Journal of Medical Imaging

ABSTRACT Background: Metallic implants such as orthopedic screws, prostheses, and dental hardware produce beam-hardening, photon-starvation, and streak artifacts that degrade computed tomography (CT) image quality, and the metal artifact reduction (MAR) methods developed to mitigate them require objective, reproducible benchmarking. Purpose: Objective evaluation of MAR algorithms in CT is hindered by the absence of phantoms that simultaneously provide anatomically realistic backgrounds, embedded implants of known geometry, and controllable, ground-truth--referenced artifact intensity. We present a dual-filament, voxel-level three-dimensional (3D) printing method that fulfills these requirements and demonstrate its capabilities on a clinically representative cervical spine case with embedded orthopedic spinal screws. Methods: The proposed method extends the PixelPrint framework, a fused-deposition-modeling (FDM) workflow that converts clinical Digital Imaging and Communications in Medicine (DICOM) data directly into 3D-printer Geometric code (G-code) without intermediate segmentation or surface meshing, to interleaved, voxel-level deposition of two filaments: a calcium-doped polylactic acid (PLA) for soft tissue and bone, and a higher-attenuation metal-doped PLA for metallic implants. For demonstration, anonymized DICOM data of a healthy cervical spine were used to design and fabricate three matched phantoms, each with six embedded spinal screws at C4--C6: a 0% metal-infill ground-truth phantom, a 50% medium-metal-infill phantom, and an 85% high-metal-infill phantom. All phantoms were scanned on a clinical spectral CT system at 120 kVp and 1000 mAs, reconstructed at 0.67 mm slice thickness with virtual monoenergetic imaging (VMI) across 50--190 keV. Method performance was characterized by region of interest (ROI)-based Hounsfield Unit (HU) agreement with the source patient data and by the noise-independent Gumbel-distribution p-index metric. Results: The dual-filament method reproduced patient anatomy, soft-tissue contrast, and screw geometry with high fidelity. ROI HU values agreed with patient data within {+/-}25 HU for soft tissue and trabecular bone; cortical regions were underestimated owing to the current ceiling of the calcium-doped PLA used in this study. The tunable-artifact behavior was quantified as follows: the Gumbel location parameter scaled monotonically from 46.7 HU (no-metal background) to 57.1 HU (50% infill) to 90.5 HU (85% infill) for the VMI 70 keV with standard filter. High-keV VMI reconstructions substantially reduced streak and beam-hardening artifacts while preserving anatomic detail. Conclusions: The proposed dual-filament, voxel-level PixelPrint method enables the fabrication of patient-specific, multi-material CT phantoms with embedded metallic implants and controllable, ground-truth--referenced artifact intensity. Although demonstrated here in a single cervical-spine case, the workflow is anatomy- and implant-agnostic by construction and could in principle be adapted to other musculoskeletal sites (e.g., knee, hip, dental) and implant materials, providing a reproducible methodological foundation for benchmarking MAR algorithms, characterizing spectral CT performance, and validating emerging photon-counting detector systems. Keywords: 3D printing methodology; fused deposition modeling; voxel-level multi-material printing; spectral computed tomography; metal artifact reduction; phantom design; orthopedic implants; dual filament; PixelPrint.

Objectives. Radiomics pipelines extract hundreds of quantitative features that are widely known to be redundant, but the structure of this redundancy is usually treated as a per-dataset nuisance to be pruned away. We tested the alternative hypothesis that a substantial number of feature-feature correlations are universal: they persist across patients and across anatomically distinct structures because they reflect shared mathematical and image-statistical properties of how the image is summarised, rather than properties of the tissue being imaged. Materials and Methods. We re-analysed the publicly available Radiomics Atlas Dataset of normal Abdominal and Pelvic CT (RADAPT), restricting the analysis to the 526 non-contrast-enhanced examinations of the 531-subject atlas and to the 107 original (non-filtered) PyRadiomics features. The 53 segmented structures were grouped into four broad anatomical categories -- bones, muscles, vessels, and parenchymal organs. RADAPT is distributed as one Excel file per structure, with patients as rows and features as columns. Within each structure file we z-score-normalised every feature across patients, computed the absolute Spearman correlation matrix, and retained edges with |{rho}| [≥] {tau} for {tau} in {0.70, 0.80, 0.90}. We then intersected the edge sets across all structure files to obtain a "universal" correlation graph, in which an edge survives only if it exceeds the threshold in every structure (each estimated across the full patient sample). Stable feature communities were defined as the maximal cliques of this graph. Robustness to patient sampling was tested by repeating the entire pipeline on five independent random splits of each file into two patient halves (10 sub-cohorts per threshold), and the implementation was independently reproduced in R. Results. Despite the strictness of the global-intersection criterion, 34, 24, and 14 stable feature communities survived at {tau} = 0.70, 0.80, and 0.90 respectively, with the largest cliques containing six members at {tau} = 0.70 and {tau} = 0.80 and five members at {tau} = 0.90. The community structure was clearly interpretable: separate cliques captured (i) variance-like intensity dispersion, (ii) long-run / low-frequency (coarse) texture, (iii) high gray-level texture, (iv) low gray-level texture, (v) volume and surface shape, and (vi) local-homogeneity and energy/entropy duals. On random-half resampling the exact-match recovery rate of these communities was 81.5 %, 86.7 %, and 80.7 % across the three thresholds; departures from exact recovery were almost always a single boundary feature added or dropped, consistent with finite-sample fluctuation of near-threshold edges rather than structural instability. The R re-implementation reproduced the Python results exactly. Conclusion. A substantial portion of radiomics feature collinearity is universal across patients and tissues. We distinguish two layers within it: trivial near-algebraic duals that are universal by construction, and non-trivial cross-matrix-family communities that are the genuine empirical finding. Together they provide an interpretable, definition-grounded basis for aggressive dimensionality reduction, for retrospectively reconciling apparently different feature selections in the literature, and for moving radiomics pipelines toward organ-agnostic, more reproducible models. Clinical relevance statement. Selecting a single representative feature from each universal community shrinks the original-feature space by roughly an order of magnitude without sacrificing biologically distinct information. For example, the five variance-family members (first-order Variance, GLCM SumSquares, GLCM ClusterTendency, GLDM and GLRLM GrayLevelVariance) can be replaced by a single representative, removing redundant degrees of freedom that would otherwise inflate model variance; and labelling each retained feature by its community lets two studies that selected different variance-family names be recognised as having found the same signal, simplifying model development and improving cross-cohort generalisability in clinical CT workflows.

Pneumonia is a leading cause of infectious disease mortality worldwide, accounting for approximately 2.5 million deaths annually and 15% of deaths in children under five. Chest X-ray imaging remains the primary diagnostic tool, but accurate interpretation requires radiological expertise that is disproportionately concentrated in high-income settings, creating a diagnostic gap where disease burden is highest. Automated deep learning offers a scalable complement to specialist-dependent diagnosis, yet clinical adoption requires both high accuracy and transparent, interpretable reasoning. Convolutional neural networks (CNNs) have shown strong potential for pneumonia detection from chest X-rays, but two barriers impede clinical translation: the interpretability of black-box models and the computational feasibility of large architectures in resource-constrained settings. Explainable AI (XAI) methods such as Grad-CAM, Grad-CAM++, and Score-CAM address the interpretability barrier, yet systematic quantitative comparisons across multiple CNN architectures remain scarce. Furthermore, CNN architectures widely used for medical image classification carry high parameter counts that limit feasibility in resource-constrained settings, motivating architectures that achieve competitive accuracy with substantially fewer parameters. Here we propose a parameter-efficient deep learning framework for pneumonia detection based on transfer learning, evaluated across three CNN architectures representing distinct architectural families: EfficientNet-B0 with fine-tuning (proposed method), ResNet50, and DenseNet121, trained under identical conditions on the Kaggle chest X-ray dataset (5,863 images). Our method achieved 90% classification accuracy, outperforming both baselines while requiring 4.8x fewer parameters than ResNet50. To evaluate explainability, Grad-CAM, Grad-CAM++, and Score-CAM were applied across all three architectures and compared quantitatively using Intersection over Union against manually annotated lung segmentation masks, Insertion score, and Deletion score, with pairwise statistical validation via Wilcoxon signed-rank tests and Bonferroni correction. Findings show that classification accuracy and XAI explanation quality must be evaluated independently, and that the proposed parameter-efficient architecture offers a favorable trade-off for resource-constrained clinical deployment.

This study presents ReCo (Research Cosmos), a self-configuring and self-extending agentic research framework for the biomedical domain. ReCo is orchestrated by a large language model that interacts with native computing tools, bundled Model Context Protocol (MCP) servers, structured skills, persistent project memory, and a desktop interface. Its bundled MCP servers provide biomedical analysis capabilities while serving as implementation paradigms for integrating new computational and AI frameworks. Structured skills encode procedures for environment configuration and framework ingestion, enabling ReCo to inspect repositories, manuscripts, or local codebases; identify dependencies and execution patterns; create isolated runtime environments; design and implement MCP interfaces. Self-extension was evaluated using five heterogeneous systems: the Merlin computed tomography foundation model, MAISI-v2 medical image synthesis framework, asari liquid chromatography-mass spectrometry workflow, DosimeTron agentic radiation-dosimetry platform, and Orthanc DICOM server. ReCo successfully operationalized all five systems and completed predefined functional evaluations. Re-hosted DosimeTron outputs demonstrated near-perfect agreement with the reference pipeline across 651 organ observations (Pearson correlation and Lin concordance correlation coefficient, 0.99999; mean absolute percentage difference, 0.37%). Notably, ReCo configured Orthanc as a PACS-like coordination layer, integrated it with DosimeTron, Merlin, and TotalSegmentator, and orchestrated data retrieval, analysis, and return of valid DICOM RTSTRUCT, RTDOSE, and Structured Report. ReCo provides a unified environment for configuring, documenting, and operationalizing heterogeneous biomedical frameworks, reducing technical barriers to the adoption and integration of emerging computational and AI methods. The official open-source ReCo GitHub repository is available at: https://github.com/eltzanis/ReCo

White matter lesion (WML) identification, assessment, and characterization using magnetic resonance imaging (MRI) are fundamental for diagnosis and monitoring of multiple sclerosis (MS). Portable ultra-low field (pULF) MRI at 64 millitesla (mT) has been shown to visualize WML with at least one dimension greater than 4 mm. An automated WML segmentation tool catered to pULF-MRI can provide standardized and accurate quantitative measurements of WML volume. In this study, we sought to investigate and compare the accuracy of machine-learning (ML) and deep-learning (DL) pULF MRI segmentation tools. Same-day paired pULF (64mT) and high-field (HF, 3T) MRI scans from 84 adults with MS or suspected-MS (mean age {+/-} SD: 48 {+/-} 13, 62 females) included T2-FLAIR and T1w images. Reference WML segmentations were manually annotated on pULF T2-FLAIR for all scans, with WML confirmed with registered HF T2-FLAIR. HF reference WML segmentations were created. Four automated segmentation methods were applied to pULF scans: Method for Inter-Modal Segmentation Analysis (MIMoSA), an ML algorithm trained on HF WML masks; WMH-SynthSeg, a convolutional neural network model with flexible segmentation capabilities across field strengths and resolution; nnU-Net, a DL algorithm trained on pULF reference WML masks; and Pseudo-Label Assisted nnU-Net (PLAn), a DL algorithm pre-trained on HF reference WML masks and refined with 64mT reference WML masks. Two models were trained with nnU-Net, one using T2-FLAIR images only (nnU-Net-FL) and one using T1w and T2-FLAIR images (nnU-Net-FL/T1). The same was done with PLAn, creating PLAn-FL and PLAn-FL/T1. The six automated WML segmentation outputs were compared to the manual segmentations to determine Dice Similarity Coefficient (DSC) scores. Associations of WML volume estimates with clinical measures were investigated. DSC scores with pULF reference WML masks from PLAn-FL (DSC mean {+/-} SD: 0.50 {+/-} 0.24) outperformed MIMoSA (0.24 {+/-} 0.20, p < 0.0001), WMH-SynthSeg (0.30 {+/-} 0.18, p < 0.0001), nnU-Net-FL (0.41 {+/-} 0.24, p < 0.0001), and nnU-Net-FL/T1 (0.41 {+/-} 0.26, p = 0.0004). Worse Expanded Disability Status Scale (EDSS) and Scripps Neurologic Rating Scale (SNRS) scores were correlated with higher WML volumes in the pULF and HF reference masks. They were also correlated with WML volumes derived from WHM-SynthSeg, nnU-Net-FL, nnU-Net-FL/T1, PLAn-FL, and PLAn-FL/T1, but not MIMoSA. After adjusting for age, WHM-SynthSeg, nnU-Net FL, nnU-Net-FL/T1, PLAn-FL, and PLAn-FL/T1 had significant associations with EDSS and SNRS scores. nnU-Net and PLAn performed best in segmenting WML on pULF-MRI at 64 mT, providing accurate quantitative estimates of WML burden. Moreover, WML volumes estimated by these algorithms were associated with clinical measures of disability, underscoring their utility for reflecting clinical and radiological disease severity. Given pULF-MRI's mobility and lower cost, these findings highlight its relevance in clinical trials, particularly in involving more participants who face logistical constraints and barriers.

Purpose: Nonresponse to routinely collected patient-reported outcome measures (PROMs) threatens the representativeness of aggregated data. We characterized patient-, provider-, and clinic-level factors associated with PROMIS Global-10 nonresponse in routine radiation oncology care. Methods: In this retrospective cohort study, all adults seen at five Mass General Brigham radiation oncology clinics over one year were included. The primary outcome was patient-level nonresponse, defined as never completing the portal-administered Global-10 versus completing it at least once. Using iterative mixed-effects logistic regression, we modeled patient-, provider-, and clinic-level factors. Results: Among 12,214 patients, 71 providers, and five clinics, patient- and appointment-level response rates were 35.4% and 10.9%, with patient-level response ranging nearly fivefold across clinics (12.8% to 66.2%). In Model 1, male sex, lower education, not working, and recent surgery had higher odds of nonresponse, and longer time since diagnosis lower odds. After provider- and clinic-level factors were added, patient sex, education, and employment became nonsignificant, whereas recent surgery (adjusted odds ratio [aOR] 1.97) and longer time since diagnosis (aOR 0.46 for >12 months) persisted. A provider's historical collection rate was protective but attenuated at the clinic level. There, a later program launch (aOR 0.29) and higher historical collection rate (aOR 0.79) correlated with lower nonresponse, whereas academic versus community setting did not. Conclusions: Nonresponse to routinely collected PROMs is a multilevel phenomenon driven substantially by clinic-level implementation factors, not patient characteristics alone. Because response rate is only a proxy for representativeness, PROMs programs and PRO-based performance measures should prioritize representative collection over volume.

As machine learning and artificial intelligence systems are increasingly used in healthcare, rigorous evaluation of their classification performance has become critical. The F1 and F{beta} scores are widely adopted metrics for assessing performance in imbalanced biomedical data. Recently, we introduced psF1, a unified statistical framework for inference and study design for single and comparative F1 and F{beta} scores under the assumption of independent classifiers. In practice, however, benchmarking two classifiers on the same dataset creates a correlated paired setting. Ignoring this intrinsic dependency leads to overestimation of the standard error and a substantial loss of statistical power. To address this, we develop psF1pair, an advanced framework for statistical inference and power analysis that explicitly accounts for correlations between classifier pairs. Extensive simulation studies demonstrate the performance of psF1pair, and its utility is further illustrated through application to a real-world imaging classification system. As expected, higher correlation between classifiers yields narrower confidence intervals and enhanced statistical power. A freely available R package is provided to facilitate implementation, supporting accurate evaluation and study design for predictive and classification models in biomedical research.

Purpose: To compare the cross-site generalization of radiomic features and deep learning embeddings for MRI prediction of substantial lymphovascular space invasion (LVSI) in endometrial cancer. Materials and Methods: This retrospective two-center study included 206 women (mean age, 59.8 years) with endometrial cancer who underwent preoperative 3-T MRI from March 2016 to March 2023. Hospital A (n = 130) was used for development and Hospital B (n = 76) for strict external testing. T2-weighted, reduced field-of-view diffusion-weighted, and apparent diffusion coefficient images were manually segmented. Radiomic features and seed-pooled embeddings from 3D ResNet18, DenseNet121, and U-NEXtractor were modeled with elastic-net logistic regression or XGBoost. Out-of-fold Platt calibration and sensitivity-targeted thresholds were estimated using development data only. AUCs were summarized with 95% bootstrap confidence intervals. Results: External radiomics with elastic-net achieved an AUC of 0.609 (95% CI: 0.464, 0.740) and sensitivity of 0 of 12 (0%). DenseNet121 with elastic-net had the highest external AUC (0.685; 95% CI: 0.538, 0.822) but sensitivity of 3 of 12 (25%). U-NEXtractor with elastic-net detected 10 of 12 positive cases (83.3%) with specificity of 32 of 64 (50.0%) and balanced accuracy of 0.667. XGBoost showed higher apparent development performance but weaker external operating behavior. Conclusion: Under real-world cross-site MRI acquisition shift, DenseNet121 and U-NEXtractor embeddings showed better external generalization than handcrafted radiomic features for substantial LVSI prediction.

Purpose: To develop an accelerated motion-compensated diffusion-weighted pseudo-continuous arterial spin labeling (MCDW-pCASL) method using a spatial subspace low-rank reconstruction method for efficient quantification of blood-brain barrier (BBB) water exchange (kw) and permeability (PSw). Methods: An accelerated multidelay MCDW-pCASL sequence was developed to simultaneously encode intravascular and extravascular diffusion-weighted ASL signals across multiple post-labeling delays (PLDs). A spatial subspace low-rank reconstruction framework was optimized to enable joint estimation of cerebral blood flow (CBF) and BBB water exchange rate and permeability. Fourteen young healthy adults underwent test-retest scans (separated by ~1 week) at 3T with both the accelerated MCDW-pCASL and a conventional diffusion-prepared (DP) pCASL sequence. Whole-brain, gray-matter, and white-matter CBF and kw values were quantified to assess test-retest repeatability and cross-method agreement. An additional cohort of 30 older adults underwent single-session MCDW and DP scans to evaluate age-related perfusion and BBB kw/PSw differences. Intraclass correlation coefficients (ICCs) were used to assess reliability and agreement. Results: Accelerated MCDW-pCASL demonstrated excellent agreement with DP-pCASL for CBF (ICC = 0.89) and fair agreement for kw (ICC = 0.56). Test-retest repeatability of MCDW-pCASL was good for CBF, BBB kw and PSw (ICC {approx} 0.6). Across both sequences, younger subjects exhibited significantly higher CBF and kw compared with older adults. Conclusion: Incorporating a spatial low-rank subspace reconstruction enables accelerated MCDW-pCASL acquisition with reliable simultaneous quantification of CBF, BBB kw and PSw. Clinical applications of this method for assessing perfusion and BBB function are warranted.

Minimally invasive endovascular procedures offer reduced surgical trauma, shorter recovery times, and improved outcomes, but rely on 2D fluoroscopic X-ray imaging, which provides limited depth perception and exposes patients and clinicians to ionizing radiation. Here we present an augmented reality (AR) system that fuses intravascular ultrasound (IVUS) and electromagnetic (EM) position tracking with preoperative computed tomography (CT) to produce an anatomically accurate, deformation-corrected navigational reference. A robotic device performs ECG-gated pullback of the IVUS probe, capturing 4D aortic motion across the cardiac cycle. We introduce a deep learning architecture for extracting vascular lumen boundaries and side-branch orifices from artifact-prone IVUS streams, and a semantically driven non-rigid CT-IVUS fusion pipeline robust to false positive landmarks. We evaluate the platform with trained surgeons in benchtop phantom studies and in-vivo ovine models, and demonstrate its application to fenestrated endovascular aneurysm repair (FEVAR). Compared to fluoroscopy alone, AR guidance significantly reduces cannulation time, radiation exposure, and cognitive workload, while improving procedural efficiency and safety. Our IVUS-EM and CT aortic datasets are released open source.

Deep learning classifiers applied to structural MRI (sMRI) have achieved high performance in detecting Alzheimer's Disease (AD), yet systematic investigation of their failure modes remains limited. In this study, we trained two deep learning architectures to classify AD from cognitively normal (CN) participants using sMRI data from the ADNI dataset, and examined whether misclassifications persist across models and training configurations. We identified a subgroup of subjects who were persistently misclassified across 100 model instances, and found that these subjects exhibited a markedly different atrophy subtype distribution compared to correctly classified AD cases, with substantial enrichment of hippocampal-sparing and minimal atrophy subtypes. To disentangle whether persistent false negatives (FN) reflect earlier disease stage or atypically presenting disease, we analyzed longitudinal follow-up scans and tested whether model predictions changed as neurodegeneration progressed. A change in prediction (from FN to true positive (TP)) was observed in only a subgroup of subjects and required intervals of up to five years, suggesting that persistent misclassification may not always be explained by disease staging alone. Although the sample size is small, these findings underscore the importance of accounting for disease heterogeneity in the development and evaluation of clinical AI models for AD detection.

The apnea-hypopnea index (AHI), the conventional metric of obstructive sleep apnea (OSA) severity, is typically studied using scalar summaries of sleep architecture, such as the total time spent in each sleep stage. Although clinically interpretable, these summaries fail to capture the temporal organization of overnight sleep-stage sequences and may obscure stage-specific associations with OSA severity. Modeling the complete sleep-stage trajectory provides substantially richer temporal information; however, because total sleep duration varies across individuals, sleep-stage trajectories are observed over subject-specific domains, limiting the applicability of conventional functional regression methods that assume a common observation interval. We therefore applied Variable-Domain Functional Regression (VDFR) to overnight polysomnographic data from the APPLES study (n= 1,103), treating the epoch-by-epoch sleep-stage sequence as a continuous, variable-length functional predictor of AHI. We compared three levels of sleep-stage granularity: five stages (Wakefulness, N1, N2, N3, REM), three stages (Wakefulness, Non-REM, REM), and binary staging (Wakefulness vs. Sleep). Functional sleep-stage terms were significant across all staging granularities and model structures (all p-values [&le;]0.001). Wake, N1, and N2 were positively associated with AHI, whereas N3 and REM were negatively associated, with REM exhibiting the strongest association. These effects were attenuated under coarser staging representations, highlighting the importance of preserving fine-grained sleep architecture. To our knowledge, this is the first application of VDFR to overnight polysomnographic data in OSA, showing that accommodating subject-specific sleep durations enables the identification of stage-specific temporal associations with AHI severity that are attenuated or obscured by coarser staging and conventional scalar analyses.

Background: Venous thromboembolism (VTE), including deep vein thrombosis (DVT), remains a major global health burden. Diagnostic pathways rely on ultrasound but are limited by availability and prolonged time-to-imaging. Novel artificial intelligence (AI) guidance systems have been designed to enable non-ultrasound-trained operators to acquire proximal lower extremity compression ultrasounds for remote clinician interpretation. Methods: This multicenter, double-blinded, prospective, nonrandomized study evaluated the performance of an AI guidance system (ThinkSono Guidance, ThinkSono, GmbH). Patients underwent AI-guided ultrasound(s) and standard of care ultrasound(s). Primary and secondary endpoints were image quality, sensitivity and specificity for proximal DVT, and prioritization specificity, a measure of specificity in identifying patients requiring standard of care ultrasound after AI-guided scan. Results: Of 634 recruited subjects, 594 were analyzed, with 67 DVTs across 700 scans. 86.83% of AI-guided scans achieved diagnostic image quality. Triage sensitivity was 92.86%, triage specificity 39.12%, prioritization specificity 97.96%. Standard of care ultrasounds could be avoided in 35.32% of patients. Total median AI-guided scan and review time was 7.57 minutes. Conclusions: Clinician-reviewed AI-guided scans were rapid, sensitive for DVT, and specific for prioritizing patients requiring standard of care ultrasounds. These findings suggest AI-guided ultrasound may be a scalable triage strategy to expand DVT evaluation access, particularly in resource-constrained and after-hours settings

We present FootNet, a 453-image multi-view smartphone foot dataset for binary foot segmentation, with expertannotated masks across six anatomical views (dorsal, medial, and plantar, both left and right). We benchmark four segmentation models under a controlled protocol: U-Net with a MobileNetV2 encoder achieves the best performance (IoU 0.9268, Dice 0.9608, 95 % CI [0.9209, 0.9320]); DeepLabV3 with MobileNetV3-Large scores IoU 0.8984 (Dice 0.9449); UNet++ with MobileNetV2 scores IoU 0.8913 (Dice 0.9391); and SAM ViT-B with oracle boundingbox prompt scores IoU 0.9219 on the matched 191-image subset. Bonferroni-corrected Wilcoxon signed-rank tests (k = 6 comparisons) show U-Net significantly outperforms DeepLab (p < 0.001, r = 0.638) and SAM ViT-B with oracle boundingbox (p = 0.005, r = 0.202); UNet++ does not significantly differ from DeepLab (p = 0.062). Connected-component postprocessing yields negligible benefit (mean {triangleup}IoU = +0.0003, 12 of 453 images improved). The extended dataset is available upon request

Background: KRAS mutation status is an important biomarker in rectal cancer, with implications for prognosis and treatment response. MRI-based radiomics has emerged as a non-invasive approach for predicting tumor genotypes. However, the diagnostic performance of MRI radiomics for predicting KRAS mutation status remains unclear. This study aimed to evaluate the diagnostic accuracy of MRI radiomics for predicting KRAS mutations in rectal cancer. Methods: A systematic search of PubMed, Cochrane Library, Scopus, and Web of Science was performed through July 2025. Diagnostic test accuracy studies evaluating MRI-based radiomics or artificial intelligence models for predicting KRAS mutation status in adult patients with rectal cancer were included, using molecular testing as the reference standard. Risk of bias was assessed using the QUADAS-2 tool. Pooled sensitivity and specificity were estimated using a bivariate random-effects model. Results: Seven studies involving 1,224 patients were included. The pooled sensitivity was 0.736 (95% CI: 0.697-0.772) and the pooled specificity was 0.645 (95% CI: 0.586-0.701). The false positive rate was 0.355 (95% CI: 0.299-0.414). The area under the hierarchical summary receiver operating characteristic curve was 0.754, with a normalized partial AUC of 0.666. Between-study heterogeneity ranged from low to moderate depending on the estimation method (I2 = 8.4%-53.3%). Conclusion: MRI radiomics demonstrates moderate diagnostic accuracy for predicting KRAS mutation status in rectal cancer and may serve as a promising non-invasive biomarker for preoperative molecular stratification. Further large-scale studies with external validation are required to confirm its clinical utility.

The aim of this work is to validate patient-specific EEG baseline establishment using the e-norms method as a screening and retrospective-review tool for seizure detection in pediatric epilepsy. The method was applied to 247 seizure-free EEG recordings (263.92 hours) from 10 patients in the CHB-MIT Scalp EEG Database (ages 3-18). A composite stability metric combining first-derivative dynamics, spectral entropy, variance, and line length was computed per 2-second epoch across 23 channels. Patient-specific detection thresholds were derived from each patient's seizure-free baseline using a weighted statistical procedure. Performance was validated against 72 expert-annotated seizures (2,705 epochs) across 62 seizure files, with durations spanning 6 to 264 seconds (44-fold range). The results show that detection achieved 94.4% event-level sensitivity (68 of 72 seizures; 95% CI 86.6-97.8%) and 81.5% epoch-level sensitivity (2,204 of 2,705 epochs; 95% CI 80.0-82.9%). Eight of ten patients achieved 100% event-level sensitivity with epoch-level sensitivity ranging from 58.7% to 100.0%. Two patients showed partial event-level failures (CHB-15: 17 of 20; CHB-18: 5 of 6), with the four missed events attributable to two characterizable failure modes. Patient-specific thresholds ranged from 4.06 to 4.81 (mean 4.51 +/- 0.25); threshold variation did not correlate reliably with age or sex, confirming that no universal threshold could achieve comparable performance. Detection margins ranged from 0.88 to 1.24 times. Patient-specific e-norms achieves 94.4% event-level sensitivity for pediatric EEG seizure detection without requiring labeled seizure training data, exceeding published human expert inter-rater agreement (50-76%) and recent automated approaches in adult cohorts using behind-the-ear EEG and wearable ECG. Two characterizable failure modes account for the four missed events and inform appropriate clinical use. As a high-sensitivity screening tool complementary to real-time alarm systems, the method is ready for adult validation, prospective deployment, and head-to-head benchmarking.

Background: Children born prematurely (before 37 weeks) or admitted to the neonatal unit (NNU) are at increased risk of adverse long-term physical health outcomes. It is also recognised that there is an association with later academic performance and special educational needs, however it is not clear whether these broad risk factors could be used as stand-alone heuristics to identify children who may benefit from additional support in educational settings. We aimed to examine the associations between neonatal unit (NNU) admission and educational attainment in mid-childhood. Methods and Findings: Pregnancy data from a prospective birth cohort (Pregnancy Outcome Prediction Study, Cambridge, United Kingdom, 2008-2012) were linked to national educational outcomes (Department for Education, United Kingdom). Multivariable regression models adjusted for maternal, child, and socioeconomic factors were used to evaluate associations between (i) all NNU admissions, (ii) at term NNU admissions >48 hours, (iii) preterm birth without ongoing physical health needs, and educational outcomes at ages 5-11 years. Children who required any NNU care were more likely not to meet expected educational standards across multiple ages and domains in early and mid-childhood: age 5 early year foundation (aOR 1.64, 95% CI 1.19-2.27, p=0.003), phonics at age 6 (aOR 2.43, 95% CI 1.72-3.57, p<0.001), and at age 7 (here assessments were divided into multiple domains): reading (aOR 1.67, 95% CI 1.18-2.38, p=0.004), writing (aOR 1.72, 95% CI 1.25-2.38, p<0.001), mathematics (aOR 1.56, 95% CI 1.09-2.22, p=0.020), and science (aOR 1.85, 95% CI 1.22-2.78, p=0.003). Similar patterns were observed among both at term-born infants who stayed >48hrs in NNU (phonics assessment at age 6 aOR 2.26, 95% CI 1.51-3.36, p<0.001) and in children born preterm without long-term physical health sequelae (phonics assessment at age 6 aOR 3.07, 95% CI 1.96-4.81, p<0.001). These associations were robust to adjustment for demographic, perinatal, and socio-economic factors. By age 11, differences in academic attainment were attenuated and no longer clearly distinguishable across all exposure groups. However, there was an increased likelihood of special educational needs (SEN) at age 11 associated with any NNU admission (aOR 1.78, 95% CI 1.15-2.73, p=0.009), at term NNU admission for >48hrs (aOR 1.88, 95% CI 1.19-3.00, p=0.007), and children born preterm without long-term physical health sequelae (aOR 1.50, 95% CI 1.00-2.25, p=0.049). Predictive performance of any NNU admission for SEN at age 11 was moderate (AUC 0.70, 95% CI: 1.14-2.65, p=0.010), with balanced sensitivity and specificity and high negative predictive value. Conclusions: NNU admission, for both term and preterm infants, is associated with poorer educational outcomes and an increased likelihood of special educational needs in mid-childhood.

Background and Aims The optimal treatment for first episodes and first recurrences of Clostridioides difficile infections (CDI) is unknown and there is emerging evidence for pulse and taper (P-T) regimens. Therefore, we sought to estimate the relative efficacy of treatment options. Methods MEDLINE and CENTRAL were searched from database inception to May 21, 2025 and unpublished conference abstracts were searched from recent infectious disease conferences. RCTs on the treatment of first episodes or first recurrences of CDI comparing fixed-dose or P-T regimens of fidaxomicin or vancomycin were included. The primary and secondary outcomes were 40- and 56-day CDI recurrence, respectively. A random-effects network meta-analysis on the risk ratio (RR) scale was conducted using a standard regimen (10-14 days) of vancomycin as the comparator. Treatments were ranked using the surface under the cumulative ranking curve (SUCRA). Results 8 RCTs were included comprising a total of 2181 patients. For 40-day recurrence, fidaxomicin P-T had the highest probability of ranking best (RR=0.10, 95%Confidence Interval [95%CI]=0.10-0.49, SUCRA=1.00), followed by vancomycin P-T (RR=0.49, 95%CI=0.32-0.76, SUCRA=0.61), fixed-dose fidaxomicin (RR=0.61, 95%CI=0.49-0.76, SUCRA=0.39), and, finally, fixed-dose of vancomycin (SUCRA=0.00). The treatments ranked in the same order for 56-day recurrence, though only 3 RCTs reported on this timepoint. Conclusion Vancomycin P-T, fidaxomicin P-T, and fixed-dose fidaxomicin were all superior to a fixed-dose vancomycin. Head-to-head comparative effectiveness RCTs are needed to quantify their relative effect sizes of and impact on long-term prevention of recurrent CDI.

Estimating dengue force of infection (FOI) is essential for understanding transmission dynamics and targeting intervention programmes, yet surveillance data in endemic settings required for estimations are often incomplete, with varying formats. We developed a Bayesian hierarchical catalytic model that jointly fits age-stratified case data, aggregate case data, and seroprevalence surveys within a single framework, incorporating external covariates to improve parameter identifiability. Synthetic validation showed that covariates alone recovered accurate FOI point estimates even when most districts contributed only aggregate data, but did so with poorly calibrated uncertainty; anchoring the model with a single seroprevalence survey was necessary to bring credible interval coverage close to nominal. Applied to 128 districts across Java and Bali, Indonesia (2016-2024), the model revealed substantial spatial heterogeneity in FOI and reporting rates. Many districts in Java exceeded the WHO-suggested seroprevalence threshold for vaccine introduction, yet were classified as low-priority when using reported incidence as prioritisation criterion, particularly in areas with weak surveillance. Model-based seroprevalence estimation, integrating multiple data sources, offers a more consistent basis for identifying high-priority districts for vaccine introduction, and is less susceptible to surveillance bias than reported incidence.

Background Post-infection conditions (PICs), such as Long Covid, are associated with heterogeneous, fluctuating symptoms that profoundly affect daily functioning. Despite moderate-certainty evidence from the NIHR-funded LISTEN trial (COV-LT2-0009) that personalised self management support improves outcomes and may reduce societal and economic impacts of Long Covid, many people living with PICs still receive condition-specific services, generic advice, or stand-alone digital tools that do not address their complex needs. Aim To map care approaches in general practice and synthesise UK evidence for PIC management. Design and setting Scoping review and online survey. Method A two-phase study was conducted: (1) a scoping review of UK evidence on PIC management in general practice; and (2) a supplementary online survey of practitioners working in UK general practice to provide contextual insights. Results The scoping review identified 32 studies focused on Long Covid. One study included a comparator group (ME/CFS). Study populations were predominantly white ethnicity and female. Evidence for non-Covid PICs in UK general practice was largely absent. The supplementary survey (n=46) provided preliminary practice-level insights. Healthcare practitioners reported varied PIC presentations, diagnostic uncertainty, limited referral pathways, inequitable access, and low confidence in managing PICs. Conclusion Evidence informing PIC management in UK general practice remains predominantly Long Covid-focused and may not reflect the range of PICs encountered in practice. While survey findings are preliminary and require confirmation in larger samples, they highlight uncertainty around PIC management. Further research is needed to evaluate whether existing Long Covid pathways should be expanded or complemented by broader PIC models. Keywords general practice; Long Covid; self-management; post-viral syndromes