Citations

Background/Objectives: To develop and evaluate a deep learning-based quality control system for Lumbar Spinal Digital Radiographs (LSDR), designed to automate and improve their evaluation and reduce reliance on manual reviews. Methods: This retrospective study utilized a deep learning workflow comprising image segmentation, feature extraction, and a classification model. The dataset, including anteroposterior (AP) and lateral (LAT) X-ray images, was expanded through data augmentation techniques. Four U-Net-based models were assessed: standard U-Net, Swin-UNet, Attention U-Net, and Attention U-Net with the weight map, with the latter selected for its superior performance. Extracted features, such as brightness, contrast, and anatomical positioning, were used in an XGBoost classifier, which was evaluated using mean intersection over union (mIoU), accuracy, sensitivity, specificity, and AUC. Results: The Attention U-Net with weighted attention outperformed the other models, achieving high mIoU scores in both AP and LAT views. The XGBoost classifier achieved the best performance in classifying images as “qualified” or “unqualified,” with an AUC of approximately 0.9, high accuracy, and balanced sensitivity and specificity. This approach effectively addressed class imbalances and improved model accuracy compared to traditional machine learning models such as MLP and SVM. Conclusions: The developed automated quality control system demonstrated potential for enhancing image quality, enhancing diagnostic reliability, and optimizing clinical workflow efficiency.

Abstract Unvetted scientific claims about vaccines can spread rapidly and undermine decades of progress in immunization and public trust. A recent non-peer-reviewed analysis, promoted at political hearings, in the documentary “An Inconvenient Study,” and on social media, has been used to suggest that vaccinated children experience higher rates of chronic illness than unvaccinated peers. Despite standard regression models, critical flaws - uncontrolled confounding, exposure misclassification, unequal follow-up, and outcome multiplicity, invalidate causal inference. An independent group of international experts critically appraises this analysis and contrast its claims with the consistent evidence confirming vaccine safety and effectiveness. We also show how poorly designed studies can distort public discourse, amplify misinformation, and fuel vaccine hesitancy. We outline actions to strengthen research integrity, such as transparent data sharing, labeling of non-peer-reviewed content, and evidence-based communication. Safeguarding public health demands that vaccine evidence be methodologically sound, reviewed, and interpreted by qualified experts.

ABSTRACT Introduction Chronic gastroduodenal disorders remain challenging to manage, and new diagnostic approaches are needed to better delineate underlying causes and guide therapeutic decisions. Body Surface Gastric Mapping (BSGM) technologies combine high‐resolution gastric myoelectrical activity measurements with symptom and psychological profiling to provide mechanistic insights into gastric motor and sensory dysfunction. An International Working Group convened to derive the first consensus classification of BSGM phenotypes (the “Auckland Classification”). Methods A Technical Group conducted a systematic literature and clinical database review to identify objective test biomarkers and candidate disease mechanisms. Evidence was synthesized across 50 studies (primarily in gastroparesis, chronic nausea and vomiting, and functional dyspepsia), and BSGM phenotypes were mapped to existing treatment guidelines. Subsequently, iterative review and development of consensus was performed by a Consensus Group composed of international clinical experts familiar with BSGM. Eleven statements underlying the classification were then derived and circulated as a final survey to establish agreement. Results Six BSGM phenotypes were endorsed: three defined by myoelectrical abnormalities (Dysrhythmic, High Frequency, and Low Meal Response) and three by characteristic symptom associations (Sensorimotor, Continuous, and Delayed Onset Symptoms). Published studies plausibly linked these phenotypes to mechanisms including interstitial cell of Cajal depletion, vagal impairment, hypomotility, visceral hypersensitivity, gut‐brain dysregulation, and small bowel dysfunction. Phenotypes were also mapped to existing mechanism‐based treatment guidelines. Ten out of the eleven statements had > 80% agreement. Conclusions The Auckland Classification, derived by international consensus, presents a structured framework for BSGM‐defined patient phenotypes. Evidence and mechanism‐based treatment options are suggested for each phenotype to provide a foundation for research, further validation, and a pathway for integrating BSGM into clinical care.

Objective Data on cardiac index (CI) in patients undergoing coronary angiography (CAG) can enhance decision-making and improve clinical outcomes. However, this necessitates an additional invasive procedure, and therefore, it is frequently omitted. This study explores the novel application of convolutional neural networks (CNNs) to predict CI from routine CAGs. Methods and analysis Patients who underwent CAG and simultaneous right heart catheterisation at Mayo Clinic between 2002 and 2023 were included. A three-dimensional (3D)-CNN model (X3D architecture) was developed to predict binary CI categories (normal: CI≥2.2 vs abnormal: CI<2.2 L/min/m²) from CAG videos. CAGs were randomly split into training (70%), validation (15%) and test (15%) sets. All available videos from each study were entered into the model. The model’s performance was evaluated using the area under the curve (AUC), sensitivity, specificity and F1 score. Results A total of 15 297 CAG studies were considered. After applying a quality-check algorithm to exclude low-quality or irrelevant CAGs, 11 475 studies from 9103 patients were included. CI was abnormal in 25.2% of studies. The model achieved an AUC of 0.83 (95% CI 0.81 to 0.85), sensitivity of 0.72 (95% CI 0.68 to 0.77), specificity of 0.78 (95% CI 0.75 to 0.80) and F1 score of 0.62 (95% CI 0.58 to 0.65) on the test dataset. Limiting the input to 4, 3 or 2 prespecified CAG videos representing standard views did not significantly affect the model’s performance, supporting its applicability in varied clinical workflows. Conclusions This study demonstrates the feasibility of leveraging deep learning models to predict CI from CAG videos. The proposed 3D-CNN model shows promise as a tool for providing physicians with real-time data to aid decision-making during CAG procedures.

Abstract FLASH radiotherapy shows promise in reducing normal tissue toxicity while maintaining tumor control. However, preclinical and early clinical evidence reveal biological and technical uncertainties. We review preclinical and veterinary studies, highlight unexpected toxicities, and argue that the fundamental principles of precision and safety in radiotherapy—particularly conformal treatment and ALARA—remain crucial.

Through a Delphi process, all 33 panelists reached consensus on topics relating to MRI reporting of knee meniscus lesions, demonstrating that interdisciplinary and multi-institutional standardization is possible.

Diffuse large B-cell lymphoma (DLBCL), the most common type of lymphoma, arises from various pathogenic mechanisms including gene translocations and fusions. Detection of gene rearrangements using fluorescence in situ hybridization (FISH) is a standard practice for DLBCL diagnosis and guides treatment decisions. High-throughput chromosome conformation capture (Hi-C) DNA sequencing is a next-generation sequencing-based technology to identify genome-wide rearrangements using a single assay. In this study, Hi-C sequencing was performed using FFPE tissues from 159 patients with DLBCL, and identified 746 cancer genes at or proximal to the rearrangement breakpoints with a total of 1903 occurrences. Focusing on clinically important rearrangements, Hi-C detected 102 rearrangements of MYC, BCL2, and/or BCL6 in 92 patients and revealed the fusion partners, including 25 rearrangements missed by FISH. Causes of FISH negative results included FISH-cryptic breakpoints, complex or faint FISH signals, low percentage of FISH positivity, and issues related to tissue fixation. Moreover, in 20 patients (12.6%), Hi-C sequencing detected 22 rearrangements characteristic of other lymphoma types, including CCND1 rearrangements that could lead to reclassification as mantle cell lymphoma. Survival analysis for genome-wide rearrangements using machine learning models identified MYC, PD-L1, CCND1, BCL2, NTRK1/PRCC, RRAS, and FANCE rearrangements with significant prognostic effects in the DLBCL cohort. In conclusion, Hi-C sequencing detects gene rearrangements crucial for diagnosis in an unbiased and molecular manner and showed high sensitivity and specificity in our study. These advantages of Hi-C sequencing offer help to improve the workflow of clinical pathology laboratories, diagnostic precision, and treatment of large B-cell lymphoma.

Importance Currently, there are no standardized outcome domains or measures in clinical trials for facial aging. Heterogeneity in outcome domains and measurement instruments across clinical trials creates difficulty in directly comparing interventions, determining superior therapies, and developing high-quality meta-analyses. Objective To develop a core outcome set (COS) of essential domains to be reported in clinical trials evaluating the efficacy of interventions for facial aging. Evidence Review PubMed/Medline, Embase, Cochrane Central Register of Controlled Trials, and CINAHL were searched from September 2005 to September 2015. An updated search of the same databases was performed from September 2015 to February 2026. Studies were included if (1) they were randomized clinical trial or controlled clinical trial in design, (2) they assessed the efficacy or safety of an intervention for facial aging, (3) they were published in English, and (4) they involved human participants. Complementary sources, including patient interviews, were used to capture further relevant outcomes. Two rounds of Delphi surveys, followed by consensus meetings, were used to identify outcome domains considered most important by both patient and physician stakeholders. Findings The final COS consists of 6 outcome domains: (1) overall convenience of treatment; (2) time to return to normal work and social activity; (3) overall assessment of focused area of treatment (at the point in time when treatment is expected to provide peak benefit); (4) duration of treatment effect; (5) severity of persistent local or systemic adverse events, including pigmentary change, skin texture change, delayed healing, scarring, and serious adverse events; and (6) patient satisfaction with treatment. Conclusions and Relevance The 6 outcome domains identified through a Delphi consensus are recommended for reporting in future facial aging trials to ensure that outcomes that matter most to patients and clinicians are measured and that results are comparable across interventions.

Objective: To evaluate the institutional learning curve of robotic liver resection (RLR), its association with surgical complexity and outcomes in an international multicenter cohort. Summary of Background Data: RLR is increasingly adopted worldwide, but the dynamics of the learning process and its impact on surgical outcomes remain poorly defined. Methods: This international, multicenter, retrospective cohort study included consecutive patients who underwent RLR between 06/2013 and 12/2024 across 22 expert centers. Based on the first 150 cases at each center, three phases were used to define the learning curve: operative time for competency, major complications for proficiency, and textbook outcome for mastery. Risk-adjusted generalized additive models were used to assess the learning process. Benchmark performance was compared to international reference values. Results: Among 2,331 patients, the most common indications were hepatocellular carcinoma (36%), benign lesions (23%) and colorectal liver metastases (21%). Operative time decreased after achieving competency (case #62), from 240 to 220 minutes ( P <0.001). Major morbidity reached a plateau during the proficiency phase (cases #63–138; 9% vs. 11%, P =0.144), while progression to mastery (cases #139–150) was associated with a higher rate of textbook outcome (76% vs. 87%, P =0.021). In contrast, conversion (5.1% vs. 4.9% vs. 2%), bile leak (4.0% vs. 5.3% vs. 3.8%), and 90-day mortality (0.7% vs. 0.9% vs. 0.9%) remained low and stable across all learning phases. Importantly, benchmark criteria for operative time, hospital stay, and textbook outcome were met across all complexity groups, including during the early learning phase. Conclusions: Robotic liver surgery shows progressive outcome improvement with early achievement of benchmark-level results and stable performance across increasing complexity. These findings indicate that, in experienced centers, RLR can be safely implemented and integrated into clinical practice, supporting its key role in modern hepatobiliary surgery.