Citations

Abstract Inflammatory bowel diseases (IBD), principally Crohn’s disease (CD) and ulcerative colitis (UC), are common chronic disorders involving inflammation and often progressive tissue damage. Genome-wide association studies have mapped many risk signals, but the causal variants, effector genes and relevant cellular contexts remain difficult to resolve, limiting mechanistic interpretation and therapeutic translation. Here we performed a multi-ancestry GWAS meta-analysis of 125,992 individuals with IBD and more than 1.2 million controls, identifying 619 independent association signals (374 novel) at 420 IBD regions that account for 77–80% of SNP-based heritability. Fine-mapping resolved 81 high-confidence variants, 41 not previously reported. Although most signals were shared between CD and UC, 39% showed IBD subtype specificity, with UC signals showing stronger enrichment in functional annotations from intestinal epithelial, secretory and enteroendocrine cells, and CD showing stronger genetic correlations with circulating inflammatory biomarkers, including C-reactive protein and glycoprotein acetylation. Latent causal modelling supported a causal effect of decreased high-density lipoprotein on CD risk. By integrating bulk and single-cell eQTL and pQTL resources using colocalisation and Mendelian randomisation, together with coding-variant evidence from exome sequencing, we prioritised 664 candidate effector genes across 341 signals, including 390 newly implicated IBD genes, revealing new biological mechanisms and candidate therapeutic targets supported by human genetics.

Abstract Inflammatory bowel disease (IBD) is a chronic immune-mediated disorder of the gastrointestinal tract whose genetic basis is only partly resolved because most risk variants identified by genome-wide association studies (GWAS) lie in non-coding regions, limiting direct gene assignment and biological interpretation 1,2 . Here we analysed whole-exome and whole-genome sequencing data from 86,213 IBD cases and 478,363 controls of European ancestry. We identified 68 IBD genes directly implicated by conditionally independent protein-coding associations across the allele frequency spectrum. Many newly implicated IBD genes are supported by orthogonal genomic or pleiotropic evidence, pointing to disease-related pathways and nominating targets with therapeutic relevance. We further identified allelic series and non-additive effects at key loci such as NOD2 and TYK2. These results show that large-scale sequencing can resolve disease genes and pathways that remain ambiguous from non-coding association alone, providing a more direct route from human genetics to biological insight and therapeutic hypotheses.

Background/Objectives: Accurate detection of pulmonary nodules on chest CT is critical for lung cancer screening, yet training robust detectors remains challenging due to the high cost of reliable annotations. In this work, we present a systematic study of curriculum learning for CT-based lung nodule detection on the enhanced LUNA25 benchmark and propose a hybrid curriculum learning framework for data-efficient optimization. Methods: Our approach estimates sample difficulty by fusing clinically interpretable handcrafted factors such as nodule size and count with model-driven signals such as prediction confidence from a teacher model, and constructs a three-stage progressive training curriculum from easy to hard samples. Using YOLOv11s as a strong baseline, the proposed hybrid curriculum is compared against conventional training without curriculum learning and against single-source curricula. Results: On the held-out LUNA25 test set, hybrid curriculum learning increases mAP50 from 0.672 to 0.696, mAP50–95 from 0.369 to 0.385, recall from 0.588 to 0.634, and precision from 0.725 to 0.764. Extensive data-efficiency experiments with proportional reductions (1/2, 1/5, 1/10) and fixed training samples (5000–40,000 slices) further confirm consistent gains across limited-data regimes. Conclusions: These results demonstrate that jointly leveraging intrinsic image complexity and optimization-aware feedback provides effective sample scheduling for robust and data-efficient lung nodule detection.

Abstract The genetic contributions of the X chromosome to Alzheimer’s disease (AD) remain poorly understood yet are expected to importantly shape sex differences in AD. We therefore performed large-scale X-chromosome-wide association studies (N=1,240,451), evaluating differential risk due to sex, APOE *4, and escape from X-chromosome inactivation, finding most X-linked loci appear relevant to female-biased AD etiology. In evaluating genetic pleiotropy with hormonal, lipid, and brain imaging traits, we discovered X-linked AD loci converged on white matter traits, particularly in the anterior corona radiata and splenium of the corpus callosum. Through brain-centric functional genomics analyses, we then nominated candidate causal genes, including 5 that appeared highly robust. Notably, we found the escape gene RBBP7 decreases AD risk in APOE *4 carriers likely through higher expression in excitatory neurons to counter tau-related neurodegeneration. Altogether, we provide an atlas of sex and APOE *4-informed candidate X-linked AD risk loci, genes, and mechanisms that will guide future studies.

Abstract Background Our group recently performed the largest‐to‐date X‐chromosome wide association study (XWAS) of Alzheimer's disease (AD). Here, we expand on this with additional samples, novel sex‐ and APOE *4‐stratified analyses, and evaluate escape from random X chromosome inactivation (eXCI) to better capture female‐biased risk genes. We then integrate these results with XWASs of various AD‐relevant traits to elucidate shared genetic signals and ultimately uncover novel AD risk genes and mechanisms. Method The AD XWAS design is shown in Figure 1A and includes random X chromosome inactivation (rXCI) and eXCI models. We further assessed suggestive AD signals ( p <1x10 ‐3 ) for pleiotropy using genetic colocalization with 2852 AD‐relevant traits (Figure 2A). Loci exhibiting X chromosome‐wide significance ( p <1x10 ‐5 ) or apparent trait colocalization underwent quantitative trait locus (QTL) colocalization analyses across 62 tissues and cell types to functionally prioritize AD risk genes. Result Full sample analyses reproduced Belloy et al. 2024 findings and identified 3 additional loci, including a male‐specific signal near GLUD2 that impacts glutamate/glutamine metabolism (Figure 1B). APOE *4‐stratified analyses revealed 9 additional loci, including 3 eXCI hits in APOE *4 carriers (Figure 1C‐D). Pleiotropy colocalization identified 38 loci, most being novel and many driven by eXCI and/or female‐specific AD XWAS, including MOSPD2, PNMA3 and GABRE loci that showed extensive colocalization with brain imaging traits (Figure 2B). The most significant XWAS locus, SLC9A7 , colocalized with total testosterone, HDL‐C, and various brain imaging traits. Only the NLGN4X locus colocalized with amyloid positivity, linking its proposed role in synaptic dysfunction to amyloid pathology. The locus at KDM6A , previously implicated as an AD resilience gene, colocalized with a functional MRI (fMRI) phenotype. QTL colocalization analyses confirmed gene prioritizations in Belloy et al. 2024, and additionally provided support for PNMA3 , an antigen highly expressed in the brain, and 3 APOE ‐stratified loci, including ACLS4 , which impacts lipid metabolism. Conclusion This study provides novel insights into biological mechanisms that contribute to X‐linked genetic risk for AD in an APOE *4 and sex‐specific manner, identifying various novel risk loci. Notably, 29 female‐biased risk loci were uncovered, which may shed light on sex disparities in AD. Overall, our findings will aid in elucidating AD pathways and drug targets relevant to personalized medicine.

To improve synthetic CT (sCT) generation from cone-beam CT (CBCT) in radiotherapy, we propose a multiscale segmentation-guided diffusion framework. The proposed model integrates anatomical priors across multiple spatial resolutions through a segmentation mask pyramid and introduces a scale-specific loss function to guide learning at each level. When evaluated on the SynthRAD2023 brain dataset, our model achieves a mean absolute error (MAE) of 61.82 HU, a peak signal-to-noise ratio (PSNR) of 32.05 dB, and a structural similarity index (SSIM) of 0.90, outperforming baseline models. These results suggest that multiscale anatomical guidance can improve the fidelity and anatomical consistency of sCT images, thus facilitating high-quality CBCT-to-CT translation in radiotherapy applications.

With the rapid development of artificial intelligence (AI), various deep learning (DL) methods have been introduced into radiation oncology. Among them, the generation of synthetic Computed Tomography (sCT) images has attracted increasing attention, as it supports different clinical scenarios, from image-guided adaptive radiotherapy (IGART) to the simulation-free workflow. This review provides a comprehensive overview of recent studies on DL-based sCT synthesis in radiotherapy from multiple imaging modalities, including Cone-Beam CT (CBCT), Magnetic Resonance Imaging (MRI), and diagnostic CT, and discusses their clinical applications in CBCT-based online adaptive radiotherapy, MRI-guided radiotherapy, and simulation-free workflows. We also examine the architectures of representative DL models such as convolutional neural networks (CNNs) and generative adversarial networks (GANs) and summarize emerging training strategies. Finally, we discuss current challenges of clinical translation of DL algorithms into clinical practice and suggest potential directions for future research. Overall, this paper highlights the potential of AI-driven sCT generation to advance treatment planning by reducing imaging burden, improving dose accuracy, and accelerating workflow efficiency, thus ultimately improving the treatment outcome of patient care.

PURPOSE Large language models (LLMs) have demonstrated remarkable versatility in oncology applications, such as cancer staging and survival analysis. Despite their potential, ethical concerns such as data privacy breaches, bias in training data, lack of transparency, and risks associated with erroneous outputs pose significant challenges to their adoption in high-stakes oncology settings. Therefore, we aim to explore the ethical challenges associated with LLM-based applications in oncology and evaluate emerging techniques designed to address these issues. METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework, a systematic review was conducted to evaluate publications related to ethical issues of LLMs in oncology across eight academic databases (eg, PubMed, Web of Science, and Embase) between January 1, 2019, and December 31, 2024. RESULTS The search retrieved 4,319 published articles, of which 65 publications were preserved and included in our analysis. We identified six prevalent ethical challenges in oncology, including trust, equity, privacy, transparency, nonmaleficence, and accountability. We then evaluated emerging technical solutions to mitigate ethical challenges and summarized evaluation metrics used to assess these solutions' effectiveness. CONCLUSION This review provides actionable recommendations for responsibly deploying LLMs in oncology, ensuring adherence to ethical guidelines, and fostering improved patient outcomes. By bridging technical and clinical perspectives, this review offers a foundational framework for advancing ethical artificial intelligence applications in oncology and highlights areas for future research.

Background: Lung cancer ranks as the leading cause of cancer-related mortality worldwide. The complexity of tumor delineation, crucial for radiation therapy, requires expertise often unavailable in resource-limited settings. Artificial Intelligence (AI), particularly with advancements in deep learning (DL) and natural language processing (NLP), offers potential solutions yet is challenged by high false positive rates. Purpose: The Oncology Contouring Copilot (OCC) system is developed to leverage oncologist expertise for precise tumor contouring using textual descriptions, aiming to increase the efficiency of oncological workflows by combining the strengths of AI with human oversight. Methods: Our OCC system initially identifies nodule candidates from CT scans. Employing Language Vision Models (LVMs) like GPT-4V, OCC then effectively reduces false positives with clinical descriptive texts, merging textual and visual data to automate tumor delineation, designed to elevate the quality of oncology care by incorporating knowledge from experienced domain experts. Results: The deployment of the OCC system resulted in a 35.0% reduction in the false discovery rate, a 72.4% decrease in false positives per scan, and an F1-score of 0.652 across our dataset for unbiased evaluation. Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs, improving contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation and reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVM hallucinations with ablation study; and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges.