Zentralbl Chir. 2025 May 15. doi: 10.1055/a-2563-3691. Online ahead of print.

ABSTRACT

Lung transplantation has evolved continuously since its first successful procedures in the 1960 s. The current guidelines from the International Society for Heart and Lung Transplantation (ISHLT) emphasise increasingly individualised patient assessment, which, in addition to the underlying lung disease, considers factors such as comorbidities, frailty, age, and social aspects. The expanded indications for lung transplantation are reflected in the refined risk assessment, which particularly includes patients with advanced chronic obstructive pulmonary disease (COPD), idiopathic pulmonary fibrosis (IPF), and pulmonary arterial hypertension (PAH). Furthermore, the criteria for patients with a history of cancer and those with infections such as HIV or multidrug-resistant organisms have been made more flexible, leading to a more inclusive transplantation policy. A key focus is on early transplant counselling, allowing patients the opportunity for transplantation before they develop acute exacerbations. These updated guidelines aim to maximise both the survival rates and the quality of life of transplant patients, through differentiated and risk-adjusted decision-making.

PMID:40373816 | DOI:10.1055/a-2563-3691

BMC Med Inform Decis Mak. 2025 May 15;25(Suppl 2):188. doi: 10.1186/s12911-025-03012-9.

ABSTRACT

BACKGROUND: Colorectal cancer is the fourth most deadly cancer, with a high mortality rate and a high probability of recurrence and metastasis. Since continuous examinations and disease monitoring for patients after surgery are currently difficult to perform, it is necessary for us to develop a predictive model for colorectal cancer metastasis and recurrence to improve the survival rate of patients.

RESULTS: Previous studies mostly used only clinical or radiological data, which are not sufficient to explain the in-depth mechanism of colorectal cancer recurrence and metastasis. Therefore, this study proposes such a multiomics data-based predictive model for the recurrence and metastasis of colorectal cancer. LR, SVM, Naïve-bayes and ensemble learning models are used to build this predictive model.

CONCLUSIONS: The experimental results indicate that our proposed multiomics data-based ensemble learning model effectively predicts the recurrence and metastasis of colorectal cancer.

PMID:40375082 | DOI:10.1186/s12911-025-03012-9

BMC Med Genomics. 2025 May 15;18(1):87. doi: 10.1186/s12920-025-02154-z.

ABSTRACT

BACKGROUND: Recent decades have witnessed a steady decrease in the use of race categories in genomic studies. While studies that still include race categories vary in goal and type, these categories already build on a history during which racial color lines have been enforced and adjusted in the service of social and political systems of power and disenfranchisement. For early modern classification systems, data collection was also considerably arbitrary and limited. Fixed, discrete classifications have limited the study of human genomic variation and disrupted widely spread genetic and phenotypic continuums across geographic scales. Relatedly, the use of broad and predefined classification schemes-e.g. continent-based-across traits can risk missing important trait-specific genomic signals.

METHODS: To address these issues, we introduce a dynamic approach to clustering human genomics cohorts based on genomic variation in trait-specific loci and without using a set of predefined categories. We tested the approach on whole-exome sequencing datasets in ten cancer types and partitioned them based on germline variants in cancer-relevant genes that could confer cancer type-specific disease predisposition.

RESULTS: Results demonstrate clustering patterns that transcend discrete continent-based categories across cancer types. Functional analysis based on cancer type-specific clusterings also captures the fundamental biological processes underlying cancer, differentiates between dynamic clusters on a functional level, and identifies novel potential drivers overlooked by a predefined continent-based clustering.

CONCLUSIONS: Through a trait-based lens, the dynamic clustering approach reveals genomic patterns that transcend predefined classification categories. We propose that coupled with diverse data collection, new clustering approaches have the potential to draw a more complete portrait of genomic variation and to address, in parallel, technical and social aspects of its study.

PMID:40375077 | DOI:10.1186/s12920-025-02154-z

Nat Commun. 2025 May 15;16(1):4534. doi: 10.1038/s41467-025-58841-z.

ABSTRACT

Suppressing immune responses promotes allograft survival but also favours tumour progression and recurrence. Selectively suppressing allograft rejection while maintaining or even enhancing antitumor immunity is challenging. Here, we show loss of allograft-related rejection in mice deficient in Setdb1, an H3K9 methyltransferase, while antitumor immunity remains intact. RNA sequencing shows that Setdb1-deficiency does not affect T-cell activation or cytokine production but induces an increase in Treg-cell-associated gene expression. Depletion of Treg cells impairs graft acceptance in Setdb1-deficient mice, indicating that the Treg cells promote allograft survival. Surprisingly, Treg cell-specific Setdb1 deficiency does not prolong allograft survival, suggesting that Setdb1 may function prior to Foxp3 induction. Using single-cell RNA sequencing, we find that Setdb1 deficiency induces a new Treg population in the thymus. This subset of Treg cells expresses less IL-1R2 and IL-18R1. Mechanistically, during Treg cell induction, Setdb1 is recruited by transcription factor ATF and altered histone methylation. Our data thus define Setdb1 in T cells as a hub for Treg cell differentiation, in the absence of which suppressing allograft rejection is uncoupled from maintaining antitumor immunity.

PMID:40374612 | DOI:10.1038/s41467-025-58841-z

Nat Commun. 2025 May 15;16(1):4529. doi: 10.1038/s41467-025-59578-5.

ABSTRACT

Latent HIV-1 presents a formidable challenge for viral eradication. HIV-1 transcription and latency reversal require interactions between the viral promoter and host proteins. Here, we perform the dCas9-targeted locus-specific protein analysis and discover the interaction of human arginine methyltransferase 3 (PRMT3) with the HIV-1 promoter. This interaction reverses latency in cell line models and primary cells from latently infected persons by increasing the levels of H4R3Me2a and transcription factor P-TEFb at the viral promoter. PRMT3 is found to promote chromatin accessibility and transcription of HIV-1 and a small subset of host genes in regions harboring the classical recognition motif for another transcription factor TEAD4. This motif attracts TEAD4 and PRMT3 to the viral promoter to synergistically activate transcription. Physical interactions among PRMT3, P-TEFb, and TEAD4 exist, which may help form a transcriptional hub at the viral promoter. Our study reveals the potential of targeting these hub proteins to eradicate latent HIV-1.

PMID:40374607 | DOI:10.1038/s41467-025-59578-5

Int J Sports Med. 2025 May 15. doi: 10.1055/a-2555-8961. Online ahead of print.

ABSTRACT

Durability is increasingly recognized as a determinant of cycling performance. However, its reliability remains unknown. In this study, we assessed the repeatability of durability (determined as the decline in power output after accumulated work). We recorded the highest power output values (maximum mean power values) attained by 18 professional cyclists (27±4 y) during training and competition for different effort durations (10 s and 1, 5, 10, and 20 min) after different levels of accumulated work (0-40 kJ/kg) during a cycling season. Repeatability was examined through the standard error of measurement and the intra-class correlation coefficient calculated from the two highest maximum mean power values obtained by each cyclist for each duration and level of accumulated work. A progressive decline of maximum mean power values compared to the non-fatigued state was observed after higher levels of accumulated work, particularly after 20 kJ/kg (p<0.001). All maximum mean power values showed high repeatability under fatigue states (all standard error of measurement<5% and intra-class correlation coefficient>0.90), with the lowest repeatability observed for the shortest efforts (10-s maximum mean power). These findings were confirmed separately for training sessions and competitions, albeit with lower repeatability (standard error of measurement<8% and intra-class correlation coefficient>0.80). The measure of durability appears therefore reliable, which might support its validity for monitoring field-based performance in professional cyclists.

PMID:40373793 | DOI:10.1055/a-2555-8961

Cell Stem Cell. 2025 May 7:S1934-5909(25)00178-X. doi: 10.1016/j.stem.2025.04.011. Online ahead of print.

ABSTRACT

Precise dorsal-ventral (D-V) patterning of the neural tube (NT) is essential for the development and function of the central nervous system. However, existing models for studying NT D-V patterning and related human diseases remain inadequate. Here, we present organizers derived from pluripotent stem cell aggregate fusion ("ORDER"), a method that establishes opposing BMP and SHH gradients within neural ectodermal cell aggregates. Using this approach, we generated NT organoids with ordered D-V patterning from both zebrafish and human pluripotent stem cells (hPSCs). Single-cell transcriptomic analysis revealed that the synthetic human NT organoids (hNTOs) closely resemble the human embryonic spinal cord at Carnegie stage 12 (CS12) and exhibit greater similarity to human NT than to mouse models. Furthermore, using the hNTO model, we demonstrated the critical role of WNT signaling in regulating intermediate progenitors, modeled TCTN2-related D-V patterning defects, and identified a rescue strategy.

PMID:40373768 | DOI:10.1016/j.stem.2025.04.011

Cell Genom. 2025 May 14;5(5):100875. doi: 10.1016/j.xgen.2025.100875.

ABSTRACT

Transcriptome-wide association studies (TWASs) help identify disease-causing genes but often fail to pinpoint disease mechanisms at the cellular level because of the limited sample sizes and sparsity of cell-type-specific expression data. Here, we propose scPrediXcan, which integrates state-of-the-art deep learning approaches that predict epigenetic features from DNA sequences with the canonical TWAS framework. Our prediction approach, ctPred, predicts cell-type-specific expression with high accuracy and captures complex gene-regulatory grammar that linear models overlook. Applied to type 2 diabetes (T2D) and systemic lupus erythematosus (SLE), scPrediXcan outperformed the canonical TWAS framework by identifying more candidate causal genes, explaining more genome-wide association study (GWAS) loci and providing insights into the cellular specificity of TWAS hits. Overall, our results demonstrate that scPrediXcan represents a significant advance, promising to deepen our understanding of the cellular mechanisms underlying complex diseases.

PMID:40373737 | DOI:10.1016/j.xgen.2025.100875

BMC Psychiatry. 2025 May 15;25(1):491. doi: 10.1186/s12888-025-06937-7.

ABSTRACT

BACKGROUND: Hypersensitivity to antipsychotic drugs is one of the supportive features of dementia with Lewy bodies, and side effects to drugs other than antipsychotics are also known to occur frequently. We experienced a case of dementia with Lewy bodies in which hallucinations and delusions repeatedly appeared and disappeared after administration and discontinuation of mirogabalin and pregabalin.

CASE PRESENTATION: The patient, a woman in her late 70s, developed hallucinations and delusional misidentification of places and persons immediately after receiving a prescription of mirogabalin (15 mg daily) for neuropathic pain. After discontinuation of mirogabalin, her hallucinatory delusions improved but remained. Mild dementia and mild parkinsonism were associated, cognitive fluctuations were evident, and dopamine-transporter scintigraphy showed bilateral striatal uptake reduction. Residual psychosis resolved with donepezil. Later, when the pain worsened, pregabalin (25 mg daily) was administered, and the psychosis recurred and resolved with discontinuation.

CONCLUSIONS: Although pregabalin-induced psychosis has been reported at higher doses (300-450 mg daily), it has not been reported at doses as low as those used in this patient. Gabapentinoids may cause psychosis in patients with dementia with Lewy bodies even at low doses, likely due to hypersensitivity to gabapentinoids in DLB.

PMID:40375230 | DOI:10.1186/s12888-025-06937-7

BMC Anesthesiol. 2025 May 15;25(1):247. doi: 10.1186/s12871-025-03109-8.

ABSTRACT

BACKGROUND: Children are at an increased risk of medication errors (MEs) during perioperative care compared to adult patients. This study aimed to critically look at medication errors and determine the frequency of adverse drug events and corrective measures taken for medication errors reported over 20 years in pediatric anesthetic care in the anesthesia department of a tertiary care teaching institution in a lower middle-income country (LMIC).

METHODS: Two investigators conducted a retrospective review of all critical incident forms received between January 2001 and December 2020 and identified medication errors related to patients aged 18 years or less. In the second phase of the audit, these medication errors were assessed in detail and adverse drug events were identified using a standardized protocol. We also analyzed the strategies that were employed to prevent such incidents in the future.

RESULTS: One hundred and ninety-six pediatric medication errors were identified. 40% of errors were reported in children between 13 and 72 months of age and 58% at induction. The majority of events took place during administration, preparation, and dispensing i.e., 45%, 41%, and 6% respectively. The adverse drug events occurred in 27 (1.2%) reports and life-threatening events in only one report.

CONCLUSION: 13% of the medication errors progressed to adverse drug events (ADE) and half of those were serious and life-threatening. Reinforcement of standard practice in departmental critical incident meetings, patient safety workshops and lessons to learn e-mails were some low-cost strategies to enhance medication safety during anesthesia.

PMID:40375141 | DOI:10.1186/s12871-025-03109-8

Fam Syst Health. 2025 Mar;43(1):173. doi: 10.1037/fsh0000910.

ABSTRACT

This short 55-word story highlights a clinical psychology doctoral student's work in therapy with individuals diagnosed with rare diseases. Upon diagnosis, clients may experience a range of emotions and feel isolated. Connection with a social network and support can increase hope and promote well-being. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

PMID:40372839 | DOI:10.1037/fsh0000910

J Med Internet Res. 2025 May 15;27:e69785. doi: 10.2196/69785.

ABSTRACT

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a common and progressive respiratory condition characterized by persistent airflow limitation and symptoms such as dyspnea, cough, and sputum production. Acute exacerbations (AE) of COPD (AE-COPD) are key determinants of disease progression; yet, existing predictive models relying mainly on spirometric measurements, such as forced expiratory volume in 1 second, reflect only a fraction of the physiological information embedded in respiratory function tests. Recent advances in artificial intelligence (AI) have enabled more sophisticated analyses of full spirometric curves, including flow-volume loops and volume-time curves, facilitating the identification of complex patterns associated with increased exacerbation risk.

OBJECTIVE: This study aimed to determine whether a predictive model that integrates clinical data and spirometry images with the use of AI improves accuracy in predicting moderate-to-severe and severe AE-COPD events compared to a clinical-only model.

METHODS: A retrospective cohort study was conducted using COPD registry data from 2 teaching hospitals from January 2004 to December 2020. The study included a total of 10,492 COPD cases, divided into a development cohort (6870 cases) and an external validation cohort (3622 cases). The AI-enhanced model (AI-PFT-Clin) used a combination of clinical variables (eg, history of AE-COPD, dyspnea, and inhaled treatments) and spirometry image data (flow-volume loop and volume-time curves). In contrast, the Clin model used only clinical variables. The primary outcomes were moderate-to-severe and severe AE-COPD events within a year of spirometry.

RESULTS: In the external validation cohort, the AI-PFT-Clin model outperformed the Clin model, showing an area under the receiver operating characteristic curve of 0.755 versus 0.730 (P<.05) for moderate-to-severe AE-COPD and 0.713 versus 0.675 (P<.05) for severe AE-COPD. The AI-PFT-Clin model demonstrated reliable predictive capability across subgroups, including younger patients and those without previous exacerbations. Higher AI-PFT-Clin scores correlated with elevated AE-COPD risk (adjusted hazard ratio for Q4 vs Q1: 4.21, P<.001), with sustained predictive stability over a 10-year follow-up period.

CONCLUSIONS: The AI-PFT-Clin model, by integrating clinical data with spirometry images, offers enhanced predictive accuracy for AE-COPD events compared to a clinical-only approach. This AI-based framework facilitates the early identification of high-risk individuals through the detection of physiological abnormalities not captured by conventional metrics. The model's robust performance and long-term predictive stability suggest its potential utility in proactive COPD management and personalized intervention planning. These findings highlight the promise of incorporating advanced AI techniques into routine COPD management, particularly in populations traditionally seen as lower risk, supporting improved management of COPD through tailored patient care.

PMID:40373296 | DOI:10.2196/69785

ACS Sens. 2025 May 15. doi: 10.1021/acssensors.4c03602. Online ahead of print.

ABSTRACT

The prevalence of sleep disorders in the aging population and the importance of sleep quality for health have emphasized the need for accurate and accessible sleep monitoring solutions. Polysomnography (PSG) remains the clinical gold standard for diagnosing sleep disorders; however, its discomfort and inconvenience limit its accessibility. To address these issues, a wearable device (WD) integrated with stretchable transparent electrodes (STEs) is developed in this study for multisignal sleep monitoring and artificial intelligence (AI)-driven sleep staging. Utilizing conductive and flexible STEs, the WD records multiple biological signals (electroencephalogram [EEG], electrooculogram [EOG], electromyogram [EMG], photoplethysmography, and motion data) with high precision and low noise, comparable to PSG (<4 μVRMS). It achieves a 73.2% accuracy and a macro F1 score of 0.72 in sleep staging using an AI model trained on multisignal inputs. Notably, accuracy marginally improves when using only the EEG, EOG, and EMG channels, which may simplify future device designs. This WD offers a compact, multisignal solution for at-home sleep monitoring, with the potential for use as an evaluation tool for personalized sleep therapies.

PMID:40373282 | DOI:10.1021/acssensors.4c03602

PLoS One. 2025 May 15;20(5):e0322586. doi: 10.1371/journal.pone.0322586. eCollection 2025.

ABSTRACT

Apples are one of the most productive fruits in the world, in addition to their nutritional and health advantages for humans. Even with the continuous development of AI in agriculture in general and apples in particular, automated systems continue to encounter challenges identifying rotten fruit and variations within the same apple category, as well as similarity in type, color, and shape of different fruit varieties. These issues, in addition to apple diseases, substantially impact the economy, productivity, and marketing quality. In this paper, we first provide a novel comprehensive collection named Apple Fruit Varieties Collection (AFVC) with 29,750 images through 85 classes. Second, we distinguish fresh and rotten apples with Apple Fruit Quality Categorization (AFQC), which has 2,320 photos. Third, an Apple Diseases Extensive Collection (ADEC), comprised of 2,976 images with seven classes, was offered. Fourth, following the state of the art, we develop an Optimized Apple Orchard Model (OAOM) with a new loss function named measured focal cross-entropy (MFCE), which assists in improving the proposed model's efficiency. The proposed OAOM gives the highest performance for apple varieties identification with AFVC; accuracy was 93.85%. For the apples rotten recognition with AFQC, accuracy was 98.28%. For the identification of the diseases via ADEC, it was 99.66%. OAOM works with high efficiency and outperforms the baselines. The suggested technique boosts apple system automation with numerous duties and outstanding effectiveness. This research benefits the growth of apple's robotic vision, development policies, automatic sorting systems, and decision-making enhancement.

PMID:40373081 | DOI:10.1371/journal.pone.0322586

PLoS One. 2025 May 15;20(5):e0322197. doi: 10.1371/journal.pone.0322197. eCollection 2025.

ABSTRACT

BACKGROUND: The use of Artificial Intelligence (AI) is exponentially rising in the healthcare sector. This change influences various domains of early identification, diagnosis, and treatment of diseases.

PURPOSE: This study examines the integration of AI in healthcare, focusing on its transformative potential in diagnostics and treatment, and the challenges and methodologies. shaping its future development.

METHODS: The review included 68 academic studies retracted from different databases (WOS, Scopus and Pubmed) from January 2020 and April 2024. After careful review and data analysis, AI methodologies, benefits and challenges, were summarized.

RESULTS: The number of studies showed a steady rise from 2020 to 2023. Most of them were the results of a collaborative work with international universities (92.1%). The majority (66.7%) were published in top-tier (Q1) journals and 40% were cited 2-10 times. The results have shown that AI tools such as deep learning methods and machine learning continue to significantly improve accuracy and timely execution of medical processes. Benefits were discussed from both the organizational and the patient perspective in the categories of diagnosis, treatment, consultation and health monitoring of diseases. However, some challenges may exist, despite these benefits, and are related to data integration, errors related to data processing and decision making, and patient safety.

CONCLUSION: The article examines the present status of AI in medical applications and explores its potential future applications. The findings of this review are useful for healthcare professionals to acquire deeper knowledge on the use of medical AI from design to implementation stage. However, a thorough assessment is essential to gather more insights into whether AI benefits outweigh its risks. Additionally, ethical and privacy issues need careful consideration.

PMID:40372995 | DOI:10.1371/journal.pone.0322197

JMIR Cancer. 2025 May 15;11:e64697. doi: 10.2196/64697.

ABSTRACT

BACKGROUND: Progression-free survival (PFS) is a crucial endpoint in cancer drug research. Clinician-confirmed cancer progression, namely real-world PFS (rwPFS) in unstructured text (ie, clinical notes), serves as a reasonable surrogate for real-world indicators in ascertaining progression endpoints. Response evaluation criteria in solid tumors (RECIST) is traditionally used in clinical trials using serial imaging evaluations but is impractical when working with real-world data. Manual abstraction of clinical progression from unstructured notes remains the gold standard. However, this process is a resource-intensive, time-consuming process. Natural language processing (NLP), a subdomain of machine learning, has shown promise in accelerating the extraction of tumor progression from real-world data in recent years.

OBJECTIVES: We aim to configure a pretrained, general-purpose health care NLP framework to transform free-text clinical notes and radiology reports into structured progression events for studying rwPFS on metastatic breast cancer (mBC) cohorts.

METHODS: This study developed and validated a novel semiautomated workflow to estimate rwPFS in patients with mBC using deidentified electronic health record data from the Nference nSights platform. The developed workflow was validated in a cohort of 316 patients with hormone receptor-positive, human epidermal growth factor receptor-2 (HER-2) 2-negative mBC, who were started on palbociclib and letrozole combination therapy between January 2015 and December 2021. Ground-truth datasets were curated to evaluate the workflow's performance at both the sentence and patient levels. NLP-captured progression or a change in therapy line were considered outcome events, while death, loss to follow-up, and end of the study period were considered censoring events for rwPFS computation. Peak reduction and cumulative decline in Patient Health Questionnaire-8 (PHQ-8) scores were analyzed in the progressed and nonprogressed patient subgroups.

RESULTS: The configured clinical NLP engine achieved a sentence-level progression capture accuracy of 98.2%. At the patient level, initial progression was captured within ±30 days with 88% accuracy. The median rwPFS for the study cohort (N=316) was 20 (95% CI 18-25) months. In a validation subset (n=100), rwPFS determined by manual curation was 25 (95% CI 15-35) months, closely aligning with the computational workflow's 22 (95% CI 15-35) months. A subanalysis revealed rwPFS estimates of 30 (95% CI 24-39) months from radiology reports and 23 (95% CI 19-28) months from clinical notes, highlighting the importance of integrating multiple note sources. External validation also demonstrated high accuracy (92.5% sentence level; 90.2% patient level). Sensitivity analysis revealed stable rwPFS estimates across varying levels of missing source data and event definitions. Peak reduction in PHQ-8 scores during the study period highlighted significant associations between patient-reported outcomes and disease progression.

CONCLUSIONS: This workflow enables rapid and reliable determination of rwPFS in patients with mBC receiving combination therapy. Further validation across more diverse external datasets and other cancer types is needed to ensure broader applicability and generalizability.

PMID:40372953 | DOI:10.2196/64697

IEEE Trans Ultrason Ferroelectr Freq Control. 2025 May 15;PP. doi: 10.1109/TUFFC.2025.3570496. Online ahead of print.

ABSTRACT

Ultrasound localization microscopy (ULM) has revolutionized microvascular imaging by breaking the acoustic diffraction limit. However, different ULM workflows depend heavily on distinct prior knowledge, such as the impulse response and empirical selection of parameters (e.g., the number of microbubbles (MBs) per frame M), or the consistency of training-test dataset in deep learning (DL)-based studies. We hereby propose a general ULM pipeline that reduces priors. Our approach leverages a DL model that simultaneously distills microbubble signals and reduces speckle from every frame without estimating the impulse response and M. Our method features an efficient channel attention vision transformer (ViT) and a progressive learning strategy, enabling it to learn global information through training on progressively increasing patch sizes. Ample synthetic data were generated using the k-Wave toolbox to simulate various MB patterns, thus overcoming the deficiency of labeled data. The ViT output was further processed by a standard radial symmetry method for sub-pixel localization. Our method performed well on model-unseen public datasets: one in silico dataset with ground truth and four in vivo datasets of mouse tumor, rat brain, rat brain bolus, and rat kidney. Our pipeline outperformed conventional ULM, achieving higher positive predictive values (precision in DL, 0.88-0.41 vs. 0.83-0.16) and improved accuracy (root-mean-square errors: 0.25-0.14 λ vs. 0.31-0.13 λ) across a range of signal-to-noise ratios from 60 dB to 10 dB. Our model could detect more vessels in diverse in vivo datasets while achieving comparable resolutions to the standard method. The proposed ViT-based model, seamlessly integrated with state-of-the-art downstream ULM steps, improved the overall ULM performance with no priors.

PMID:40372868 | DOI:10.1109/TUFFC.2025.3570496

IEEE Trans Neural Netw Learn Syst. 2025 May 15;PP. doi: 10.1109/TNNLS.2025.3566021. Online ahead of print.

ABSTRACT

Speech enhancement (SE) is critical for improving speech intelligibility and quality in various audio devices. In recent years, deep learning-based methods have significantly improved SE performance, but they often come with a high computational cost, which is prohibitive for a large number of edge devices, such as headsets and hearing aids. This work proposes an ultralow-power SE system based on the brain-inspired spiking neural network (SNN) called Spiking-FullSubNet. Spiking-FullSubNet follows a full-band and subband fusioned approach to effectively capture both global and local spectral information. To enhance the efficiency of computationally expensive subband modeling, we introduce a frequency partitioning method inspired by the sensitivity profile of the human peripheral auditory system. Furthermore, we introduce a novel spiking neuron model that can dynamically control the input information integration and forgetting, enhancing the multiscale temporal processing capability of SNN, which is critical for speech denoising. Experiments conducted on the recent Intel Neuromorphic Deep Noise Suppression (N-DNS) Challenge dataset show that the Spiking-FullSubNet surpasses state-of-the-art (SOTA) methods by large margins in terms of both speech quality and energy efficiency metrics. Notably, our system won the championship of the Intel N-DNS Challenge (algorithmic track), opening up a myriad of opportunities for ultralow-power SE at the edge. Our source code and model checkpoints are publicly available at github.com/haoxiangsnr/spiking-fullsubnet.

PMID:40372867 | DOI:10.1109/TNNLS.2025.3566021

IEEE Trans Med Imaging. 2025 May 15;PP. doi: 10.1109/TMI.2025.3570342. Online ahead of print.

ABSTRACT

Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation exposure to patients and healthcare providers. Reducing the tracer injection dose and eliminating the CT acquisition for attenuation correction can reduce the overall radiation dose, but often results in PET with high noise and bias. Thus, it is desirable to develop 3D methods to translate the non-attenuation-corrected low-dose PET (NAC-LDPET) into attenuation-corrected standard-dose PET (AC-SDPET). Recently, diffusion models have emerged as a new state-of-the-art deep learning method for image-to-image translation, better than traditional CNN-based methods. However, due to the high computation cost and memory burden, it is largely limited to 2D applications. To address these challenges, we developed a novel 2.5D Multi-view Averaging Diffusion Model (MADM) for 3D image-to-image translation with application on NAC-LDPET to AC-SDPET translation. Specifically, MADM employs separate diffusion models for axial, coronal, and sagittal views, whose outputs are averaged in each sampling step to ensure the 3D generation quality from multiple views. To accelerate the 3D sampling process, we also proposed a strategy to use the CNN-based 3D generation as a prior for the diffusion model. Our experimental results on human patient studies suggested that MADM can generate high-quality 3D translation images, outperforming previous CNN-based and Diffusion-based baseline methods. The code is available at https://github.com/tianqic/MADM.

PMID:40372846 | DOI:10.1109/TMI.2025.3570342

Science. 2025 May 15;388(6748):eadk5081. doi: 10.1126/science.adk5081. Epub 2025 May 15.

ABSTRACT

Genome sequencing of 1537 individuals from 139 ethnic groups reveals the genetic characteristics of understudied populations in North Asia and South America. Our analysis demonstrates that West Siberian ancestry, represented by the Kets and Nenets, contributed to the genetic ancestry of most Siberian populations. West Beringians, including the Koryaks, Inuit, and Luoravetlans, exhibit genetic adaptation to Arctic climate, including medically relevant variants. In South America, early migrants split into four groups-Amazonians, Andeans, Chaco Amerindians, and Patagonians-~13,900 years ago. Their longest migration led to population decline, whereas settlement in South America's diverse environments caused instant spatial isolation, reducing genetic and immunogenic diversity. These findings highlight how population history and environmental pressures shaped the genetic architecture of human populations across North Asia and South America.

PMID:40373127 | DOI:10.1126/science.adk5081