Citations

Abstract Background The left anterior descending (LAD) coronary artery is a critical organ‐at‐risk in thoracic radiotherapy. In thoracic stereotactic body radiation therapy (SBRT), sharp dose gradients and poor LAD contrast on 4DCT scans introduce uncertainty in LAD dose assessment. Methods We evaluated the performance of an AI‐generated LAD region structure as a surrogate for manual LAD contours in early‐stage NSCLC. We used deep inspiration breath hold (DIBH) scans from 49 patients with manually delineated LADs; planning risk volume contours were expanded by 3 mm. Then, 96 lung SBRT dose maps were registered by matching the left anterior portion of the heart contours. Dice similarity coefficient (DSC), inclusion ratios (IR), dose–volume histogram (DVH) metrics, linear regression, and linear mixed models were used to compare the structures. The correlation of the AI LAD region and LAD dose to mean heart dose (MHD) was assessed. Results The AI LAD region showed strong correlation with manual LAD contours for maximum dose (D1%, R 2 = 0.93) and volume receiving ≥10 Gy (V10Gy, R 2 = 0.81). The planning risk volume also demonstrated high correlation to the AI LAD region. MHD was a poor predictor of LAD dose ( R 2 ≈0.4). Additional dose metric correlations were assessed. Discussion To investigate dose volume effects to the LAD during radiotherapy for stage I NSCLC, a robust segmentation paradigm must be established. It must be easily implementable on typical imaging acquired during treatment, with an emphasis on clinical translatability. Our model has shown that the AI LAD region has a strong correlation with LAD dose under typical lung SBRT doses and supports its use for further investigation into LAD dose volume constraints during lung SBRT. Conclusion AI LAD region provides a clinically feasible and scalable alternative to manual LAD contouring for dose estimation in lung SBRT. Its strong correlation with key dose metrics validates its use in large‐scale retrospective and prospective studies.

Importance There is no consensus on staging and surveillance imaging for cutaneous squamous cell carcinoma (CSCC). Although imaging has been shown to affect management, broad recommendations from the National Comprehensive Cancer Network have led to variability in clinical practice. Objective To develop multidisciplinary consensus recommendations on the use of staging and surveillance imaging of localized CSCC. Evidence Review A multidisciplinary expert panel across academic and clinical practice settings convened a Delphi consensus, with 3 iterative survey rounds from January to June 2025. Data were analyzed from February 2025 to January 2026. Eligibility defined by at least 1 to 2 CSCC publications during the previous 5 years, involvement in a relevant clinical trial, experience treating at least 3 patients monthly with CSCC, and/or 5 years or longer of clinical practice. Fifty-four experts were invited and 45 (83%) completed all 3 rounds and were included in the final analysis. Structured Delphi surveys evaluated clinical scenarios, imaging modalities, and surveillance strategies for CSCC. Consensus and near-consensus recommendations were generated, defined as 80% or greater and 70% to 79% agreement, respectively. Findings The 45 participants (21 female individuals [47%] and 24 male individuals [53%]; 14 Asian individuals [31%], 1 multiracial individual [2%], and 30 White individuals [67%]) consisted of dermatology (15 [33%]), medical oncology (7 [16%]), radiation oncology (9 [20%]), radiology (9 [20%]), surgery (3 [7%]), and otolaryngology specialists (2 [4%]). The Delphi panel recommended staging and surveillance for CSCCs with at least a 15% risk of metastasis. Consensus or near consensus was reached to recommend staging and surveillance imaging for tumors with a concern for metastasis, bone invasion, invasion beyond subcutaneous fat, large-caliber nerve invasion, or a diameter of 4 cm or larger or the combination of tumors with poorly differentiated histology and any of the following: diameter of 2 cm or larger, lymphovascular invasion and subcutaneous fat invasion, or lymphovascular invasion and small-caliber perineural invasion. Computed tomography imaging was the preferred modality for nodal staging (38 [84%]) and surveillance (35 [78%]). For surveillance duration, consensus was reached to provide imaging for at least 2 years, and near consensus was reached for at least 3 years. Conclusions and Relevance This study provides an expert consensus–based framework to standardize imaging in localized CSCC that may inform future guidelines.

Abstract Background Multiplexed immunofluorescence (MxIF) enables high-dimensional immune cell phenotyping and detailed characterization of the tumor immune microenvironment (TIME), but complex cyclic staining can introduce signal degradation and uncertainty in cell-level measurements. In routine practice, pathologists rely on hematoxylin and eosin (H&E) staining as the primary reference for tissue morphology and frequently cross-reference H&E to interpret MxIF findings. Methods We present a framework for aligning H&E and MxIF images at the tissue microarray (TMA) core level to support cross-modal analysis. Cell nucleus detections from each modality are used as anchor points, formulating the task as a point-set alignment problem. Coherent Point Drift (CPD) is applied for global alignment, followed by graph-matching–based refinement to improve local consistency. Evaluation on ovarian TMAs demonstrates consistent alignment performance for both restained and serial sections. We further explore the use of restained H&E as a reference for MxIF interpretation and investigate virtual H&E generation from MxIF data as a complementary approach when restained H&E is unavailable. Results The aligned images enable quantitative assessment of cross-modal feature concordance between MxIF-derived measurements and H&E morphology. The generated virtual H&E demonstrated similar cell population compared to the real H&E. Conclusions Cell-centric alignment can facilitate integrative multimodal histopathology analysis for TMA cores in spatial co-localization, cell feature validation, and virtual H&E generation.

Black race and Hispanic ethnicity are associated with higher mortality in severe combined immunodeficiency (SCID) following hematopoietic cell transplantation (HCT), though mechanisms remain unclear. We evaluated 796 children with SCID who received nonsibling HCT between 1982 and 2020 using data from the Primary Immune Deficiency Treatment Consortium. Overall survival for Black (aHR 2.47, 95%CI 1.64, 3.71) and Asian/Pacific Islander patients (aHR 1.82, 95%CI 1.00, 3.30) was significantly lower compared with non-Hispanic White patients, while Hispanic patients had lower event-free survival (aHR 1.83, 95%CI 1.27, 2.63) compared with non-Hispanic White patients. Even after adjusting for age and infection, Black patients with SCID had more than twofold hazard of death compared with non-Hispanic White patients. NBS was associated with earlier diagnosis, reduced infection at HCT, and elimination of survival disparities between Black and non-Hispanic White patients. These findings suggest that universal, system-level interventions such as NBS can mitigate disparities in outcomes for children with SCID.

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.

Background: Integrating machine learning (ML) with population pharmacokinetic (PPK) modeling may improve therapeutic drug monitoring predictions. Methods: Tacrolimus trough concentrations from lung transplant patients were split into a training data set (1151 concentrations in 80 patients) and a testing data set (224 concentrations in 20 patients). A PPK model was developed using NONMEM, followed by the development of 10 ML models to fit individual pharmacokinetic parameters from the PPK model with Bayesian forecasting. The best performing ML model was selected as the final model. Both the final PPK and ML models were compared for prediction performance. A web-based dashboard was established with R-shiny to recommend dosing regimens based on patient data. Results: In the PPK model, postoperative days, hematocrit, aspartate aminotransferase, tacrolimus daily dose, coadministered voriconazole or posaconazole, and the CYP3A5*3 genotype were identified significant covariates on the clearance. The Cubist ML model outperformed the PPK model, showing lower root mean squared error for tacrolimus concentrations in the testing data set. An online web-based precision dosing dashboard was created, accessible at (https://tac-dose-ml.shinyapps.io/shiny/). Conclusions: Integrating ML with PPK modeling could yield superior tacrolimus concentration predictions for lung transplant patients, offering an efficient alternative to Bayesian forecasting. The online dashboard provides rapid, individualized dosing recommendations.

Background Evidence to guide the optimal timing of antiplatelet and oral anticoagulants (OACs) therapy after hemorrhagic infarction (HI) versus parenchymal hematoma (PH) is limited and inconsistent, leading to substantial variation in practice. This study's goal was to study the practice pattern and compare clinical outcomes associated with early‐versus‐delayed initiation of antiplatelet/OACs after hemorrhagic transformation (HT). Methods This multicenter, retrospective, cross‐sectional study included patients with acute ischemic stroke and HT. Patients with an HI or PH were categorized by HT to antithrombotic initiation time, and their outcomes—30‐day HT exacerbation, composite outcomes of recurrent stroke/systemic emboli, 90‐day vascular death, and functional outcomes—were compared. Results Of 748 patients, 496 received antiplatelets, and 252 received OACs after HT. The median HT‐to‐antiplatelet time was significantly shorter after HI than PH (1 [interquartile range, 0–2] versus 3 [interquartile range, 1–5] days; P <0.001). There were no statistically significant differences in HT exacerbation and composite outcomes (30‐day), as well as vascular death and unfavorable functional outcomes (90‐day), between patients who received same‐day, early (HI, <1 day; PH, <3 days), or late (HI, >1 day; PH, >3 days) antiplatelets after either HI or PH. Among patients on OACs, those with HI had shorter median HT‐to‐OAC time than PH (7 [interquartile range, 2–15] versus 15 [interquartile range, 7–32] days; P <0.001). Although HT exacerbation rates (30‐day) were comparable between early (HI, <7 days; PH, <15 days) and late (HI, >7 days; PH, >15 days) OAC initiation after either HI or PH, late initiation after PH was accompanied by higher rates of composite outcomes (30‐day) than early initiation (20.7% versus 3%; P =0.044). Regression models adjusted for demographics, National Institutes of Health Stroke Scale, and stroke severity showed no statistically significant association between early initiation of antiplatelets or OACs with HT exacerbation risk. Conclusions Our study found no statistically significant difference in HT exacerbation between early and late initiation of antiplatelets or OACs among patients with HI/PH, while prolonged delay among patients with PH were accompanied by increased systemic thromboembolic events. Although these findings offer preliminary clinical insight, prospective studies are needed.

SUMMARY This protocol describes a standardized and reproducible minimally invasive approach for establishing mouse models of bisphosphonate-related osteonecrosis of the jaw (BRONJ) and osteoradionecrosis of the jaw (ORNJ). The method combines a unified low-trauma oral surgical procedure with disease-specific injury induction strategies to generate robust and clinically relevant models of jaw osteonecrosis. For BRONJ, systemic zoledronic acid administration is coupled with mandibular first molar extraction using tape-assisted mouth opening and customized bent micro-forceps, minimizing soft tissue damage and reducing procedural variability. For ORNJ, a customized lead-shielding platform enables precise, noninvasive mandible-targeted irradiation, producing reproducible bone injury while limiting off-target radiation exposure. Together, these complementary models provide a consistent and minimally invasive framework for investigating jaw osteonecrosis arising from distinct etiologies. The protocol supports comprehensive downstream analyses, including micro-computed tomography, histology, and immunofluorescence, and facilitates mechanistic studies of disease pathogenesis, bone regeneration, and therapeutic intervention.