Sci Rep. 2024 Jun 21;14(1):14289. doi: 10.1038/s41598-024-65182-2.

ABSTRACT

The error correction model's main purpose in heavy hexagonal quantum codes is to improve their reliability for quantum computing applications. Existing challenges include finding the optimal decoder for quantum error correction in heavy hexagonal codes. This research propels the frontier of quantum error correction, with a specific focus on tailoring topological quantum error-correcting codes for the unique challenges posed by superconducting qubits in quantum computers. In response, this research harnesses the power of deep learning, presenting a Humming sparrow optimization based self-adaptive deep CNN (HSO-based SADCNN) model designed for heavy hexagonal codes. This decoder incorporates a Self-adaptive Deep CNN (SADCNN) Noise Correction Module, a sophisticated component to refine error correction. The proposed decoder's efficacy is rigorously evaluated across varying code distances (three, five, and seven) using the Humming Sparrow Optimization (HSO) algorithm. HSO, intricately designed to fine-tune the SADCNN decoder, significantly enhances its error correction capabilities for heavy hexagonal quantum codes. The algorithm seamlessly integrates advantageous characteristics of herding and tracing from Humming Bird optimization and Sparrow search optimization, representing a critical stride in advancing the reliability of quantum computing applications, particularly within the intricate domain of heavy hexagonal quantum codes. Based upon the achievements, the Training Percentage (TP) 90 metrics demonstrate significant progress, boasting a commendable accuracy of 97.35 % , coupled with reduced logical error probability and a diminished bit error rate, marked at 5.51 and 3.72, respectively.

PMID:38906948 | DOI:10.1038/s41598-024-65182-2

Trends Neurosci. 2024 Jun 20:S0166-2236(24)00091-2. doi: 10.1016/j.tins.2024.05.011. Online ahead of print.

ABSTRACT

Functional network (FN) analyses play a pivotal role in uncovering insights into brain function and understanding the pathophysiology of various brain disorders. This paper focuses on classical and advanced methods for deriving brain FNs from functional magnetic resonance imaging (fMRI) data. We systematically review their foundational principles, advantages, shortcomings, and interrelations, encompassing both static and dynamic FN extraction approaches. In the context of static FN extraction, we present hypothesis-driven methods such as region of interest (ROI)-based approaches as well as data-driven methods including matrix decomposition, clustering, and deep learning. For dynamic FN extraction, both window-based and windowless methods are surveyed with respect to the estimation of time-varying FN and the subsequent computation of FN states. We also discuss the scope of application of the various methods and avenues for future improvements.

PMID:38906797 | DOI:10.1016/j.tins.2024.05.011

J Struct Biol. 2024 Jun 19:108107. doi: 10.1016/j.jsb.2024.108107. Online ahead of print.

ABSTRACT

Atomic force microscope enables ultra-precision imaging of living cells. However, atomic force microscope imaging is a complex and time-consuming process. The obtained images of living cells usually have low resolution and are easily influenced by noise leading to unsatisfactory imaging quality, obstructing the research and analysis based on cell images. Herein, an adaptive attention image reconstruction network based on residual encoder-decoder was proposed, through the combination of deep learning technology and atomic force microscope imaging supporting high-quality cell image acquisition. Compared with other learning-based methods, the proposed network showed higher peak signal-to-noise ratio, higher structural similarity and better image reconstruction performances. In addition, the cell images reconstructed by each method were used for cell recognition, and the cell images reconstructed by the proposed network had the highest cell recognition rate. The proposed network has brought insights into the atomic force microscope-based imaging of living cells and cell image reconstruction, which is of great significance in biological and medical research.

PMID:38906499 | DOI:10.1016/j.jsb.2024.108107

Neural Netw. 2024 Jun 1;178:106423. doi: 10.1016/j.neunet.2024.106423. Online ahead of print.

ABSTRACT

Generative models based on neural networks present a substantial challenge within deep learning. As it stands, such models are primarily limited to the domain of artificial neural networks. Spiking neural networks, as the third generation of neural networks, offer a closer approximation to brain-like processing due to their rich spatiotemporal dynamics. However, generative models based on spiking neural networks are not well studied. Particularly, previous works on generative adversarial networks based on spiking neural networks are conducted on simple datasets and do not perform well. In this work, we pioneer constructing a spiking generative adversarial network capable of handling complex images and having higher performance. Our first task is to identify the problems of out-of-domain inconsistency and temporal inconsistency inherent in spiking generative adversarial networks. We address these issues by incorporating the Earth-Mover distance and an attention-based weighted decoding method, significantly enhancing the performance of our algorithm across several datasets. Experimental results reveal that our approach outperforms existing methods on the MNIST, FashionMNIST, CIFAR10, and CelebA. In addition to our examination of static datasets, this study marks our inaugural investigation into event-based data, through which we achieved noteworthy results. Moreover, compared with hybrid spiking generative adversarial networks, where the discriminator is an artificial analog neural network, our methodology demonstrates closer alignment with the information processing patterns observed in the mouse. Our code can be found at https://github.com/Brain-Cog-Lab/sgad.

PMID:38906053 | DOI:10.1016/j.neunet.2024.106423

Sci Rep. 2024 Jun 21;14(1):14317. doi: 10.1038/s41598-024-63144-2.

ABSTRACT

To improve the understanding of potential pathological mechanisms of macular edema (ME), we try to discover biomarker candidates related to ME caused by diabetic retinopathy (DR) and retinal vein occlusion (RVO) in spectral-domain optical coherence tomography images by means of deep learning (DL). 32 eyes of 26 subjects with non-proliferative DR (NPDR), 77 eyes of 61 subjects with proliferative DR (PDR), 120 eyes of 116 subjects with branch RVO (BRVO), and 17 eyes of 15 subjects with central RVO (CRVO) were collected. A DL model was implemented to guide biomarker candidate discovery. The disorganization of the retinal outer layers (DROL), i.e., the gray value of the retinal tissues between the external limiting membrane (ELM) and retinal pigment epithelium (RPE), the disrupted and obscured rate of the ELM, ellipsoid zone (EZ), and RPE, was measured. In addition, the occurrence, number, volume, and projected area of hyperreflective foci (HRF) were recorded. ELM, EZ, and RPE are more likely to be obscured in RVO group and HRFs are observed more frequently in DR group (all P ≤ 0.001). In conclusion, the features of DROL and HRF can be possible biomarkers related to ME caused by DR and RVO in OCT modality.

PMID:38906954 | DOI:10.1038/s41598-024-63144-2

Lancet Digit Health. 2024 Jul;6(7):e500-e506. doi: 10.1016/S2589-7500(24)00094-3.

ABSTRACT

BACKGROUND: Cooling towers containing Legionella spp are a high-risk source of Legionnaires' disease outbreaks. Manually locating cooling towers from aerial imagery during outbreak investigations requires expertise, is labour intensive, and can be prone to errors. We aimed to train a deep learning computer vision model to automatically detect cooling towers that are aerially visible.

METHODS: Between Jan 1 and 31, 2021, we extracted satellite view images of Philadelphia (PN, USA) and New York state (NY, USA) from Google Maps and annotated cooling towers to create training datasets. We augmented training data with synthetic data and model-assisted labelling of additional cities. Using 2051 images containing 7292 cooling towers, we trained a two-stage model using YOLOv5, a model that detects objects in images, and EfficientNet-b5, a model that classifies images. We assessed the primary outcomes of sensitivity and positive predictive value (PPV) of the model against manual labelling on test datasets of 548 images, including from two cities not seen in training (Boston [MA, USA] and Athens [GA, USA]). We compared the search speed of the model with that of manual searching by four epidemiologists.

FINDINGS: The model identified visible cooling towers with 95·1% sensitivity (95% CI 94·0-96·1) and a PPV of 90·1% (95% CI 90·0-90·2) in New York City and Philadelphia. In Boston, sensitivity was 91·6% (89·2-93·7) and PPV was 80·8% (80·5-81·2). In Athens, sensitivity was 86·9% (75·8-94·2) and PPV was 85·5% (84·2-86·7). For an area of New York City encompassing 45 blocks (0·26 square miles), the model searched more than 600 times faster (7·6 s; 351 potential cooling towers identified) than did human investigators (mean 83·75 min [SD 29·5]; mean 310·8 cooling towers [42·2]).

INTERPRETATION: The model could be used to accelerate investigation and source control during outbreaks of Legionnaires' disease through the identification of cooling towers from aerial imagery, potentially preventing additional disease spread. The model has already been used by public health teams for outbreak investigations and to initialise cooling tower registries, which are considered best practice for preventing and responding to outbreaks of Legionnaires' disease.

FUNDING: None.

PMID:38906615 | DOI:10.1016/S2589-7500(24)00094-3

Med Eng Phys. 2024 Jul;129:104179. doi: 10.1016/j.medengphy.2024.104179. Epub 2024 May 9.

ABSTRACT

Cardiopulmonary resuscitation (CPR) is a crucial life-saving technique commonly administered to individuals experiencing cardiac arrest. Among the important aspects of CPR is ensuring the correct airway position of the patient, which is typically monitored by human tutors or supervisors. This study aims to utilize deep transfer learning for the detection of the patient's correct and incorrect airway position during cardiopulmonary resuscitation. To address the challenge of identifying the airway position, we curated a dataset consisting of 198 recorded video sequences, each lasting 6-8 s, showcasing both correct and incorrect airway positions during mouth-to-mouth breathing and breathing with an Ambu Bag. We employed six cutting-edge deep networks, namely DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ResNet50, and NasnetMobile. These networks were initially pre-trained on computer vision data and subsequently fine-tuned using the CPR dataset. The validation of the fine-tuned networks in detecting the patient's correct airway position during mouth-to-mouth breathing achieved impressive results, with the best sensitivity (98.8 %), specificity (100 %), and F-measure (97.2 %). Similarly, the detection of the patient's correct airway position during breathing with an Ambu Bag exhibited excellent performance, with the best sensitivity (100 %), specificity (99.8 %), and F-measure (99.7 %).

PMID:38906566 | DOI:10.1016/j.medengphy.2024.104179

J Dent. 2024 Jun 19:105142. doi: 10.1016/j.jdent.2024.105142. Online ahead of print.

ABSTRACT

OBJECTIVES: To compare the outcomes of implant support crowns (ISCs) designed using deep learning (DL) software with those of ISCs designed by a technician using conventional computer-aided design software.

METHODS: Twenty resin-based partially edentulous casts (maxillary and mandibular) used for fabricating ISCs were evaluated retrospectively. ISCs were designed using a DL-based method with no modification of the as-generated outcome (DB), a DL-based method with further optimization by a dental technician (DM), and a conventional computer-aided design method by a technician (NC). Time efficiency, crown contour, occlusal table area, cusp angle, cusp height, emergence profile angle, occlusal contacts, and proximal contacts were compared among groups. Depending on the distribution of measured data, various statistical methods were used for comparative analyses with a significance level of 0.05.

RESULTS: ISCs in the DB group showed a significantly higher efficiency than those in the DM and NC groups (P≤0.001). ISCs in the DM group exhibited significantly smaller volume deviations than those in the DB group when superimposed on ISCs in the NC group (DB-NC vs. DM-NC pairs, P≤0.008). Except for the number and intensity of occlusal contacts (P≤0.004), ISCs in the DB and DM groups had occlusal table areas, cusp angles, cusp heights, proximal contact intensities, and emergence profile angles similar to those in the NC group (P≥0.157).

CONCLUSIONS: A DL-based method can be beneficial for designing posterior ISCs in terms of time efficiency, occlusal table area, cusp angle, cusp height, proximal contact, and emergence profile, similar to the conventional human-based method.

CLINICAL SIGNIFICANCE: A deep learning-based design method can achieve clinically acceptable functional properties of posterior ISCs. However, further optimization by a technician could improve specific outcomes, such as the crown contour or emergence profile angle.

PMID:38906454 | DOI:10.1016/j.jdent.2024.105142

Sci Total Environ. 2024 Jun 19:174038. doi: 10.1016/j.scitotenv.2024.174038. Online ahead of print.

ABSTRACT

BACKGROUND: Poor sperm quality is a major cause of male infertility. However, evidence remains scarce on how greenness affects male sperm quality.

OBJECTIVES: To assess the associations of residential greenness with male sperm quality and the modification effect of air pollution exposure on the relationship.

METHODS: A total of 78,742 samples from 33,184 sperm donors from 6 regions across China during 2014-2020 were included and analyzed. Individual residential greenness exposures of study subjects were estimated using the Normalized Difference Vegetation Index (NDVI) during the entire (0-90 lag days) and two key stages (0-37, and 34-77 lag days) of sperm development. Contemporaneous personal exposure levels to air pollutants were estimated using a spatio-temporal deep learning method. Linear mixed models were employed to assess the impact of greenspace in relation to sperm quality. The modification effect of air pollution on the greenspace-sperm quality relationship was also estimated.

RESULTS: Per IQR increment in NDVI exposure throughout spermatogenesis were statistically associated with increasing sperm count by 0.0122 (95 % CI: 0.0007, 0.0237), progressive motility by 0.0162 (95 % CI: 0.0045, 0.0280), and total motility by 0.0147 (95 % CI: 0.0014, 0.0281), respectively. Similar results were observed when the model added air pollutants (PM1, PM2.5 or O3) for adjustment. Additionally, specific air pollutants, including PM1, PM2.5, and O3, were found to modify this association. Notably, the protective effects of greenness exposure were more pronounced at higher concentrations of PM1 and PM2.5 and lower concentrations of O3 (all Pinteraction < 0.05). Statistically significant positive effects of NDVI were observed on sperm motility in early spermatogenesis and sperm count in late spermatogenesis.

CONCLUSIONS: Exposure to residential greenness may have beneficial effects on sperm quality and air pollution modifies their relationship. These findings highlight the importance of adopting adaptable urban greenspace planning and policies to safeguard male fertility against environmental factors.

PMID:38906295 | DOI:10.1016/j.scitotenv.2024.174038

Comput Methods Programs Biomed. 2024 Jun 7;254:108254. doi: 10.1016/j.cmpb.2024.108254. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVES: Episodes of Freezing of Gait (FoG) are among the most debilitating motor symptoms of Parkinson's Disease (PD), leading to falls and significantly impacting patients' quality of life. Accurate assessment of FoG by neurologists provides crucial insights into patients' conditions and disease symptoms. This proposed strategy involves utilizing a Weighted Fuzzy Logic Controller, Kalman Filter, and Kaiser-Meyer-Olkin test to detect the gait parameters while walking, resting, and standing phases. Parameters such as neuromodulation format, intensity, duration, frequency, and velocity are computed to pre-empt freezing episodes, thus aiding their prevention.

METHOD: The AiCarePWP is a wearable electronics device designed to identify instances when a patient is on the brink of experiencing a freezing episode and subsequently deliver a brief electrical impulse to the patient's shank muscles to stimulate movement. The AiCarePWP wearable device aims to identify impending freezing episodes in PD patients and deliver brief electrical impulses to stimulate movement. The study validates this innovative approach using plantar insoles with a 3D accelerometer and electrical stimulator, analysing data from the inertial measuring unit and plantar-pressure foot data to detect and predict FoG.

RESULTS: Using a Convolutional Neural Network-based model, the study evaluated 47 gait features for their ability to differentiate resting, standing, and walking conditions. Variable selection was based on sensitivity, specificity, and overall accuracy, followed by Principal Component Analysis and Varimax rotation to extract and interpret factors. Factors with eigenvalues exceeding 1.0 were retained, and 37 features were retained.

CONCLUSION: This study validates CNN's effectiveness in detecting FoG during various activities. It introduces a novel cueing method using electrical stimulation, which improves gait function and reduces FoG incidence in PD patients. Trustworthy wearable devices, based on Artificial Intelligence of Things (AIoT) and Artificial Intelligence of Medical Things (AIoMT), have been developed to support such interventions.

PMID:38905989 | DOI:10.1016/j.cmpb.2024.108254

Comput Methods Programs Biomed. 2024 Jun 19;254:108295. doi: 10.1016/j.cmpb.2024.108295. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: To evaluate the feasibility and accuracy of radiomics, dosiomics, and deep learning (DL) in predicting Radiation Pneumonitis (RP) in lung cancer patients underwent volumetric modulated arc therapy (VMAT) to improve radiotherapy safety and management.

METHODS: Total of 318 and 31 lung cancer patients underwent VMAT from First Affiliated Hospital of Wenzhou Medical University (WMU) and Quzhou Affiliated Hospital of WMU were enrolled for training and external validation, respectively. Models based on radiomics (R), dosiomics (D), and combined radiomics and dosiomics features (R+D) were constructed and validated using three machine learning (ML) methods. DL models trained with CT (DLR), dose distribution (DLD), and combined CT and dose distribution (DL(R+D)) images were constructed. DL features were then extracted from the fully connected layers of the best-performing DL model to combine with features of the ML model with the best performance to construct models of R+DLR, D+DLD, R+D+DL(R+D)) for RP prediction.

RESULTS: The R+D model achieved a best area under curve (AUC) of 0.84, 0.73, and 0.73 in the internal validation cohorts with Support Vector Machine (SVM), XGBoost, and Logistic Regression (LR), respectively. The DL(R+D) model achieved a best AUC of 0.89 and 0.86 using ResNet-34 in training and internal validation cohorts, respectively. The R+D+DL(R+D) model achieved a best performance in the external validation cohorts with an AUC, accuracy, sensitivity, and specificity of 0.81(0.62-0.99), 0.81, 0.84, and 0.67, respectively.

CONCLUSIONS: The integration of radiomics, dosiomics, and DL features is feasible and accurate for the RP prediction to improve the management of lung cancer patients underwent VMAT.

PMID:38905987 | DOI:10.1016/j.cmpb.2024.108295

Comput Med Imaging Graph. 2024 Jun 12;116:102410. doi: 10.1016/j.compmedimag.2024.102410. Online ahead of print.

ABSTRACT

Trabecular bone analysis plays a crucial role in understanding bone health and disease, with applications like osteoporosis diagnosis. This paper presents a comprehensive study on 3D trabecular computed tomography (CT) image restoration, addressing significant challenges in this domain. The research introduces a backbone model, Cascade-SwinUNETR, for single-view 3D CT image restoration. This model leverages deep layer aggregation with supervision and capabilities of Swin-Transformer to excel in feature extraction. Additionally, this study also brings DVSR3D, a dual-view restoration model, achieving good performance through deep feature fusion with attention mechanisms and Autoencoders. Furthermore, an Unsupervised Domain Adaptation (UDA) method is introduced, allowing models to adapt to input data distributions without additional labels, holding significant potential for real-world medical applications, and eliminating the need for invasive data collection procedures. The study also includes the curation of a new dual-view dataset for CT image restoration, addressing the scarcity of real human bone data in Micro-CT. Finally, the dual-view approach is validated through downstream medical bone microstructure measurements. Our contributions open several paths for trabecular bone analysis, promising improved clinical outcomes in bone health assessment and diagnosis.

PMID:38905961 | DOI:10.1016/j.compmedimag.2024.102410

Comput Biol Med. 2024 Jun 4;178:108691. doi: 10.1016/j.compbiomed.2024.108691. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVES: This study aims to develop and evaluate NeuNN, a system based on convolutional neural networks (CNN) and generative adversarial networks (GAN) for the automatic identification of normal neutrophils and those containing several types of inclusions or showing hypogranulation.

METHODS: From peripheral blood smears, a set of 5605 digital images was obtained with neutrophils belonging to seven categories: Normal neutrophils (NEU), Hypogranulated (HYP) or containing cryoglobulins (CRY), Döhle bodies (DB), Howell-Jolly body-like inclusions (HJBLI), Green-blue inclusions of death (GBI) and phagocytosed bacteria (BAC). The dataset utilized in this study has been made publicly available. The class of GBI was augmented using synthetic images generated by GAN. The NeuNN classification model is based on an EfficientNet-B7 architecture trained from scratch.

RESULTS: NeuNN achieved an overall performance of 94.3% accuracy on the test data set. Performance metrics, including sensitivity, specificity, precision, F1-Score, Jaccard index, and Matthews correlation coefficient indicated overall values of 94%, 99.1%, 94.3%, 94.3%, 89.6%, and 93.6%, respectively.

CONCLUSIONS: The proposed approach, combining data augmentation and classification techniques, allows for automated identification of morphological findings in neutrophils, such us inclusions or hypogranulation. The system can be used as a support tool for clinical pathologists to detect these specific abnormalities with clinical relevance.

PMID:38905894 | DOI:10.1016/j.compbiomed.2024.108691

Comput Biol Med. 2024 May 29;178:108673. doi: 10.1016/j.compbiomed.2024.108673. Online ahead of print.

ABSTRACT

Deformable Image registration is a fundamental yet vital task for preoperative planning, intraoperative information fusion, disease diagnosis and follow-ups. It solves the non-rigid deformation field to align an image pair. Latest approaches such as VoxelMorph and TransMorph compute features from a simple concatenation of moving and fixed images. However, this often leads to weak alignment. Moreover, the convolutional neural network (CNN) or the hybrid CNN-Transformer based backbones are constrained to have limited sizes of receptive field and cannot capture long range relations while full Transformer based approaches are computational expensive. In this paper, we propose a novel multi-axis cross grating network (MACG-Net) for deformable medical image registration, which combats these limitations. MACG-Net uses a dual stream multi-axis feature fusion module to capture both long-range and local context relationships from the moving and fixed images. Cross gate blocks are integrated with the dual stream backbone to consider both independent feature extractions in the moving-fixed image pair and the relationship between features from the image pair. We benchmark our method on several different datasets including 3D atlas-based brain MRI, inter-patient brain MRI and 2D cardiac MRI. The results demonstrate that the proposed method has achieved state-of-the-art performance. The source code has been released at https://github.com/Valeyards/MACG.

PMID:38905891 | DOI:10.1016/j.compbiomed.2024.108673

Medicine (Baltimore). 2024 Jun 21;103(25):e38478. doi: 10.1097/MD.0000000000038478.

ABSTRACT

The diagnosis of pneumoconiosis is complex and subjective, leading to inevitable variability in readings. This is especially true for inexperienced doctors. To improve accuracy, a computer-assisted diagnosis system is used for more effective pneumoconiosis diagnoses. Three models (Resnet50, Resnet101, and DenseNet) were used for pneumoconiosis classification based on 1250 chest X-ray images. Three experienced and highly qualified physicians read the collected digital radiography images and classified them from category 0 to category III in a double-blinded manner. The results of the 3 physicians in agreement were considered the relative gold standards. Subsequently, 3 models were used to train and test these images and their performance was evaluated using multi-class classification metrics. We used kappa values and accuracy to evaluate the consistency and reliability of the optimal model with clinical typing. The results showed that ResNet101 was the optimal model among the 3 convolutional neural networks. The AUC of ResNet101 was 1.0, 0.9, 0.89, and 0.94 for detecting pneumoconiosis categories 0, I, II, and III, respectively. The micro-average and macro-average mean AUC values were 0.93 and 0.94, respectively. The accuracy and Kappa values of ResNet101 were 0.72 and 0.7111 for quadruple classification and 0.98 and 0.955 for dichotomous classification, respectively, compared with the relative standard classification of the clinic. This study develops a deep learning based model for screening and staging of pneumoconiosis is using chest radiographs. The ResNet101 model performed relatively better in classifying pneumoconiosis than radiologists. The dichotomous classification displayed outstanding performance, thereby indicating the feasibility of deep learning techniques in pneumoconiosis screening.

PMID:38905434 | DOI:10.1097/MD.0000000000038478

Medicine (Baltimore). 2024 Jun 21;103(25):e38596. doi: 10.1097/MD.0000000000038596.

ABSTRACT

BACKGROUND: Diabetic Macular Edema (DME) significantly impairs vision in diabetics, with varied patient responses to current treatments like anti-vascular endothelial growth factor (VEGF) therapy underscoring the necessity for continued research into more effective strategies. This study aims to evaluate global research trends and identify emerging frontiers in DME to guide future research and clinical management.

METHODS: A qualitative and quantitative analysis of publications related to diabetic macular edema retrieved from the Web of Science Core Collection (WoSCC) between its inception and September 4, 2023, was conducted. Microsoft Excel, CiteSpace, VOSviewer, Bibliometrix Package, and Tableau were used for the bibliometric analysis and visualization. This encompasses an examination of the overall distribution of annual output, major countries, regions, institutions, authors, core journals, co-cited references, and keyword analyses.

RESULTS: Overall, 5624 publications were analyzed, indicating an increasing trend in DME research. The United States was identified as the leading country in DME research, with the highest h-index of 135 and 91,841 citations. Francesco Bandello emerged as the most prolific author with 97 publications. Neil M. Bressler has the highest h-index and highest total citation count of 46 and 9692, respectively. The journals "Retina - the Journal of Retinal and Vitreous Diseases" and "Ophthalmology" were highlighted as the most prominent in this field. "Retina" leads with 354 publications, a citation count of 11,872, and an h-index of 59. Meanwhile, "Ophthalmology" stands out with the highest overall citation count of 31,558 and the highest h-index of 90. The primary research focal points in diabetic macular edema included "prevalence and risk factors," "pathological mechanisms," "imaging modalities," "treatment strategies," and "clinical trials." Emerging research areas encompassed "deep learning and artificial intelligence," "novel treatment modalities," and "biomarkers."

CONCLUSION: Our bibliometric analysis delineates the leading role of the United States in DME research. We identified current research hotspots, including epidemiological studies, pathophysiological mechanisms, imaging advancements, and treatment innovations. Emerging trends, such as the integration of artificial intelligence and novel therapeutic approaches, highlight future directions. These insights underscore the importance of collaborative and interdisciplinary approaches in advancing DME research and clinical management.

PMID:38905408 | DOI:10.1097/MD.0000000000038596

Tree Physiol. 2024 Jun 21:tpae072. doi: 10.1093/treephys/tpae072. Online ahead of print.

ABSTRACT

Epigenetic changes serve as a cellular memory for cumulative cold recognition in both herbaceous and tree species, including bud dormancy. However, most studies have discussed predicted chromatin structure with respect to histone marks. In the present study, we investigated the structural dynamics of bona fide chromatin to determine how plants recognise prolonged chilling during the initial stage of bud dormancy. The vegetative axillary buds of the 'Fuji' apple, which shows typical low temperature-dependent, but not photoperiod, dormancy induction, were used for the chromatin structure and transcriptional change analyses. The results were integrated using a deep-learning model and interpreted using statistical models, including Bayesian estimation. Although our model was constructed using a small dataset of two time points, chromatin remodelling due to random changes was excluded. The involvement of most nucleosome structural changes in transcriptional changes and the pivotal contribution of cold-driven circadian rhythm-dependent pathways regulated by the mobility of cis-regulatory elements were predicted. These findings may help to develop potential genetic targets for breeding species with less bud dormancy to overcome the effects of short winters during global warming. Our artificial intelligence concept can improve epigenetic analysis using a small dataset, especially in non-model plants with immature genome databases.

PMID:38905284 | DOI:10.1093/treephys/tpae072

PLoS One. 2024 Jun 21;19(6):e0304422. doi: 10.1371/journal.pone.0304422. eCollection 2024.

ABSTRACT

This study delves into the critical need for generating real-world compatible data to support the application of deep reinforcement learning (DRL) in vehicle routing. Despite the advancements in DRL algorithms, their practical implementation in vehicle routing is hindered by the scarcity of appropriate real-world datasets. Existing methodologies often rely on simplistic distance metrics, failing to accurately capture the complexities inherent in real-world routing scenarios. To address this challenge, we present a novel approach for generating real-world compatible data tailored explicitly for DRL-based vehicle routing models. Our methodology centers on the development of a spatial data extraction and curation tool adept at extracting geocoded locations from diverse urban environments, encompassing both planned and unplanned areas. Leveraging advanced techniques, the tool refines location data, accounting for unique characteristics of urban environments. Furthermore, it integrates specialized distance metrics and location demands to construct vehicle routing graphs that represent real-world conditions. Through comprehensive experimentation on varied real-world testbeds, our approach showcases its efficacy in producing datasets closely aligned with the requirements of DRL-based vehicle routing models. It's worth mentioning that this dataset is structured as a graph containing location, distance, and demand information, with each graph stored independently to facilitate efficient access and manipulation. The findings underscore the adaptability and reliability of our methodology in tackling the intricacies of real-world routing challenges. This research marks a significant stride towards enabling the practical application of DRL techniques in addressing real-world vehicle routing problems.

PMID:38905257 | DOI:10.1371/journal.pone.0304422

PLoS One. 2024 Jun 21;19(6):e0304819. doi: 10.1371/journal.pone.0304819. eCollection 2024.

ABSTRACT

Solar cells are playing a significant role in aerospace equipment. In view of the surface defect characteristics in the manufacturing process of solar cells, the common surface defects are divided into three categories, which include difficult-detecting defects (mismatch), general defects (bubble, glass-crack and cell-crack) and easy-detecting defects (glass-upside-down). Corresponding to different types of defects, the deep learning model with different optimization methods and a classification detection method based on multi-models fusion are proposed in the paper. In the proposed model, in order to solve the mismatch problem between the default anchor boxes size of YOLOv5s model and the extreme scale of the battery mismatch defect label boxes, the K-means algorithm was adopted to re-cluster the dedicated anchor boxes for the mismatch defect label boxes. In order to improve the comprehensive detection accuracy of YOLOv5s model for the general defects, the YOLOv5s model was also improved by the methods of image preprocessing, anchor box improving and detection head replacing. In order to ensure the recognition accuracy and improve the detection speed for easy-detecting defects, the lightweight classification network MobileNetV2 was also used to classify the cells with glass-upside-down defects. The experimental results show that the proposed optimization model and classification detection method can significantly improve the defect detection precision. Respectively, the detection precision for mismatch, bubble, glass-crack and cell-crack defects are up to 95.64%, 91.8%, 93.1% and 98.0%. By using lightweight model to train the glass-upside-down defect dataset, the average classification accuracy reaches 100% and the detection speed reaches 13.29 frames per second. The comparison experiments show that the proposed model has a great improvement in detection accuracy compared with the original model, and the defect detection speed of lightweight classification network is improved more obviously, which confirms the effectiveness of the proposed optimization model and the multi-defect classification detection method for solar cells defect detection.

PMID:38905246 | DOI:10.1371/journal.pone.0304819

PLoS One. 2024 Jun 21;19(6):e0304657. doi: 10.1371/journal.pone.0304657. eCollection 2024.

ABSTRACT

To address the growing demand for sustainable agriculture practices, new technologies to boost crop productivity and soil health must be developed. In this research, we propose designing and building an agricultural rover capable of autonomous vegetable harvesting and soil analysis utilizing cutting-edge deep learning algorithms (YOLOv5). The precision and recall score of the model was 0.8518% and 0.7624% respectively. The rover uses robotics, computer vision, and soil sensing technology to perform accurate and efficient agricultural tasks. We go over the rover's hardware and software, as well as the soil analysis system and the tomato ripeness detection system using deep learning models. Field experiments indicate that this agricultural rover is effective and promising for improving crop management and soil monitoring in modern agriculture, hence achieving the UN's SDG 2 Zero Hunger goals.

PMID:38905232 | DOI:10.1371/journal.pone.0304657