JACC Clin Electrophysiol. 2025 Jul 17:S2405-500X(25)00471-2. doi: 10.1016/j.jacep.2025.06.009. Online ahead of print.

ABSTRACT

Intracardiac echocardiography (ICE) is increasingly being used to guide electrophysiologic (EP) procedures but requires a considerable learning curve. ICE images collected from 2 separate institutions (605 EP procedures, 196,768 images) were used to develop an automated deep learning-based algorithm to detect anatomic structures from the right atrium. Fifteen of 21 anatomic structures were correctly identified with >70% precision and recall. Mislabeling of one anatomic structure for another was rare. This fully automated anatomy labeling algorithm can serve as an education tool or can be used as a navigation tool to guide ICE operators in EP procedures.

PMID:40767798 | DOI:10.1016/j.jacep.2025.06.009

Codas. 2025 Aug 8;37(4):e20240305. doi: 10.1590/2317-1782/e20240305en. eCollection 2025.

ABSTRACT

PURPOSE: This scoping review aimed to map and synthesize evidence on technological advancements using Artificial Intelligence in the diagnosis and management of dysphagia. We followed the PRISMA guidelines and those of the Joanna Briggs Institute, focusing on research about technological innovations in dysphagia.

RESEARCH STRATEGIES: The protocol was registered on the Open Science Framework platform. The databases consulted included EMBASE, Latin American and Caribbean Health Sciences Literature (LILACS), Livivo, PubMed/Medline, Scopus, Cochrane Library, Web of Science, and grey literature.

SELECTION CRITERIA: The acronym 'PCC' was used to consider the eligibility of studies for this review.

DATA ANALYSIS: After removing duplicates, 56 articles were initially selected. A subsequent update resulted in 205 articles, of which 61 were included after applying the selection criteria.

RESULTS: Videofluoroscopy of swallowing was used as the reference examination in most studies. Regarding the underlying diseases present in the patients who participated in the studies, there was a predominance of various neurological conditions. The algorithms used varied across the categories of Machine Learning, Deep Learning, and Computer Vision, with a predominance in the use of Deep Learning.

CONCLUSION: Technological advancements in artificial intelligence for the diagnosis and management of dysphagia have been mapped, highlighting the predominance and applicability of Deep Learning in examinations such as videofluoroscopy. The findings suggest significant potential to improve diagnostic accuracy and clinical management effectiveness, particularly in neurological patients. Identified research gaps require further investigations to solidify the clinical applicability and impact of these technologies.

PMID:40767676 | DOI:10.1590/2317-1782/e20240305en

Radiol Artif Intell. 2025 Aug 6:e240478. doi: 10.1148/ryai.240478. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a dentate nucleus (DN) segmentation tool using deep learning (DL) applied to brain MRI-based quantitative susceptibility mapping (QSM) images. Materials and Methods Brain QSM images from healthy controls and individuals with cerebellar ataxia or multiple sclerosis were collected from nine different datasets (2016-2023) worldwide for this retrospective study (ClinicalTrials.gov Identifier: NCT04349514). Manual delineation of the DN was performed by experienced raters. Automated segmentation performance was evaluated against manual reference segmentations following training with several DL architectures. A two-step approach was used, consisting of a localization model followed by DN segmentation. Performance metrics included intraclass correlation coefficient (ICC), Dice score, and Pearson correlation coefficient. Results The training and testing datasets comprised 328 individuals (age range, 11-64 years; 171 female), including 141 healthy individuals and 187 with cerebellar ataxia or multiple sclerosis. The manual tracing protocol produced reference standards with high intrarater (average ICC 0.91) and interrater reliability (average ICC 0.78). Initial DL architecture exploration indicated that the nnU-Net framework performed best. The two-step localization plus segmentation pipeline achieved a Dice score of 0.90 ± 0.03 and 0.89 ± 0.04 for left and right DN segmentation, respectively. In external testing, the proposed algorithm outperformed the current leading automated tool (mean Dice scores for left and right DN: 0.86 ± 0.04 vs 0.57 ± 0.22, P < .001; 0.84 ± 0.07 vs 0.58 ± 0.24, P < .001). The model demonstrated generalizability across datasets unseen during the training step, with automated segmentations showing high correlation with manual annotations (left DN: r = 0.74; P < .001; right DN: r = 0.48; P = .03). Conclusion The proposed model accurately and efficiently segmented the DN from brain QSM images. The model is publicly available (https://github.com/art2mri/DentateSeg). ©RSNA, 2025.

PMID:40767617 | DOI:10.1148/ryai.240478

Radiol Artif Intell. 2025 Aug 6:e240777. doi: 10.1148/ryai.240777. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and validate MRSegmentator, a retrospective cross-modality deep learning model for multiorgan segmentation of MRI scans. Materials and Methods This retrospective study trained MRSegmentator on 1,200 manually annotated UK Biobank Dixon MRI sequences (50 participants), 221 in-house abdominal MRI sequences (177 patients), and 1228 CT scans from the TotalSegmentator-CT dataset. A human-in-the-loop annotation workflow leveraged cross-modality transfer learning from an existing CT segmentation model to segment 40 anatomic structures. The model's performance was evaluated on 900 MRI sequences from 50 participants in the German National Cohort (NAKO), 60 MRI sequences from AMOS22 dataset, and 29 MRI sequences from TotalSegmentator-MRI. Reference standard manual annotations were used for comparison. Metrics to assess segmentation quality included Dice Similarity Coefficient (DSC). Statistical analyses included organ-and sequence-specific mean ± SD reporting and two-sided t tests for demographic effects. Results 139 participants were evaluated; demographic information was available for 70 (mean age 52.7 years ± 14.0 [SD], 36 female). Across all test datasets, MRSegmentator demonstrated high class wise DSC for well-defined organs (lungs: 0.81-0.96, heart: 0.81-0.94) and organs with anatomic variability (liver: 0.82-0.96, kidneys: 0.77-0.95). Smaller structures showed lower DSC (portal/splenic veins: 0.64-0.78, adrenal glands: 0.56-0.69). The average DSC on the external testing using NAKO data, ranged from 0.85 ± 0.08 for T2-HASTE to 0.91 ± 0.05 for in-phase sequences. The model generalized well to CT, achieving mean DSC of 0.84 ± 0.12 on AMOS CT data. Conclusion MRSegmentator accurately segmented 40 anatomic structures on MRI and generalized to CT; outperforming existing open-source tools. Published under a CC BY 4.0 license.

PMID:40767616 | DOI:10.1148/ryai.240777

J Chem Inf Model. 2025 Aug 6. doi: 10.1021/acs.jcim.5c01307. Online ahead of print.

ABSTRACT

The coronavirus main protease, essential for viral replication, is a well-validated antiviral target. Here, we present Deep-CovBoost, a computational pipeline integrating deep learning with free energy perturbation (FEP) simulations to guide the structure-based optimization of inhibitors targeting the coronavirus main protease. Starting from a reported noncovalent inhibitor, the pipeline generated and prioritized analogs using predictive modeling, followed by rigorous validation through FEP and molecular dynamics simulations. This approach led to the identification of optimized compounds (e.g., I3C-1, I3C-2, I3C-35) that enhance binding affinity by engaging the underexploited S4 and S5 subpockets. These results highlight the potential of combining physics-based and AI-driven approaches to accelerate lead optimization and antiviral design.

PMID:40767530 | DOI:10.1021/acs.jcim.5c01307

Curr Opin Rheumatol. 2025 Aug 7. doi: 10.1097/BOR.0000000000001114. Online ahead of print.

ABSTRACT

PURPOSE OF REVIEW: The purpose of this review is to summarize the uses of artificial intelligence for advancing systemic sclerosis (SSc) skin and lung disease research through 2024.

RECENT FINDINGS: Applications of AI in SSc research have expanded markedly in recent years. The most common artificial intelligence method identified was supervised machine learning for predictive modeling. Supervised machine learning uses input data labeled with a known outcome to train a model to predict outcomes when encountering new data. Using machine learningassisted feature selection and posttraining feature importance techniques also highlighted key predictors within complex datasets, informing possible mechanisms underlying heterogeneous patient outcomes. Additionally, unsupervised machine learning approaches have been used to identify patient subsets with distinct clinical trajectories. Unsupervised machine learning identifies groups with similar characteristics within a dataset, without considering a specific outcome. Digital image analysis using deep learning has also been undertaken in lung imaging studies to quantify interstitial lung disease (ILD) extent and automate ILD subtype classification, as well as skin biopsy analysis to quantify histologic changes. These scalable tools could efficiently automate prognostic assessments for use across centers of varying local expertise.

SUMMARY: Artificial intelligence represents a tool for analyzing high-dimensional, complex datasets to derive robust results, even within relatively small SSc cohorts. To date, artificial intelligence driven insights to SSc skin and lung disease have focused on identifying patient subsets, quantifying disease severity, and building predictive models to inform personalized patient care.

PMID:40767529 | DOI:10.1097/BOR.0000000000001114

Am J Physiol Cell Physiol. 2025 Aug 6. doi: 10.1152/ajpcell.00140.2025. Online ahead of print.

ABSTRACT

Pulmonary fibrosis, a life-threatening respiratory condition affecting millions globally, is characterized by progressive lung scarring that severely compromises respiratory function. With few effective treatment options available, it carries a poor prognosis for those affected. Disrupted iron homeostasis is increasingly implicated in its pathogenesis, yet the precise mechanisms linking iron overload to fibrotic progression remain elusive. This study unveils a novel pathway by which iron accumulation orchestrates fibrotic remodeling via secreted phosphoprotein 1 (SPP1)-mediated reprogramming of alveolar type 2 (AT2) cells. Using an integrated approach combining analysis of public single-cell and single-nucleus RNA sequencing datasets with functional validation across multiple murine models of pulmonary fibrosis (iron-induced, bleomycin-induced, and silica-induced), we demonstrate that iron overload within AT2 cells triggers a coordinated transcriptional cascade affecting iron handling, immune cell recruitment, and cellular differentiation. Mechanistically, SPP1 emerges as a key mediator, functioning both externally as a paracrine signal for macrophage recruitment following iron-induced secretion from AT2 cells, and internally as a driver of pathological epithelial transitions, specifically fostering the development of a Krt8+ alveolar intermediate phenotype. The clinical relevance of these findings is substantiated by analysis of human idiopathic pulmonary fibrosis specimens using publicly available single-cell and spatial transcriptomic datasets. These analyses reveal conserved pathway activation and a distinctive spatial organization of SPP1-expressing AT2 cells within remodeled tissue microenvironments, notably in close proximity to macrophages. By establishing SPP1 as a critical nexus between iron dysregulation and fibrotic progression, our work identifies the SPP1 signaling axis as a compelling therapeutic target for this devastating condition.

PMID:40767540 | DOI:10.1152/ajpcell.00140.2025

Appl Biochem Biotechnol. 2025 Aug 6. doi: 10.1007/s12010-025-05322-0. Online ahead of print.

ABSTRACT

Hydrothermal processing is known to influence the nutritional and functional properties of cereals; however, its effects on the bioactive metabolite composition of traditional Indian brown rice varieties remain underexplored. In this study, we investigated the impact of hydrothermal treatment on four indigenous rice varieties, Seeraga samba, Kattu ponni, Kuzhiyadichaan, and Poongar, focusing on the compositional changes in lipophilic bioactive compounds. Using GC-MS/MS analysis, we quantified the alterations in fatty acids, phytosterols, triterpenes, and tocopherols before and after processing. Significant varietal responses were also observed. Seeraga samba exhibited a 20.38% increase in total fatty acid post-treatment, whereas Kuzhiyadichaan showed a 13.72% increase in β-sitosterol (p < 0.01). Poongar displayed an 18.92% increase in polyunsaturated fatty acids, whereas Kattu ponni showed a 2.13% increase in squalene content. Notably, vitamin E and γ-tocopherol were detected exclusively in hydrothermally processed Kuzhiyadichaan and Poongar, indicating enhanced micronutrient release. Statistical analysis revealed significant compositional differences (p < 0.05) between the raw and processed samples with distinct clustering patterns. These findings suggest that hydrothermal processing can be strategically optimized to enhance the nutraceutical value of traditional brown rice, thereby offering a promising approach for dietary biofortification and functional food development.

PMID:40768180 | DOI:10.1007/s12010-025-05322-0

Forensic Sci Med Pathol. 2025 Aug 6. doi: 10.1007/s12024-025-01044-1. Online ahead of print.

NO ABSTRACT

PMID:40767910 | DOI:10.1007/s12024-025-01044-1

Front Pharmacol. 2025 Jul 22;16:1607814. doi: 10.3389/fphar.2025.1607814. eCollection 2025.

ABSTRACT

BACKGROUND: Oxaliplatin, in combination with 5-fluorouracil and leucovorin, is a standard treatment for colorectal cancer and shows high efficacy. However, oxaliplatin induces side effects, such as chemotherapy-induced peripheral neuropathy and myelosuppression, which may lead to dose reduction, temporary drug withdrawal, or discontinuation. Lecithinized superoxide dismutase (PC-SOD) is a drug delivery system formulation with improved blood stability and tissue affinity for SOD. A phase II clinical trial of PC-SOD for chemotherapy-induced peripheral neuropathy has been conducted, and its efficacy has been confirmed for certain parameters.

METHODS: In this study, we focused on myelosuppression, a major side effect of oxaliplatin, and aimed to elucidate the preventive effect of PC-SOD in a murine model of myelosuppression.

RESULTS: Oxaliplatin administration decreased the white blood cell, platelet, and red blood cell counts and hemoglobin levels in the whole blood of mice. PC-SOD treatment significantly restored the oxaliplatin-dependent reduction in white blood cell count (day 10). The gene expression of cytokines involved in hematopoietic progenitor cell differentiation and proliferation, including colony-stimulating factor (CSF)2, CSF3, interleukin (IL)-3, IL-4, IL-5, IL-6, IL-9, and stem cell factor, was also decreased by oxaliplatin administration. In contrast, PC-SOD treatment markedly restored the gene expression of these cytokines. In vivo imaging analysis showed that oxaliplatin treatment enhanced reactive oxygen species (ROS) production in the femur and tibia, whereas PC-SOD significantly suppressed this production. Furthermore, analysis of mouse-derived bone marrow cells revealed that PC-SOD suppressed oxaliplatin-induced cytotoxicity and ROS production in vitro.

CONCLUSION: These results suggest that PC-SOD exerts an antioxidant effect and prevents oxaliplatin-induced myelosuppression, particularly in a murine model of leukopenia.

PMID:40766760 | PMC:PMC12322972 | DOI:10.3389/fphar.2025.1607814

medRxiv [Preprint]. 2025 Jul 30:2025.07.29.25332397. doi: 10.1101/2025.07.29.25332397.

ABSTRACT

While antiretroviral therapy (ART) has significantly improved disease prognosis in people with HIV (PWH), understanding the biological mechanisms underlying plasma HIV-1 RNA viral load (VL) can inform additional strategies to slow HIV/AIDS disease progression. Here, we integrated multi-omic datasets and used two machine learning network biology tools (GRIN and MENTOR) to identify biological mechanisms associated with VL across 10 cohorts from multiple omics data sets. We integrated the following gene sets: 3 genes from HIV set point VL GWAS, 258 genes whose expression was associated with set point VL in CD4+ T-cells, 143 genes based on DNA methylation associations with VL, and 8 genes previously known to affect the pharmacokinetics of ART. Using GRIN, we retained 194 VL genes based on their high network interconnectivity. We then used MENTOR to collaboratively interpret subsets of these genes and identified the following biological processes: cell cycle checkpoint pathways associated with non-AIDS defining cancers, oxidative stress, viral replication, and interferon signaling. Using these network tools for multi-omic integration, we present a conceptual model of mechanisms underlying HIV VL, and identify drug repurposing candidates to complement existing ART to enhance treatment response and reduce HIV-related comorbidities.

PMID:40766151 | PMC:PMC12324665 | DOI:10.1101/2025.07.29.25332397

BioData Min. 2025 Aug 5;18(1):51. doi: 10.1186/s13040-025-00466-5.

ABSTRACT

Drug repurposing (DR) offers a promising alternative to the high cost and low success rate of traditional drug development, especially for complex diseases like Alzheimer's disease (AD). This study addressed DR for AD from three key angles: (1) demonstrating how disease-specific knowledge graphs can improve DR performance, (2) evaluating the role of large language models (LLMs) in enhancing the usability and efficiency of these graphs, and (3) assessing whether Graph-of-Thoughts (GoT)-enhanced LLMs, when integrated with AD knowledge graphs, can outperform traditional machine learning and LLM-based approaches. We tested five distinct DR strategies (DR1-DR5) for AD: DR1, a machine learning method using TxGNN; DR2, a machine learning model leveraging the Alzheimer's KnowledgeBase (AlzKB); DR3, an LLM-based chatbot built on AlzKB; DR4, our ESCARGOT framework combining GoT-enhanced LLMs with AlzKB; and DR5, a general reasoning-driven LLM approach. Results showed that AlzKB significantly improved DR outcomes. ESCARGOT further enhanced performance while reducing the need for coding or advanced expertise in knowledge graph analysis. Because the architecture of AlzKB is easily adaptable to other diseases and ESCARGOT can integrate with various knowledge graph platforms, this framework offers a broadly applicable, innovative tool for accelerating drug discovery through repurposing.

PMID:40764997 | DOI:10.1186/s13040-025-00466-5

Front Vet Sci. 2025 Jul 22;12:1511341. doi: 10.3389/fvets.2025.1511341. eCollection 2025.

ABSTRACT

Cytochrome P450 (CYP) 1A2 plays a key role in the metabolism of various drugs in dogs. However, the impact of genetic variation on differences in CYP1A2 metabolism among dogs remains unclear. Recent studies have identified variability in the copy number of the CYP1A2 gene, ranging from two to five copies. Additionally, a genetic polymorphism (stop codon) has been identified which results in the expression of an inactive protein, this has been investigated and changes in the pharmacokinetics of some clinically used drugs have been described. If these additional copies are functional, dogs with more CYP1A2 gene copies may exhibit faster drug clearance, potentially affecting appropriate drug dosing. To investigate this possibility, a well-characterized dog liver bank (N = 58) was analyzed to determine whether CYP1A2 copy number variation (CNV) correlates with CYP1A2 protein levels and enzyme activity. Real-time PCR was used to assess CYP1A2 CNV, while label-free mass spectrometry measured CYP1A2 protein concentration in liver microsomes. Theobromine N-3 demethylation was examined as a marker of canine CYP1A2 activity using commercially available recombinant CYPs and liver microsomes from dogs treated with isoform-selective enzyme inducers. Only CYP1A1 and CYP1A2 demonstrated the ability to catalyze theobromine N-3 demethylation, and this activity was induced exclusively by β-naphthoflavone. Liver microsome theobromine N-3 demethylation activity showed a moderate correlation with CYP1A2 protein levels (R s = 0.46; p = 0.0003). Among the 58 liver samples genotyped for CYP1A2 CNV, nine dogs had two copies, 20 had three copies, 23 had four copies, and six had five copies. However, CYP1A2 CNV did not significantly correlate with CYP1A2 protein concentration (R s = -0.14; p = 0.30) and showed a weak negative correlation with theobromine N-3 demethylation activity (R s = -0.45; p = 0.00035). These findings suggest that CYP1A2 CNV is not a strong predictor of increased CYP1A2 protein expression or activity. According to the literature, CNV might not be relevant, but the genetic polymorphism (stop codon) could potentially be. The studies available show relationships between the stop codon and protein inactivity in the metabolizing of clinically used drugs. Further studies are necessary to validate these preliminary results.

PMID:40765748 | PMC:PMC12322894 | DOI:10.3389/fvets.2025.1511341

Health Sci Rep. 2025 Aug 5;8(8):e71142. doi: 10.1002/hsr2.71142. eCollection 2025 Aug.

ABSTRACT

BACKGROUND AND AIMS: People with cystic fibrosis (pwCF) often have vitamin D deficiency and require vitamin D supplementation. The primary objective of this study was to evaluate the impact of ultrahigh dose cholecalciferol ("stoss dosing") in pwCF with variable adherence to maintenance cholecalciferol.

METHODS: Retrospective cohort study of pwCF who received initial stoss dose per protocol between January 2017 and November 2021 at University of Iowa Health Care adult and pediatric CF centers. Serum 25(OH)D concentrations were extracted from the EMR. The increase in serum 25(OH)D concentration associated with receiving stoss doses was evaluated using a longitudinal linear mixed effects regression model.

RESULTS: Fifty-eight patients were included in the final analysis. The mean baseline 25(OH)D concentration before stoss therapy was 20.1 ng/mL (standard deviation [SD] = 5.9). The mean serum 25(OH)D concentration following stoss therapy increased to 27.9 ng/mL (SD = 7.5) and was measured on average 116 days after stoss administration. For patients with self-reported non-adherence to vitamin regimens, 16 out of 20 (80%) achieved a serum 25(OH)D concentration of at least 30 ng/mL after stoss therapy.

CONCLUSIONS: Our findings suggest that stoss dosing was associated with increased serum 25(OH)D concentrations. This benefit also existed for individuals with self-reported non-adherence to maintenance cholecalciferol regimens with most patients reaching concentration goals.

PMID:40766771 | PMC:PMC12322582 | DOI:10.1002/hsr2.71142

Respirol Case Rep. 2025 Aug 4;13(8):e70308. doi: 10.1002/rcr2.70308. eCollection 2025 Aug.

ABSTRACT

People with cystic fibrosis (CF) typically experience chronic respiratory infections, but neurological sequelae are rare. Guillain-Barre Syndrome (GBS) is classically precipitated by a respiratory or gastrointestinal infection, although other rarer aetiologies exist. This case series outlines four adults with CF who developed GBS. The association with acute and chronic respiratory infections in people with CF is explored, as well as other potential precipitants. An autoimmune phenomenon in the context of chronic systemic inflammation or a possible contributory role of dysfunctional CFTR protein is also considered.

PMID:40766167 | PMC:PMC12322314 | DOI:10.1002/rcr2.70308

Front Artif Intell. 2025 Jul 22;8:1582257. doi: 10.3389/frai.2025.1582257. eCollection 2025.

ABSTRACT

Two-wheeler traffic offenses are a well-known fact about the Indian Road scenario. In addition to endangering the offenders, these offenses also endanger other commuters. Two-wheeler traffic violations can take many different forms, such as overloading, triple riding, and helmetless riding. Effective identification and enforcement strategies are necessary for these offenses since they pose a serious risk to public safety. Due to the inadequacy of traditional traffic monitoring and enforcement techniques, advanced technology-based solutions are now required. Deep learning-based systems have demonstrated significant promise in identifying and stopping such infractions in recent years. We propose a two-step deep learning approach that leverages the strengths of pre-trained object detection models to detect two-wheeler riders and specialized helmet classifiers to identify helmet wear status as well as detect number plates. In the first stage, we utilized a highly efficient, robust, and accurate object identification DetectNet (Model 1) framework developed by NVIDIA, and it uses the ResNet18 Convolutional Neural Network (CNN) architecture as part of the Transfer Learning Toolkit known as TAO (Train, Adapt, Optimize). The second stage demands accurate detection of a helmet on the identified rider and extracting numbers from the violator's license plates using the OCR module in real time. We employed YOLOv8 (Model 2), a deep learning-based architecture that has proven effective in several applications involving object detection in real time. It predicts bounding boxes and class probabilities for objects within an image using a single neural network, making it a perfect choice for real-time applications like rider helmet violations detections and number plate processing. Due to a lack of publicly available traffic datasets, we created a custom dataset containing motorcycle rider images captured under complex scenarios for training and validating our models. Experimental analysis shows that our proposed two-step model achieved a promising helmet detection accuracy of 98.56% and a 97.6% number plate detection accuracy of persons not wearing helmets. The major objective of our proposed study is to enforce stringent traffic laws in real-time to decrease rider helmet violations.

PMID:40766945 | PMC:PMC12321817 | DOI:10.3389/frai.2025.1582257

Front Psychiatry. 2025 Jul 22;16:1628216. doi: 10.3389/fpsyt.2025.1628216. eCollection 2025.

ABSTRACT

INTRODUCTION: Autism spectrum disorder (ASD) is characterized by persistent deficits in social communication and restrictive, repetitive behaviors. Current diagnostic and intervention pathways rely heavily on clinician expertise, leading to delays and limited scalability. Generative artificial intelligence (GenAI) offers emerging opportunities for automatically assisting and personalizing ASD care, though technical and ethical concerns persist.

METHODS: We conducted systematic searches in Embase, PsycINFO, PubMed, Scopus, and Web of Science (January 2014 to February 2025). Two reviewers independently screened and extracted eligible studies reporting empirical applications of GenAI in ASD screening, diagnosis, or intervention. Data were charted across GenAI architectures, application domains, evaluation metrics, and validation strategies. Comparative performance against baseline methods was synthesized where available.

RESULTS: From 553 records, 10 studies met the inclusion criteria across three domains: (1) screening and diagnosis (e.g., transformer-based classifiers and GAN-based data augmentation), (2) assessment and intervention, (e.g., multimodal emotion recognition and feedback systems), and (3) caregiver education and support (e.g., LLM-based chatbots). While most studies reported potential performance improvements, they also highlighted limitations such as small sample sizes, data biases, limited validation, and model hallucinations. Comparative analyses were sparse and lacked standardized metrics.

DISCUSSION: This review (i) maps GenAI applications in ASD care, (ii) compares GenAI and traditional approaches, (iii) highlights methodological and ethical challenges, and (iv) proposes future research directions. Our findings underscore GenAI's emerging potential in autism care and the prerequisites for its ethical, transparent, and clinically validated implementation.

SYSTEMATIC REVIEW REGISTRATION: https://osf.io/4gsyj/, identifier DOI: 10.17605/OSF.IO/4GSYJ.

PMID:40766925 | PMC:PMC12322814 | DOI:10.3389/fpsyt.2025.1628216

ArXiv [Preprint]. 2025 Jul 31:arXiv:2508.00164v1.

ABSTRACT

Virtual staining, or in-silico-labeling, has been proposed to computationally generate synthetic fluorescence images from label-free images by use of deep learning-based image-to-image translation networks. In most reported studies, virtually stained images have been assessed only using traditional image quality measures such as structural similarity or signal-to-noise ratio. However, in biomedical imaging, images are typically acquired to facilitate an image-based inference, which we refer to as a downstream biological or clinical task. This study systematically investigates the utility of virtual staining for facilitating clinically relevant downstream tasks (like segmentation or classification) with consideration of the capacity of the deep neural networks employed to perform the tasks. Comprehensive empirical evaluations were conducted using biological datasets, assessing task performance by use of label-free, virtually stained, and ground truth fluorescence images. The results demonstrated that the utility of virtual staining is largely dependent on the ability of the segmentation or classification task network to extract meaningful task-relevant information, which is related to the concept of network capacity. Examples are provided in which virtual staining does not improve, or even degrades, segmentation or classification performance when the capacity of the associated task network is sufficiently large. The results demonstrate that task network capacity should be considered when deciding whether to perform virtual staining.

PMID:40766889 | PMC:PMC12324553

bioRxiv [Preprint]. 2025 Aug 1:2025.07.29.667497. doi: 10.1101/2025.07.29.667497.

ABSTRACT

Quantitative oblique back-illumination microscopy (qOBM) has emerged as a powerful technique for label-free, 3D quantitative phase imaging of arbitrarily thick biological specimens. However, in its initial embodiment, qOBM requires multiple captures for phase recovery, which reduces imaging speed and increases system complexity. In this work, we present a novel advancement in qOBM: single-capture qOBM (SCqOBM) which utilizes a deep learning model to accurately reconstruct phase information from a single oblique back-illumination capture. We demonstrate that SCqOBM achieves remarkable phase imaging accuracy, closely matching the results of traditional four-capture qOBM in diverse biological samples. We first highlight the unique potential of SCqOBM for non-invasive, in-vivo imaging applications by visualizing blood flow in mouse brain and human arm. Additionally, we demonstrate single-slice (en-face) quantitative phase imaging at 2 kHz and volumetric refractive index tomography at speeds up to 10 volumes per second. SCqOBM offers transformative advantages in speed, simplicity, and system accessibility, making it highly suitable for dynamic and real-time imaging applications. Its ability to produce high-resolution, quantitative phase and refractive index images with minimal hardware complexity opens new frontiers in biomedical research and clinical diagnostics, including non-invasive hematological assessments and in-vivo tissue imaging.

PMID:40766649 | PMC:PMC12324366 | DOI:10.1101/2025.07.29.667497

bioRxiv [Preprint]. 2025 Jul 31:2025.07.25.666829. doi: 10.1101/2025.07.25.666829.

ABSTRACT

Long-read single-cell RNA sequencing using platforms such as Oxford Nanopore Technologies (ONT) enables full-length transcriptome profiling at single-cell resolution. However, high sequencing error rates, diverse library architectures, and increasing dataset scale introduce major challenges for accurately identifying cell barcodes (CBCs) and unique molecular identifiers (UMIs) - key prerequisites for reliable demultiplexing and deduplication, respectively. Existing pipelines rely on hard-coded heuristics or local transition rules that cannot fully capture this broader structural context and often fail to robustly interpret reads with indel-induced shifts, truncated segments, or non-canonical element ordering. We introduce Tranquillyzer (TRANscript QUantification In Long reads-anaLYZER), a flexible, architecture-aware deep learning framework for processing long-read single-cell RNA-seq data. Tranquillyzer employs a hybrid neural network architecture and a global, context-aware design, and enables precise identification of structural elements - even when elements are shifted, partially degraded, or repeated due to sequencing noise or library construction variability. In addition to supporting established single-cell protocols, Tranquillyzer accommodates custom library formats through rapid, one-time model training on user-defined label schemas, typically completed within a few hours on standard GPUs. Additional features such as scalability across large datasets and comprehensive visualization capabilities further position Tranquillyzer as a flexible and scalable framework solution for processing long-read single-cell transcriptomic datasets.

PMID:40766630 | PMC:PMC12324178 | DOI:10.1101/2025.07.25.666829