Med Biol Eng Comput. 2025 Feb 17. doi: 10.1007/s11517-025-03311-3. Online ahead of print.

ABSTRACT

Aortic aneurysms pose a significant risk of rupture. Previous research has shown that areas exposed to low wall shear stress (WSS) are more prone to rupture. Therefore, precise WSS determination on the aneurysm is crucial for rupture risk assessment. Computational fluid dynamics (CFD) is a powerful approach for WSS calculations, but they are computationally intensive, hindering time-sensitive clinical decision-making. In this study, we propose a deep learning (DL) surrogate, MultiViewUNet, to rapidly predict time-averaged WSS (TAWSS) distributions on abdominal aortic aneurysms (AAA). Our novel approach employs a domain transformation technique to translate complex aortic geometries into representations compatible with state-of-the-art neural networks. MultiViewUNet was trained on 23 real and 230 synthetic AAA geometries, demonstrating an average normalized mean absolute error (NMAE) of just 0.362 % in WSS prediction. This framework has the potential to streamline hemodynamic analysis in AAA and other clinical scenarios where fast and accurate stress quantification is essential.

PMID:39961912 | DOI:10.1007/s11517-025-03311-3

Med Biol Eng Comput. 2025 Feb 17. doi: 10.1007/s11517-025-03318-w. Online ahead of print.

ABSTRACT

Caries segmentation holds significant clinical importance in medical image analysis, particularly in the early detection and treatment of dental caries. However, existing deep learning segmentation methods often struggle with accurately segmenting complex caries boundaries. To address this challenge, this paper proposes a novel network, named AEDD-Net, which combines an attention mechanism with a dual-decoder structure to enhance the performance of boundary segmentation for caries. Unlike traditional methods, AEDD-Net integrates atrous spatial pyramid pooling with cross-coordinate attention mechanisms to effectively fuse global and multi-scale features. Additionally, the network introduces a dedicated boundary generation module that precisely extracts caries boundary information. Moreover, we propose an innovative boundary loss function to further improve the learning of boundary features. Experimental results demonstrate that AEDD-Net significantly outperforms other comparison networks in terms of Dice coefficient, Jaccard similarity, precision, and sensitivity, particularly showing superior performance in boundary segmentation. This study provides an innovative approach for automated caries segmentation, with promising potential for clinical applications.

PMID:39961911 | DOI:10.1007/s11517-025-03318-w

Eur Radiol. 2025 Feb 17. doi: 10.1007/s00330-025-11450-2. Online ahead of print.

ABSTRACT

OBJECTIVES: This study proposes a multimodal deep learning (DL) approach to investigate the impact of tumors and visceral fat on occult peritoneal metastasis in colorectal cancer (CRC) patients.

METHODS: We developed a DL model named Multi-scale Feature Fusion Network (MSFF-Net) based on ResNet18, which extracted features of tumors and visceral fat from the longest diameter tumor section and the third lumbar vertebra level (L3) in preoperative CT scans of CRC patients. Logistic regression analysis was applied to patients' clinical data that integrated with DL features. A random forest (RF) classifier was established to evaluate the MSFF-Net's performance on internal and external test sets and compare it with radiologists' performance.

RESULTS: The model incorporating fat features outperformed the single tumor modality in the internal test set. Combining clinical information with DL provided the best diagnostic performance for predicting peritoneal metastasis in CRC patients. The AUCs were 0.941 (95% CI: [0.891, 0.986], p = 0.03) for the internal test set and 0.911 (95% CI: [0.857, 0.971], p = 0.013) for the external test set. CRC patients with peritoneal metastasis had a higher visceral adipose tissue index (VATI) compared to those without. Maximum tumor diameter and VATI were identified as independent prognostic factors for peritoneal metastasis. Grad-CAM decision regions corresponded with the independent prognostic factors identified by logistic regression analysis.

CONCLUSION: The study confirms the network features of tumors and visceral fat significantly enhance predictive performance for peritoneal metastasis in CRC. Visceral fat is a meaningful imaging biomarker for peritoneal metastasis's early detection in CRC patients.

KEY POINTS: Question Current research on predicting colorectal cancer with peritoneal metastasis mainly focuses on single-modality analysis, while studies based on multimodal imaging information are relatively scarce. Findings The Multi-scale Feature Fusion Network, constructed based on ResNet18, can utilize CT images of tumors and visceral fat to detect occult peritoneal metastasis in colorectal cancer. Clinical relevance This study identified independent prognostic factors for colorectal cancer peritoneal metastasis and combines them with tumor and visceral fat network features, aiding early diagnosis and accurate prognostic assessment.

PMID:39961863 | DOI:10.1007/s00330-025-11450-2

Med Biol Eng Comput. 2025 Feb 17. doi: 10.1007/s11517-025-03325-x. Online ahead of print.

ABSTRACT

Computational drug repositioning approaches should be investigated for the identification of new treatments for Alzheimer's patients as a huge amount of omics data has been produced during pre-clinical and clinical studies. Here, we investigated a gene network in Alzheimer's patients to detect a proper therapeutic target. We screened the targets of different drugs (34,006 compounds) using data available in the Connectivity Map database. Then, we analyzed transcriptome profiles of Alzheimer's patients to discover a network of gene-drugs based on mutual information, representing an index of dependence among genes. This study identified a network consisting of 25 genes and compounds and interconnected biological processes using computational approaches. The results also highlight the diagnostic role of the 25 genes since we obtained good classification performances using a neural network model. We also suggest 12 repurposable drugs (like KU-60019, AM-630, CP55940, enflurane, ginkgolide B, linopirdine, apremilast, ibudilast, pentoxifylline, roflumilast, acitretin, and tamibarotene) interacting with 6 genes (ATM, CNR1, GLRB, KCNQ2, PDE4B, and RARA), that we linked to retrograde endocannabinoid signaling, synaptic vesicle cycle, morphine addiction, and homologous recombination.

PMID:39961913 | DOI:10.1007/s11517-025-03325-x

J Bioinform Comput Biol. 2024 Dec;22(6):2450028. doi: 10.1142/S0219720024500288. Epub 2025 Feb 1.

ABSTRACT

The prediction of drug-target affinity (DTA) is crucial for efficiently identifying potential targets for drug repurposing, thereby reducing resource wastage. In this paper, we propose a novel graph-based deep learning model for DTA that leverages adaptive structure-aware pooling for graph processing. Our approach integrates a self-attention mechanism with an enhanced graph neural network to capture the significance of each node in the graph, marking a significant advancement in graph feature extraction. Specifically, adjacent nodes in the 2D molecular graph are aggregated into clusters, with the features of these clusters weighted according to their attention scores to form the final molecular representation. In terms of model architecture, we utilize both global and hierarchical pooling, and assess the performance of the model on multiple benchmark datasets. The evaluation results on the KIBA dataset show that our model achieved the lowest mean squared error (MSE) of 0.126, which is a 0.5% reduction compared to the best-performing baseline method. Additionally, to validate the generalization capabilities of the model, we conduct comparative experiments on regression and binary classification tasks. The results demonstrate that our model outperforms previous models in both types of tasks.

PMID:39961610 | DOI:10.1142/S0219720024500288

Ageing Res Rev. 2025 Feb 15:102693. doi: 10.1016/j.arr.2025.102693. Online ahead of print.

ABSTRACT

Repurposing the existing drugs for the management of both common and rare diseases is increasingly appealing due to challenges such as high attrition rates, economic, and the slow pace of discovering and improving new drugs. Drug repurposing involves the utilization of existing medications to treat diseases for which they were not originally intended. Despite encountering scientific and economic challenges, the pharmaceutical industry is intrigued by the potential to uncover new indications for medications. Medication repurposing is applicable across different stages of drug development, with the greatest potential observed when the drug has undergone prior safety testing. In this review, strategies for repurposing drugs for Parkinson's disease (PD) are outlined, a neurodegenerative disorder predominantly impacting dopaminergic neurons in the substantia nigra pars compacta region. PD is a debilitating neurodegenerative condition marked by an amalgam of motor and non-motor symptoms. Despite the availability of certain symptomatic treatments, particularly targeting motor symptoms, there remains a lack of established drugs capable of modifying the course of PD, leading to its unchecked progression. Although standard drug discovery initiatives focusing on treatments that relieve diseases have yielded valuable understanding into the underlying mechanisms of PD, none of the numerous promising candidates identified in preclinical studies have successfully transitioned into clinically effective medications. Due to the substantial expenses associated with drug discovery endeavors, it is understandable that there has been a notable shift towards reprofiling strategies. Assessing the efficacy of an existing medication offers the additional advantage of circumventing the requirement for preclinical safety assessments and formulation enhancements, consequently streamlining the process and reducing both the duration of time and financial investments involved in bringing a treatment to clinical fruition. Furthermore, repurposed drugs may benefit from lower rates of failure, presenting an additional potential advantage. various strategies for repurposing drugs are available to researchers in the field of PD. Some of these strategies have demonstrated effectiveness in identifying appropriate drugs for clinical trials, thereby providing validation for such techniques. This review provides an overview of the diverse strategies employed for drug reprofiling from approaches that emphasise on single-gene transcriptional investigations to comprehensive epidemiological correlation analysis. Additionally, instances of previous or current research endeavors employing each strategy has been discussed. For strategies not yet implemented in PD research, their efficacy is demonstrated using examples from other disorders. In this review, we assess the safety and efficacy potential of prominent candidates repurposed as potential treatments for modifying the course of PD undergoing advanced clinical trials.

PMID:39961372 | DOI:10.1016/j.arr.2025.102693

Sci Data. 2025 Feb 17;12(1):282. doi: 10.1038/s41597-025-04580-1.

ABSTRACT

The Provenance Ontology (PROV-O) is a World Wide Web Consortium (W3C) recommended ontology used to structure data about provenance across a wide variety of domains. Basic Formal Ontology (BFO) is a top-level ontology ISO/IEC standard used to structure a wide variety of ontologies, such as the OBO Foundry ontologies and the Common Core Ontologies (CCO). To enhance interoperability between these two ontologies, their extensions, and data organized by them, a mapping methodology and set of alignments are presented according to specific criteria which prioritize semantic and logical principles. The ontology alignments are evaluated by checking their logical consistency with canonical examples of PROV-O instances and querying terms that do not satisfy the alignment criteria as formalized in SPARQL. A variety of semantic web technologies are used in support of FAIR (Findable, Accessible, Interoperable, Reusable) principles.

PMID:39962095 | DOI:10.1038/s41597-025-04580-1

J Biomed Inform. 2025 Feb 15:104804. doi: 10.1016/j.jbi.2025.104804. Online ahead of print.

ABSTRACT

OBJECTIVE: Visual representations generally serve as supplements to information, rather than as bearers of computable information themselves. Our objective is to develop a method for creating semantically-augmented graphic libraries that will serve as visual standards and can be implemented as visual assets in intelligent information systems.

METHODS: Graphics were developed using a composable approach and specified using SVG. OWL was used to represent the entities of our system, which include elements, units, graphics, graphic libraries, and library collections. A graph database serves as our data management system. Semantics are applied at multiple levels: (a) each element is associated with a semantic style class to link visual style to semantic meaning, (b) graphics are described using object properties and data properties, (c) relationships are specified between graphics, and (d) mappings are made between the graphics and outside resources.

RESULTS: The Graphic Library web application enables users to browse the libraries, view information pages for each graphic, and download individual graphics. We demonstrate how SPARQL can be employed to query the graphics database and the APIs can be used to retrieve the graphics and associated data for applications. In addition, this work shows that our method of designing composable graphics is well-suited to depicting variations in human anatomy.

CONCLUSION: This work provides a bridge between visual communication and the field of knowledge representation. We demonstrate a method for creating visual standards that are compatible with practices in biomedical ontology and implement a system for making them accessible to information systems.

PMID:39961540 | DOI:10.1016/j.jbi.2025.104804

Pharmacol Res. 2025 Feb 15:107660. doi: 10.1016/j.phrs.2025.107660. Online ahead of print.

ABSTRACT

Atypical teratoid/rhabdoid tumor (AT/RT) is a highly malignant embryonal brain tumor driven by genetic alterations inactivating the SMARCB1 or, less commonly, the SMARCA4 gene. Large-scale molecular profiling studies have identified distinct molecular subtypes termed AT/RT-TYR, -SHH and -MYC. Despite the increasing knowledge of AT/RT biology, curative treatment options are still lacking for certain risk groups and outcomes of these patients remain poor. We performed an in vitro high-throughput drug screen of 768 small molecule drugs covering conventional chemotherapeutic agents and late-stage developmental drugs in 13 AT/RT cell lines and determined intra- and inter-entity differential responses to unravel specific vulnerabilities. Our data demonstrated in vitro preferential activity of mitogen-activated protein kinase kinase (MEK) and mouse double minute 2 homolog (MDM2) inhibitors in AT/RT cell lines compared to other high-grade brain tumor cell lines including medulloblastoma and malignant glioma models. Moreover, we were able to link distinct drug response patterns to AT/RT molecular subtypes through integration of drug response data with large-scale DNA methylation and RNASeq-based expression profiles. Subtype-dependent drug response profiles demonstrated sensitivity of AT/RT-SHH cell lines to B-cell lymphoma 2 (BCL2) and heat shock protein 90 (HSP90) inhibitors, and increased activity of microtubule inhibitors, kinesin spindle protein (KSP) inhibitors, and the eukaryotic translation initiation factor 4E (eIF4E) inhibitor briciclib in a subset of AT/RT-MYC cell lines. In summary, our in vitro pharmacogenomic approach revealed preclinical evidence of tumor type- and subtype-specific therapeutic vulnerabilities in AT/RT cell lines that may inform future in vivo and clinical evaluations of novel pharmacological strategies.

PMID:39961404 | DOI:10.1016/j.phrs.2025.107660

Respir Med. 2025 Feb 15:107995. doi: 10.1016/j.rmed.2025.107995. Online ahead of print.

NO ABSTRACT

PMID:39961395 | DOI:10.1016/j.rmed.2025.107995

Sci Rep. 2025 Feb 17;15(1):5759. doi: 10.1038/s41598-025-90430-4.

ABSTRACT

The concept of a smart city has spread as a solution ensuring wider availability of data and services to citizens, apart from as a means to lower the environmental footprint of cities. Crowd density monitoring is a cutting-edge technology that enables smart cities to monitor and effectively manage crowd movements in real time. By utilizing advanced artificial intelligence and video analytics, valuable insights are accumulated from crowd behaviour, assisting cities in improving operational efficiency, improving public safety, and urban planning. This technology also significantly contributes to resource allocation and emergency response, contributing to smarter, safer urban environments. Crowd density classification in smart cities using deep learning (DL) employs cutting-edge NN models to interpret and analyze information from sensors such as IoT devices and CCTV cameras. This technique trains DL models on large datasets to accurately count people in a region, assisting traffic management, safety, and urban planning. By utilizing recurrent neural networks (RNNs) for time-series data and convolutional neural networks (CNNs) for image processing, the model adapts to varying crowd scenarios, lighting, and angles. This manuscript presents a Deep Convolutional Neural Network-based Crowd Density Monitoring for Intelligent Urban Planning (DCNNCDM-IUP) technique on smart cities. The proposed DCNNCDM-IUP technique utilizes DL methods to detect crowd densities, which can significantly assist in urban planning for smart cities. Initially, the DCNNCDM-IUP technique performs image preprocessing using Gaussian filtering (GF). The DCNNCDM-IUP technique utilizes the SE-DenseNet approach, which effectually learns complex feature patterns for feature extraction. Moreover, the hyperparameter selection of the SE-DenseNet approach is accomplished by using the red fox optimization (RFO) methodology. Finally, the convolutional long short-term memory (ConvLSTM) methodology recognizes varied crowd densities. A comprehensive simulation analysis is conducted to demonstrate the improved performance of the DCNNCDM-IUP technique. The experimental validation of the DCNNCDM-IUP technique portrayed a superior accuracy value of 98.40% compared to existing DL models.

PMID:39962323 | DOI:10.1038/s41598-025-90430-4

Nat Methods. 2025 Feb 17. doi: 10.1038/s41592-024-02581-3. Online ahead of print.

NO ABSTRACT

PMID:39962313 | DOI:10.1038/s41592-024-02581-3

Nat Methods. 2025 Feb 17. doi: 10.1038/s41592-024-02582-2. Online ahead of print.

ABSTRACT

The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation learning method, MARBLE, which decomposes on-manifold dynamics into local flow fields and maps them into a common latent space using unsupervised geometric deep learning. In simulated nonlinear dynamical systems, recurrent neural networks and experimental single-neuron recordings from primates and rodents, we discover emergent low-dimensional latent representations that parametrize high-dimensional neural dynamics during gain modulation, decision-making and changes in the internal state. These representations are consistent across neural networks and animals, enabling the robust comparison of cognitive computations. Extensive benchmarking demonstrates state-of-the-art within- and across-animal decoding accuracy of MARBLE compared to current representation learning approaches, with minimal user input. Our results suggest that a manifold structure provides a powerful inductive bias to develop decoding algorithms and assimilate data across experiments.

PMID:39962310 | DOI:10.1038/s41592-024-02582-2

Sci Rep. 2025 Feb 17;15(1):5707. doi: 10.1038/s41598-025-90164-3.

ABSTRACT

In order to detect epileptic spikes, this paper suggests a deep learning architecture that blends 1D residual convolutional neural networks (1D-ResCNN) with a hybrid optimization strategy. The Layer-wise Adaptive Moments (LAMB) and AdamW algorithms have been used in the model's optimization to improve efficiency and accelerate convergence while extracting features from time and frequency domain EEG data. The framework has been considered on two public epilepsy datasets CHB-MIT and Siena. In the CHB-MIT dataset, comprising 24-channel EEG recordings from 12 patients, the model achieved an accuracy of 99.71%, a sensitivity of 99.60%, and a specificity of 99.61% for detecting epileptic spikes. Similarly, in the Siena dataset, which includes EEG data from 14 adult patients, the model demonstrated an average accuracy of 99.75%. Sensitivity averaged 99.94%, while specificity averaged 99.95%. The false positive rate (FPR) remained low at 0.0011, and the model obtained an average F1-score of 99.74%. For real-time hardware validation, the 1D-ResCNN model was deployed within the Typhoon HIL simulator, utilizing embedded C2000 microcontrollers. This hardware configuration allowed for immediate spike detection with minimal latency, ensuring reliable performance in real-time clinical applications. The findings imply that the suggested approach provides suitable for identifying epileptic spikes in real time for medical settings.

PMID:39962290 | DOI:10.1038/s41598-025-90164-3

Sci Rep. 2025 Feb 17;15(1):5766. doi: 10.1038/s41598-025-89672-z.

ABSTRACT

Accurately discerning lead-zinc open pit mining areas using traditional remote sensing methods is challenging due to spectral signature class mixing. However, machine learning (ML) algorithms have been implemented to classify satellite images, achieving better accuracy in discriminating complex landcover features. This study aims to characterise various ML models for detecting and classifying lead-zinc open pit mining areas amidst surrounding landcover features based on Sentinel 2 image analysis. Various associated band ratios and spectral indices were integrated with processed Sentinel 2 reflectance bands to enhance detection accuracy. Suitable bands highlighting lead and zinc mine areas were identified based on optimal index factor (OIF) analysis and various deep learning-based stacked encoders. Furthermore, 15 different ML classifiers were tested to identify optimised algorithms for accurately discriminating complex mining areas and associated landcover features. After detailed evaluation and comparison of their accuracies, the extra tree classifier (et) was the most effective, achieving an overall accuracy of 0.94 and a kappa coefficient of 0.93. The light gradient boosting machine classifier (lightgbm) and random forest classifier (rf) models also performed well, with overall accuracies of 0.937 and 0.936 and kappa coefficients of 0.925 and 0.925, respectively.

PMID:39962260 | DOI:10.1038/s41598-025-89672-z

Sci Rep. 2025 Feb 17;15(1):5734. doi: 10.1038/s41598-025-90034-y.

ABSTRACT

This study aims to address the diagnostic challenges in distinguishing gastric polyps from protrusions, emphasizing the need for accurate and cost-effective diagnosis strategies. It explores the application of Convolutional Neural Networks (CNNs) to improve diagnostic accuracy. This research introduces MultiAttentiveScopeNet, a deep learning model that incorporates multi-layer feature ensemble and attention mechanisms to enhance gastroscopy image analysis accuracy. A weakly supervised labeling strategy was employed to construct a large multi-class gastroscopy image dataset for training and validation. MultiAttentiveScopeNet demonstrates significant improvements in prediction accuracy and interpretability. The integrated attention mechanism effectively identifies critical areas in images to aid clinical decisions. Its multi-layer feature ensemble enables robust analysis of complex gastroscopy images. Comparative testing against human experts shows exceptional diagnostic performance, with accuracy, micro and macro precision, micro and macro recall, and micro and macro AUC reaching 0.9308, 0.9312, 0.9325, 0.9283, 0.9308, 0.9847 and 0.9853 respectively. This highlights its potential as an effective tool for primary healthcare settings. This study provides a comprehensive solution to address diagnostic challenges differentiating gastric polyps and protrusions. MultiAttentiveScopeNet improves accuracy and interpretability, demonstrating the potential of deep learning for gastroscopy image analysis. The constructed dataset facilitates continued model optimization and validation. The model shows promise in enhancing diagnostic outcomes in primary care.

PMID:39962226 | DOI:10.1038/s41598-025-90034-y

Sci Rep. 2025 Feb 17;15(1):5787. doi: 10.1038/s41598-025-90115-y.

ABSTRACT

Current deep learning methods for diagnosing Alzheimer's disease (AD) typically rely on analyzing all or parts of high-resolution 3D volumetric features, which demand expensive computational resources and powerful GPUs, particularly when using multimodal data. In contrast, lightweight cortical surface representations offer a more efficient approach for quantifying AD-related changes across different cortical regions, such as alterations in cortical structures, impaired glucose metabolism, and the deposition of pathological biomarkers like amyloid-β and tau. Despite these advantages, few studies have focused on diagnosing AD using multimodal surface-based data. This study pioneers a novel method that leverages multimodal, lightweight cortical surface features extracted from MRI and PET scans, providing an alternative to computationally intensive 3D volumetric features. Our model employs a middle-fusion approach with a cross-attention mechanism to efficiently integrate features from different modalities. Experimental evaluations on the ADNI series dataset, using T1-weighted MRI and [Formula: see text]Fluorodeoxyglucose PET, demonstrate that the proposed model outperforms volume-based methods in both early AD diagnosis accuracy and computational efficiency. The effectiveness of our model is further validated with the combination of T1-weighted MRI, Aβ PET, and Tau PET scans, yielding favorable results. Our findings highlight the potential of surface-based transformer models as a superior alternative to conventional volume-based approaches.

PMID:39962212 | DOI:10.1038/s41598-025-90115-y

Commun Eng. 2025 Feb 17;4(1):24. doi: 10.1038/s44172-025-00367-9.

ABSTRACT

Regular monitoring of marine life is essential for preserving the stability of marine ecosystems. However, underwater target detection presents several challenges, particularly in balancing accuracy with model efficiency and real-time performance. To address these issues, we propose an innovative approach that combines the Structured Space Model (SSM) with feature enhancement, specifically designed for small target detection in underwater environments. We developed a high-accuracy, lightweight detection model-UWNet. The results demonstrate that UWNet excels in detection accuracy, particularly in identifying difficult-to-detect organisms like starfish and scallops. Compared to other models, UWNet reduces the number of model parameters by 5% to 390%, substantially improving computational efficiency while maintaining top detection accuracy. Its lightweight design enhances the model's applicability for deployment on underwater robots.

PMID:39962196 | DOI:10.1038/s44172-025-00367-9

Sci Rep. 2025 Feb 17;15(1):5805. doi: 10.1038/s41598-024-72539-0.

ABSTRACT

Cervical spinal cord injury is often catastrophic, frequently leading to irreversible impairment. MRI has become the gold standard for evaluating spinal cord injuries (SCI). Our study aimed to assess the accuracy of a radiomics approach, based on machine learning and utilizing conventional MRI, in predicting the prognosis of patients with SCI. In a retrospective analysis of 82 SCI patients from three hospitals, we categorized them into good (n = 49) and poor (n = 33) prognosis groups. Preoperative T2-weighted MRI images were segmented using 3D-Region of Interest (ROI) techniques, and both radiomic and deep transfer learning features were extracted. These features were normalized using Z-score and harmonized via ComBat. Feature selection was performed using a greedy algorithm and Least absolute shrinkage and selection operator (LASSO), and others, followed by the calculation of radiomics scores through linear regression. Machine learning was then used to identify the most predictive radiomic features. Model performance was evaluated by analyzing the area under the curve (AUC) and other indicators.Univariate analysis indicated that the demographic characteristics of cervical spinal cord injury were not statistically significant. In the test dataset, the random forest (RF) combined with radiomics and ResNet34 demonstrated better performance, with an accuracy of 0.800 and an AUC of 0.893.Using MRI, deep learning-based radiomics signals show promise in evaluating and predicting the postoperative prognosis of these patients.

PMID:39962172 | DOI:10.1038/s41598-024-72539-0

Sci Rep. 2025 Feb 17;15(1):5761. doi: 10.1038/s41598-025-86673-w.

ABSTRACT

Software requirement smell detection is an important part of establishing high-quality software specifications. These smells, which frequently indicate difficulties like ambiguity, vagueness, or incompleteness, can lead to misunderstandings and mistakes in the latter phases of software development. Traditionally, identifying requirement smells was a manual process, time-consuming, prone to inconsistency, and human mistakes. Moreover, the previous machine learning and deep learning research was insufficient for detecting multiple smells in a single requirement statement. To address this problem, we developed a multi-label software requirement smell model to detect multiple software requirement smells in a single requirement. Therefore, this study explores a deep learning-based approach to multi-label classification of software requirement smells, incorporating advanced neural network architectures such as LSTM, Bi-LSTM, and GRU with combined word embedding like ELMo and Word2Vec. We collected and prepared an 8120 requirements dataset from different sources categorized into 11 linguistic aspects and we used a binary relevance multi-label classification strategy in which each category was treated independently and used the F1-macro average of each label of the smell. Next, we built models that can classify software requirement smell in a multi-label manner using deep learning algorithms. After executing numerous experiments with different parameters in the Bi-LSTM, LSTM, and GRU models, we obtained 90.3%, 89%, and 88.7% of F1-score macro averages with ELMo, respectively. Therefore, Bi-LSTM achieved a greater F1-score macro average than the other algorithms.

PMID:39962114 | DOI:10.1038/s41598-025-86673-w