J Clin Endocrinol Metab. 2025 Feb 20:dgaf099. doi: 10.1210/clinem/dgaf099. Online ahead of print.

ABSTRACT

BACKGROUND: Highly effective CFTR modulators, such as elexacaftor/tezacaftor/ivacaftor (ETI), herald a new era in therapeutic strategy of cystic fibrosis (CF). ETI impact on glucose tolerance remains controversial.

METHODS: All the participants underwent a baseline oral glucose tolerance test (OGTT) before ETI initiation (M0) and 12 months (M12), and at 24 months if possible. The cohort was stratified in two subgroups based on the baseline OGTT: normal glucose tolerance (NGT) and abnormal glucose tolerance (AGT) defined by impaired fasting glucose or impaired glucose tolerance or diabetes not requiring insulin treatment.

RESULTS: We included 106 adolescents with CF (age 14.1±1.5 years), 75 with NGT, 31 with AGT. The baseline characteristics of the two groups were similar except for a higher glucose level at 1 and 2-h OGTT in the AGT group. ETI induced an increase in BMIz-score and in Forced Expiratory Volume in 1 second (FEV1) (p<0.001). After 12 months, participants with NGT did not experience any change of 1-h and 2-h glucose. By contrast, those with AGT displayed a reduction of 2-h glucose at M12 (p=0.006). 15out of the 31 (48%) adolescents in the AGT group reversed to NGT but 9/75 (17%) in the NGT group progressed to AGT. 3 participants with CF related diabetes at baseline reversed to AGT. 1-hour glucose concentrations at or above 8.7 mmol/L (157mg/dL) during baseline OGTT had 80% sensitivity to identify those with AGT at 12 months (OR 1.51 [1.20, 1.92], p=0.001). 20 participants had a 24-month OGTT that confirmed preserved insulin secretion.

CONCLUSION: ETI may improve glucose tolerance in adolescents with CF by preserving insulin secretion. 1-hour glucose during the OGTT helps to detect risk for AGT after ETI treatment.

PMID:39977216 | DOI:10.1210/clinem/dgaf099

JCO Clin Cancer Inform. 2025 Feb;9:e2400198. doi: 10.1200/CCI-24-00198. Epub 2025 Feb 20.

ABSTRACT

PURPOSE: Primary barriers to application of immune checkpoint inhibitor (ICI) therapy for cancer include severe side effects (such as potentially life threatening pneumonitis [PN]), which can cause the discontinuation of treatment. Predicting which patients may develop PN while on ICI would improve both safety and potential efficacy because treatments could be safely administered for longer or discontinued before severe toxicity.

METHODS: Starting from a cohort of 3,351 patients with cancer who received previous ICI therapy at the Vanderbilt University Medical Center, we curated 2,700 contrast chest computed tomography (CT) volumes for 671 patients. Three different pure imaging models predicted the potential for PN using only a single time point before the first ICI dose.

RESULTS: The first model used 109 radiomics features only and achieved an AUC of 0.747 (CI, 0.705 to 0.789) with a positive predictive value (PPV) of 0.244 (CI, 0.211 to 0.276) at a sensitivity of 0.553 (CI, 0.485 to 0.621) using mainly features describing the global lung properties. The second model used a convolutional neural network (CNN) on the raw CTs to improve to an AUC of 0.819 (CI, 0.781 to 0.857) with a PPV of 0.244 (CI, 0.203 to 0.284) at a sensitivity of 0.743 (CI, 0.681 to 0.806). The third model combined both radiomics and deep learning but, with an AUC of 0.829 (CI, 0.797 to 0.862) and a PPV of 0.254 (CI, 0.228 to 0.281) at a sensitivity of 0.780 (CI, 0.721 to 0.840), did not show a significant improvement on the CNN-only model.

CONCLUSION: This new model suggests the utility of deep learning in PN prediction over traditional pure radiomics and promises better management for patients receiving ICI and the ability to better stratify patients in immunotherapy drug trials.

PMID:39977708 | DOI:10.1200/CCI-24-00198

Hum Reprod Update. 2025 Feb 20:dmaf002. doi: 10.1093/humupd/dmaf002. Online ahead of print.

ABSTRACT

BACKGROUND: Ovarian aging occurs earlier than the aging of many other organs and has a lasting impact on women's overall health and well-being. However, effective interventions to slow ovarian aging remain limited, primarily due to an incomplete understanding of the underlying molecular mechanisms and drug targets. Recent advances in omics data resources, combined with innovative computational tools, are offering deeper insight into the molecular complexities of ovarian aging, paving the way for new opportunities in drug discovery and development.

OBJECTIVE AND RATIONALE: This review aims to synthesize the expanding multi-omics data, spanning genome, transcriptome, proteome, metabolome, and microbiome, related to ovarian aging, from both tissue-level and single-cell perspectives. We will specially explore how the analysis of these emerging omics datasets can be leveraged to identify novel drug targets and guide therapeutic strategies for slowing and reversing ovarian aging.

SEARCH METHODS: We conducted a comprehensive literature search in the PubMed database using a range of relevant keywords: ovarian aging, age at natural menopause, premature ovarian insufficiency (POI), diminished ovarian reserve (DOR), genomics, transcriptomics, epigenomics, DNA methylation, RNA modification, histone modification, proteomics, metabolomics, lipidomics, microbiome, single-cell, genome-wide association studies (GWAS), whole-exome sequencing, phenome-wide association studies (PheWAS), Mendelian randomization (MR), epigenetic target, drug target, machine learning, artificial intelligence (AI), deep learning, and multi-omics. The search was restricted to English-language articles published up to September 2024.

OUTCOMES: Multi-omics studies have uncovered key mechanisms driving ovarian aging, including DNA damage and repair deficiencies, inflammatory and immune responses, mitochondrial dysfunction, and cell death. By integrating multi-omics data, researchers can identify critical regulatory factors and mechanisms across various biological levels, leading to the discovery of potential drug targets. Notable examples include genetic targets such as BRCA2 and TERT, epigenetic targets like Tet and FTO, metabolic targets such as sirtuins and CD38+, protein targets like BIN2 and PDGF-BB, and transcription factors such as FOXP1.

WIDER IMPLICATIONS: The advent of cutting-edge omics technologies, especially single-cell technologies and spatial transcriptomics, has provided valuable insights for guiding treatment decisions and has become a powerful tool in drug discovery aimed at mitigating or reversing ovarian aging. As technology advances, the integration of single-cell multi-omics data with AI models holds the potential to more accurately predict candidate drug targets. This convergence offers promising new avenues for personalized medicine and precision therapies, paving the way for tailored interventions in ovarian aging.

REGISTRATION NUMBER: Not applicable.

PMID:39977580 | DOI:10.1093/humupd/dmaf002

PLoS One. 2025 Feb 20;20(2):e0317461. doi: 10.1371/journal.pone.0317461. eCollection 2025.

ABSTRACT

Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevolution algorithm, denoted as ANEAT. First, sample features are applied to the transfer function using a pointwise intensity transformation to obtain new feature samples. It solves the problems of imbalanced data samples and insufficient diversity. Second, the feature importance score sorting and Sparse PCA dimensionality reduction are performed on the data-augmented samples. It provides the initial genome code for the evolutionary neural network. Finally, an evolutionary neural network for CGO prediction is constructed through population initialization, fitness evaluation, species differentiation, genome mutation, and recombination. The optimal phenotype is obtained in the evolutionary generations. In the experiment, we verify the effectiveness of ANEAT from multiple aspects such as data augmentation effectiveness analysis, deep learning model comparison, swarm intelligence optimization algorithm comparison, and other method comparisons. The results show that the MAE, RMSE, and EVAR indexes of ANEAT on the test set are 0.0816, 0.1322, and 0.8972, respectively. It has the optimal CGO prediction effect. ANEAT realizes the high-precision mapping of feature parameters and outburst risk with a lightweight network architecture, which can be well applied to CGO prediction.

PMID:39977390 | DOI:10.1371/journal.pone.0317461

Bioinformatics. 2025 Feb 20:btaf078. doi: 10.1093/bioinformatics/btaf078. Online ahead of print.

ABSTRACT

MOTIVATION: S-sulfhydration, a crucial post-translational protein modification, is pivotal in cellular recognition, signaling processes, and the development and progression of cardiovascular and neurological disorders, so identifying S-sulfhydration sites is crucial for studies in cell biology. Deep learning shows high efficiency and accuracy in identifying protein sites compared to traditional methods that often lack sensitivity and specificity in accurately locating nonsulfhydration sites. Therefore, we employ deep learning methods to tackle the challenge of pinpointing S-sulfhydration sites.

RESULTS: In this work, we introduce a deep learning approach called Sul-BertGRU, designed specifically for predicting S-sulfhydration sites in proteins, that integrates multi-directional gated recurrent unit (GRU) and BERT. First, Sul-BertGRU proposes an information entropy-enhanced BERT (IE-BERT) to preprocess protein sequences and extract initial features. Subsequently, confidence learning is employed to eliminate potential S-sulfhydration samples from the nonsulfhydration samples and select reliable negative samples. Then, considering the directional nature of the modification process, protein sequences are categorized into left, right, and full sequences centred on cysteines. We build a multi-directional GRU to enhance the extraction of directional sequence features and model the details of the enzymatic reaction involved in S-sulfhydration. Ultimately, we apply a parallel multi-head self-attention mechanism alongside a convolutional neural network (CNN) to deeply analyze sequence features that might be missed at a local level. Sul-BertGRU achieves sensitivity, specificity, precision, accuracy, Matthews correlation coefficient, and area under the curve scores of 85.82%, 68.24%, 74.80%, 77.44%, 55.13%, and 77.03%, respectively. Sul-BertGRU demonstrates exceptional performance and proves to be a reliable method for predicting protein S-sulfhydration sites.

AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/Severus0902/Sul-BertGRU/.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39977366 | DOI:10.1093/bioinformatics/btaf078

Proc Natl Acad Sci U S A. 2025 Feb 25;122(8):e2411492122. doi: 10.1073/pnas.2411492122. Epub 2025 Feb 20.

ABSTRACT

Longitudinal imaging data are routinely acquired for health studies and patient monitoring. A central goal in longitudinal studies is tracking relevant change over time. Traditional methods remove nuisance variation with custom pipelines to focus on significant changes. In this work, we present a machine learning-based method that automatically ignores irrelevant changes and extracts the time-varying signal of interest. Our method, called Learning-based Inference of Longitudinal imAge Changes (LILAC), performs a pairwise comparison of longitudinal images in order to make a temporal difference prediction. LILAC employs a convolutional Siamese architecture to extract feature pairs, followed by subtraction and a bias-free fully connected layer to learn meaningful temporal image differences. We first showcase LILAC's ability to capture key longitudinal changes by simply training it to predict the temporal ordering of images. In our experiments, temporal ordering accuracy exceeded 0.98, and predicted time differences were strongly correlated with actual changes in relevant variables (Pearson Correlation Coefficient r = 0.911 with embryo phase change, and r = 0.875 with time interval in wound healing). Next, we trained LILAC to explicitly predict specific targets, such as the change in clinical scores in patients with mild cognitive impairment. LILAC models achieved over a 40% reduction in root mean square error compared to baseline methods. Our empirical results demonstrate that LILAC effectively localizes and quantifies relevant individual-level changes in longitudinal imaging data, offering valuable insights for studying temporal mechanisms or guiding clinical decisions.

PMID:39977323 | DOI:10.1073/pnas.2411492122

Science. 2025 Feb 21;387(6736):eadp2407. doi: 10.1126/science.adp2407. Epub 2025 Feb 21.

ABSTRACT

Clinical diagnosis typically incorporates physical examination, patient history, various laboratory tests, and imaging studies but makes limited use of the human immune system's own record of antigen exposures encoded by receptors on B cells and T cells. We analyzed immune receptor datasets from 593 individuals to develop MAchine Learning for Immunological Diagnosis, an interpretive framework to screen for multiple illnesses simultaneously or precisely test for one condition. This approach detects specific infections, autoimmune disorders, vaccine responses, and disease severity differences. Human-interpretable features of the model recapitulate known immune responses to severe acute respiratory syndrome coronavirus 2, influenza, and human immunodeficiency virus, highlight antigen-specific receptors, and reveal distinct characteristics of systemic lupus erythematosus and type-1 diabetes autoreactivity. This analysis framework has broad potential for scientific and clinical interpretation of immune responses.

PMID:39977494 | DOI:10.1126/science.adp2407

Science. 2025 Feb 21;387(6736):880-885. doi: 10.1126/science.ads7942. Epub 2025 Feb 20.

ABSTRACT

The vision of robotic materials-cohesive collectives of robotic units that can arrange into virtually any form with any physical properties-has long intrigued both science and fiction. Yet, this vision requires a fundamental physical challenge to be overcome: The collective must be strong, to support loads, yet flow, to take new forms. We achieve this in a material-like robotic collective by modulating the interunit tangential forces to control topological rearrangements of units within a tightly packed structure. This allows local control of rigidity transitions between solid and fluid-like states in the collective and enables spatiotemporal control of shape and strength. We demonstrate structure-forming and healing and show the collective supporting 700 newtons (500 times the weight of a robot) before "melting" under its own weight.

PMID:39977492 | DOI:10.1126/science.ads7942

Proc Natl Acad Sci U S A. 2025 Feb 25;122(8):e2420164122. doi: 10.1073/pnas.2420164122. Epub 2025 Feb 20.

ABSTRACT

Biosynthetic gene clusters (BGCs) are sets of often heterologous genes that are genetically and functionally linked. Among eukaryotes, BGCs are most common in plants and fungi and ensure the coexpression of the different enzymes coordinating the biosynthesis of specialized metabolites. Here, we report the identification of a withanolide BGC in Physalis grisea (ground-cherry), a member of the nightshade family (Solanaceae). A combination of transcriptomic, epigenomic, and metabolic analyses revealed that, following a duplication event, this BGC evolved two tissue-specifically expressed subclusters, containing several pairs of paralogs that contribute to related but distinct biochemical processes; this subfunctionalization is tightly associated with epigenetic features and the local chromatin environment. The two subclusters appear strictly isolated from each other at the structural chromatin level, each forming a highly self-interacting chromatin domain with tissue-dependent levels of condensation. This correlates with gene expression in either above- or below-ground tissue, thus spatially separating the production of different withanolide compounds. By comparative phylogenomics, we show that the withanolide BGC most likely evolved before the diversification of the Solanaceae family and underwent lineage-specific diversifications and losses. The tissue-specific subfunctionalization is common to species of the Physalideae tribe but distinct from other, independent duplication events outside of this clade. In sum, our study reports on an instance of an epigenetically modulated subfunctionalization within a BGC and sheds light on the biosynthesis of withanolides, a highly diverse group of steroidal triterpenoids important in plant defense and amenable to pharmaceutical applications due to their anti-inflammatory, antibiotic, and anticancer properties.

PMID:39977312 | DOI:10.1073/pnas.2420164122

J Infect Dev Ctries. 2025 Jan 31;19(1):58-66. doi: 10.3855/jidc.19554.

ABSTRACT

INTRODUCTION: A prescribing cascade occurs when new medications are prescribed to address an adverse drug reaction (ADR) associated with the preceding use of a medication, which may be mistaken as the onset of a novel disease or condition. The aim of this study was to evaluate the perceptions of hospital pharmacists regarding roles in preventing and minimizing prescribing cascades.

METHODOLOGY: A qualitative, semi-structured interview, followed by a quantitative, questionnaire-based study, was carried out at the Shifa International Hospital (SIH; Islamabad, Pakistan). Discharge summaries of patients aged ≥ 60 years were collected to assess the prevalence of polypharmacy at SIH.

RESULTS: Discharge summaries of n = 350 patients were collected; 60.2% (n = 211) had comorbid conditions, and the co-occurrence of diabetes and hypertension were the most common. 37.8% (n = 132) were taking 8 or more medications. Eight (n = 8) hospital pharmacists participated in the qualitative study, and 4 major themes were identified in their perceptions regarding prescribing cascades. Fifty-two (n = 52) pharmacists were recruited in the quantitative phase. 86.5% (n = 45) of the participants reported long standing illness/chronic conditions; 67.3% (n = 35) noted the presence of comorbidities as a high risk, while 90.3% (n = 47) noted multiple prescribers, and 75.0% (n = 39) identified the ageing population as important risks factors for polypharmacy.

CONCLUSIONS: The current research may inform the role and responsibilities of hospital pharmacists in outpatient and inpatient departments, and in interprofessional care teams, in preventing and minimizing prescribing cascades.

PMID:39977468 | DOI:10.3855/jidc.19554

Expert Opin Drug Saf. 2025 Feb 20:1-9. doi: 10.1080/14740338.2025.2468861. Online ahead of print.

ABSTRACT

BACKGROUND: Drug-induced hypokalemia is often associated with adverse clinical outcomes, and unfortunately, the inability to fully understand the drugs that cause hypokalemia puts us in a passive position. This study applies pharmacovigilance data to present a panorama of suspected medications associated with hyperkalemia.

RESEARCH DESIGN AND METHODS: This study used disproportionality analysis to mine adverse events in OpenFDA, identified all suspected drugs that caused hypokalemia, and coded and classified the suspected drugs according to the Anatomical Therapeutic Chemical (ATC) classification system.

RESULTS: There are 19755 reports related to drug-induced hypokalemia. The majority of individuals with hypokalemia are females, with a concentrated age range of 65 to 84 years old. After the occurrence of hypokalemia, 8.02% died due to hypokalemia. This study identified 1141 suspected drugs, and among the top 50 drugs, 32 drugs did not include hypokalemia in their instructions. All suspected drugs can be categorized into 73 subgroups according to the ATC classification system.

CONCLUSIONS: By mining the OpenFDA database, we have identified all suspected drugs that cause hypokalemia and conducted a comprehensive evaluation. The instructions for most of the suspected drugs do not focus on hypokalemia. When the treatment regimen includes other drugs that can directly/indirectly cause a decrease in blood potassium, we recommend actively monitoring blood potassium when using suspected drugs.

PMID:39977281 | DOI:10.1080/14740338.2025.2468861

Microbiology (Reading). 2025 Feb;171(2). doi: 10.1099/mic.0.001536.

ABSTRACT

Obtaining sputum samples from people with cystic fibrosis (pwCF) for microbiology has become challenging due to the positive clinical effects of the cystic fibrosis transmembrane conductance regulator modulator therapy, elexacaftor-tezacaftor-ivacaftor (ETI). Although ETI improves lung function and reduces sputum production, recent data shows that bacterial pathogens persist, making continued monitoring of infection important. As an alternative to sputum sampling, this study developed a non-invasive technique called 'Cough Breath' (CB) to identify volatile organic compounds (VOCs) in exhaled breath condensate (EBC) and link them to cystic fibrosis (CF) bacterial pathogens using purge and trap GC-MS. The CB culturing approach was able to isolate pathogens from expectorated particulates simultaneously with EBC collection; however, culturing positivity was low, with 6% of samples collected (n=47) positive for either Pseudomonas aeruginosa or Staphylococcus aureus. From EBC, we identified VOCs matching those uniquely produced by P. aeruginosa (7), S. aureus (12), Achromobacter xylosoxidans (8) and Granulicatella adiacens (2); however, the overall detection rate was also low. Expanding to VOCs produced across multiple pathogens identified 30 frequently detected in the EBC of pwCF, including 2,3-pentanedione, propyl pyruvate, oxalic acid diallyl ester, methyl isobutyl ketone, methyl nitrate, 2-propenal, acetonitrile, acetoin and 2,3-butanedione. Comparing isolate volatilomes and EBC samples from the same pwCF enhanced detection rates with key VOCs, such as 2,3-pentanedione (86%) and propyl pyruvate (83%), in P. aeruginosa isolates. Further investigation showed that VOC production differed across strains and at different growth phases, creating variability that may explain the overall low EBC detection rate. Although this study successfully cultured CF pathogens from cough particulates and matched their unique VOCs in EBC samples, our results indicate that microbial volatiles more generally indicative of infection, such as 2,3-pentanedione, may have the most utility in aiding diagnostics in pwCF on ETI who have reduced sputum production in the clinic.

PMID:39976612 | DOI:10.1099/mic.0.001536

Int J Comput Assist Radiol Surg. 2025 Feb 20. doi: 10.1007/s11548-025-03335-y. Online ahead of print.

ABSTRACT

PURPOSE: While deep learning methods have shown great promise in improving the effectiveness of prostate cancer (PCa) diagnosis by detecting suspicious lesions from trans-rectal ultrasound (TRUS), they must overcome multiple simultaneous challenges. There is high heterogeneity in tissue appearance, significant class imbalance in favor of benign examples, and scarcity in the number and quality of ground truth annotations available to train models. Failure to address even a single one of these problems can result in unacceptable clinical outcomes.

METHODS: We propose TRUSWorthy, a carefully designed, tuned, and integrated system for reliable PCa detection. Our pipeline integrates self-supervised learning, multiple-instance learning aggregation using transformers, random-undersampled boosting and ensembling: These address label scarcity, weak labels, class imbalance, and overconfidence, respectively. We train and rigorously evaluate our method using a large, multi-center dataset of micro-ultrasound data.

RESULTS: Our method outperforms previous state-of-the-art deep learning methods in terms of accuracy and uncertainty calibration, with AUROC and balanced accuracy scores of 79.9% and 71.5%, respectively. On the top 20% of predictions with the highest confidence, we can achieve a balanced accuracy of up to 91%.

CONCLUSION: The success of TRUSWorthy demonstrates the potential of integrated deep learning solutions to meet clinical needs in a highly challenging deployment setting, and is a significant step toward creating a trustworthy system for computer-assisted PCa diagnosis.

PMID:39976857 | DOI:10.1007/s11548-025-03335-y

Eur J Trauma Emerg Surg. 2025 Feb 20;51(1):115. doi: 10.1007/s00068-025-02779-w.

ABSTRACT

OBJECTIVES: Pediatric elbow fractures are a common injury among children. Recent advancements in artificial intelligence (AI), particularly deep learning (DL), have shown promise in diagnosing these fractures. This study systematically evaluated the performance of DL models in detecting pediatric elbow fractures.

MATERIALS AND METHODS: A comprehensive search was conducted in PubMed (Medline), EMBASE, and IEEE Xplore for studies published up to October 20, 2023. Studies employing DL models for detecting elbow fractures in patients aged 0 to 16 years were included. Key performance metrics, including sensitivity, specificity, and area under the curve (AUC), were extracted. The study was registered in PROSPERO (ID: CRD42023470558).

RESULTS: The search identified 22 studies, of which six met the inclusion criteria for the meta-analysis. The pooled sensitivity of DL models for pediatric elbow fracture detection was 0.93 (95% CI: 0.91-0.96). Specificity values ranged from 0.84 to 0.92 across studies, with a pooled estimate of 0.89 (95% CI: 0.85-0.92). The AUC ranged from 0.91 to 0.99, with a pooled estimate of 0.95 (95% CI: 0.93-0.97). Further analysis highlighted the impact of preprocessing techniques and the choice of model backbone architecture on performance.

CONCLUSION: DL models demonstrate exceptional accuracy in detecting pediatric elbow fractures. For optimal performance, we recommend leveraging backbone architectures like ResNet, combined with manual preprocessing supervised by radiology and orthopedic experts.

PMID:39976732 | DOI:10.1007/s00068-025-02779-w

Eur J Nucl Med Mol Imaging. 2025 Feb 20. doi: 10.1007/s00259-025-07145-x. Online ahead of print.

ABSTRACT

BACKGROUND: Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is a well-established modality for noninvasive diagnostic assessment of coronary artery disease (CAD). However, the time-consuming and experience-dependent visual interpretation of SPECT images remains a limitation in the clinic.

PURPOSE: We aimed to develop advanced models to diagnose CAD using different supervised and semi-supervised deep learning (DL) algorithms and training strategies, including transfer learning and data augmentation, with SPECT-MPI and invasive coronary angiography (ICA) as standard of reference.

MATERIALS AND METHODS: A total of 940 patients who underwent SPECT-MPI were enrolled (281 patients included ICA). Quantitative perfusion SPECT (QPS) was used to extract polar maps of rest and stress states. We defined two different tasks, including (1) Automated CAD diagnosis with expert reader (ER) assessment of SPECT-MPI as reference, and (2) CAD diagnosis from SPECT-MPI based on reference ICA reports. In task 2, we used 6 strategies for training DL models. We implemented 13 different DL models along with 4 input types with and without data augmentation (WAug and WoAug) to train, validate, and test the DL models (728 models). One hundred patients with ICA as standard of reference (the same patients in task 1) were used to evaluate models per vessel and per patient. Metrics, such as the area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity, precision, and balanced accuracy were reported. DeLong and pairwise Wilcoxon rank sum tests were respectively used to compare models and strategies after 1000 bootstraps on the test data for all models. We also compared the performance of our best DL model to ER's diagnosis.

RESULTS: In task 1, DenseNet201 Late Fusion (AUC = 0.89) and ResNet152V2 Late Fusion (AUC = 0.83) models outperformed other models in per-vessel and per-patient analyses, respectively. In task 2, the best models for CAD prediction based on ICA were Strategy 3 (a combination of ER- and ICA-based diagnosis in train data), WoAug InceptionResNetV2 EarlyFusion (AUC = 0.71), and Strategy 5 (semi-supervised approach) WoAug ResNet152V2 EarlyFusion (AUC = 0.77) in per-vessel and per-patient analyses, respectively. Moreover, saliency maps showed that models could be helpful for focusing on relevant spots for decision making.

CONCLUSION: Our study confirmed the potential of DL-based analysis of SPECT-MPI polar maps in CAD diagnosis. In the automation of ER-based diagnosis, models' performance was promising showing accuracy close to expert-level analysis. It demonstrated that using different strategies of data combination, such as including those with and without ICA, along with different training methods, like semi-supervised learning, can increase the performance of DL models. The proposed DL models could be coupled with computer-aided diagnosis systems and be used as an assistant to nuclear medicine physicians to improve their diagnosis and reporting, but only in the LAD territory.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:39976703 | DOI:10.1007/s00259-025-07145-x

J Appl Clin Med Phys. 2025 Feb 20:e70031. doi: 10.1002/acm2.70031. Online ahead of print.

ABSTRACT

PURPOSE: To compare image quality and clinical utility of a T2-weighted (T2W) 3-dimensional (3D) fast spin echo (FSE) sequence using deep learning reconstruction (DLR) versus conventional reconstruction for rectal magnetic resonance imaging (MRI).

METHODS: The study included 50 patients with rectal cancer who underwent rectal MRI consecutively between July 7, 2020 and January 20, 2021 using a T2W 3D FSE sequence with DLR and conventional reconstruction. Three radiologists reviewed the two sets of images, scoring overall SNR, motion artifacts, and overall image quality on a 3-point scale and indicating clinical preference for DLR or conventional reconstruction based on those three criteria as well as image characterization of bowel wall layer definition, tumor invasion of muscularis propria, residual disease, fibrosis, nodal margin, and extramural venous invasion.

RESULTS: Image quality was rated as moderate or good for both DLR and conventional reconstruction for most cases. DLR was preferred over conventional reconstruction in all of the categories except for bowel wall layer definition.

CONCLUSION: Both conventional reconstruction and DLR provide acceptable image quality for T2W 3D FSE imaging of rectal cancer. DLR was clinically preferred over conventional reconstruction in almost all categories.

PMID:39976552 | DOI:10.1002/acm2.70031

Med Phys. 2025 Feb 20. doi: 10.1002/mp.17696. Online ahead of print.

ABSTRACT

BACKGROUND: Deformable medical image registration aims to align image pairs with local differences, improving the accuracy of medical analyses and assisting various diagnostic scenarios.

PURPOSE: We aim to overcome these challenges: Deep learning-based registration approaches have greatly enhanced registration speed and accuracy by continuously improving registration networks and processes. However, the lack of extensive medical datasets limits the complexity of registration models. Optimizing registration networks within a fixed dataset often leads to overfitting, hindering further accuracy improvements and reducing generalization capabilities.

METHODS: We explore the application of the foundational model DINOv2 to registration tasks, leveraging its prior knowledge to support learning-based unsupervised registration networks and overcome network bottlenecks to improve accuracy. We investigate three modes of DINOv2-assisted registration, including direct registration architecture, enhanced architecture, and refined architecture. Additionally, we study the applicability of three feature aggregation methods-convolutional interaction, direct fusion, and cross-attention-within the proposed DINOv2-based registration frameworks.

RESULTS: We conducted extensive experiments on the IXI and OASIS public datasets, demonstrating that the enhanced and refined architectures notably improve registration accuracy, reduce data dependency, and maintain strong generalization capabilities.

CONCLUSION: This study offers novel approaches for applying foundational models to deformable image registration tasks.

PMID:39976314 | DOI:10.1002/mp.17696

Stat Med. 2025 Feb 28;44(5):e70020. doi: 10.1002/sim.70020.

ABSTRACT

Freezing of Gait (FOG) is a prevalent symptom in advanced Parkinson's Disease (PD), characterized by intermittent transitions between normal gait and freezing episodes. This study introduces a novel graph-theoretic approach to detect FOG from video data of PD patients. We construct a sequence of pose graphs that represent the spatial relations and temporal progression of a patient's posture over time. Each graph node corresponds to an estimated joint position, while the edges reflect the anatomical connections and their proximity. We propose a hypothesis testing procedure that deploys the Fréchet statistics to identify break points in time between regular gait and FOG episodes, where we model the central tendency and dispersion of the pose graphs in the presentation of graph Laplacian matrices by computing their Fréchet mean and variance. We implement binary segmentation and incremental computation in our algorithm for efficient calculation. The proposed framework is validated on two datasets, Kinect3D and AlphaPose, demonstrating its effectiveness in detecting FOG from video data. The proposed approach that extracts matrix features is distinct from the prevailing pixel-based deep learning methods. It provides a new perspective on feature extraction for FOG detection and potentially contributes to improved diagnosis and treatment of PD.

PMID:39976295 | DOI:10.1002/sim.70020

Crit Rev Immunol. 2025;45(2):77-89. doi: 10.1615/CritRevImmunol.2025056518.

ABSTRACT

BACKGROUND: Sarcoidosis is a complex inflammatory disease of unknown etiology affecting mostly the lungs and poses a significant diagnostic challenge, particularly in regions where tuberculosis (TB) is endemic. The diagnostic complexity intensifies due to shared clinical and radiological features between sarcoidosis and TB, as well as similarities with idiopathic pulmonary fibrosis (IPF) in cases that progress to pulmonary fibrosis. Accurately distinguishing between these diseases is critical for timely and effective patient management.

OBJECTIVE: This study breaks new ground by evaluating the diagnostic power of the bronchoalveolar lavage (BAL) CD4/ CD8 ratio, along with key activation and memory markers to differentiate sarcoidosis from TB, IPF, and other-interstitial lung diseases (ILDs).

METHODS: A cohort of 68 patients with ILDs, including sarcoidosis (n = 37), TB (n = 19), IPF (n = 6), and Other-ILDs (n = 6) were assessed. The CD4/CD8 ratio and a panel of activation and memory markers were analyzed through flow cytometry.

RESULTS: Sarcoidosis exhibited a significantly higher CD4/CD8 ratio compared to those with TB, IPF, and Other-ILDs. An optimal cutoff value of 3.7 for the CD4/CD8 ratio in sarcoidosis with an area under the ROC curve (AUC) of 0.7%, had a specificity of 96.8%, and a sensitivity of 43.2%. In addition, a significant difference was detected in CD38, CD45RA, CD45RO, and CD62L expression.

CONCLUSION: Combining the CD4/CD8 ratio (> 3.7) with the expression of CD38, CD62L, and memory markers is a promising new tool for the differential diagnosis of sarcoidosis.

PMID:39976519 | DOI:10.1615/CritRevImmunol.2025056518

Elife. 2025 Feb 20;13:RP99352. doi: 10.7554/eLife.99352.

ABSTRACT

Populations can adapt to stressful environments through changes in gene expression. However, the fitness effect of gene expression in mediating stress response and adaptation remains largely unexplored. Here, we use an integrative field dataset obtained from 780 plants of Oryza sativa ssp. indica (rice) grown in a field experiment under normal or moderate salt stress conditions to examine selection and evolution of gene expression variation under salinity stress conditions. We find that salinity stress induces increased selective pressure on gene expression. Further, we show that trans-eQTLs rather than cis-eQTLs are primarily associated with rice's gene expression under salinity stress, potentially via a few master-regulators. Importantly, and contrary to the expectations, we find that cis-trans reinforcement is more common than cis-trans compensation which may be reflective of rice diversification subsequent to domestication. We further identify genetic fixation as the likely mechanism underlying this compensation/reinforcement. Additionally, we show that cis- and trans-eQTLs are under balancing and purifying selection, respectively, giving us insights into the evolutionary dynamics of gene expression variation. By examining genomic, transcriptomic, and phenotypic variation across a rice population, we gain insights into the molecular and genetic landscape underlying adaptive salinity stress responses, which is relevant for other crops and other stresses.

PMID:39976326 | DOI:10.7554/eLife.99352