Developmental Biology

How embryonic cells generate large clones of cells in the adult represents a fundamental question in biology. Here, using melanocyte stem cells (McSCs) in the zebrafish as a model, we explore the function of the master melanocyte transcription factor (MITF) in safeguarding McSCs in embryonic development and their potential to pigment large clones in the adult. MITF is well known is for its role in the specification of melanoblasts from the neural crest (NC) and their differentiation into melanocytes, yet little is known about how this activity shapes the stem cell lineages. Here, we use live imaging coupled with single-cell transcriptomics and lineage tracing to show that MITF (mitfa in zebrafish) protects the melanocyte stem cell (McSC) fate in zebrafish. Utilizing a temperature sensitive mitfavc7 mutant, we show loss of Mitfa leads to a surprising premature and aberrant expansion of McSC progeny at the niche during embryogenesis, coupled with novel emergent transcriptional cell states. Linage tracing of McSCs from the embryonic to juvenile stages reveals Mitfa activity is subsequently required in regeneration by Schwann cell-like and melanocyte stem cell progenitors that serve as a reservoir for fast-responding pigment progenitors. Thus, the impact of Mitfa loss on the melanocyte lineage is cell-state and stage-specific. The emergent cell states upon mitfa loss may have important implications for our understanding the loss of MITF activity in human genetic disease and melanoma.

Improving diversity in U.S. Alzheimers disease (AD) research is a pressing need. By 2050, Hispanic and Latino Americans will comprise 30% of the population. Hispanics are 1.5 times more likely and Blacks are twice as likely to develop AD compared to Whites, yet both remain vastly underrepresented in clinical trials research. Aging and AD research mentorship of underrepresented STEM undergraduates is designed to promote entry into related professions by students committed to decreasing disparities in AD research participation and clinical care. The NIA-funded MADURA program recruited 93 students from backgrounds historically underrepresented in STEM majors and/or from NIH-defined disadvantaged backgrounds. Trainees were placed in aging/AD research labs and received weekly training and mentorship from faculty research PIs and other types of supervisors (postdoctoral researchers, graduate students, research assistant staff...) Our study examined student ratings of the program and mentor behaviors, using a program-specific survey and the Mentoring Competency Assessment-21 (MCA-21). Trainees were highly satisfied with both mentoring relationships and the overall program. Student rated MCA-21 competency areas were quite high for both P.I.s and other types of research mentors. However, there were striking differences in associations between competencies and relationship and program satisfaction, by mentor type. For PI mentors, no MCA-21 competencies were associated with relationship satisfaction, but five of six competencies were associated with relationship satisfaction for other mentor types. Similarly, no PI mentor competencies were significantly correlated with overall placement satisfaction, but all six competencies were correlated with overall placement satisfaction for other mentor types. The authors discuss the likelihood of differing student expectations of faculty PI versus other types of research mentors, recommendations for assessing role-specific student expectations (including functions primarily possible only for senior faculty PIs), and utilizing nearer-peer plus PI faculty mentors to comprehensively address the gamut of mentee needs.

Purpose: Alpha-gal syndrome (AGS) is an emerging health issue. This syndrome, caused by the bites of ticks, induces allergic reactions to the sugar molecule galactose-alpha-1,3-galactose after exposure to non-primate mammalian meat and other byproducts. Agricultural workers spend significant time outdoors placing them at an increased risk for tick bites and tick-borne diseases, like AGS. This study aimed to characterize farmers and ranchers' prior knowledge, symptomology, and diagnostic experiences with AGS. Methods: We conducted a cross-sectional survey of more than 200 farmers and ranchers with a self-reported AGS diagnosis. The survey captured farmers and ranchers' experiences related to prior knowledge and experience with tick bites and AGS, reported symptoms, and obtaining a diagnosis. Findings: A total of 201 respondents across 26 states participated in the survey, with the majority from Missouri and Oklahoma. We identified four distinct symptom clusters, with the most reported symptoms being abdominal cramping, diarrhea, itchy skin, and nausea. Women more often reported gastrointestinal discomfort, and men were more likely to be in the mild symptom category. On average, participants reported 2.98 medical provider visits before receiving a diagnosis, most being diagnosed by general practitioners and allergists. Conclusions: No previous studies have focused on the symptom and diagnostic experiences of farmers and ranchers with AGS. Capturing such data is essential as these workers may experience unique occupational challenges following AGS diagnosis. The diagnostic experience data support a continuing need to educate and empower AGS patients and providers, especially agricultural workers and providers serving rural communities.

Fluorescent in situ hybridization (FISH) enables highly sensitive, high-resolution detection of gene transcripts. Moreover, by employing multiple probes, this technique allows for multiplexed, simultaneous detection of distinct gene expression patterns spatiotemporally, making it a valuable spatial transcriptomics approach. Owing to these advantages, FISH techniques are rapidly being adopted across diverse areas of basic biology. However, conventional protocols often rely on volatile, toxic reagents such as formalin or methanol, posing potential health risks to researchers. Here, we present a safer protocol that replaces these chemicals with low-toxicity alternatives, without compromising the high detection sensitivity of FISH. We validated this protocol using both in situ hybridization chain reaction (HCR) and signal amplification by exchange reaction (SABER)-FISH in frozen sections of various model organisms, including mouse (Mus musculus), amphibians (Xenopus laevis and Pleurodeles waltl), and medaka (Oryzias latipes). Our results demonstrate successful multiplexed detection of morphogenetic and cell-type marker genes in these model animals using this safer protocol. The protocol has the additional advantage of requiring no proteolytic enzyme treatment, thus preserving tissue integrity. Furthermore, we show that this protocol is fully compatible with EGFP immunostaining, allowing for the simultaneous detection of mRNAs and reporter proteins in transgenic animals. This protocol retains the benefits of highly sensitive, multiplexed, and multimodal detection afforded by integrating in situ HCR and SABER-FISH with immunohistochemistry, while providing a safer option for researchers, thereby offering a valuable tool for basic biology.

BackgroundArtificial intelligence and machine learning (AI/ML) are among the fastest-growing domains in NIH research funding, but whether children have shared equitably in this expansion is unknown. We characterized pediatric representation in NIH AI/ML funding from fiscal years (FY) 2020 to 2024. MethodsNIH grant data were obtained from Research Portfolio Online Reporting Tools Expenditures and Results bulk files for FY2020 to FY2024. AI/ML grants were identified using the NIH Research, Condition, and Disease Categorization "Machine Learning and Artificial Intelligence" category, and pediatric grants using the "Pediatric" category. Subprojects were excluded. Grants were deduplicated within each fiscal year by core project number for trend analyses and across all years retaining the most recent fiscal year for cross-sectional totals. Disease areas were identified by keyword searches of titles and abstracts. ResultsAcross FY2020 to FY2024, 5,624 unique NIH AI/ML grants totaling $3,371 million were identified. Of these, 836 grants (14.9%) were classified as pediatric, representing $401 million (11.9%) of total NIH AI/ML funding. Although this share was consistent with the historically reported overall NIH pediatric funding baseline of approximately 10% to 12%, it remained substantially below the US pediatric population share of approximately 22%. The pediatric share of NIH AI/ML funding declined from 12.3% in FY2020 to 10.8% in FY2024, despite growth in absolute pediatric funding. Indexed to FY2020, pediatric AI/ML funding grew approximately 2.6-fold compared with 3.0-fold growth in the total portfolio. Across disease areas, unadjusted adult/general-to-pediatric funding ratios ranged from 2.0-fold in mental health to 9.8-fold in cancer. ConclusionsPediatric representation in NIH AI/ML funding remained low and declined over time as the overall portfolio expanded. These findings suggest that growth in NIH AI/ML investment has not been matched by proportional gains for pediatric research.

Introduction: Solitary plasmacytomas (SP) are rare neoplasm of localised proliferation of clonal plasma cells. It can be classified based on site of involvement and bone marrow involvement. It is an indolent disease in the majority of patients. Primary modality of treatment is radiotherapy and surgical excision. Materials and methods: This was a retrospective audit of SP who were treated and followed up at a tertiary care center in eastern India from January 2012 to December 2025. Patients who has solitary plasma cytoma with more than 10% plasma cells, POEMS syndrome, have been excluded from analysis. Results: We identified 46 patients of SP. The median age of the studied population was 53 years (23-75 years). Males were more commonly affected than females (M:F=2.2:1). Most common chief complaints were bony pain (67.4%). SBP was seen in 39 (84.8%) cases whereas SEP was seen in 7 (15.2%) cases. Vertebra was the most common site of involvement (61.4%). Median M band concentration 0.24 g/dL (0.1 to 1.95 gm/dL). IgG was the most common isotype accounting for 60.6% cases. Six cases (13%) had minimal bone marrow involvement. The majority of the patients received local radiotherapy (89.1%). With a median follow up of 5.4 years (95% CI: 1.8 - 9.0), median OS was not reached, median PFS was 9.22 years (95% CI: 5.8-12.6), median time to next treatment (TTNT) was 9.86 years (95% CI: 6.8 - 12.9). Conclusion: Solitary plasmacytoma commonly affects young males. Bones are more commonly affected than extramedullary sites. SP has a lower rate of progression and excellent prognosis when treated with local radiotherapy.

Background: To investigate the safety and efficacy of CTguided lung nodule localization needles for the preoperative localization of small pulmonary nodules. Methods: A retrospective study was conducted on 102 patients with a total of 113 small pulmonary nodules who underwent preoperative localization at Jinan Fourth People's Hospital from January 2024 to December 2025. Nodule diameter and depth, localization time, the number of pleural punctures, the localization success rate, and postoperative complications (hook dislodgement, hemorrhage, and pneumothorax) were recorded. All patients underwent video assisted thoracoscopic surgery (VATS) after localization. Results: The mean nodule diameter was 0.97{+/-}0.36 cm, the mean depth was 1.26{+/-}0.48 cm, and the mean localization time was 9.8{+/-}3.65 minutes. The hook dislodgement rate was 0.98% (1/102), the intrapulmonary hemorrhage rate was 14.71% (15/102), and the pneumothorax rate was 16.67% (17/102). All pulmonary nodules were successfully resected by VATS at 73.82{+/-}13.83 minutes after localization, and no severe complications occurred. Conclusions: The use of a CTguided lung nodule localization needle for the preoperative localization of small pulmonary nodules decreases the time needed for intraoperative nodule detection and operation time. This strategy is a simple, safe, and accurate preoperative localization method that is worthy of increased clinical use.

Objectives: For suspected hip fractures, prehospital protocols directing patients to an orthopaedic centre rather than the nearest emergency department (ED) could reduce time-to-surgery but may impact EMS travel burden. This study evaluates the impact of transfer protocols by quantifying transport to hospitals from long term care (LTC) facilities across Ontario. Methods: A retrospective cross-sectional analysis of all Ontario LTC facilities and hospitals was performed. Two protocols were modeled: standard transfer to the nearest ED with subsequent transfer if required, and selective transfer based on Collingwood Hip Fracture Rule prehospital screening1 directly to the nearest orthopaedic services (orthoED). Median one-way travel distances were calculated from Google Maps. Results: In Ontario, 15.4% of LTC residents require hospital destination decisions because their nearest ED lacks orthopaedic services; for these facilities, median distances were 2.7km to the ED and 36.0km to the orthoED. Among the 52 LTC facilities where selective transfer was distance-optimal, it substantially reduced travel for patients with hip fracture (31.1km vs 49.6km; P<.01) while only modestly increasing travel for patients without hip fracture. Where standard transfer was distance-optimal, little travel difference was noted for patients with hip fracture, however false positive screened patients traveled significantly further to an orthoED. Greatest negative consequences of selective transfer lie in the 1.3% of residents living farthest (>100km) from an orthoED. Conclusions: EMS direct transportation to hospitals with orthopaedics may improve hip fracture care but can increase EMS burden due to patients identified falsely as having a hip fracture, particularly in remote communities.

Background: Large Language Models (LLMs) have demonstrated strong performance in medical question-answering tasks, highlighting their potential for clinical decision support and medical education. However, their effectiveness in subspecialty areas such as nephrology remains underexplored. In this study, we assess the performance of open-source LLMs in answering multiple-choice questions from the Nephrology Self-Assessment Program (NephSAP) to better understand their capabilities and limitations within this specialized clinical domain. Methods: We evaluated the performance of five open-source large language models (LLMs): PodGPT which a podcast-pretrained model focused on STEMM disciplines, Llama 3.2-11B, Mistral-7B-Instruct-v0.2, Falcon3-10B-Instruct, and Gemma-2-9B-it. Each model was tested on its ability to answer multiple-choice questions derived from the NephSAP. Model performance was quantified using accuracy, defined as the proportion of correctly answered questions. In addition, the quality of the models explanatory responses was assessed using several natural language processing (NLP) metrics: Bilingual Evaluation Understudy (BLEU), Word Error Rate (WER), cosine similarity, and Flesch-Kincaid Grade Level (FKGL). For qualitative analysis, three board-certified nephrologists reviewed 40 randomly selected model responses to identify factual and clinical reasoning errors, with performance summarized as average error ratios based on the proportion of error-associated words per response. Results: Among the evaluated models, PodGPT achieved the highest accuracy (64.77%), whereas Llama showed the lowest performance with an accuracy of 45.08%. Qualitative analysis showed that PodGPT had the lowest factual error rate (0.017), while Llama and Falcon achieved the lowest reasoning error rates (0.038). Conclusions: This study highlights the importance of STEMM-based training to enhance the reasoning capabilities and reliability of LLMs in clinical contexts, supporting the development of more effective AI-driven decision-support tools in nephrology and other medical specialties.

Military aviation training noise remains understudied despite its widespread impacts across urban, rural, and wilderness areas. The predominance of low-frequency noise and repetitive training can create pervasive noise pollution, yet past research often fails to capture the full range of health and quality-of-life effects. This study analyzed two complaint datasets related to Whidbey Island Naval Air Station noise: U.S. Navy records (2017-2020) and Quiet Skies Over San Juan County data (2021-2023). We analyzed and mapped sentiment intensity from noise complaints relative to modeled annual noise exposure, developed a typology to classify impacts, and modeled the environmental and operational factors influencing complaints. Findings revealed widespread negative sentiment and anger, often beyond the bounds of estimated noise contours, suggesting that annual cumulative noise models inadequately estimate community impacts. Complaints consistently highlighted sleep disturbance, hearing and health concerns, and compromised home environments due to shaking, vibration, and disruption of daily life. Residents also reported significant social, recreational, and work disruptions, along with feelings of fear, helplessness, and concern for children's well-being. The number of complaints were strongly associated with training schedules, with late-night sessions being the strongest predictor. A delayed response pattern suggests residents reach a frustration threshold before filing complaints. Overall, our findings demonstrate persistent negative sentiment and diverse impacts from military aviation noise. Results highlight the need for improved noise metrics, modeling and operational adjustments to mitigate the most disruptive effects.

Background and Objectives: We report the first intraoperative deployment of a real-time machine vision system in neurosurgery, derived from our previous anatomical detection work, automatically identifying structures during endoscopic endonasal surgery. Existing systems demonstrate promising performance in offline anatomical recognition, yet so far none have been implemented during live operations. Methods: A real-time anatomy detection model was trained using the YOLOv8 architecture (Ultralytics). Following training completion in the PyTorch environment, the model was exported to ONNX format and further optimized using the NVIDIA TensorRT engine. Deployment was carried out using the NVIDIA Holoscan SDK, the system ran on an NVIDIA Clara AGX developer kit. We used the model for real-time recognition of intraoperative anatomical structures and compared it with the same video labelled manually as reference. Model performance was reported using the average precision at an intersection-over-union threshold of 0.5 (AP50). Furthermore, end-to-end delay from frame acquisition to the display of the annotated output was measured. Results: A mean AP50 of 0.56 was achieved. The model demonstrated reliable detection of the most relevant landmarks in the transsphenoidal corridor. The mean end-to-end latency of the model was 47.81 ms (median 46.57 ms). Conclusion: For the first time, we demonstrate that clinical-grade, real-time machine-vision assistance during neurosurgery is feasible and can provide continuous, automated anatomical guidance from the surgical field. This approach may enhance intraoperative orientation, reduce cognitive load, and offer a powerful tool for surgical training. These findings represent an initial step toward integrating real-time AI support into routine neurosurgical workflows.

Computer vision and deep learning techniques, including convolutional neural networks (CNNs) and transformers, have increased the performance of medical image classification systems. However, training deep learning models using medical images is a challenging task that necessitates a substantial amount of annotated data. In this paper, we implement data augmentation strategies to tackle dataset imbalance in the VinDr-SpineXR dataset, which has a lower number of spine abnormality X-ray images compared to normal spine X-ray images. Geometric transformations and synthetic image generation using Generative Adversarial Networks are explored and applied to the abnormal classes of the dataset, and classifier performance is validated using VGG-16 and InceptionNet to identify the most effective augmentation technique. Additionally, we introduce a hybrid augmentation technique that addresses class imbalance, reduces computational overhead relative to a GAN-only approach, and achieves ~99% validation accuracy with both classifiers across all three case studies. Keywords: Data augmentation, Generative Adversarial Network, VGG-16, InceptionNet, Class imbalance, Computer vision, Spine X-ray, Radiology.

Background: Placental function is associated with congenital heart defects (CHD), frequently presenting with malperfusion lesions and small-for-gestational-age size. However, placental villous vasculature in the setting of CHD is understudied. This study evaluated differences in placental, neonatal, and maternal outcomes among maternal/infant dyads with versus without CHD. Methods: We conducted a gestational age- and fetal sex-matched retrospective case control study using specimens prospectively collected by a local biobank. Neonatal outcomes included birthweight, placental weight, and their ratio (placental efficiency). We estimated the proportion of placental villous tissue comprised of fetal vascular endothelial cells (%FVE) using anti-CD34 immunohistochemistry and a pixel count algorithm. Placental weight multiplied by %FVE estimated the grams of placental tissue comprised of villous vasculature (placental vascular index). Maternal outcomes included hypertensive disorders of pregnancy and gestational diabetes. We compared cases and controls using linear and logistic regression adjusted for maternal smoking and cold ischemia time. Stratified analyses examined associations by preterm birth status. Results: Dyads (n=34 with CHD, n=34 without CHD) had maternal age of 29.4 +/- 4.9 years and were 35.6 +/- 4.0 gestational weeks at delivery. Groups had similar placental, neonatal, and maternal parameters. Among preterm neonates, we observed small-to-moderate effect sizes indicating lower placental weight, %FVE, and placental vascular index, and higher placental efficiency, in CHD cases. Among term neonates, moderate effect sizes suggested lower birthweight, placental weight, and placental vascular index in CHD cases. Conclusions: Though differences between groups were not significant, moderate effect sizes suggested that placental vascularization was lower among preterm neonates with CHD.

IntroductionComparison of rectal cancer characteristics in Pakistani Americans and native Pakistanis remains poorly investigated, as migrant studies have predominantly concentrated on East and Southeast Asian groups. This research aims to compare clinicopathological characteristics between the two groups. We hypothesize that significant differences will exist between these cohorts, mediated by gene-environment interactions. MethodsThis was a retrospective cohort study utilizing two multi-institutional databases to identify adult patients with rectal cancer: the National Cancer Database in the U.S (2018-2022) and the Rectal Cancer Surgery and Epidemiology Study in Pakistan (2020-2021). Non-Hispanic Whites (NHWs) were included as a reference population for comparative analysis. Clinicopathological characteristics were compared using Wilcoxon rank-sum and chi-square tests. ResultsA total of 523 Pakistani Americans and 608 native Pakistanis were included in the study. The median age at diagnosis was 57 years in Pakistani Americans (IQR 48-68), 42 years (IQR 33-54) in native Pakistanis and 63 years in NHWs (IQR 54-73) (p < 0.001). Native Pakistanis presented with early-stage disease less often than Pakistani Americans and NHWs (5.3%, 25.1%, and 20.5%, respectively; p < 0.001) and had markedly higher rates of signet cell carcinoma (20.1%, 0.6%, and 0.4%, respectively; p < 0.001) and poorly differentiated tumors (29.0%, 10.4%, and 11.4%, respectively; p < 0.001). ConclusionsThis study found that Native Pakistanis with rectal cancer presented at a younger age and with more aggressive tumor characteristics compared to both Pakistani Americans and NHWs. Notably, Pakistani Americans displayed a distinct clinical profile, intermediate between both groups.

BackgroundDental caries and periodontal disease represent the most prevalent global oral health conditions, collectively affecting several billion people. The diagnostic interpretation of dental radiographs, a cornerstone of modern dentistry, is associated with considerable inter-observer variability. In routine clinical practice, clinicians are required to evaluate a high volume of radiographic images daily, a cognitively demanding task in which diagnostic fatigue, time constraints, and the inherent complexity of overlapping anatomical structures can lead to the inadvertent oversight of early-stage pathologies. Artificial intelligence (AI) offers a transformative opportunity to augment clinical decision-making by providing rapid, objective, and consistent radiographic analysis, thereby serving as a tireless adjunct capable of flagging findings that may be missed during routine human inspection. MethodsThis study developed and validated a deep learning system for the automated detection of dental caries and alveolar bone loss using a dataset of 1,063 periapical and bitewing radiographs. Two separate YOLOv8s object detection models were trained and evaluated using a rigorous 5-fold cross-validation methodology. To align with the clinical use-case of a screening tool where high sensitivity is paramount, a custom image-level evaluation criterion was employed: a true positive was recorded if any predicted bounding box had a Jaccard Index (IoU) > 0 with any ground truth annotation. Model performance was systematically evaluated at confidence thresholds of 0.10 and 0.05. ResultsAt a confidence threshold of 0.05, the caries detection model achieved a mean precision of 84.41% ({+/-}0.72%), recall of 85.97% ({+/-}4.72%), and an F1-score of 85.13% ({+/-}2.61%). The alveolar bone loss model demonstrated exceptionally high performance, with a mean precision of 95.47% ({+/-}0.94%), recall of 98.60% ({+/-}0.49%), and an F1-score of 97.00% ({+/-}0.46%). ConclusionThe YOLOv8-based models demonstrated high accuracy and high sensitivity for detecting dental caries and alveolar bone loss on periapical radiographs. The system shows significant potential as a reliable automated assistant for dental practitioners, helping to improve diagnostic consistency, reduce the risk of missed pathology, and ultimately enhance the standard of patient care.

Autosomal dominant polycystic liver disease (ADPLD) commonly results from a pathogenic variant in one of 6 genes (GANAB, ALG8, LRP5, PRKCSH, SEC61B, SEC63). Pathogenic variants in these genes are also associated with kidney cysts, which rarely cause kidney failure, but the genes are included in cystic kidney panels. This study determined the population frequency of predicted pathogenic variants in the ADPLD genes in the general population. Variants for each gene were downloaded from gnomAD and annotated with ANNOVAR. The population frequencies were calculated from the number of people with "predicted pathogenic" variants in gnomAD v.2.1.1:loss-of-function structural and copy number; null; and rare, computationally-damaging missense changes that affected a conserved residue. Frequencies were also estimated from the number of gnomADv.4.1 variants assessed as Pathogenic or Likely pathogenic in ClinVar. Predicted pathogenic variants affected one in 95 people using our strategy and gnomAD v.2.1.1, and one in 151 with ClinVar assessments of gnomAD v.4.1 variants. LRP5 and ALG8 which are associated with a milder clinical phenotype, were the commonest affected genes with both strategies. Predicted pathogenic variants in ADPLD appear more frequent in admixed American (one in 100), Finnish (one in 107) and African/African American (one in 130) people (p all <0.0001 compared with Europeans (one in 197).Predicted pathogenic variants for ADPLD may be even more common because of additional unidentified causative genes. However not all ADPLD variants result in liver cysts, nor indeed cystic kidneys, because of incomplete penetrance and variable expressivity.

Patients who participate in intracranial neuroscience research make invaluable contributions to our understanding of the brain, accelerating the development of neurotechnological interventions. Engagement of patients as part of this research presents unique challenges, where study goals can be distant from immediate clinical applications and require specialized domain knowledge. Yet methods for meaningfully integrating patient communities as part of these research efforts is essential, as intracranial neuroscience guides the application of artificial intelligence for understanding and enhancing human cognition. In order to identify what patients consider meaningful research engagement we interviewed individuals who participated in a study during their Deep Brain Stimulation (DBS) surgery and attended a group event where they interacted with our research team. Analysis of semi-structured interviews identified four main themes: interest in science and the future of clinical care, contributing to science to improve lives, connecting with others, and accessibility considerations. Based on these insights, we propose strategies for transformational participation of patient communities in intracranial neuroscience research with respect to engagement objectives, communication and scope. This approach offers a foundation for sustaining relationships between scientists and communities rooted in trust and transparency, to ensure that impacts of neurotechnology on human health and cognition are aligned with patient needs as well as desired public values.

End-stage liver disease (ESLD) is one of the leading causes of death worldwide. Currently, the only curative option for patients with ESLD is liver transplantation. However, the demand for donor livers far exceeds the available supply, partly because many potentially viable livers are discarded following biopsy evaluation. While biopsy is the gold standard for assessing liver histological features related to graft quality and transplant suitability, it often leads to high discard rates due to its susceptibility to sampling errors and limited spatial coverage. Besides, biopsy is invasive, time-consuming, and unavailable in clinical facilities with limited resources. Here, we present an AI-assisted photoacoustic/ultrasound (PA/US) imaging framework for quantitative assessment of human donor liver graft quality and transplant suitablity at the whole-organ scale. With multimodal volumetric PA/US images as the input, our deep-learning (DL) model accurately predicted the risk level of fibrosis and steatosis, which indicate the graft quality and transplant suitability, when comparing with true pathological scores. DL also identified the imaging modes (PAI wavelength and B-mode USI) that correlated the most with prediction accuracy, without relying on ill-posed spectral unmixing. Our method was evaluated in six discarded human donor livers comprising sixty spatially matched regions of interest. Our study will pave the way for a new standard of care in organ graft quality and transplant suitability that is fast, noninvasive, and spatially thorough to prevent unnecessary organ discards in liver transplantation.

Although several ancillary tests are available in limited laboratories, diagnosis of microphthalmia (MiT)/TFE family translocation renal cell carcinoma (tRCC) could be challenging due to diverse and overlapping tumor morphology and the lack of reliable biomarkers. GPNMB has been recently identified as a diagnostic marker for various renal neoplasms with FLCN/TSC/mTOR-TFE alterations. However, the sensitivity and specificity of GPNMB immunostain are suboptimal and the result interpretation in ambiguous cases could be difficult. To search additional biomarkers that could improve the screening sensitivity and predict genetic aberrations in FLCN/TSC/mTOR-TFE pathway in renal tumors, we performed bioinformatic analysis of publicly available cancer databases and found GPR143, a transmembrane protein regulated by MiT transcription factors, was highly expressed in a subset of renal cell carcinomas (RCCs). In two the Cancer Genome Atlas (TCGA) kidney cancer cohorts, RCCs with high levels of GPR143 expression were enriched for renal neoplasms with FLCN/TSC/mTOR-TFE alterations. Similar to GPNMB labeling, GPR143 immunostain was positive in the majority of tRCC cases and renal tumors with FLCN/TSC/mTOR alterations, suggesting that GPR143 could function as another surrogate marker for FLCN/TSC/mTOR-TFE alterations in certain renal tumors. Interestingly, despite the concordant GPR143 and GPNMB immunoreactivity in most renal neoplasms with FLCN/TSC/mTOR-TFE alterations, diffuse GPR143 immunostain was observed in some cases with negative or focal GPNMB labeling. Taken together, our results indicate GPR143 could serve as a useful adjunct marker to improve the sensitivity for screening renal tumors with FLCN/TSC/mTOR-TFE alterations.

Background: Paediatric pneumonia is a leading cause of childhood morbidity and mortality worldwide. Chest X-rays (CXR) are an important diagnostic tool in the diagnosis of pneumonia, but shortages in specialist radiology services lead to clinically significant delays in CXR reporting. The ability to communicate findings both to clinicians and laypersons allows MLLMs to be deployed throughout clinical workflows, from image analysis to patient communication. However, MLLMs currently underperform state-of-the-art deep learning classifiers. Objective: To evaluate the diagnostic accuracy of ensemble strategies with MLLMs compared to the baseline average agent for paediatric radiological pneumonia detection. Methods: We conducted a retrospective cohort study using paediatric CXRs from two independent hospital datasets totalling 2300 CXRs. Fifteen MedGemma-4B-it agents independently classified each CXR into five pneumonia likelihood categories. Majority voting, soft voting, and GPTOSS-20B aggregation were compared against the average agent performance. The primary metric evaluated was OvR AUROC. Secondary metrics included accuracy, sensitivity, specificity, F1-score, Cohen's kappa, and OvO AUROC. Results: Soft voting achieved improvements in OvR AUROC (p_balanced = 0.0002, p_real-world = 0.0003), accuracy (p_balanced = 0.0008, p_real-world < 0.0001), Cohen's Kappa (p_balanced = 0.0006, p_real-world = 0.0054) and OvO AUROC (p_balanced < 0.0001, p_real-world = 0.0011) across both datasets, and a superior F1-value (pbalanced = 0.0028) for the balanced dataset. Conclusion: Soft voting enhances MedGemma's diagnostic discriminatory performance for paediatric radiological pneumonia detection. Our system enables privacy-preserving, near real-time clinical decision support with explainable outputs, having potential for integration into emergency departments. Our system's high specificity supports triage by flagging high-risk radiological pneumonia cases.