB HL was additionally applied. DPOAE responses were considered absent when the signal-to-noise ratio (SNR) was <6 dB. Results: The MacTel2 and control groups were comparable with respect to age and sex distribution. Patients with MacTel2 demonstrated significantly higher air-conduction thresholds than controls across both conventional and extended high frequencies, with the largest differences observed in the extended high-frequency range (10-16 kHz). PTA4 values were significantly higher in the MacTel2 group in both better- and worse-hearing ears, and the prevalence of clinically relevant hearing loss (PTA4 > 25 dB HL) was significantly greater among MacTel2 patients. DPOAE amplitudes were markedly reduced at all tested frequencies (0.5-8 kHz) in the MacTel2 group, and frequency-specific DPOAE absence/reduction (SNR < 6 dB) was substantially more frequent in MacTel2 than in controls. In contrast, ABR wave I and wave V latencies and the I-V interpeak interval did not differ significantly between groups, suggesting preserved brainstem-level auditory conduction. Within the MacTel2 cohort, no significant correlations were observed between the disease grade and audiological measures. Conclusions: MacTel2 was associated with significantly impaired peripheral auditory function, characterized by elevated conventional and extended high-frequency thresholds and pronounced reductions or the absence of DPOAE responses, while ABR parameters remained comparable to those of controls. These findings support a predominantly cochlear (outer hair cell-related) involvement in MacTel2 and suggest that auditory screening including conventional pure-tone audiometry, with consideration of extended high-frequency audiometry and otoacoustic emissions when feasible, may be clinically relevant in this population.

Background: AchievTing primary fascial closure in complex incisional hernia repair can be challenging when abdominal wall compliance is reduced. Preoperative ultrasound-guided botulinum toxin A (BTA) is used as a chemical component relaxation adjunct, and intraoperative fascial traction (IFT) is a traction-based technique to facilitate medialization. This study assessed the association of adding BTA to a traction-treated cohort. Methods: Retrospective observational analysis of prospectively collected Herniamed Registry data from the Hamburg Hernia Center (1 February 2022-13 October 2025) was conducted. Elective incisional hernia repairs with IFT were included and stratified into BTA + IFT versus IFT-only. The primary outcome was primary fascial closure as documented in the registry. Categorical variables were compared using Fisher's exact test. Results: A total of 81 patients were analyzed (BTA + IFT, n = 64; IFT-only, n = 17). Primary fascial closure was achieved in 51/64 (79.7%) in the BTA + IFT group and 8/17 (47.1%) in the IFT-only group (OR 4.3, 95% CI 1.22-15.84; p = 0.013). Mean operative time was similar (193 vs. 195 min). Mean length of stay was longer in the BTA + IFT group (8 vs. 5 days). Perioperative complications were recorded 8/64 (12.5%) in the BTA + IFT group and 0/17 (0.0%) in the IFT-only group. Conclusions: In traction-assisted incisional hernia repair, adjunctive preoperative ultrasound-guided BTA was associated with higher primary fascial closure rates compared with traction alone. Findings are hypothesis-generating due to non-randomized allocation and baseline differences between cohorts.

Background and Clinical Significance: Traumatic brain injuries (TBI), most frequently caused by falls, represent a major source of morbidity and mortality and pose significant challenges in forensic investigations, especially when events are unwitnessed or testimonies conflict. Despite advances in imaging and autopsy, reconstructing the mechanism of head trauma often remains impossible. The objective of this study is to assess how biomechanical modeling can support forensic practitioners by narrowing the range of plausible scenarios and strengthening evidence-based interpretation in complex medico-legal contexts, without seeking to establish legal causality or certainty. Case Presentation: This case report investigates forensic biomechanics as a decision-support tool using a combined multibody and finite element (FE) modeling approach. An initial set of twenty-five scenarios, derived from witness statements and investigative data, was reconstructed to simulate potential fall- and assault-related mechanisms. Multibody simulations with the human facet model were first performed to estimate head impact velocities and orientations. These parameters were then applied to an FE head model to evaluate tissue response. Conclusions: Skull fracture patterns and intracerebral von Mises stress distributions were analyzed and systematically compared with clinical, radiological, and autopsy findings. Although simulated stress magnitudes were generally lower than injury thresholds reported in the literature, several scenarios reproduced fracture propagation and intracerebral stress patterns consistent with the documented lesions, including corpus callosum involvement. This multidisciplinary approach highlights the growing role of biomechanics in forensic investigations and forensic anthropology.

Background: Alzheimer's disease is the most common type of dementia and a progressive neurodegenerative disease that begins with neuronal damage and leads to a reduction in brain tissue. Currently, there is no cure for this disease, and existing approaches focus on alleviating symptoms. Methods: This study proposes NeuroFusion-ViT, a highly accurate and computationally efficient hybrid deep learning model for early-stage detection of Alzheimer's disease. The model combines an EVA-02-based Vision Transformer (ViT) with the ConvNeXt-Small CNN architecture, providing powerful representation learning that can process both global context and local details. The proposed Gated Cross-Attention Fusion (G-CAF) mechanism dynamically combines two different features, offering high discriminative power and model stability. Results: In experiments conducted on the OASIS MRI dataset, the model achieved 99.86% accuracy, 0.9989 Macro F1, and 0.999 ROC-AUC values, demonstrating clear superiority over single-modal and hybrid models described in the literature. Furthermore, 5-fold cross-validation results also support the model's high generalizability. Ablation studies showed that each of the components-cross-attention, gate mechanism, Dual LayerNorm, and FFN-Dropout-made a meaningful contribution to performance. Conclusions: The results demonstrate that the NeuroFusion-ViT architecture offers a reliable, stable, and clinically applicable solution for Alzheimer's stage classification.

Background and Aims: Neurovascular abnormalities, such as aberrant nerve migration in Hirschsprung's disease and reduced vascular density in necrotizing enterocolitis, are frequently observed in intestinal diseases. Traditional 2-dimensional (2D) staining methods are complicated, time-consuming and fail to comprehensively visualize the intricate neurovascular structures and morphology of the intestine. This study focuses on evaluating a novel 3D staining technique that promises simpler, faster, and more effective visualization of intact neurovascular structures in the colon. Additionally, it aims to compare the strengths and limitations of this 3D method against traditional 2D techniques for analyzing neuronal and vascular changes in two prevalent pathological conditions. Methods: A novel tissue-clearing approach was used to render mouse and patient distal colon tissues transparent. Neural structures and blood vessels were stained. 2D and 3D imaging were performed with laser confocal or tiling light sheet microscopy. Parameters include total imaging time, imaging range, image quality, operational complexity, and post-processing were compared between 2D and 3D methods. Results: Compared to 2D imaging, 3D imaging reveals the complete morphology and trajectory of neurovascular structures. Confocal 3D imaging offers superior clarity, higher transparency, and faster workflow efficiency, whereas light-sheet microscopy provides broader coverage at the expense of lower image quality. Post-processing facilitated spatial modeling and quantitative analyses. Applications included Hirschsprung's disease, where 3D imaging revealed abnormal nerve distribution, and congenital heart disease, where hypoperfusion impacted vascular development in the colon. Conclusions: Confocal 3D staining and imaging offered a more streamlined workflow and enabled comprehensive visualization of neurovascular architecture, supporting efficient assessment of intestinal neurovascular phenotypic features.