Waste Manag. 2025 Mar 14;200:114742. doi: 10.1016/j.wasman.2025.114742. Online ahead of print.

ABSTRACT

The surge in medical waste has highlighted the urgent need for cost-effective and advanced management solutions. In this paper, a novel medical waste management approach, "MedBin," is proposed for automated sorting, reusing, and recycling. A comprehensive medical waste dataset, "MedBin-Dataset" is established, comprising 2,119 original images spanning 36 categories, with samples captured in various backgrounds. The lightweight "MedBin-Net" model is introduced to enable detection and instance segmentation of medical waste, enhancing waste recognition capabilities. Experimental results demonstrate the effectiveness of the proposed approach, achieving an average precision of 0.91, recall of 0.97, and F1-score of 0.94 across all categories with just 2.51 M parameters (where M stands for million, i.e., 2.51 million parameters), 5.20G FLOPs (where G stands for billion, i.e., 5.20 billion floating-point operations per second), and 0.60 ms inference time. Additionally, the proposed method includes a World Health Organization (WHO) Guideline-Based Classifier that categorizes detected waste into 5 types, each with a corresponding disposal method, following WHO medical waste classification standards. The proposed method, along with the dedicated dataset, offers a promising solution that supports sustainable medical waste management and other related applications. To access the MedBin-Dataset samples, please visit https://universe.roboflow.com/uob-ylti8/medbin_dataset. The source code for MedBin-Net can be found at https://github.com/Wayne3918/MedbinNet.

PMID:40088805 | DOI:10.1016/j.wasman.2025.114742

Toxicol Appl Pharmacol. 2025 Mar 13:117285. doi: 10.1016/j.taap.2025.117285. Online ahead of print.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF), a progressive interstitial lung disease of unknown etiology, remains a therapeutic challenge with limited treatment options. This study investigates the therapeutic potential and molecular mechanisms of Tryptanthrin, a bioactive indole quinazoline alkaloid derived from Isatis tinctoria L., in pulmonary fibrosis. In a bleomycin-induced murine IPF model, Tryptanthrin administration (5 and 10 mg/kg/day for 28 days) significantly improved pulmonary function parameters and attenuated histological evidence of fibrosis. Mechanistic analysis revealed dual pathway modulation: Tryptanthrin suppressed MAPK/NF-κB signaling through inhibition of phosphorylation events, subsequently reducing pulmonary levels of pro-inflammatory cytokines (TNF-α, IL-1β, IL-6). Concurrently, it attenuated TGF-β1/Smad pathway activation by decreasing TGF-β1 expression and Smad2/3 phosphorylation, thereby downregulating fibrotic markers including COL1A1, α-smooth muscle actin (α-SMA), and fibronectin in lung tissues. Complementary in vitro studies using Lipopolysaccharide (LPS) or TGF-β1-stimulated NIH3T3 fibroblasts confirmed these anti-inflammatory and anti-fibrotic effects through analogous pathway inhibition. Our findings demonstrate that Tryptanthrin exerts therapeutic effects against pulmonary fibrosis via coordinated modulation of both inflammatory (MAPK/NF-κB) and fibrotic (TGF-β1/Smad) signaling cascades, suggesting its potential as a novel multi-target therapeutic agent for IPF management.

PMID:40089192 | DOI:10.1016/j.taap.2025.117285

Bioinformatics. 2025 Mar 14:btaf115. doi: 10.1093/bioinformatics/btaf115. Online ahead of print.

ABSTRACT

SUMMARY: AlphaPulldown2 streamlines protein structural modeling by automating workflows, improving code adaptability, and optimizing data management for large-scale applications. It introduces an automated Snakemake pipeline, compressed data storage, support for additional modeling backends like UniFold and AlphaLink2, and a range of other improvements. These upgrades make AlphaPulldown2 a versatile platform for predicting both binary interactions and complex multi-unit assemblies.

AVAILABILITY AND IMPLEMENTATION: AlphaPulldown2 is freely available at https://github.com/KosinskiLab/AlphaPulldown.

SUPPLEMENTARY INFORMATION: Supplementary information is available at Bioinformatics online.

PMID:40088942 | DOI:10.1093/bioinformatics/btaf115

Comput Biol Med. 2025 Mar 14;189:110021. doi: 10.1016/j.compbiomed.2025.110021. Online ahead of print.

ABSTRACT

Regulatory T cells (Tregs) are critical for maintaining the stability of the immune system and facilitating tumor escape through various mechanisms. Resting T cells are involved in cell-mediated immunity and remain in a resting state until stimulated, while effector T cells promote immune responses. Here, we investigated the roles of two gene signatures, one for resting Tregs (FOXP3 and IL2RA) and another for effector Tregs (FOXP3, CTLA-4, CCR8 and TNFRSF9) in pan-cancer. Using data from The Cancer Genome Atlas (TCGA), The Cancer Proteome Atlas (TCPA) and Gene Expression Omnibus (GEO), we focused on the expression profile of the two signatures, the existence of single nucleotide variants (SNVs) and copy number variants (CNVs), methylation, infiltration of immune cells in the tumor and sensitivity to different drugs. Our analysis revealed that both signatures are differentially expressed across different cancer types, and correlate with patient survival. Furthermore, both types of Tregs influence important pathways in cancer development and progression, like apoptosis, epithelial-to-mesenchymal transition (EMT) and the DNA damage pathway. Moreover, a positive correlation was highlighted between the expression of gene markers in both resting and effector Tregs and immune cell infiltration in adrenocortical carcinoma, while mutations in both signatures correlated with enrichment of specific immune cells, mainly in skin melanoma and endometrial cancer. In addition, we reveal the existence of widespread CNVs and hypomethylation affecting both Treg signatures in most cancer types. Last, we identified a few correlations between the expression of CCR8 and TNFRSF9 and sensitivity to several drugs, including COL-3, Chlorambucil and GSK1070916, in pan-cancer. Overall, these findings highlight new evidence that both Treg signatures are crucial regulators of cancer progression, providing potential clinical outcomes for cancer therapy.

PMID:40088713 | DOI:10.1016/j.compbiomed.2025.110021

Mol Divers. 2025 Mar 14. doi: 10.1007/s11030-025-11162-1. Online ahead of print.

ABSTRACT

Telomerase, a reverse transcriptase implicated in replicative immortality of cancers, remains a challenging target for therapeutic intervention due to its structural complexity and the absence of clinically approved small-molecule inhibitors. In this study, we explored drug repurposing as a pragmatic approach to address this gap, leveraging FDA-approved drugs to accelerate the identification of potential telomerase inhibitors. Using a structure-based drug discovery framework, we screened the DrugBank database through a previously validated pharmacophore model for the FVYL pocket in the hTERT thumb domain, the established binding site of BIBR1532. This was followed by molecular docking, pharmacokinetic filtering, and molecular dynamics (MD) simulations to evaluate the stability of protein-ligand complexes. Binding free energy calculations (MM-PBSA and MM-GBSA) were employed for cross-validation, identifying five promising candidates. Experimental validation using the Telomerase Repeat Amplification Protocol (TRAP) assay confirmed the inhibitory potential of Raltitrexed, showing significant inhibition with IC50 8.899 µM in comparison to control. Decomposition analysis and Structure-Activity Relationship (SAR) studies further offered insights into the binding mechanism, reinforcing the utility of the FVYL pocket as a druggable site. Raltitrexed's dual mechanism of action, targeting both telomerase and thymidylate synthase, underscores its potential as a versatile anticancer agent, suitable for combination therapies or standalone treatment. As the top lead, Raltitrexed demonstrates the potential of repurposed drugs in telomerase-targeted therapies, offering a time and cost-effective strategy for advancing its clinical development. The study also provides a robust framework for future drug development, addressing challenges in targeting telomerase for anticancer therapy.

PMID:40087255 | DOI:10.1007/s11030-025-11162-1

J Assoc Physicians India. 2025 Mar;73(3):11-12. doi: 10.59556/japi.73.0884.

ABSTRACT

Guillain-Barré syndrome (GBS) is a rare but common cause of acute flaccid paralysis globally.1 This syndrome, first described in 1916 by Georges Guillain, Jean Alexandre Barré, and André Strohl, has captured the interest of clinicians, researchers, and patients all over the world.2.

PMID:40087924 | DOI:10.59556/japi.73.0884

Skelet Muscle. 2025 Mar 15;15(1):7. doi: 10.1186/s13395-025-00376-4.

ABSTRACT

BACKGROUND: SELENON-Congenital Myopathy (SELENON-CM) is a rare congenital myopathy caused by mutations of the SELENON gene characterized by axial muscle weakness and progressive respiratory insufficiency. Muscle histopathology may be non-specific, but commonly includes multiminicores or a dystrophic pattern. The SELENON gene encodes selenoprotein N (SelN), a selenocysteine-containing redox enzyme located in the endo/sarcoplasmic reticulum membrane where it colocalizes with mitochondria-associated membranes. However, the molecular mechanism(s) by which SelN deficiency cause SELENON-CM remain poorly understood. A hurdle is the lack of cellular and animal models that show easily assayable phenotypes.

METHODS: Using CRISPR-Cas9 we generated three zebrafish models of SELENON-CM, which were then studied by spontaneous coiling, hatching, and activity assays. We also performed selenon coexpression analysis using a single cell RNAseq zebrafish embryo-atlas. SelN-deficient myoblasts were generated and assayed for glutathione, reactive oxygen species, carbonylation, and nytrosylation levels. Finally, we tested Selenon-deficient myoblasts' metabolism using a Seahorse cell respirometer.

RESULTS: We report deep-phenotyping of SelN-deficient zebrafish and muscle cells. SelN-deficient zebrafish exhibit changes in embryonic muscle function and swimming activity in larvae. Analysis of single cell RNAseq data in a zebrafish embryo-atlas revealed coexpression of selenon and genes involved in the glutathione redox pathway. SelN-deficient zebrafish and mouse myoblasts exhibit altered glutathione and redox homeostasis, as well as abnormal patterns of energy metabolism, suggesting roles for SelN in these functions.

CONCLUSIONS: These data demonstrate a role for SelN in zebrafish early development and myoblast metabolism and provide a basis for cellular and animal model assays for SELENON-CM.

PMID:40087793 | DOI:10.1186/s13395-025-00376-4

Orphanet J Rare Dis. 2025 Mar 14;20(1):125. doi: 10.1186/s13023-025-03614-6.

ABSTRACT

BACKGROUND: Clinical trials for rare diseases pose unique challenges warranting alternative approaches in demonstrating treatment efficacy. Such trials face challenges including small patient populations, variable onset of symptoms and rate of disease progression, and ethical considerations, particularly in neurodegenerative diseases. In this study, we present the retrospective clinical global impression (RCGI) severity and change (RCGI-S/C) scale on 27 patients with GM1 gangliosidosis, a post hoc clinician-rated outcome measure to evaluate natural history study participants as historical controls for comparisons with treated patients in a clinical trial.

METHODS: We conducted a systematic chart review of 27 GM1 gangliosidosis natural history participants across 95 total visits. RCGI-S was assessed at the first visit and rated 1 (normal) to 7 (among the most extremely ill). Each subsequent follow-up was rated on the RCGI-C scale from 1 (very much improved) to 7 (very much worse). We demonstrate scoring guidelines of both scales with examples and justifications for this pilot in GM1 gangliosidosis natural history participants. The convergent validity of the RCGI scales was explored through correlations with magnetic resonance imaging (MRI) and the Vineland Adaptive Behavioral Scales.

RESULTS: We found strong association between the RCGI-S scores with gray matter volume (r(14) = -0.81; 95% CI [-0.93, -0.51], p < 0.001), and RCGI-C scores significantly correlated with increases in ventricular volume (χ2(1) = 18.6, p < 0.001). Baseline RCGI-S scores also strongly correlated with Vineland adaptive behavioral composite scores taken at the same visit (r(14) = -0.72; 95% CI [-0.93, -0.17], p = 0.02).

CONCLUSION: RCGI-S/C scales, which use the clinical evaluation to assess the severity of disease of each patient visit over time, were consolidated into a single quantitative metric in this study. Longitudinal RCGI-C scores allowed us to quantify disease progression in our late-infantile and juvenile GM1 patients. We suggest that the retrospective CGI may be an important tool in evaluating historical data for comparison with changes in disease progression/mitigation following therapeutic interventions.

PMID:40087722 | DOI:10.1186/s13023-025-03614-6

BMC Bioinformatics. 2025 Mar 14;26(1):82. doi: 10.1186/s12859-025-06096-2.

ABSTRACT

BACKGROUND: Diagnosing Mendelian and rare genetic conditions requires identifying phenotype-associated genetic findings and prioritizing likely disease-causing genes. This task is labor-intensive for molecular and clinical geneticists, who must review extensive literature and databases to link patient phenotypes with causal genotypes. The challenge is further complicated by the large number of genetic variants detected through next-generation sequencing, which impacts both diagnosis timelines and patient care strategies. To address this, in silico methods that prioritize causal genes based on patient-derived phenotypes offer an effective solution, reducing the time involved in diagnostic case reviews and enhancing the efficiency of clinical diagnosis.

RESULTS: We developed the phenotype prioritization and analysis for rare diseases (PPAR) to rank genes based on human phenotype ontology (HPO) terms, with the specific goal of aiding the interpretation of genetic testing for Mendelian and rare diseases. PPAR leverages embeddings from a knowledge graph and incorporates knowledge from connections between genes, HPO terms, and gene ontology annotations. When applied on a clinical rare disease cohort and the publicly available deciphering developmental disorders (DDD) dataset. PPAR ranked the causal gene in the top 10 for 27% of cases in the clinical cohort and for 85% of cases in the DDD dataset, outperforming other established HPO-based methods.

CONCLUSION: Our findings demonstrate that PPAR, a method developed from the clinical knowledge graph, effectively ranks causal genes based on patient-derived HPO terms in rare and Mendelian disease contexts. PPAR has shown superior performance compared to other well-established HPO-only methods and provides an efficient, accessible solution for clinical geneticists. The Python-based tool is publicly available at https://github.com/dimi-lab/PPAR , offering a user-friendly platform for gene prioritization.

PMID:40087567 | DOI:10.1186/s12859-025-06096-2

Nat Commun. 2025 Mar 14;16(1):2500. doi: 10.1038/s41467-025-57695-9.

ABSTRACT

With ongoing improvements in the detection of complex genomic and epigenomic variations, long-read sequencing (LRS) technologies could serve as a unified platform for clinical genetic testing, particularly in rare disease settings, where nearly half of patients remain undiagnosed using existing technologies. Here, we report a simplified funnel-down filtration strategy aimed at enhancing the identification of small and large deleterious variants as well as abnormal episignature disease profiles from whole-genome LRS data. This approach detected all pathogenic single nucleotide, structural, and methylation variants in a positive control set (N = 76) including an independent sample set with known methylation profiles (N = 57). When applied to patients who previously had negative short-read testing (N = 51), additional diagnoses were uncovered in 10% of cases, including a methylation profile at the spinal muscular atrophy locus utilized for diagnosing this life-threatening, yet treatable, condition. Our study illustrates the utility of LRS in clinical genetic testing and the discovery of novel disease variation.

PMID:40087273 | DOI:10.1038/s41467-025-57695-9

Liver Int. 2025 Apr;45(4):e70069. doi: 10.1111/liv.70069.

NO ABSTRACT

PMID:40087980 | DOI:10.1111/liv.70069

Eur J Med Res. 2025 Mar 14;30(1):170. doi: 10.1186/s40001-025-02412-x.

ABSTRACT

The present systematic review investigates whether different doses of vitamin D and calcium supplementation in women with postmenopausal osteoporosis undergoing antiresorptive therapy have an association with BMD (spine, hip, femur neck), serum markers of osteoporosis (bone-ALP, NTX, CTX), the rate of pathological vertebral and non-vertebral fractures, adverse events, and mortality. This systematic review was conducted according to the PRISMA 2020 guidelines. PubMed, Google Scholar, Embase, and Scopus databases were accessed in September 2024. All randomised clinical trials (RCTs) comparing two or more treatments for postmenopausal osteoporosis supplemented with vitamin D and/or calcium were accessed. Only studies that indicated daily vitamin D and/or calcium supplementation doses were accessed. Data from 37 RCTs (43,397 patients) were retrieved. Patients received a mean of 833.6 ± 224.0 mg and 92.8 ± 228.7 UI of calcium and vitamin D supplementation, respectively. The mean length of the follow-up was 25.8 ± 13.3 months. The mean age of the patients was 66.4 ± 5.6 years, and the mean BMI was 25.2 ± 1.6 kg/m2. There was evidence of a statistically significant negative association between daily vitamin D supplementation and gastrointestinal adverse events (r = - 0.5; P = 0.02) and mortality (r = - 0.7; P = 0.03). No additional statistically significant associations were evidenced. In postmenopausal women who undergo antiresorptive treatment for osteoporosis, vitamin D was associated with a lower frequency of gastrointestinal adverse events and mortality. Calcium supplementation did not evidence an association with any of the endpoints of interest.Level of evidence Level I, systematic review of RCTs.

PMID:40087804 | DOI:10.1186/s40001-025-02412-x

United European Gastroenterol J. 2025 Mar 15. doi: 10.1002/ueg2.70011. Online ahead of print.

ABSTRACT

Malabsorption is a complex and multifaceted condition characterised by the defective passage of nutrients into the blood and lymphatic streams. Several congenital or acquired disorders may cause either selective or global malabsorption in both children and adults, such as cystic fibrosis, exocrine pancreatic insufficiency (EPI), coeliac disease (CD) and other enteropathies, lactase deficiency, small intestinal bacterial overgrowth (SIBO), autoimmune atrophic gastritis, Crohn's disease, and gastric or small bowel resections. Early recognition of malabsorption is key for tailoring a proper diagnostic work-up for identifying the cause of malabsorption. Patient's medical and pharmacological history are essential for identifying risk factors. Several examinations like endoscopy with small intestinal biopsies, non-invasive functional tests, and radiologic imaging are useful in diagnosing malabsorption. Due to its high prevalence, CD should always be looked for in case of malabsorption with no other obvious explanations and in high-risk individuals. Nutritional support is key in management of patients with malabsorption; different options are available, including oral supplements, enteral or parenteral nutrition. In patients with short bowel syndrome, teduglutide proved effective in reducing the need for parenteral nutrition, thus improving the quality of life of these patients. Primary care physicians have a central role in early detection of malabsorption and should be involved into multidisciplinary teams for improving the overall management of these patients. In this European consensus, involving 10 scientific societies and several experts, we have dissected all the issues around malabsorption, including the definitions and diagnostic testing (Part 1), high-risk categories and special populations, nutritional assessment and management, and primary care perspective (Part 2).

PMID:40088199 | DOI:10.1002/ueg2.70011

J Assoc Physicians India. 2025 Mar;73(3):86-89. doi: 10.59556/japi.73.0858.

ABSTRACT

BACKGROUND: Allergic bronchopulmonary aspergillosis (ABPA) is an immune-mediated hypersensitivity reaction to Aspergillus, a common environmental fungus. It is typically seen in asthmatic patients and those with cystic fibrosis. Lack of clinical suspicion and misdiagnosis often make the management of this condition difficult.

CASE DESCRIPTION: We are reporting a case of ABPA that was diagnosed and managed at Divisional Railway Hospital, Kharagpur, South Eastern Railway. The patient was a 66-year-old female who presented with fever, cough, and shortness of breath. She had been asthmatic since childhood and was on treatment for the same. On initial evaluation, her clinical and radiological features were suggestive of community-acquired pneumonia and were treated with antibiotics. However, the patient did not show improvement, and asthma also remained poorly controlled despite treatment. This raised the possibility of ABPA in this patient. The International Society for Human and Animal Mycology-ABPA (ISHAM-ABPA) working group criterion was used for making the diagnosis. She was successfully managed with low-dose steroids and itraconazole.

CONCLUSION: A high index of clinical suspicion is needed for timely detection of ABPA. Features of nonresolving pneumonia in the background of poorly controlled asthma raised the possibility of ABPA in this patient. Misdiagnosis and delay in initiating proper treatment can lead to permanent lung damage, such as bronchiectasis and lung fibrosis, which can even lead to life-threatening complications like cor pulmonale and respiratory failure.

PMID:40087942 | DOI:10.59556/japi.73.0858

Ecohealth. 2025 Mar 15. doi: 10.1007/s10393-025-01705-1. Online ahead of print.

ABSTRACT

The World Health Organization (WHO) aims to ensure the highest level of health for all populations. Despite progress, increased life expectancy has not translated into a proportional rise in healthy life years, as chronic diseases are on the rise. In this context, health ecology emerges as a new scientific discipline focused on preserving health rather than curing diseases. It seeks to calculate healthy life expectancy by analyzing individual, social, and systemic choices, offering a proactive and rigorous approach to making informed decisions and improving long-term well-being.

PMID:40088354 | DOI:10.1007/s10393-025-01705-1

Interdiscip Sci. 2025 Mar 15. doi: 10.1007/s12539-025-00695-6. Online ahead of print.

ABSTRACT

Drug combination therapy has shown improved efficacy and decreased adverse effects, making it a practical approach for conditions like cancer. However, discovering all potential synergistic drug combinations requires extensive experimentation, which can be challenging. Recent research utilizing deep learning techniques has shown promise in reducing the number of experiments and overall workload by predicting synergistic drug combinations. Therefore, developing reliable and effective computational methods for predicting these combinations is essential. This paper proposed a novel method called Drug-molecule Connect Cell (DconnC) for predicting synergistic drug combinations. DconnC leverages cellular features as nodes to establish connections between drug molecular structures, allowing the extraction of pertinent features. These features are then optimized through self-augmented contrastive learning using bidirectional recurrent neural networks (Bi-RNN) and long short-term memory (LSTM) models, ultimately predicting the drug synergy. By integrating information about the molecular structure of drugs for the extraction of cell features, DconnC uncovers the inherent connection between drug molecular structures and cellular characteristics, thus improving the accuracy of predictions. The performance of our method is evaluated using a five-fold cross validation approach, demonstrating a 35 % reduction in the mean square error (MSE) compared to the next-best method. Moreover, our method significantly outperformed alternative approaches in various evaluation criteria, particularly in predicting different cell lines and Loewe synergy score intervals.

PMID:40088336 | DOI:10.1007/s12539-025-00695-6

J Mol Neurosci. 2025 Mar 15;75(1):36. doi: 10.1007/s12031-025-02329-4.

ABSTRACT

Parkinson's disease recognition (PDR) involves identifying Parkinson's disease using clinical evaluations, imaging studies, and biomarkers, focusing on early symptoms like tremors, rigidity, and bradykinesia to facilitate timely treatment. However, due to noise, variability, and the non-stationary nature of EEG signals, distinguishing PD remains a challenge. Traditional deep learning methods struggle to capture the intricate temporal and spatial dependencies in EEG data, limiting their precision. To address this, a novel fusion framework called graph embedding class-based convolutional recurrent attention network with Brown Bear Optimization Algorithm (GECCR2ANet + BBOA) is introduced for EEG-based PD recognition. Preprocessing is conducted using numerical operations and noise removal with weighted guided image filtering and entropy evaluation weighting (WGIF-EEW). Feature extraction is performed via the improved VGG19 with graph triple attention network (IVGG19-GTAN), which captures spatial and temporal dependencies in EEG data. The extracted features are classified using the graph embedding class-based convolutional recurrent attention network (GECCR2ANet), further optimized through the Brown Bear Optimization Algorithm (BBOA) to enhance classification accuracy. The model achieves 99.9% accuracy, 99.4% sensitivity, and a 99.3% F1-score on the UNM dataset, and 99.8% accuracy, 99.1% sensitivity, and 99.2% F1-score on the UC San Diego dataset, significantly outperforming existing methods. Additionally, it records an error rate of 0.5% and a computing time of 0.25 s. Previous models like 2D-MDAGTS, A-TQWT, and CWCNN achieved below 95% accuracy, while the proposed model's 99.9% accuracy underscores its superior performance in real-world clinical applications, enhancing early PD detection and improving diagnostic efficiency.

PMID:40088329 | DOI:10.1007/s12031-025-02329-4

Abdom Radiol (NY). 2025 Mar 15. doi: 10.1007/s00261-025-04883-2. Online ahead of print.

ABSTRACT

PURPOSE: Magnetic resonance elastography (MRE) measures liver stiffness for fibrosis staging, but its utility can be hindered by quality control (QC) challenges and measurement variability. The objective of the study was to fully automate liver MRE QC and liver stiffness measurement (LSM) using a deep learning (DL) method.

METHODS: In this retrospective, single center, IRB-approved human study, a curated dataset involved 897 MRE magnitude slices from 146 2D MRE scans [1.5 T and 3 T MRI, 2D Gradient Echo (GRE), and 2D Spin Echo-Echo Planar Imaging (SE-EPI)] of 69 patients (37 males, mean age 51.6 years). A SqueezeNet-based binary QC model was trained using combined and individual inputs of MRE magnitude slices and their 2D Fast-Fourier transforms to detect artifacts from patient motion, aliasing, and blurring. Three independent observers labeled MRE magnitude images as 0 (non-diagnostic quality) or 1 (diagnostic quality) to create a reference standard. A 2D U-Net segmentation model was trained on diagnostic slices with liver masks to support LSM. Intersection over union between the predicted segmentation and confidence masks identified measurable areas for LSM on elastograms. Cohen's unweighted Kappa coefficient, mean LSM error (%), and intra-class correlation coefficient were calculated to compare the DL-assisted approach with the observers' annotations. An efficiency analysis compared the DL-assisted vs manual LSM durations.

RESULTS: The top QC ensemble model (using MRE magnitude alone) achieved accuracy, precision, and recall of 0.958, 0.982, and 0.886, respectively. The mean LSM error between the DL-assisted approach and the reference standard was 1.9% ± 4.6%. DL-assisted approach completed LSM for 29 diagnostic slices in under 1 s, compared to 20 min manually.

CONCLUSION: An automated DL-based classification of liver MRE diagnostic quality, liver segmentation, and LSM approach demonstrates a promising high performance, with potential for clinical adoption.

PMID:40088296 | DOI:10.1007/s00261-025-04883-2

Med Biol Eng Comput. 2025 Mar 15. doi: 10.1007/s11517-025-03334-w. Online ahead of print.

ABSTRACT

Neurodegenerative disorders (NDD) represent a broad spectrum of diseases that progressively impact neurological function, yet available therapeutics remain conspicuously limited. They lead to altered rhythms and dynamics of walking, which are evident in the sequential footfall contact times measured from one stride to the next. Early detection of aberrant walking patterns can prevent the progression of risks associated with neurodegenerative diseases, enabling timely intervention and management. In this study, we propose a new methodology based on a parallel-path ConvMixer neural network for neurodegenerative disease classification from gait analysis. Earlier research in this field depended on either gait parameter-derived features or the ground reaction force signal. This study has emerged to combine both ground reaction force signals and extracted features to improve gait pattern analysis. The study is being carried out on the gait dynamics in the NDD database, i.e., on the benchmark dataset Physionet gaitndd. Leave one out cross-validation is carried out. The proposed model achieved the best average rates of accuracy, precision, recall, and an F1-score of 97.77 % , 96.37 % , 96.5 % , and 96.25 % , respectively. The experimental findings demonstrate that our approach outperforms the best results achieved by other state-of-the-art methods.

PMID:40088256 | DOI:10.1007/s11517-025-03334-w

J Am Chem Soc. 2025 Mar 15. doi: 10.1021/jacs.5c02046. Online ahead of print.

ABSTRACT

Determining hydrogen positions in metal hydride clusters remains a formidable challenge, which relies heavily on unaffordable neutron diffraction. While machine learning has shown promise, only one deep learning-based method has been proposed so far, which relies heavily on neutron diffraction data for training, limiting its general applicability. In this work, we present an innovative strategy─SSW-NN (stochastic surface walking with neural network)─a robust, non-neutron diffraction-dependent technique that accurately predicts hydrogen positions. Validated against neutron diffraction data for copper hydride clusters, SSW-NN proved effective for clusters where only X-ray diffraction data or DFT predictions are available. It offers superior accuracy, efficiency, and versatility across different metal hydrides, including silver and alloy hydride systems, currently without any neutron diffraction references. This approach not only establishes a new research paradigm for metal hydride clusters but also provides a universal solution for hydrogen localization in other research fields constrained by neutron sources.

PMID:40088162 | DOI:10.1021/jacs.5c02046