Res Sq [Preprint]. 2025 Jan 17:rs.3.rs-5584635. doi: 10.21203/rs.3.rs-5584635/v1.

ABSTRACT

The spatial arrangement of cells plays a pivotal role in shaping tissue functions in various biological systems and diseased microenvironments. However, it is still under-investigated of the topological coordinating rules among different cell types as tissue spatial patterns. Here, we introduce the Triangulation cellular community motif Neural Network (TrimNN), a bottom-up approach to estimate the prevalence of sizeable conservative cell organization patterns as Cellular Community (CC) motifs in spatial transcriptomics and proteomics. Different from clustering cell type composition from classical top-down analysis, TrimNN differentiates cellular niches as countable topological blocks in recurring interconnections of various types, representing multicellular neighborhoods with interpretability and generalizability. This graph-based deep learning framework adopts inductive bias in CCs and uses a semi-divide and conquer approach in the triangulated space. In spatial omics studies, various sizes of CC motifs identified by TrimNN robustly reveal relations between spatially distributed cell-type patterns and diverse phenotypical biological functions.

PMID:39877090 | PMC:PMC11774463 | DOI:10.21203/rs.3.rs-5584635/v1

iScience. 2024 Dec 9;28(1):111558. doi: 10.1016/j.isci.2024.111558. eCollection 2025 Jan 17.

ABSTRACT

Flax, as a functional crop with rich essential fatty acids and nutrients, is important in nutrition and industrial applications. However, the current process of flax seed detection relies mainly on manual operation, which is not only inefficient but also prone to error. The development of computer vision and deep learning techniques offers a new way to solve this problem. In this study, based on RT-DETR, we introduced the RepNCSPELAN4 module, ADown module, Context Aggregation module, and TFE module, and designed the HWD-ADown module, HiLo-AIFI module, and DSSFF module, and proposed an improved model, called LEHP-DETR. Experimental results show that LEHP-DETR achieves significant performance improvement on the flax dataset and comprehensively outperforms the comparison model. Compared to the base model, LEHP-DETR reduces the number of parameters by 67.3%, the model size by 66.3%, and the FLOPs by 37.6%. the average detection accuracy mAP50 and mAP50:95 increased by 2.6% and 3.5%, respectively.

PMID:39877068 | PMC:PMC11773470 | DOI:10.1016/j.isci.2024.111558

J Hand Microsurg. 2024 Oct 28;17(1):100171. doi: 10.1016/j.jham.2024.100171. eCollection 2025 Jan.

ABSTRACT

BACKGROUND: Trigger finger is a common disorder of the hand characterized by pain and locking of the digits during flexion or extension. In cases refractory to nonoperative management, surgical release of the A1 pulley can be performed. This study evaluates the ability of machine learning (ML) techniques to predict short-term complications following trigger digit release surgery.

METHODS: A retrospective study was conducted using data for trigger digit release from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) years 2005-2020. Outcomes of interest were 30-day complications and 30-day return to the operating room. Three ML algorithms were evaluated - a Random Forest (RF), Elastic-Net Regression (ENet), and Extreme Gradient Boosted Tree (XGBoost), along with a deep learning Neural Network (NN). Feature importance analysis was performed in the highest performing model for each outcome to identify predictors with the greatest contributions.

RESULTS: We included a total of 1209 cases of trigger digit release. The best algorithm for predicting wound complications was the RF, with an AUC of 0.64 ± 0.04. The XGBoost algorithm was best performing for medical complications (AUC: 0.70 ± 0.06) and reoperations (AUC: 0.60 ± 0.07). All three models had performance significantly above the AUC benchmark of 0.50 ± 0.00. On our feature importance analysis, age was distinctively the highest contributing predictor of wound complications.

CONCLUSIONS: Machine learning can be successfully used for risk stratification in surgical patients. Moving forwards, it is imperative for hand surgeons to continue evaluating applications of ML in the field.

PMID:39876951 | PMC:PMC11770221 | DOI:10.1016/j.jham.2024.100171

HGG Adv. 2025 Jan 27:100410. doi: 10.1016/j.xhgg.2025.100410. Online ahead of print.

ABSTRACT

Most genetic variants identified through genome-wide association studies (GWAS) are suspected to be regulatory in nature, but only a small fraction colocalize with expression quantitative trait loci (eQTLs, variants associated with expression of a gene). Therefore, it is hypothesized but largely untested that integration of disease GWAS with context-specific eQTLs will reveal the underlying genes driving disease associations. We used colocalization and transcriptomic analyses to identify shared genetic variants and likely causal genes associated with critically ill COVID-19 and idiopathic pulmonary fibrosis. We first identified five genome-wide significant variants associated with both diseases. Four of the variants did not demonstrate clear colocalization between GWAS and healthy lung eQTL signals. Instead, two of the four variants colocalized only in cell-type and disease-specific eQTL datasets. These analyses pointed to higher ATP11A expression from the C allele of rs12585036, in monocytes and in lung tissue from primarily smokers, which increased risk of IPF and decreased risk of critically ill COVID-19. We also found lower DPP9 expression (and higher methylation at a specific CpG) from the G allele of rs12610495, acting in fibroblasts and in IPF lungs, and increased risk of IPF and critically ill COVID-19. We further found differential expression of the identified causal genes in diseased lungs when compared to non-diseased lungs, specifically in epithelial and immune cell types. These findings highlight the power of integrating GWAS, context-specific eQTLs, and transcriptomics of diseased tissue to harness human genetic variation to identify causal genes and where they function during multiple diseases.

PMID:39876559 | DOI:10.1016/j.xhgg.2025.100410

Front Plant Sci. 2025 Jan 14;15:1525729. doi: 10.3389/fpls.2024.1525729. eCollection 2024.

ABSTRACT

The formation of the female germline is the fundamental process in most flowering plants' sexual reproduction. In Arabidopsis, only one somatic cell obtains the female germline fate, and this process is regulated by different pathways. Megaspore mother cell (MMC) is the first female germline, and understanding MMC development is essential for comprehending the complex mechanisms of plant reproduction processes. Recently, more advanced technologies such as whole-mount single-molecule fluorescence in situ hybridization (smFISH), laser-assisted microdissection (LCM), chromatin immunoprecipitation/sequencing, and CRISPR gene editing have provided opportunities to reveal the mechanism of female germline development at different stages. Single-cell transcriptome/spatial transcriptomics analysis helps to investigate complex cellular systems at the single-cell level, reflecting the biological complexity of different cell types. In this review, we highlight recent progress that facilitates the development of the female germline to explore the roles of crucial gene regulatory networks, epigenetic pathways, cell-cycle regulators, and phytohormones in this process. This review discusses three key phases in female germline development and provides the possibility of distinct pathways restricting germline development in the future.

PMID:39877734 | PMC:PMC11773337 | DOI:10.3389/fpls.2024.1525729

Heliyon. 2025 Jan 10;11(2):e41610. doi: 10.1016/j.heliyon.2024.e41610. eCollection 2025 Jan 30.

ABSTRACT

BACKGROUND: Normothermic machine perfusion (NMP) provides a platform for kidney quality assessment. Donation after circulatory death (DCD) donor kidneys are associated with great ischemic injury and high intrarenal resistance (IRR). This experimental study aims to investigate the impact of different perfusion pressures on marginal kidney function and injury during NMP.

METHODS: Twenty-seven slaughterhouse porcine kidneys were retrieved and subjected to 60 min of warm ischemia time to mimic DCD condition. These kidneys were randomized into 75 mmHg (subphysiological, n = 9), 95 mmHg (physiological, n = 9), and 115 mmHg NMP (high physiological, n = 9). Renal function and injury were assessed during NMP.

RESULTS: Three groups showed comparable IRR, with the 115 mmHg group exhibiting the highest blood flow. The 95 mmHg group [0.48 (0.36-1.15) ml/min/100g] and 115 mmHg group [0.93 (0.45-1.41) ml/min/100g] showed significantly higher creatinine clearance compared to the 75 mmHg group [0.16 (0.08-0.37) ml/min/100g] during the first hour of NMP (p = 0.049, p = 0.009, respectively). The 115 mmHg group exhibited significantly higher oxygen consumption compared to the 75 mmHg group at 30 min of NMP [1.37 (1.05-1.92) versus 0.72 (0.61-0.82) mlO2/min/100g, p = 0.009]. Perfusate neutrophil gelatinase-associated lipocalin (NGAL) levels were consistently lowest in the 95 mmHg group and highest in the 75 mmHg group. Aspartate aminotransferase (AST) levels of the 115 mmHg group were significantly higher than the 75 mmHg group.

CONCLUSIONS: For kidneys with high IRR, both 95 mmHg and 115 mmHg perfusion pressures enable an early improvement in renal hemodynamics and function compared to 75 mmHg during NMP, while a high physiological perfusion can cause additional injury.

PMID:39877618 | PMC:PMC11773052 | DOI:10.1016/j.heliyon.2024.e41610

Res Sq [Preprint]. 2025 Jan 17:rs.3.rs-5629379. doi: 10.21203/rs.3.rs-5629379/v1.

ABSTRACT

Antigen processing and presentation via major histocompatibility complex (MHC) molecules are central to immune surveillance. Yet, quantifying the dynamic activity of MHC class I and II antigen presentation remains a critical challenge, particularly in diseases like cancer, infection and autoimmunity where these pathways are often disrupted. Current methods fall short in providing precise, sample-specific insights into antigen presentation, limiting our understanding of immune evasion and therapeutic responses. Here, we present PSAA (PINN-empowered Systems Biology Analysis of Antigen Presentation Activity), which is designed to estimate sample-wise MHC class I and class II antigen presentation activity using bulk, single-cell, and spatially resolved transcriptomics or proteomics data. By reconstructing MHC pathways and employing pathway flux estimation, PSAA offers a detailed, stepwise quantification of MHC pathway activity, enabling predictions of gene-specific impacts and their downstream effects on immune interactions. Benchmarked across diverse omics datasets and experimental validations, PSAA demonstrates a robust prediction accuracy and utility across various disease contexts. In conclusion, PSAA and its downstream functions provide a comprehensive framework for analyzing the dynamics of MHC antigen presentation using omics data. By linking antigen presentation to immune cell activity and clinical outcomes, PSAA both elucidates key mechanisms driving disease progression and uncovers potential therapeutic targets.

PMID:39877095 | PMC:PMC11774464 | DOI:10.21203/rs.3.rs-5629379/v1

Nucleic Acids Res. 2025 Jan 24;53(3):gkaf001. doi: 10.1093/nar/gkaf001.

ABSTRACT

Cell fate determination at the chromatin level is not fully comprehended. Here, we report that c-JUN acts on chromatin loci to limit mesoderm cell fate specification as cells exit pluripotency. Although c-JUN is widely expressed across various cell types in early embryogenesis, it is not essential for maintaining pluripotency. Instead, it functions as a repressor to constrain mesoderm development while having a negligible impact on ectoderm differentiation. c-JUN interacts with MBD3-NuRD complex, which helps maintain chromatin in a low accessibility state at mesoderm-related genes during the differentiation of human pluripotent stem cells into mesoderm. Furthermore, c-JUN specifically inhibits the activation of key mesoderm factors, such as EOMES and GATA4. Knocking out c-JUN or inhibiting it with a JNK inhibitor can alleviate this suppression, promoting mesoderm cell differentiation. Consistently, knockdown of MBD3 enhances mesoderm generation, whereas MBD3 overexpression impedes it. Overexpressing c-JUN redirects differentiation toward a fibroblast-like lineage. Collectively, our findings suggest that c-JUN acts as a chromatin regulator to restrict the mesoderm cell fate.

PMID:39876710 | DOI:10.1093/nar/gkaf001

Protein Sci. 2025 Feb;34(2):e5163. doi: 10.1002/pro.5163.

ABSTRACT

Amyloid fibril formation of α-synuclein (αSN) is a hallmark of synucleinopathies. Although the previous studies have provided numerous insights into the molecular basis of αSN amyloid formation, it remains unclear how αSN self-assembles into amyloid fibrils in vivo. Here, we show that αSN amyloid formation is accelerated in the presence of two macromolecular crowders, polyethylene glycol (PEG) (MW: ~10,000) and dextran (DEX) (MW: ~500,000), with a maximum at approximately 7% (w/v) PEG and 7% (w/v) DEX. Under these conditions, the two crowders induce a two-phase separation of upper PEG and lower DEX phases with a small number of liquid droplets of DEX and PEG in PEG and DEX phases, respectively. Fluorescence microscope images revealed that the interfaces of DEX droplets in the upper PEG phase are the major sites of amyloid formation. We consider that the depletion interactions working in micro phase-segregated state with DEX and PEG systems causes αSN condensation at the interface between solute PEG and DEX droplets, resulting in accelerated amyloid formation. Ultrasonication further accelerated the amyloid formation in both DEX and PEG phases, confirming the droplet-dependent amyloid formation. Similar PEG/DEX-dependent accelerated amyloid formation was observed for amyloid β peptide. In contrast, amyloid formation of β2-microglobulin or hen egg white lysozyme with a native fold was suppressed in the PEG/DEX mixtures, suggesting that the depletion interactions work adversely depending on whether the protein is unfolded or folded.

PMID:39876094 | DOI:10.1002/pro.5163

Orphanet J Rare Dis. 2025 Jan 29;20(1):42. doi: 10.1186/s13023-024-03518-x.

ABSTRACT

BACKGROUND: Rare diseases (RDs) are a heterogeneous group of complex and low-prevalence conditions in which the time to establish a definitive diagnosis is often too long. In addition, for most RDs, few to no treatments are available and it is often difficult to find a specialized care team.

OBJECTIVES: The project "acERca las enfermedades raras" (in English: "bringing RDs closer") is an initiative primary designed to generate a consensus by a multidisciplinary group of experts to detect the strengths and weaknesses in the public healthcare system concerning the comprehensive care of persons living with a RD (PLWRD) in the region of Catalonia, Spain, where a Network of Clinical Expert Units (Xarxa d'Unitats de Expertesa Clínica or XUEC) was created and is being implemented since 2015. The additional primary aim was to propose recommendations to solve or improve the limitations found.

METHODS: A task force of 13 participants with multidisciplinary expertise on RDs completed a questionnaire and participated in two focus groups. A document was drafted with an item series of strengths and weaknesses of the healthcare system regarding the care of PLWRD, and a set of proposals or recommendations to overcome the problems identified.

RESULTS: The Catalan Government healthcare model of XUECs for the comprehensive care for RDs is currently valid and adapted to the needs of PLWRD and their families since its strategic optimal and operational framework, and it is aligned with the European Reference Networks (ERNs) thematic areas. The problems found in the current healthcare model were grouped into ten main areas: (1) the healthcare model for RDs; (2) coordination with primary healthcare providers and other tertiary and secondary hospitals; (3) access to and coordination with non-medical services; (4) the role of case manager in the XUEC; (5) genetic diagnosis; (6) undiagnosed patients; (7) treatments; (8) referring process, continuous follow-up, and transition from pediatric to adult centers; (9) research and education for professionals; and (10) associations of PLWRD and their families (patients' advocacy). The need for more resources was currently detected as the common factor for most of them. Ten key recommendations to improve the healthcare system regarding RDs were postulated.

CONCLUSIONS: Catalonia has established a unique healthcare model for RDs in Spain, with clear strengths and advantages. However, after analyzing them, the experts suggested that new governmental political and administrative decisions are needed to ensure the efficient implementation of a healthcare plan for PLWRD in Catalonia, which could be applied to other regions and nations worldwide.

PMID:39875900 | DOI:10.1186/s13023-024-03518-x

Sci Rep. 2025 Jan 28;15(1):3546. doi: 10.1038/s41598-025-88078-1.

ABSTRACT

The rapid increase in sea levels driven by climate change presents serious risks to coastal communities around the globe. Traditional prediction models frequently concentrate on developed regions with extensive tide gauge networks, leaving a significant gap in data and forecasts for developing countries where the tide gauges are sparse. This study presents a novel deep learning approach that combines TimesGAN with ConvLSTM to enhance regional sea level predictions using the more widely available satellite altimetry data. By generating synthetic training data with TimesGAN, we can significantly improve the predictive accuracy of the ConvLSTM model. Our method is tested across three developed regions-Shanghai, New York, and Lisbon-and three developing regions-Liberia, Gabon, and Somalia. The results reveal that integrating TimesGAN reduces the average mean squared error of the ConvLSTM prediction by approximately 66.1%, 76.6%, 64.5%, 78.2%, 81.7% and 85.1% for Shanghai, New York, Lisbon, Liberia, Gabon, and Somalia, respectively. This underscores the effectiveness of synthetic data in enhancing sea level prediction accuracy, across all regions studied.

PMID:39875524 | DOI:10.1038/s41598-025-88078-1

Sci Rep. 2025 Jan 28;15(1):3591. doi: 10.1038/s41598-025-87778-y.

ABSTRACT

Prediction of isocitrate dehydrogenase (IDH) mutation status and epilepsy occurrence are important to glioma patients. Although machine learning models have been constructed for both issues, the correlation between them has not been explored. Our study aimed to exploit this correlation to improve the performance of both of the IDH mutation status identification and epilepsy diagnosis models in patients with glioma II-IV. 399 patients were retrospectively enrolled and divided into a training (n = 279) and an independent test (n = 120) cohort. Multi-center dataset (n = 228) from The Cancer Imaging Archive (TCIA) was used for external test for identification of IDH mutation status. Region of interests comprising the entire tumor and peritumoral edema were automatically segmented using a pre-trained deep learning model. Radiomic features were extracted from T1-weighted, T2-weighted, post-Gadolinium T1 weighted, and T2 fluid-attenuated inversion recovery images. We proposed an iterative approach derived from LASSO to select features shared by two tasks and features specific to each task, before using them to construct the final models. Receiver operating characteristic (ROC) analysis was employed to evaluate the model. The IDH mutation identification model achieved area under the ROC curve (AUC) values of 0.948, 0.946 and 0.860 on the training, internal test, and external test cohorts, respectively. The epilepsy diagnosis model achieved AUCs of 0.924 and 0.880 on the training and internal test cohorts, respectively. The proposed models can identify IDH status and epilepsy with fewer features, thus having better interpretability and lower risk of overfitting. This not only improves its chance of application in clinical settings, but also provides a new scheme to study multiple correlated clinical tasks.

PMID:39875517 | DOI:10.1038/s41598-025-87778-y

NPJ Digit Med. 2025 Jan 28;8(1):67. doi: 10.1038/s41746-025-01464-x.

ABSTRACT

Accurately predicting binding affinities between drugs and targets is crucial for drug discovery but remains challenging due to the complexity of modeling interactions between small drug and large targets. This study proposes DMFF-DTA, a dual-modality neural network model integrates sequence and graph structure information from drugs and proteins for drug-target affinity prediction. The model introduces a binding site-focused graph construction approach to extract binding information, enabling more balanced and efficient modeling of drug-target interactions. Comprehensive experiments demonstrate DMFF-DTA outperforms state-of-the-art methods with significant improvements. The model exhibits excellent generalization capabilities on completely unseen drugs and targets, achieving an improvement of over 8% compared to existing methods. Model interpretability analysis validates the biological relevance of the model. A case study in pancreatic cancer drug repurposing demonstrates its practical utility. This work provides an interpretable, robust approach to integrate multi-view drug and protein features for advancing computational drug discovery.

PMID:39875637 | DOI:10.1038/s41746-025-01464-x

Stem Cell Res Ther. 2025 Jan 29;16(1):29. doi: 10.1186/s13287-025-04152-5.

ABSTRACT

Chronic pulmonary diseases pose a prominent health threat globally owing to their intricate pathogenesis and lack of effective reversal therapies. Nowadays, lung transplantation stands out as a feasible treatment option for patients with end-stage lung disease. Unfortunately, the use of this this option is limited by donor organ shortage and severe immunological rejection reactions. Recently, airway basal stem cells (BSCs) have emerged as a novel therapeutic strategy in pulmonary regenerative medicine because of their substantial potential in repairing lung structure and function. Airway BSCs, which are strongly capable of self-renewal and multi-lineage differentiation, can effectively attenuate airway epithelial injury caused by environmental factors or genetic disorders, such as cystic fibrosis. This review comprehensively explores the efficacy and action mechanisms of airway BSCs across various lung disease models and describes potential strategies for inducing pluripotent stem cells to differentiate into pulmonary epithelial lineages on the basis of the original research findings. Additionally, the review also discusses the technical and biological challenges in translating these research findings into clinical applications and offers prospective views on future research directions, therefore broadening the landscape of pulmonary regenerative medicine.

PMID:39876014 | DOI:10.1186/s13287-025-04152-5

J Cheminform. 2025 Jan 28;17(1):11. doi: 10.1186/s13321-025-00957-x.

ABSTRACT

The human ether-a-go-go-related gene (hERG) channel plays a critical role in the electrical activity of the heart, and its blockers can cause serious cardiotoxic effects. Thus, screening for hERG channel blockers is a crucial step in the drug development process. Many in silico models have been developed to predict hERG blockers, which can efficiently save time and resources. However, previous methods have found it hard to achieve high performance and to interpret the predictive results. To overcome these challenges, we have proposed hERGAT, a graph neural network model with an attention mechanism, to consider compound interactions on atomic and molecular levels. In the atom-level interaction analysis, we applied a graph attention mechanism (GAT) that integrates information from neighboring nodes and their extended connections. The hERGAT employs a gated recurrent unit (GRU) with the GAT to learn information between more distant atoms. To confirm this, we performed clustering analysis and visualized a correlation heatmap, verifying the interactions between distant atoms were considered during the training process. In the molecule-level interaction analysis, the attention mechanism enables the target node to focus on the most relevant information, highlighting the molecular substructures that play crucial roles in predicting hERG blockers. Through a literature review, we confirmed that highlighted substructures have a significant role in determining the chemical and biological characteristics related to hERG activity. Furthermore, we integrated physicochemical properties into our hERGAT model to improve the performance. Our model achieved an area under the receiver operating characteristic of 0.907 and an area under the precision-recall of 0.904, demonstrating its effectiveness in modeling hERG activity and offering a reliable framework for optimizing drug safety in early development stages.Scientific contribution:hERGAT is a deep learning model for predicting hERG blockers by combining GAT and GRU, enabling it to capture complex interactions at atomic and molecular levels. We improve the model's interpretability by analyzing the highlighted molecular substructures, providing valuable insights into their roles in determining hERG activity. The model achieves high predictive performance, confirming its potential as a preliminary tool for early cardiotoxicity assessment and enhancing the reliability of the results.

PMID:39875959 | DOI:10.1186/s13321-025-00957-x

BMC Oral Health. 2025 Jan 28;25(1):152. doi: 10.1186/s12903-025-05425-4.

ABSTRACT

BACKGROUND: Assessing the difficulty of impacted lower third molar (ILTM) surgical extraction is crucial for predicting postoperative complications and estimating procedure duration. The aim of this study was to evaluate the effectiveness of a convolutional neural network (CNN) in determining the angulation, position, classification and difficulty index (DI) of ILTM. Additionally, we compared these parameters and the time required for interpretation among deep learning (DL) models, sixth-year dental students (DSs), and general dental practitioners (GPs) with and without CNN assistance.

MATERIALS AND METHODS: The dataset included cropped panoramic radiographs of 1200 ILTMs. The parameters examined were ILTM angulation, class, and position. The radiographs were randomly split into test datasets, while the remaining images were utilized for training and validation. Data augmentation techniques were applied. Another set of radiographs was used to compare the accuracy between human experts and the top-performing CNN. This dataset was also given to DSs and GPs. The participants were instructed to classify the parameters of the ILTMs both with and without the aid of the best-performing CNN model. The results, as well as the Pederson DI and time taken for both groups with and without CNN assistance, were statistically analyzed.

RESULTS: All the selected CNN models successfully classified ILTM angulation, class, and position. Within the DS and GP groups, the accuracy and kappa scores were significantly greater when CNN assistance was used. Among the groups, performance tests without CNN assistance revealed no significant differences in any category. However, compared with DSs, GPs took significantly less time for the class and total time, a trend that persisted when CNN assistance was used. With the CNN, the GPs achieved significantly higher accuracy and kappa scores for class classification than the DSs did (p = 0.035 and 0.010). Conversely, the DS group, with the CNN, exhibited higher accuracy and kappa scores for position classification than did the GP group (p < 0.001).

CONCLUSION: The CNN can achieve accuracies ranging from 87 to 96% for ILTM classification. With the assistance of the CNN, both DSs and GPs exhibited significantly higher accuracy in ILTM classification. Additionally, compared with DSs with and without CNN assistance, GPs took significantly less time to inspect the class and overall.

PMID:39875882 | DOI:10.1186/s12903-025-05425-4

BMC Med. 2025 Jan 29;23(1):49. doi: 10.1186/s12916-025-03893-7.

ABSTRACT

BACKGROUND: This study aimed to construct a radiomics-based imaging biomarker for the non-invasive identification of transformed follicular lymphoma (t-FL) using PET/CT images.

METHODS: A total of 784 follicular lymphoma (FL), diffuse large B-cell lymphoma, and t-FL patients from 5 independent medical centers were included. The unsupervised EMFusion method was applied to fuse PET and CT images. Deep-based radiomic features were extracted from the fusion images using a deep learning model (ResNet18). These features, along with handcrafted radiomics, were utilized to construct a radiomic signature (R-signature) using automatic machine learning in the training and internal validation cohort. The R-signature was then tested for its predictive ability in the t-FL test cohort. Subsequently, this R-signature was combined with clinical parameters and SUVmax to develop a t-FL scoring system.

RESULTS: The R-signature demonstrated high accuracy, with mean AUC values as 0.994 in the training cohort and 0.976 in the internal validation cohort. In the t-FL test cohort, the R-signature achieved an AUC of 0.749, with an accuracy of 75.2%, sensitivity of 68.0%, and specificity of 77.5%. Furthermore, the t-FL scoring system, incorporating the R-signature along with clinical parameters (age, LDH, and ECOG PS) and SUVmax, achieved an AUC of 0.820, facilitating the stratification of patients into low, medium, and high transformation risk groups.

CONCLUSIONS: This study offers a promising approach for identifying t-FL non-invasively by radiomics analysis on PET/CT images. The developed t-FL scoring system provides a valuable tool for clinical decision-making, potentially improving patient management and outcomes.

PMID:39875864 | DOI:10.1186/s12916-025-03893-7

BMC Med Res Methodol. 2025 Jan 28;25(1):24. doi: 10.1186/s12874-025-02473-w.

ABSTRACT

BACKGROUND: Early detection and diagnosis of cancer are vital to improving outcomes for patients. Artificial intelligence (AI) models have shown promise in the early detection and diagnosis of cancer, but there is limited evidence on methods that fully exploit the longitudinal data stored within electronic health records (EHRs). This review aims to summarise methods currently utilised for prediction of cancer from longitudinal data and provides recommendations on how such models should be developed.

METHODS: The review was conducted following PRISMA-ScR guidance. Six databases (MEDLINE, EMBASE, Web of Science, IEEE Xplore, PubMed and SCOPUS) were searched for relevant records published before 2/2/2024. Search terms related to the concepts "artificial intelligence", "prediction", "health records", "longitudinal", and "cancer". Data were extracted relating to several areas of the articles: (1) publication details, (2) study characteristics, (3) input data, (4) model characteristics, (4) reproducibility, and (5) quality assessment using the PROBAST tool. Models were evaluated against a framework for terminology relating to reporting of cancer detection and risk prediction models.

RESULTS: Of 653 records screened, 33 were included in the review; 10 predicted risk of cancer, 18 performed either cancer detection or early detection, 4 predicted recurrence, and 1 predicted metastasis. The most common cancers predicted in the studies were colorectal (n = 9) and pancreatic cancer (n = 9). 16 studies used feature engineering to represent temporal data, with the most common features representing trends. 18 used deep learning models which take a direct sequential input, most commonly recurrent neural networks, but also including convolutional neural networks and transformers. Prediction windows and lead times varied greatly between studies, even for models predicting the same cancer. High risk of bias was found in 90% of the studies. This risk was often introduced due to inappropriate study design (n = 26) and sample size (n = 26).

CONCLUSION: This review highlights the breadth of approaches to cancer prediction from longitudinal data. We identify areas where reporting of methods could be improved, particularly regarding where in a patients' trajectory the model is applied. The review shows opportunities for further work, including comparison of these approaches and their applications in other cancers.

PMID:39875808 | DOI:10.1186/s12874-025-02473-w

NPJ Digit Med. 2025 Jan 29;8(1):69. doi: 10.1038/s41746-025-01470-z.

ABSTRACT

Existing prognostic models are useful for estimating the prognosis of lung adenocarcinoma patients, but there remains room for improvement. In the current study, we developed a deep learning model based on histopathological images to predict the recurrence risk of lung adenocarcinoma patients. The efficiency of the model was then evaluated in independent multicenter cohorts. The model defined high- and low-risk groups successfully stratified prognosis of the entire cohort. Moreover, multivariable Cox analysis identified the model defined risk groups as an independent predictor for disease-free survival. Importantly, combining TNM stage with the established model helped to distinguish subgroups of patients with high-risk stage II and stage III disease who are highly likely to benefit from adjuvant chemotherapy. Overall, our study highlights the significant value of the constructed model to serve as a complementary biomarker for survival stratification and adjuvant therapy selection for lung adenocarcinoma patients after resection.

PMID:39875799 | DOI:10.1038/s41746-025-01470-z

J Imaging Inform Med. 2025 Jan 28. doi: 10.1007/s10278-025-01399-5. Online ahead of print.

ABSTRACT

Deep learning models have shown promise in diagnosing neurodevelopmental disorders (NDD) like ASD and ADHD. However, many models either use graph neural networks (GNN) to construct single-level brain functional networks (BFNs) or employ spatial convolution filtering for local information extraction from rs-fMRI data, often neglecting high-order features crucial for NDD classification. We introduce a Multi-view High-order Network (MHNet) to capture hierarchical and high-order features from multi-view BFNs derived from rs-fMRI data for NDD prediction. MHNet has two branches: the Euclidean Space Features Extraction (ESFE) module and the Non-Euclidean Space Features Extraction (Non-ESFE) module, followed by a Feature Fusion-based Classification (FFC) module for NDD identification. ESFE includes a Functional Connectivity Generation (FCG) module and a High-order Convolutional Neural Network (HCNN) module to extract local and high-order features from BFNs in Euclidean space. Non-ESFE comprises a Generic Internet-like Brain Hierarchical Network Generation (G-IBHN-G) module and a High-order Graph Neural Network (HGNN) module to capture topological and high-order features in non-Euclidean space. Experiments on three public datasets show that MHNet outperforms state-of-the-art methods using both AAL1 and Brainnetome Atlas templates. Extensive ablation studies confirm the superiority of MHNet and the effectiveness of using multi-view fMRI information and high-order features. Our study also offers atlas options for constructing more sophisticated hierarchical networks and explains the association between key brain regions and NDD. MHNet leverages multi-view feature learning from both Euclidean and non-Euclidean spaces, incorporating high-order information from BFNs to enhance NDD classification performance.

PMID:39875742 | DOI:10.1007/s10278-025-01399-5