Proc Natl Acad Sci U S A. 2025 May 13;122(19):e2426449122. doi: 10.1073/pnas.2426449122. Epub 2025 May 6.

ABSTRACT

Phase separation is an important mechanism to generate certain biomolecular condensates and organize the cell interior. Condensate formation and function remain incompletely understood due to difficulties in visualizing the condensate interior at high resolution. Here, we analyzed the structure of biochemically reconstituted chromatin condensates through cryoelectron tomography. We found that traditional blotting methods of sample preparation were inadequate, and high-pressure freezing plus focused ion beam milling was essential to maintain condensate integrity. To identify densely packed molecules within the condensate, we integrated deep learning-based segmentation with context-aware template matching. Our approaches were developed on chromatin condensates and were also effective on condensed regions of in situ native chromatin. Using these methods, we determined the average structure of nucleosomes to 6.1 and 12 Å resolution in reconstituted and native systems, respectively, found that nucleosomes form heterogeneous interaction networks in both cases, and gained insight into the molecular origins of surface tension in chromatin condensates. Our methods should be applicable to biomolecular condensates containing large and distinctive components in both biochemical reconstitutions and certain cellular systems.

PMID:40327693 | DOI:10.1073/pnas.2426449122

IEEE Trans Vis Comput Graph. 2025 May 6;PP. doi: 10.1109/TVCG.2025.3567117. Online ahead of print.

ABSTRACT

Urban segregation refers to the physical and social division of people, often driving inequalities within cities and exacerbating socioeconomic and racial tensions. While most studies focus on residential spaces, they often neglect segregation across "activity spaces" where people work, socialize, and engage in leisure. Human mobility data offers new opportunities to analyze broader segregation patterns, encompassing both residential and activity spaces, but challenges existing methods in capturing the complexity and local nuances of urban segregation. This work introduces InclusiViz, a novel visual analytics system for multi-level analysis of urban segregation, facilitating the development of targeted, data-driven interventions. Specifically, we developed a deep learning model to predict mobility patterns across social groups using environmental features, augmented with explainable AI to reveal how these features influence segregation. The system integrates innovative visualizations that allow users to explore segregation patterns from broad overviews to fine-grained detail and evaluate urban planning interventions with real-time feedback. We conducted a quantitative evaluation to validate the model's accuracy and efficiency. Two case studies and expert interviews with social scientists and urban analysts demonstrated the system's effectiveness, highlighting its potential to guide urban planning toward more inclusive cities.

PMID:40327496 | DOI:10.1109/TVCG.2025.3567117

IEEE Trans Neural Netw Learn Syst. 2025 May 6;PP. doi: 10.1109/TNNLS.2025.3562363. Online ahead of print.

ABSTRACT

Deep neural networks (DNNs) have shown significant progress in many application fields. However, overfitting remains a significant challenge in their development. While existing data-augmentation techniques such as MixUp have been successful in preventing overfitting, they often fail to generate hard mixed samples near the decision boundary, impeding model optimization. In this article, we present adversarial MixUp (AdvMixUp), a novel sample-dependent method for regularizing DNNs. AdvMixUp addresses this issue by incorporating adversarial training (AT) to create sample-dependent and feature-level interpolation masks, generating more challenging mixed samples. These virtual samples enable DNNs to learn more robust features, ultimately reducing overfitting. Empirical evaluations on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet demonstrate that AdvMixUp outperforms existing MixUp variants.

PMID:40327482 | DOI:10.1109/TNNLS.2025.3562363

IEEE Trans Neural Netw Learn Syst. 2025 May 6;PP. doi: 10.1109/TNNLS.2025.3561225. Online ahead of print.

ABSTRACT

Deep learning models achieve remarkable accuracy in computer vision tasks yet remain vulnerable to adversarial examples-carefully crafted perturbations to input images that can deceive these models into making confident but incorrect predictions. This vulnerability poses significant risks in high-stakes applications such as autonomous vehicles, security surveillance, and safety-critical inspection systems. While the existing literature extensively covers adversarial attacks in image classification, comprehensive analyses of such attacks on object detection systems remain limited. This article presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures, synthesizes existing robustness metrics, and provides a comprehensive empirical evaluation of state-of-the-art attack methodologies on popular object detection models, including both traditional detectors and modern detectors with vision-language pretraining. Through rigorous analysis of open-source attack implementations and their effectiveness across diverse detection architectures, we derive key insights into attack characteristics. Furthermore, we delineate critical research gaps and emerging challenges to guide future investigations in securing object detection systems against adversarial threats. Our findings establish a foundation for developing more robust detection models while highlighting the urgent need for standardized evaluation protocols in this rapidly evolving domain.

PMID:40327472 | DOI:10.1109/TNNLS.2025.3561225

Bioinformatics. 2025 May 6:btaf289. doi: 10.1093/bioinformatics/btaf289. Online ahead of print.

ABSTRACT

MOTIVATION: The intricate network of RNA-RNA interactions, crucial for orchestrating essential cellular processes like transcriptional and translational regulations, has been unveiling through high-throughput techniques and computational predictions. As experimental determination of RNA-RNA interactions at the base-pair resolution remains challenging, a timely update for assessing complementary computational tools is necessary, particularly given the recent emergence of deep learning-based methods.

RESULTS: Here, we employed base pairs derived from three-dimensional RNA complex structures as a gold standard benchmark to assess the performance of 23 different methods ranging from alignment-based methods, free-energy-based minimization to deep-learning techniques. The result indicates that a deep-learning-based method, SPOT-RNA, can be generalized to make accurate zero-shot predictions of RNA-RNA interactions not only between previously unseen RNA structures but also between RNAs without monomeric structures. The finding underscores the potential of deep learning as a robust tool for advancing our understanding of these complex molecular interactions.

AVAILABILITY: All data and codes are available at https://github.com/meilanglang/RNA-RNA-Interaction.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:40327448 | DOI:10.1093/bioinformatics/btaf289

Proc Natl Acad Sci U S A. 2025 May 13;122(19):e2421747122. doi: 10.1073/pnas.2421747122. Epub 2025 May 6.

ABSTRACT

Infiltrating neutrophils are key effector cells in inflammatory bowel disease (IBD) while providing antimicrobial defense and tissue restitution in the intestine. The complexity of neutrophil functions in local environments underscores our limited understanding of how their adaptation in tissues influences disease progression. Here, we demonstrate that neutrophils recruited in murine colitis and infection models, idiopathic IBD, and chronic granulomatous disease-associated IBD undergo extensive transcriptional reprogramming, resulting in the emergence of neutrophil populations that feature unique DUOX2 NADPH oxidase expression. Functional studies utilizing mice with myeloid and neutrophil specific DUOX2 inactivation reveal a vital and dichotomous role for this NADPH oxidase in both colitis and intestinal infection. Niche-directed reprogramming promoted a DUOX2-dependent chemokine and cytokine-rich intestinal environment that amplified and prolonged inflammatory responses, suggesting that selectively suppressing DUOX2 may constitute an anti-inflammatory strategy for IBD treatment. Altering spatiotemporal redox signaling by de novo expression of a ROS-generating enzyme represents an important feature for functional neutrophil diversification in disease, with implications for other neutrophil-driven diseases in specialized niches.

PMID:40327691 | DOI:10.1073/pnas.2421747122

Bioinformatics. 2025 May 6:btaf280. doi: 10.1093/bioinformatics/btaf280. Online ahead of print.

ABSTRACT

MOTIVATION: Boolean networks are popular dynamical models of cellular processes in systems biology. Their attractors model phenotypes that arise from the interplay of key regulatory subcircuits. A succession diagram describes this interplay in a discrete analog of Waddington's epigenetic attractor landscape that allows for fast identification of attractors and attractor control strategies. Efficient computational tools for studying succession diagrams are essential for the understanding of Boolean attractor landscapes and connecting them to their biological functions.

RESULTS: We present a new approach to succession diagram construction for asynchronously updated Boolean networks, implemented in the biologist's Boolean attractor landscape mapper, biobalm. We compare biobalm to similar tools and find a substantial performance increase in succession diagram construction, attractor identification, and attractor control. We perform the most comprehensive comparative analysis to date of the succession diagram structure in experimentally-validated Boolean models of cell processes and random ensembles. We find that random models (including critical Kauffman networks) have relatively small succession diagrams, indicating simple decision structures. In contrast, non-random models from the literature are enriched in extremely large succession diagrams, indicating an abundance of decision points and suggesting the presence of complex Waddington landscapes in nature.

AVAILABILITY AND IMPLEMENTATION: The tool biobalm is available online at https://github.com/jcrozum/biobalm. Further data, scripts for testing, analysis and figure generation are available online at https://github.com/jcrozum/biobalm-analysis and in the reproducibility artefact at https://doi.org/10.5281/zenodo.13854760.

CONTACT AND SUPPLEMENTARY INFORMATION: giang.trinh91@gmail.com (V.G.T.), xpastva@fi.muni.cz (S.P.), jrozum@binghamton.edu (J.C.R.); The Supplementary Text is available online through Bioinformatics.

PMID:40327535 | DOI:10.1093/bioinformatics/btaf280

Naunyn Schmiedebergs Arch Pharmacol. 2025 May 6. doi: 10.1007/s00210-025-04233-5. Online ahead of print.

ABSTRACT

Since the onset of the COVID-19 pandemic in March 2020, researchers worldwide have sought effective drugs to prevent and manage SARS-CoV-2 and its spectrum of symptoms. Ivermectin, originally developed as an anthelmintic for controlling parasitic infections in humans and animals, has drawn attention based on the hypothesis that it inhibits viral replication. In Austria, ivermectin usage peaked in November 2021, following promotion by the right-wing Freedom Party of Austria (FPÖ) as an alternative treatment to vaccination, resonating strongly within anti-vaccine and skeptical communities. The topic is also very present in the United States of America due to the re-election of D. Trump as US President and the designation of R. Kennedy as the United States' Secretary of Health and Human Services. To critically examine the controversial use of ivermectin for COVID-19 and publication trends during the pandemic, this study analysed all publications listed in PubMed from 1 January 2020 to 31 December 2022 using the keywords 'ivermectin' and 'COVID-19', resulting in a dataset of 353 publications. These publications were assessed for scientific quality, methodological rigour and bias, with particular focus on the influence of social and political dynamics on publication practices, as well as the prevalence of preprints, citation trends and the role of funding sources. Our study shows that many highly cited studies on ivermectin display methodological weaknesses and data gaps, contributing to the propagation of hypotheses lacking substantial empirical support. This analysis underscores the necessity of rigorous quality control during crises and highlights the long-term risks posed to scientific databases and public health by methodologically deficient research.

PMID:40327060 | DOI:10.1007/s00210-025-04233-5

Anal Chem. 2025 May 6. doi: 10.1021/acs.analchem.5c00390. Online ahead of print.

ABSTRACT

The interpretation of proteomics data often relies on functional enrichment analysis, such as Gene Ontology (GO) enrichment, to uncover the biological functions of proteins, as well as the examination of protein expression patterns across data sets like the Clinical Proteomic Tumor Analysis Consortium (CPTAC) database. However, conventional approaches to functional enrichment frequently produce extensive and redundant term lists, complicating interpretation and synthesis. Moreover, the absence of specialized tools tailored to proteomics researchers limits the efficient exploration of protein expression within specific biological contexts. To address these challenges, we developed Ontolomics-P, a user-friendly web-based tool designed to advance proteomics data interpretation. Ontolomics-P integrates topic modeling using latent Dirichlet allocation (LDA) with GO semantic similarity analysis, enabling the consolidation of redundant terms into coherent topics. These topics are further refined and reannotated using the GPT-4o language model, creating a novel topics database that provides precise and interpretable insights into shared biological functions. Additionally, Ontolomics-P incorporates quantitative proteomic data from 10 diverse cancer types archived in the CPTAC database, allowing for a comprehensive exploration of protein expression profiles from a data-driven perspective. Through detailed case studies, we demonstrate the tool's capacity to streamline workflows, simplify interpretation, and provide actionable biological insights. Ontolomics-P represents a significant advancement in proteomics data analysis, offering innovative solutions for functional annotation, quantitative exploration, and visualization, ultimately empowering researchers to accelerate discoveries in systems biology and beyond.

PMID:40326493 | DOI:10.1021/acs.analchem.5c00390

Pharmacogenet Genomics. 2025 May 6. doi: 10.1097/FPC.0000000000000568. Online ahead of print.

ABSTRACT

OBJECTIVES: Evaluate the feasibility of implementing a multigene pharmacogenetic (PGx) test and genotype-guided pharmacist recommendations into gynecologic perioperative workflows and fidelity to pharmacist genotype-guided postoperative analgesic recommendations.

METHODS: A randomized, prospective, open-label pilot study was conducted in gynecologic patients undergoing abdominal surgery. Participants received multigene PGx testing and were randomized to the PGx-guided group where results were returned to the electronic health record with pharmacist genotype-guided postoperative analgesic recommendations or usual care. Primary outcomes included the proportion of PGx results and pharmacist recommendations completed before surgery, the number of prescriptions in alignment with pharmacist recommendations, and the proportion of analgesics prescribed differing from usual care.

RESULTS: Of the 101 participants analyzed, all were female, 50 ± 14 years old, 49% were Black, 48% were White, 60% were treated by gynecologic oncology, and 76% underwent minimally invasive surgery. PGx results were returned to the genomics results portal a median of 7 (interquartile range: 6-9) business days after ordering the test. A majority (85%) of results were returned before the participant's surgery. Pharmacist genotype-guided analgesic recommendations were completed for 35 (73%) of the 48 participants in the PGx-guided group. And, 32 (91%) of the prescribed nonsteroidal anti-inflammatory drugs and 23 (66%) of the prescribed opioids matched the pharmacist's recommendations. Barriers included missed pharmacist notes when surgery dates were moved and low use of study-specific order set.

CONCLUSION: PGx test results were available before most surgeries, but the pharmacist recommendations were not always followed. Enhanced implementation strategies will need to be developed in future genotype-guided protocols.

PMID:40327052 | DOI:10.1097/FPC.0000000000000568

J Patient Rep Outcomes. 2025 May 6;9(1):48. doi: 10.1186/s41687-025-00879-0.

ABSTRACT

BACKGROUND: Elexacaftor/Tezacaftor/Ivacaftor (ETI) is a therapy approved for cystic fibrosis (CF) that has given improved clinical outcomes in patients carrying the F508del mutation. There are few published data regarding ETI's effects on patients' quality of life (QoL). This study aims to (fill the data gap in current literature by assessing) evaluate the long-term effects of ETI on QoL.

METHODOLOGY: A prospective observational study was conducted with thirty-seven severe patients that received ETI for compassionate use (group A), 184 received it for on-label use (group B). All carried one F508del mutation. Patients were assessed using the CFQ-R (Cystic Fibrosis Questionnaire-Revised). The evaluation time-points were pre-treatment (T0), and after 12 (T1) and 24 months (T2); group A was also assessed after 36 months (T3). Twenty-five patients completed 3 years of treatment and 65 patients completed 2 years of treatment, in groups A and B respectively.

RESULTS: At T1, median values for almost all areas of CFQ-R statistically significant increased in group A, particularly Physical Functioning (+ 25.0), Respiratory (+ 22.2) and Health Perception (+ 22.2).The Social Functioning area statistically significant increased at T2 (+ 5.6). At T3, these improvements remained stable. At T1, all areas of CFQ-R statistically significant increased in group B, particularly the Health Perception (+ 22,2) heading. At T2, these improvements remained stable. For both groups, the changes identified at the last follow-up showed no major differences by gender, age or genetic status.

CONCLUSIONS: Treatment with ETI significantly improved patients' QoL in both groups at 12-24 months, these improvements remaining stable in patients tested at 36 months.

PMID:40327240 | DOI:10.1186/s41687-025-00879-0

Allergy. 2025 May 6. doi: 10.1111/all.16581. Online ahead of print.

NO ABSTRACT

PMID:40326788 | DOI:10.1111/all.16581

Pediatr Pulmonol. 2025 May;60(5):e71110. doi: 10.1002/ppul.71110.

ABSTRACT

BACKGROUND: There have been significant improvements in the health of infants and children with cystic fibrosis (CF) since universal newborn screening (NBS) was implemented in the United States (US). However, a significant proportion of infants with CF are not evaluated in a timely manner, and delays disproportionately affect children from minoritized racial/ethnic groups. The aim of this study was to understand experiences of NBS in caregivers of young children with CF in the United States.

METHODS: We recruited caregivers of children (0-13 years) with CF through listservs and social media of CF organizations. The survey was administered online in 2023 and included questions about their recollections of their child's NBS and the process of getting a CF diagnosis.

RESULTS: Of 383 caregiver respondents, 43% reported being informed that their child's race or ethnicity was a predictor of the chances of their child having CF. Most reported that after they were notified of a positive NBS test, the initial evaluation for CF was scheduled ≥ 4 days later, 45% reported a delay of ≥ 8 days, and 5% reporting a delay of ≥ 15 days. Most (91%) felt the initial evaluation for CF was thorough, but 35% reported delays in getting information about their child's diagnosis.

CONCLUSIONS: Caregivers report delays in evaluation after a positive NBS. A significant proportion reported delays in receiving information about their child's diagnosis or being told that race or ethnicity were related to risk of CF. These findings show the need for education and practice changes in both primary care and CF center settings.

PMID:40326644 | DOI:10.1002/ppul.71110

Acta Physiol (Oxf). 2025 Jun;241(6):e70051. doi: 10.1111/apha.70051.

ABSTRACT

AIM: Amino acids, sugars, short-chain fatty acids (SCFA), vitamins, and other small molecules compose the extracellular metabolome on the airway lumen surface, but how the airway epithelium deals with these molecules has not been deeply studied. Due to the broad spectrum of metabolites transported by SLC5A8 and SLC5A12, we aim to determine if they are functionally expressed and participate in the absorption of Na+, short-chain fatty acids, and monocarboxylates in mouse and human airway epithelium.

METHODS: Tracheas isolated from male or female mice and human bronchial epithelial cells (HBECs) were used for electrophysiological studies in the Ussing chamber and to detect members of the SLC16 family by RT-PCR and bulk RNAseq. Additionally, cell lines expressing the human and murine SLC5A8 transporter were employed for uptake studies using a fluorescent lactate probe.

RESULTS: We showed for the first time that human and murine airway epithelium express a functional SLC5A8 transporter, facilitating the absorption of glucose metabolites and SCFAs. The Na+-coupled monocarboxylate transport was not additive with ENaC-mediated Na+ absorption in mouse trachea. We observed that valproate acts as an inhibitor of the murine but not of the human SLC5A8 transporter.

CONCLUSIONS: Our results demonstrate that several metabolites derived from bacterial and cellular metabolism can be transported from the airway lumen into the epithelial cells, participating in a homeostatic relation of the tissue with its environment.

PMID:40326639 | DOI:10.1111/apha.70051

Pediatr Pulmonol. 2025 May;60(5):e71117. doi: 10.1002/ppul.71117.

ABSTRACT

BACKGROUND: Previous research showed that lung function abnormalities are common in infants with cystic fibrosis (IwCF) but real-world data are missing.

METHODS: This single-center retrospective study analyzed infant lung function results from IwCF born in 2012-2018. The tests were conducted at Great Ormond Street Hospital, London, as part of routine care at 3 months, 1 year, and 2 years of age. Z-scores for SF6 Lung Clearance Index (zLCI), plethysmographic FRC (zFRCpleth) and FEV0.5 were derived. Microbiology and antibiotics prescription from 3 months before lung function assessments, up to the closest medical review following the lung function encounter, were analyzed, along with changes in management advised by the physician.

RESULTS: A total of 126 lung function encounters (n = 43 at 3 months, 46 at 1 year, 37 at 2 years) from 60 IwCF were included. LCI was abnormal (zLCI > 1.96) in 31% (12/39) of 3-month-olds (mean± zLCI 1.21 ± 1.08), 28% (12/43) of 1-year-olds and 19% (7/36) of 2-year-olds (mean± zLCI 1.13 ± 1.10). Among 74 cases with recent positive microbiology or abnormal chest findings at medical review, 100% (31/31) of those with abnormal lung function and 86% (37/43) of those with normal lung function (p = 0.04) had a recent antibiotic prescription or a change in clinical management. Conversely, in encounters with abnormal lung function but normal clinical findings, management changes occurred in only 12% (2/16) of cases.

CONCLUSION: In this real-word cohort of IwCF, clinical management was mainly influenced by clinical findings and only marginally by abnormal lung function (elevated FRC or LCI).

PMID:40326637 | DOI:10.1002/ppul.71117

JMIR Med Inform. 2025 May 6;13:e66556. doi: 10.2196/66556.

NO ABSTRACT

PMID:40327366 | DOI:10.2196/66556

Mol Biol Cell. 2025 May 6:mbcE25010009. doi: 10.1091/mbc.E25-01-0009. Online ahead of print.

ABSTRACT

The life cycle of eukaryotic microorganisms involves complex transitions between states such as dormancy, mating, meiosis, and cell division, which are often studied independently from each other. Therefore, most microbial life cycles are theoretical reconstructions from partial observations of cellular states. Here we show that complete microbial life cycles can be directly and continuously studied by combining microfluidic culturing, life cycle stage-specific segmentation of micrographs, and a novel cell tracking algorithm, FIEST, based on deep learning video frame interpolation. As proof of principle, we quantitatively imaged and compared cell growth and the activity state of the cell division kinase, Cdk1, across the life cycle of Saccharomyces cerevisiae for up to three sexually reproducing generations. Our analysis of S. cerevisiae's life cycle provided the following new insights: (1) the accumulation of cell cycle regulators, such as Whi5, is tailored to each life cycle stage; (2) cell growth always preceded exit from non-proliferative states in our conditions; (3) the temporal coordination of meiotic events is the same across sexually reproducing populations when each generation is exposed to same conditions; (4) information such as cell size and morphology resets after each sexual reproduction cycle. Image processing and tracking algorithms are available as the Python package Yeastvision, which could be used study pathogens such as Candida glabrata, Cryptococcus neoformans, Colletotrichum acutatum, and other unicellular systems. [Media: see text] [Media: see text] [Media: see text] [Media: see text] [Media: see text] [Media: see text] [Media: see text] [Media: see text] [Media: see text].

PMID:40327364 | DOI:10.1091/mbc.E25-01-0009

JMIR Mhealth Uhealth. 2025 May 6;13:e70473. doi: 10.2196/70473.

ABSTRACT

BACKGROUND: Encouraging physical activity improves mental health and is recommended in workplace mental health guidelines. Although mobile health (mHealth) interventions are promising for physical activity promotion, their impact on mental health outcomes is inconsistent. Furthermore, poor user retention rates of mHealth apps pose a major challenge.

OBJECTIVE: This study aimed to examine the effectiveness and implementation outcomes of the smartphone app ASHARE in Japanese workplace settings, leveraging a deep learning model to monitor depression and anxiety through physical activity.

METHODS: This hybrid effectiveness-implementation trial was a 3-month nonrandomized controlled trial conducted from October 2023 to September 2024. Work units and employees were recruited and allocated to the intervention or active control group based on preference. The intervention group installed the ASHARE app, whereas the control group participated in an existing multicomponent workplace program promoting physical activity. Changes in physical activity and psychological distress levels were compared between the groups. User retention rates, participation rates, acceptability, appropriateness, feasibility, satisfaction, and potential harm were also assessed.

RESULTS: A total of 84 employees from 7 work units participated (67 from 5 units in the intervention group and 17 from 2 units in the control group). In total, 78 employees completed the 3-month follow-up survey (follow-up rate: 93%). Both groups showed increased physical activity, and the intervention group showed reduced psychological distress; however, the differences between groups were not statistically significant (P=.20; P=.36). In a sensitivity analysis of protocol-compliant employees (n=21), psychological distress levels were significantly reduced in the intervention group compared with the control group (coefficient=-3.68, SE 1.65; P=.03). The app's 3-month user retention rate was 20% (12/61), which was lower than the participation rate in each component of the control programs. Implementation outcomes evaluated by employees were less favorable in the intervention group than in the control group, whereas health promotion managers found them to be similar.

CONCLUSIONS: The ASHARE app did not show superior effectiveness compared with an existing multicomponent workplace program for promoting physical activity. An implementation gap may exist between health promotion managers and employees, possibly contributing to the app's low user retention rate. Future research should focus on examining the effectiveness of strategies to get engagement from managers and from segments of employees with favorable responses in the workplace at an early stage.

PMID:40327360 | DOI:10.2196/70473

Med Biol Eng Comput. 2025 May 6. doi: 10.1007/s11517-025-03357-3. Online ahead of print.

ABSTRACT

The corticospinal tract (CST) is the primary neural pathway responsible for voluntary motor functions, and preoperative CST reconstruction is crucial for preserving nerve functions during neurosurgery. Diffusion magnetic resonance imaging-based tractography is the only noninvasive method to preoperatively reconstruct CST in clinical practice. However, for the largesize bundle CST with complex fiber geometry (fanning fibers), reconstructing its full extent remains challenging with local-derived methods without incorporating global information. Especially in the presence of tumors, the mass effect and partial volume effect cause abnormal diffusion signals. In this work, a CST reconstruction tractography method based on a novel direction filter was proposed, designed to ensure robust CST reconstruction in the clinical dataset with tumors. A direction filter based on a fourth-order differential equation was introduced for global direction estimation. By considering the spatial consistency and leveraging anatomical prior knowledge, the direction filter was computed by minimizing the energy between the target directions and initial fiber directions. On the basis of the new directions corresponding to CST obtained by the direction filter, the fiber tracking method was implemented to reconstruct the fiber trajectory. Additionally, a deep learning-based method along with tractography template prior information was employed to generate the regions of interest (ROIs) and initial fiber directions. Experimental results showed that the proposed method yields higher valid connections and lower no connections and exhibits the fewest broken fibers and short-connected fibers. The proposed method offers an effective tool to enhance CST-related surgical outcomes by optimizing tumor resection and preserving CST.

PMID:40327206 | DOI:10.1007/s11517-025-03357-3

Med Biol Eng Comput. 2025 May 6. doi: 10.1007/s11517-025-03372-4. Online ahead of print.

ABSTRACT

Rehabilitation exercises are critical for recovering from motor dysfunction caused by neurological conditions like stroke, back pain, Parkinson's disease, and spinal cord injuries. Traditionally, these exercises require constant monitoring by therapists, which is time-consuming and costly, often leading to therapist shortages. This paper introduces a deep learning model, convolutional neural network - squeeze excitation (CNN-SE), to automate rehabilitation exercise assessment. By optimizing its parameters with the grey wolf optimization algorithm, the model was fine-tuned for optimal performance. The model's effectiveness was tested on both healthy and unhealthy participants with motor dysfunction, providing a comprehensive evaluation of its capabilities. To interpret the model's decisions and understand its inner workings, we employed Shapley additive explanations (SHAP) to analyze feature importance at each time step. Our CNN-SE model achieved a state-of-the-art mean absolute deviation of 0.127 on the KIMORE dataset and a comparable MAD of 0.014 on the UI-PRMD dataset across various exercises, demonstrating its potential to provide a cost-effective, efficient alternative to traditional therapist-led evaluations.

PMID:40327204 | DOI:10.1007/s11517-025-03372-4