Front Plant Sci. 2024 Dec 18;15:1434222. doi: 10.3389/fpls.2024.1434222. eCollection 2024.

ABSTRACT

Few-shot learning (FSL) methods have made remarkable progress in the field of plant disease recognition, especially in scenarios with limited available samples. However, current FSL approaches are usually limited to a restrictive setting where base classes and novel classes come from the same domain such as PlantVillage. Consequently, when the model is generalized to new domains (field disease datasets), its performance drops sharply. In this work, we revisit the cross-domain performance of existing FSL methods from both data and model perspectives, aiming to better achieve cross-domain generalization of disease by exploring inter-domain correlations. Specifically, we propose a broader cross-domain few-shot learning(CD-FSL) framework for crop disease identification that allows the classifier to generalize to previously unseen categories and domains. Within this framework, three representative CD-FSL models were developed by integrating the Brownian distance covariance (BCD) module and improving the general feature extractor, namely metric-based CD-FSL(CDFSL-BDC), optimization-based CD-FSL(CDFSL-MAML), and non-meta-learning-based CD-FSL (CDFSL-NML). To capture the impact of domain shift on model performance, six public datasets with inconsistent feature distributions between domains were selected as source domains. We provide a unified testbed to conduct extensive meta-training and meta-testing experiments on the proposed benchmarks to evaluate the generalization performance of CD-FSL in the disease domain. The results showed that the accuracy of the three CD-FSL models improved significantly as the inter-domain similarity increased. Compared with other state-of-the-art CD-FSL models, the CDFSL-BDC models had the best average performance under different domain gaps. Shifting from the pest domain to the crop disease domain, the CDFSL-BDC model achieved an accuracy of 63.95% and 80.13% in the 1-shot/5-shot setting, respectively. Furthermore, extensive evaluation on a multi-domain datasets demonstrated that multi-domain learning exhibits stronger domain transferability compared to single-domain learning when there is a large domain gap between the source and target domain. These comparative results suggest that optimizing the CD-FSL method from a data perspective is highly effective for solving disease identification tasks in field environments. This study holds promise for expanding the application of deep learning techniques in disease detection and provides a technical reference for cross-domain disease detection.

PMID:39744608 | PMC:PMC11688362 | DOI:10.3389/fpls.2024.1434222

Imaging Sci Dent. 2024 Dec;54(4):305-312. doi: 10.5624/isd.20240321. Epub 2024 Aug 25.

ABSTRACT

PURPOSE: This review aimed to explore the scientific literature concerning the methodologies and applications of artificial intelligence (AI) in the field of endodontics. The findings may equip dentists with the necessary technical knowledge to understand the opportunities presented by AI.

MATERIALS AND METHODS: Articles published between 1992 and 2023 were retrieved through an electronic search of Medline via the PubMed, Scopus, and Google Scholar databases. The search, which was limited to articles published in English, aimed to identify relevant studies by employing the following keywords: "artificial intelligence," "machine learning," "deep learning," "endodontic," "root canal treatment," and "radiography." Ultimately, 71 studies that addressed the application of AI in endodontics were selected.

RESULTS: Numerous studies have demonstrated the effectiveness of AI applications in endodontics. These uses encompass the identification of root fractures and periapical lesions, assessment of working length, investigation of root canal system anatomy, prediction of retreatment success, and evaluation of dental pulp stem cell viability.

CONCLUSION: AI technology is poised to advance aspects of endodontics including scheduling, patient care, management of drug-drug interactions, prognostic diagnosis, and the emerging area of robotic endodontic surgery. AI methods have demonstrated accuracy and precision in the identification, assessment, and prediction of diseases. Thus, AI can significantly improve endodontic diagnosis and treatment, increasing the overall efficacy of endodontic therapy.

PMID:39744558 | PMC:PMC11685306 | DOI:10.5624/isd.20240321

Front Mol Neurosci. 2024 Dec 18;17:1497735. doi: 10.3389/fnmol.2024.1497735. eCollection 2024.

ABSTRACT

INTRODUCTION: The prostate is densely innervated like many visceral organs and glands. However, studies to date have focused on sympathetic and parasympathetic nerves and little attention has been given to the presence or function of sensory nerves in the prostate. Recent studies have highlighted a role for sensory nerves beyond perception of noxious stimuli, as anterograde release of neuropeptides from sensory nerves can affect vascular tone and local immune responses.

METHODS: To identify the degree of sensory innervation in the prostate, we utilized state-of-the-art tissue clearing and microscopy to visualize sensory innervation in the different lobes of the mouse prostate. To determine whether sensory nerves have a role in regulating proliferation within the prostate, we used an intersectional genetic and toxin approach to ablate peptidergic sensory nerves systemically.

RESULTS: We found that sensory neurons are abundant in the prostate both in nerve bundles along the vasculature and as independent nerve fibers wrapped around prostatic acini in a net-like fashion. In addition to the dense innervation of the prostate, we found that Calca haploinsufficiency, the genotype control for our intersectional ablation model, results in a diminished level of Ki67 staining in the stromal compartment of the dorsal lobe and a diminishing Ki67 trend in other lobes.

DISCUSSION: These findings suggest that sensory neurons might have developmental or homeostatic effects within the prostate. Further studies are warranted to assess the role of sensory neurons and the sensory neuropeptides on prostatic development and on proliferation in the presence of pro-inflammatory stimuli such as bacterial infection or tumor cells.

PMID:39744541 | PMC:PMC11688385 | DOI:10.3389/fnmol.2024.1497735

Front Med (Lausanne). 2024 Dec 18;11:1521712. doi: 10.3389/fmed.2024.1521712. eCollection 2024.

ABSTRACT

OBJECTIVE: With the development of ChatGPT, the number of studies within the nursing field has increased. The sophisticated language capabilities of ChatGPT, coupled with its exceptional precision, offer significant support within the nursing field, which includes clinical nursing, nursing education, and the clinical decision-making process. Preliminary findings suggest positive outcomes, underscoring its potential as a valuable resource for enhancing clinical care. However, a comprehensive analysis of this domain is lacking, and the application of bibliometric methods remains rare. This study aims to describe and predict the developmental trajectory of the discipline, identify research hotspots and trends, and provide a comprehensive framework for the integration of ChatGPT in nursing.

METHODS: Following the development of a search strategy in collaboration with librarians, the implementation of this strategy occurred in the Web of Science Core Collection (WoSCC) on June 30, 2024. For bibliometric and visual analyses-including evaluations of sources, institutions, countries, author collaboration networks, and keywords-Bibliometrix (version 4.4.2) and CiteSpace (version 6.2.R2 Basic) were employed.

RESULTS: A total of 81 articles published by 67 authors were retrieved from the Web of Science Core Collection database, covering the period of June 30, 2024. The number of published studies has exhibited an increasing trend. The "European Journal of Cardiovascular Nursing" emerged as the most productive journals, while the USA, the UK, and China were identified as the leading countries in terms of publication output. The top 10 keywords identified in this study include artificial intelligence, nursing education, large language models, ChatGPT, natural language processing, generative artificial intelligence, care, nursing practice, clinical decision-making, and deep learning.

CONCLUSION: ChatGPT is an emerging tool in the nursing field, currently in the foundational research phase. While there is significant international collaboration, cooperation among author groups remains somewhat limited. Studies focusing on ChatGPT in nursing primarily concentrate on two key themes: (1) the deep learning of ChatGPT in nursing and (2) the feasibility of its application. It is essential for nurses across various specialties to collaborate in exploring the diverse applications of ChatGPT within their domains, thereby fostering the ongoing development and enhancement of this technology.

PMID:39744533 | PMC:PMC11688491 | DOI:10.3389/fmed.2024.1521712

Eur J Cancer. 2024 Dec 26;216:115199. doi: 10.1016/j.ejca.2024.115199. Online ahead of print.

ABSTRACT

PURPOSE: Ovarian cancer patients with a Homologous Recombination Deficiency (HRD) often benefit from polyadenosine diphosphate-ribose polymerase (PARP) inhibitor maintenance therapy after response to platinum-based chemotherapy. HR status is currently analyzed via complex molecular tests. Predicting benefit from PARP inhibitors directly on histological whole slide images (WSIs) could be a fast and cheap alternative.

PATIENTS AND METHODS: We trained a Deep Learning (DL) model on H&E stained WSIs with "shrunken centroid" (SC) based HRD ground truth using the AGO-TR1 cohort (n = 208: 108 training, 100 test) and tested its ability to predict HRD as evaluated by the Myriad classifier and the benefit from olaparib in the PAOLA-1 cohort (n = 447) in a blinded manner.

RESULTS: In contrast to the HRD prediction AUROC of 72 % on hold-out, our model only yielded an AUROC of 57 % external. Kaplan-Meier analysis showed that progression free survival (PFS) in the PARP inhibitor treated PAOLA-1 patients was significantly improved in the HRD positive group as defined by our model, but not in the HRD negative group. PFS improvement in PARP inhibitor-treated patients was substantially longer in our HRD positive group, hinting at a biologically meaningful prediction of benefit from PARP inhibitors.

CONCLUSION: Together, our results indicate that it might be possible to generate a predictor of benefit from PARP inhibitors based on the DL-mediated analysis of WSIs. However, further studies with larger cohorts and further methodological improvements will be necessary to generate a predictor with clinically useful accuracy across independent patient cohorts.

PMID:39742559 | DOI:10.1016/j.ejca.2024.115199

Sci Adv. 2025 Jan 3;11(1):eadn1870. doi: 10.1126/sciadv.adn1870. Epub 2025 Jan 1.

ABSTRACT

DNA methylation (DNAm) is essential for brain development and function and potentially mediates the effects of genetic risk variants underlying brain disorders. We present INTERACT, a transformer-based deep learning model to predict regulatory variants affecting DNAm levels in specific brain cell types, leveraging existing single-nucleus DNAm data from the human brain. We show that INTERACT accurately predicts cell type-specific DNAm profiles, achieving an average area under the receiver operating characteristic curve of 0.99 across cell types. Furthermore, INTERACT predicts cell type-specific DNAm regulatory variants, which reflect cellular context and enrich the heritability of brain-related traits in relevant cell types. We demonstrate that incorporating predicted variant effects and DNAm levels of CpG sites enhances the fine mapping for three brain disorders-schizophrenia, depression, and Alzheimer's disease-and facilitates mapping causal genes to particular cell types. Our study highlights the power of deep learning in identifying cell type-specific regulatory variants, which will enhance our understanding of the genetics of complex traits.

PMID:39742481 | DOI:10.1126/sciadv.adn1870

NPJ Syst Biol Appl. 2025 Jan 2;11(1):1. doi: 10.1038/s41540-024-00484-9.

ABSTRACT

CITE-seq provides a powerful method for simultaneously measuring RNA and protein expression at the single-cell level. The integrated analysis of RNA and protein expression in identical cells is crucial for revealing cellular heterogeneity. However, the high experimental costs associated with CITE-seq limit its widespread application. In this paper, we propose scTEL, a deep learning framework based on Transformer encoder layers, to establish a mapping from sequenced RNA expression to unobserved protein expression in the same cells. This computation-based approach significantly reduces the experimental costs of protein expression sequencing. We are now able to predict protein expression using single-cell RNA sequencing (scRNA-seq) data, which is well-established and available at a lower cost. Moreover, our scTEL model offers a unified framework for integrating multiple CITE-seq datasets, addressing the challenge posed by the partial overlap of protein panels across different datasets. Empirical validation on public CITE-seq datasets demonstrates scTEL significantly outperforms existing methods.

PMID:39743530 | DOI:10.1038/s41540-024-00484-9

Methods. 2024 Dec 30:S1046-2023(24)00284-6. doi: 10.1016/j.ymeth.2024.12.010. Online ahead of print.

ABSTRACT

5-Methylcytosine (m5C) plays a pivotal role in various RNA metabolic processes, including RNA localization, stability, and translation. Current high-throughput sequencing technologies for m5C site identification are resource-intensive in terms of cost, labor, and time. As such, there is a pressing need for efficient computational approaches. Many existing computational methods rely on intricate hand-crafted features, requiring unavailable features, often leading to suboptimal prediction accuracy. Addressing these challenges, we introduce a novel deep-learning method, Trans-m5C. We first categorize m5C sites into NSUN2-dependent and NSUN6-dependent types for independent feature extraction. Subsequently, meticulously crafted transformer neural networks are employed to distill global features. The prediction of m5C sites is then accomplished using a discriminator built from a a multi-layer perceptron. A rigorous evaluation for the performance of Trans-m5C on experimentally validated m5C data from human and mouse species reveals that our method offers a competitive edge over both baseline and existing methodologies.

PMID:39742984 | DOI:10.1016/j.ymeth.2024.12.010

Environ Int. 2024 Dec 28;195:109244. doi: 10.1016/j.envint.2024.109244. Online ahead of print.

ABSTRACT

Chemically induced neurotoxicity is a critical aspect of chemical safety assessment. Traditional and costly experimental methods call for the development of high-throughput virtual screening. However, the small datasets of neurotoxicity have limited the application of advanced deep learning techniques. The current study developed a hybrid deep learning architecture, NeuTox 2.0, through multimodal feature fusion for enhanced prediction accuracy and generalization ability. We incorporated transfer learning based on self-supervised learning, graph neural networks, and molecular fingerprints/descriptors. Four datasets were used to profile neurotoxicity; these were related to blood-brain barrier permeability, neuronal cytotoxicity, microelectrode array-based neural activity, and mammalian neurotoxicity. Comprehensive performance evaluations demonstrated that NeuTox 2.0 has relatively higher predictive capability across all statistical metrics. Specifically, NeuTox 2.0 exhibits remarkable performance in three of the four datasets. In the BBB dataset, although it does not outperform the PaDEL descriptor model, its performance closely approximates that of the top single-modal model. The ablation experiments indicated that NeuTox 2.0 can learn the deeper structural differences of molecules from various feature extractions and capture complex interactions and mapping relationships between various modalities, thereby improving performance for neurotoxicity prediction. Evaluations of anti-noise ability indicated that NeuTox 2.0 has excellent noise resistance relative to traditional machine learning. We applied the NeuTox 2.0 model to predict the neurotoxicity of 315,790 compounds in the REACH database. The results showed that 701 compounds exhibited potential neurotoxicity in the four neurotoxicity-related predictions. In conclusion, NeuTox 2.0 can be used as an efficient tool for early neurotoxicity screening of environmental chemicals.

PMID:39742830 | DOI:10.1016/j.envint.2024.109244

Comput Biol Med. 2024 Dec 31;186:109641. doi: 10.1016/j.compbiomed.2024.109641. Online ahead of print.

ABSTRACT

Osteoarthritis (OA) is a prevalent condition resulting in physical limitations. Early detection of OA is critical to effectively manage this condition. However, the diagnosis of early-stage arthritis remains challenging. The Kellgren and Lawrence (KL) grading system is a common method that is accepted worldwide, uses five grades to classify the severity of OA, and relies on the ability of the orthopedist to accurately interpret radiograph images. To improve the accuracy of radiograph image interpretation, artificial intelligence-assisted models have been developed that include shallow or deep learning approaches and multi-step techniques; however, their accuracy remains variable. This work proposes a transfer learning approach using an InceptionV3-based model fine-tuned on the Osteoarthritis Initiative dataset, and aims to enhance the identification of OA severity levels through dual-stage preprocessing and convolutional neural networks for feature extraction. The fine-tuned IV3 (FT-IV3) model outperformed the IV3 model with training, validation, and testing accuracies of (96.33, 93.82, and 92.25) %, compared to IV3 accuracies of (91.64, 82.04, and 86.20) %, respectively. Additionally, Cohen's Kappa value for the FT-IV3 model (90.69 %) exceeds that of the IV3 model (83.15 %), indicating a better diagnosis of OA severity. This improvement allows the FT-IV3 model to effectively classify moderate and severe-grade OA.

PMID:39742824 | DOI:10.1016/j.compbiomed.2024.109641

J Electrocardiol. 2024 Dec 25;89:153862. doi: 10.1016/j.jelectrocard.2024.153862. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Atrial fibrillation (AF), a common arrhythmia, is linked with atrial electrical and structural changes, notably low voltage areas (LVAs) which are associated with poor ablation outcomes and increased thromboembolic risk. This study aims to evaluate the efficacy of a deep learning model applied to 12‑lead ECGs for non-invasively predicting the presence of LVAs, potentially guiding pre-ablation strategies and improving patient outcomes.

METHODS: A retrospective analysis was conducted on 204 AF patients, who underwent catheter ablation. Pre-procedural sinus rhythm ECGs and electroanatomical maps (EAM) were utilized alongside demographic data to train a deep learning model combining Long Short-Term Memory networks and Convolutional Neural Networks with a cross-attention layer. Model performance was evaluated using a 5-fold cross-validation strategy.

RESULTS: The model effectively identified the presence of LVA on the examined atrial walls, achieving accuracies of 78 % for both the anterior and posterior walls, and 82 % for the LA roof. Moreover, it accurately predicted the global left atrial (LA) average voltage <0.7 mV, with an accuracy of 88 %.

CONCLUSION: The study showcases the potential of deep learning applied to 12‑lead ECGs to effectively predict regional LVAs and global LA voltage in AF patients non-invasively. This model offers a promising tool for the pre-ablation assessment of atrial substrate, facilitating personalized therapeutic strategies and potentially enhancing ablation success rates.

PMID:39742814 | DOI:10.1016/j.jelectrocard.2024.153862

J Electrocardiol. 2024 Dec 27;89:153858. doi: 10.1016/j.jelectrocard.2024.153858. Online ahead of print.

ABSTRACT

Electrocardiography (ECG) is a widely used, non-invasive, and cost-effective diagnostic method that plays a crucial role in the early detection and management of cardiac conditions. However, the ECG signal is easily disrupted by various noise signals in the real world, leading to a decrease in signal quality and potentially compromising accurate clinical interpretation. With the goal of reducing noise in ECG signals, this research proposes an end-to-end multi-resolution deep learning network with attention mechanism, namely the MrSeNet to perform effective denoising of ECG data. Our MrSeNet fuses features at different scales for effective denoising with the squeeze-and-excitation module to enhance the features of the ECG signal channel. CPSC2018 database and the MIT-BIH database were used to verify the validity of the model by adding different intensity noises based on NSTDB. Using Pearson correlation coefficient, signal-to-noise ratio, and root mean square error performance evaluation model, the experimental results show that MrSeNet performs better than the traditional method, the model can achieve a good denoising effect to different degrees of noise signal data, and has a good future application prospect.

PMID:39742813 | DOI:10.1016/j.jelectrocard.2024.153858

Clin Imaging. 2024 Dec 24;119:110392. doi: 10.1016/j.clinimag.2024.110392. Online ahead of print.

ABSTRACT

BACKGROUND: Thyroid cancer, a common endocrine malignancy, has seen increasing incidence, making lymph node metastasis (LNM) a critical factor for recurrence and survival. Radiomics and deep learning (DL) advancements offer the potential for improved LNM prediction using CT and MRI, though challenges in diagnostic accuracy remain.

METHODS: A systematic review and meta-analysis were conducted per established guidelines, with searches across PubMed, Scopus, Web of Science, and Embase up to February 15, 2024. Studies developing CT/MRI-based radiomics and/or DL models for preoperative LNM assessment in thyroid cancer patients were included. Data were extracted and analyzed using R software.

RESULTS: Sixteen studies were analyzed. In internal validation sets, sensitivity was 81.1 % (95 % CI: 75.6 %-85.6 %) and specificity 76.4 % (95 % CI: 68.4 %-82.9 %). Training sets showed a sensitivity of 84.4 % (95 % CI: 81.5 %-87 %) and a specificity of 84.7 % (95 % CI: 74.4 %-91.4 %). The pooled AUC was 86 % for internal validation and 87 % for training. Handcrafted radiomics had a sensitivity of 79.4 % and specificity of 69.2 %, while DL models showed 80.8 % sensitivity and 78.7 % specificity. Subgroup analysis revealed that models for papillary thyroid cancer (PTC) had a pooled specificity of 76.3 %, while those including other or unspecified cancers showed 68.3 % specificity. Despite heterogeneity, significant differences (p = 0.037) were noted between models with and without clinical data.

CONCLUSION: Radiomics and DL models show promising potential for detecting LNM in thyroid cancer, particularly in PTC. However, study heterogeneity underscores the need for further research to optimize these imaging tools.

PMID:39742800 | DOI:10.1016/j.clinimag.2024.110392

Clin Imaging. 2024 Dec 26;119:110386. doi: 10.1016/j.clinimag.2024.110386. Online ahead of print.

ABSTRACT

We aimed to systematically review and meta-analyze the predictive value of magnetic resonance imaging (MRI)-derived radiomics/end-to-end deep learning (DL) models in predicting glioma alpha thalassemia/mental retardation syndrome X-linked (ATRX) status. We conducted a comprehensive search across four major databases-Web of Science, PubMed, Scopus, and Embase. All the studies that assessed the performance of radiomics and/or end-to-end DL models for predicting glioma ATRX status were included. Quality assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) criteria and the METhodological RadiomICs Score (METRICS). Pooled estimates for performance metrics were calculated. I-squared was used to assess heterogeneity, while subgroup and sensitivity analyses were performed to find its potential sources. Publication bias was assessed using Deeks' funnel plots. Seventeen and eleven studies were included in the systematic review and meta-analysis, respectively. Most of the studies had a low risk of bias and low concern for applicability according to the QUADAS-2. Also, most of them had good quality according to the METRICS. Meta-analysis showed a pooled sensitivity of 0.80 (95%CI: 0.71-0.96), a specificity of 0.82 (95%CI: 0.67-0.93), a positive diagnostic likelihood ratio (DLR) of 6.77 (95%CI: 4.67-9.82), a negative DLR of 0.15 (95%CI: 0.06-0.38), a diagnostic odds ratio of 30.36 (95%CI: 15.87-58.05), and an area under the curve (AUC) of 0.92 (95%CI: 0.89-0.94). Subgroup analysis revealed significant intergroup differences based on several factors. Radiomics models can accurately predict ATRX status in gliomas, enhancing non-invasive tumor characterization and guiding treatment strategies.

PMID:39742798 | DOI:10.1016/j.clinimag.2024.110386

Biochem Biophys Res Commun. 2024 Dec 24;746:151240. doi: 10.1016/j.bbrc.2024.151240. Online ahead of print.

ABSTRACT

Utilizing Artificial Intelligence (AI) in computational biology techniques could offer significant advantages in alleviating the growing workloads faced by structural biologists, especially with the emergence of big data. In this study, we employed Delaunay tessellation as a promising method to obtain the overall structural topology of proteins. Subsequently, we developed multi-class deep neural network models to classify protein superfamilies based on their local topology. Our models achieved a test accuracy of approximately 0.92 in classifying proteins into 18 well-populated superfamilies. We believe that the results of this study hold substantial value since, to the best of our knowledge, no previous studies have reported the utilization of protein topological data for protein classification through deep learning and Delaunay tessellation.

PMID:39742787 | DOI:10.1016/j.bbrc.2024.151240

Comput Methods Programs Biomed. 2024 Dec 28;260:108571. doi: 10.1016/j.cmpb.2024.108571. Online ahead of print.

ABSTRACT

BACKGROUND: Data sharing in healthcare is vital for advancing research and personalized medicine. However, the process is hindered by privacy, ethical, and legal challenges associated with patient data. Synthetic data generation emerges as a promising solution, replicating statistical properties of real data while enhancing privacy protection.

METHODS: This systematic review examines deep learning techniques for synthetic data generation in healthcare, focusing on their ability to maintain data utility and enhance privacy. Studies from Scopus, Web of Science, PubMed, and IEEE databases published between 2019 and 2023 were analyzed. Key methods explored include Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models. Evaluation metrics encompass data resemblance, utility, and privacy preservation, with special attention to privacy-enhancing methods like differential privacy and federated learning.

RESULTS: GANs and VAEs demonstrated robust capabilities in generating realistic synthetic data for tabular, signal, image, and multi-modal datasets. Privacy-preserving approaches such as differential privacy and adversarial training significantly reduced re-identification risks while maintaining data fidelity. However, challenges persist in preserving temporal correlations, reducing biases, and aligning with regulatory frameworks, particularly for longitudinal and high-dimensional data.

CONCLUSION: Synthetic data generation holds significant potential for privacy-preserving data sharing in healthcare. Ongoing research is required to develop advanced algorithms and evaluation frameworks, ensuring synthetic data's quality and privacy. Collaboration between technologists and policymakers is essential to create comprehensive guidelines, fostering secure and effective data sharing in healthcare.

PMID:39742693 | DOI:10.1016/j.cmpb.2024.108571

Front Radiol. 2024 Dec 17;4:1523389. doi: 10.3389/fradi.2024.1523389. eCollection 2024.

NO ABSTRACT

PMID:39742350 | PMC:PMC11685185 | DOI:10.3389/fradi.2024.1523389

Front Radiol. 2024 Dec 16;4:1498411. doi: 10.3389/fradi.2024.1498411. eCollection 2024.

ABSTRACT

BACKGROUND: MR fingerprinting (MRF) is a novel method for quantitative assessment of in vivo MR relaxometry that has shown high precision and accuracy. However, the method requires data acquisition using customized, complex acquisition strategies and dedicated post processing methods thereby limiting its widespread application.

OBJECTIVE: To develop a deep learning (DL) network for synthesizing MRF signals from conventional magnitude-only MR imaging data and to compare the results to the actual MRF signal acquired.

METHODS: A U-Net DL network was developed to synthesize MRF signals from magnitude-only 3D T 1-weighted brain MRI data acquired from 37 volunteers aged between 21 and 62 years of age. Network performance was evaluated by comparison of the relaxometry data (T 1, T 2) generated from dictionary matching of the deep learning synthesized and actual MRF data from 47 segmented anatomic regions. Clustered bootstrapping involving 10,000 bootstraps followed by calculation of the concordance correlation coefficient were performed for both T 1 and T 2 MRF data pairs. 95% confidence limits and the mean difference between true and DL relaxometry values were also calculated.

RESULTS: The concordance correlation coefficient (and 95% confidence limits) for T 1 and T 2 MRF data pairs over the 47 anatomic segments were 0.8793 (0.8136-0.9383) and 0.9078 (0.8981-0.9145) respectively. The mean difference (and 95% confidence limits) were 48.23 (23.0-77.3) s and 2.02 (-1.4 to 4.8) s.

CONCLUSION: It is possible to synthesize MRF signals from MRI data using a DL network, thereby creating the potential for performing quantitative relaxometry assessment without the need for a dedicated MRF pulse sequence.

PMID:39742349 | PMC:PMC11686891 | DOI:10.3389/fradi.2024.1498411

Imeta. 2024 Oct 17;3(6):e244. doi: 10.1002/imt2.244. eCollection 2024 Dec.

ABSTRACT

Antimicrobial peptides (AMPs) have become a viable source of novel antibiotics that are effective against human pathogenic bacteria. In this study, we construct a bank of culturable marine biofilm bacteria constituting 713 strains and their nearly complete genomes and predict AMPs using ribosome profiling and deep learning. Compared with previous approaches, ribosome profiling has improved the identification and validation of small open reading frames (sORFs) for AMP prediction. Among the 80,430 expressed sORFs, 341 are identified as candidate AMPs with high probability. Most potential AMPs have less than 40% similarity in their amino acid sequence compared to those listed in public databases. Furthermore, these AMPs are associated with bacterial groups that are not previously known to produce AMPs. Therefore, our deep learning model has acquired characteristics of unfamiliar AMPs. Chemical synthesis of 60 potential AMP sequences yields 54 compounds with antimicrobial activity, including potent inhibitory effects on various drug-resistant human pathogens. This study extends the range of AMP compounds by investigating marine biofilm microbiomes using a novel approach, accelerating AMP discovery.

PMID:39742298 | PMC:PMC11683478 | DOI:10.1002/imt2.244

Rev Cardiovasc Med. 2024 Dec 24;25(12):454. doi: 10.31083/j.rcm2512454. eCollection 2024 Dec.

ABSTRACT

BACKGROUND: This study aimed to develop and evaluate the detection and classification performance of different deep learning models on carotid plaque ultrasound images to achieve efficient and precise ultrasound screening for carotid atherosclerotic plaques.

METHODS: This study collected 5611 carotid ultrasound images from 3683 patients from four hospitals between September 17, 2020, and December 17, 2022. By cropping redundant information from the images and annotating them using professional physicians, the dataset was divided into a training set (3927 images) and a test set (1684 images). Four deep learning models, You Only Look Once Version 7 (YOLO V7) and Faster Region-Based Convolutional Neural Network (Faster RCNN) were employed for image detection and classification to distinguish between vulnerable and stable carotid plaques. Model performance was evaluated using accuracy, sensitivity, specificity, F1 score, and area under curve (AUC), with p < 0.05 indicating a statistically significant difference.

RESULTS: We constructed and compared deep learning models based on different network architectures. In the test set, the Faster RCNN (ResNet 50) model exhibited the best classification performance (accuracy (ACC) = 0.88, sensitivity (SEN) = 0.94, specificity (SPE) = 0.71, AUC = 0.91), significantly outperforming the other models. The results suggest that deep learning technology has significant potential for application in detecting and classifying carotid plaque ultrasound images.

CONCLUSIONS: The Faster RCNN (ResNet 50) model demonstrated high accuracy and reliability in classifying carotid atherosclerotic plaques, with diagnostic capabilities approaching that of intermediate-level physicians. It has the potential to enhance the diagnostic abilities of primary-level ultrasound physicians and assist in formulating more effective strategies for preventing ischemic stroke.

PMID:39742249 | PMC:PMC11683696 | DOI:10.31083/j.rcm2512454