Front Plant Sci. 2024 Aug 6;15:1420584. doi: 10.3389/fpls.2024.1420584. eCollection 2024.

ABSTRACT

Tomato disease image recognition plays a crucial role in agricultural production. Today, while machine vision methods based on deep learning have achieved some success in disease recognition, they still face several challenges. These include issues such as imbalanced datasets, unclear disease features, small inter-class differences, and large intra-class variations. To address these challenges, this paper proposes a method for classifying and recognizing tomato leaf diseases based on machine vision. First, to enhance the disease feature details in images, a piecewise linear transformation method is used for image enhancement, and oversampling is employed to expand the dataset, compensating for the imbalanced dataset. Next, this paper introduces a convolutional block with a dual attention mechanism called DAC Block, which is used to construct a lightweight model named LDAMNet. The DAC Block innovatively uses Hybrid Channel Attention (HCA) and Coordinate Attention (CSA) to process channel information and spatial information of input images respectively, enhancing the model's feature extraction capabilities. Additionally, this paper proposes a Robust Cross-Entropy (RCE) loss function that is robust to noisy labels, aimed at reducing the impact of noisy labels on the LDAMNet model during training. Experimental results show that this method achieves an average recognition accuracy of 98.71% on the tomato disease dataset, effectively retaining disease information in images and capturing disease areas. Furthermore, the method also demonstrates strong recognition capabilities on rice crop disease datasets, indicating good generalization performance and the ability to function effectively in disease recognition across different crops. The research findings of this paper provide new ideas and methods for the field of crop disease recognition. However, future research needs to further optimize the model's structure and computational efficiency, and validate its application effects in more practical scenarios.

PMID:39166234 | PMC:PMC11333365 | DOI:10.3389/fpls.2024.1420584

Heliyon. 2024 Jul 26;10(15):e35247. doi: 10.1016/j.heliyon.2024.e35247. eCollection 2024 Aug 15.

ABSTRACT

Recently, autonomous mobile robots (AMRs) have begun to be used in the delivery of goods, but one of the biggest challenges faced in this field is the navigation system that guides a robot to its destination. The navigation system must be able to identify objects in the robot's path and take evasive actions to avoid them. Developing an object detection system for an AMR requires a deep learning model that is able to achieve a high level of accuracy, with fast inference times, and a model with a compact size that can be run on embedded control systems. Consequently, object recognition requires a convolutional neural network (CNN)-based model that can yield high object classification accuracy and process data quickly. This paper introduces a new CNN-based object detection system for an AMR that employs real-world vehicle datasets. First, we create original real-world datasets of images from Banda Aceh city. We then develop a new CNN-based object identification system that is capable of identifying cars, motorcycles, people, and rickshaws under morning, afternoon, and evening lighting conditions. An SSD Mobilenetv2 FPN Lite 320 × 320 architecture is employed for retraining using these real-world datasets. Quantitative and qualitative performance indicators are then applied to evaluate the CNN model. Training the pre-trained SSD Mobilenetv2 FPN Lite 320 × 320 model improves its classification and detection accuracy, as indicated by its performance results. We conclude that the proposed CNN-based object detection system has the potential for use in an AMR.

PMID:39166079 | PMC:PMC11334655 | DOI:10.1016/j.heliyon.2024.e35247

Heliyon. 2024 Jul 30;10(15):e35407. doi: 10.1016/j.heliyon.2024.e35407. eCollection 2024 Aug 15.

ABSTRACT

In the context of burgeoning industrial advancement, there is an increasing trend towards the integration of intelligence and precision in mechanical equipment. Central to the functionality of such equipment is the rolling bearing, whose operational integrity significantly impacts the overall performance of the machinery. This underscores the imperative for reliable fault diagnosis mechanisms in the continuous monitoring of rolling bearing conditions within industrial production environments. Vibration signals are primarily used for fault diagnosis in mechanical equipment because they provide comprehensive information about the equipment's condition. However, fault data often contain high noise levels, high-frequency variations, and irregularities, along with a significant amount of redundant information, like duplication, overlap, and unnecessary information during signal transmission. These characteristics present considerable challenges for effective fault feature extraction and diagnosis, reducing the accuracy and reliability of traditional fault detection methods. This research introduces an innovative fault diagnosis methodology for rolling bearings using deep convolutional neural networks (CNNs) enhanced with variational autoencoders (VAEs). This deep learning approach aims to precisely identify and classify faults by extracting detailed vibration signal features. The VAE enhances noise robustness, while the CNN improves signal data expressiveness, addressing issues like gradient vanishing and explosion. The model employs the reparameterization trick for unsupervised learning of latent features and further trains with the CNN. The system incorporates adaptive threshold methods, the "3/5" strategy, and Dropout methods. The diagnosis accuracy of the VAE-CNN model for different fault types at different rotational speeds typically reaches more than 90 %, and it achieves a generally acceptable diagnosis result. Meanwhile, the VAE-CNN augmented fault diagnosis model, after experimental validation in various dimensions, can achieve more satisfactory diagnosis results for various fault types compared to several representative deep neural network models without VAE augmentation, significantly improving the accuracy and robustness of rolling bearing fault diagnosis.

PMID:39166054 | PMC:PMC11334817 | DOI:10.1016/j.heliyon.2024.e35407

Heliyon. 2024 Jul 26;10(15):e35236. doi: 10.1016/j.heliyon.2024.e35236. eCollection 2024 Aug 15.

ABSTRACT

PURPOSE: To develop and validate deep learning algorithms that can identify and classify angle-closure (AC) mechanisms using anterior segment optical coherence tomography (AS-OCT) images.

METHODS: This cross-sectional study included participants of the Handan Eye Study aged ≥35 years with AC detected via gonioscopy or on the AS-OCT images. These images were classified by human experts into the following to indicate the predominant AC mechanism (ground truth): pupillary block, plateau iris configuration, or thick peripheral iris roll. A deep learning architecture, known as comprehensive mechanism decision net (CMD-Net), was developed to simulate the identification of image-level AC mechanisms by human experts. Cross-validation was performed to optimize and evaluate the model. Human-machine comparisons were conducted using a held-out and separate test sets to establish generalizability.

RESULTS: In total, 11,035 AS-OCT images of 1455 participants (2833 eyes) were included. Among these, 8828 and 2.207 images were included in the cross-validation and held-out test sets, respectively. A separate test was formed comprising 228 images of 35 consecutive patients with AC detected via gonioscopy at our eye center. In the classification of AC mechanisms, CMD-Net achieved a mean area under the receiver operating characteristic curve (AUC) of 0.980, 0.977, and 0.988 in the cross-validation, held-out, and separate test sets, respectively. The best-performing ophthalmologist achieved an AUC of 0.903 and 0.891 in the held-out and separate test sets, respectively. And CMD-Net outperformed glaucoma specialists, achieving an accuracy of 89.9 % and 93.0 % compared to 87.0 % and 86.8 % for the best-performing ophthalmologist in the held-out and separate test sets, respectively.

CONCLUSIONS: Our study suggests that CMD-Net has the potential to classify AC mechanisms using AS-OCT images, though further validation is needed.

PMID:39166052 | PMC:PMC11334645 | DOI:10.1016/j.heliyon.2024.e35236

Heliyon. 2024 Jul 26;10(15):e35167. doi: 10.1016/j.heliyon.2024.e35167. eCollection 2024 Aug 15.

ABSTRACT

In developing countries, smart grids are nonexistent, and electricity theft significantly hampers power supply. This research introduces a lightweight deep-learning model using monthly customer readings as input data. By employing careful direct and indirect feature engineering techniques, including Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), UMAP (Uniform Manifold Approximation and Projection), and resampling methods such as Random-Under-Sampler (RUS), Synthetic Minority Over-sampling Technique (SMOTE), and Random-Over-Sampler (ROS), an effective solution is proposed. Previous studies indicate that models achieve high precision, recall, and F1 score for the non-theft (0) class, but perform poorly, even achieving 0 %, for the theft (1) class. Through parameter tuning and employing Random-Over-Sampler (ROS), significant improvements in accuracy, precision (89 %), recall (94 %), and F1 score (91 %) for the theft (1) class are achieved. The results demonstrate that the proposed model outperforms existing methods, showcasing its efficacy in detecting electricity theft in non-smart grid environments.

PMID:39166039 | PMC:PMC11334629 | DOI:10.1016/j.heliyon.2024.e35167

Heliyon. 2024 Jul 27;10(15):e35115. doi: 10.1016/j.heliyon.2024.e35115. eCollection 2024 Aug 15.

ABSTRACT

PROBLEM: Previous studies had confirmed that some deep learning models had high diagnostic performance in staging liver fibrosis. However, training efficiency of models predicting liver fibrosis need to be improved to achieve rapid diagnosis and precision medicine.

AIM: The deep learning framework of EfficientNetV2-S was noted because of its faster training speed and better parameter efficiency compared with other models. Our study sought to develop noninvasive predictive models based on EfficientNetV2-S framework for staging liver fibrosis.

METHODS: Patients with chronic liver disease who underwent multi-parametric abdominal MRI were included in the retrospective study. Data augmentation methods including horizontal flip, vertical flip, perspective transformation and edge enhancement were applied to multi-parametric MR images to solve the data imbalance between different liver fibrosis groups. The EfficientNetV2-S models were used for the prediction of liver fibrosis stages F1-2, F1-3, F3, F4 and F3-4. We evaluated the diagnostic performance of our models in training, validation, and test sets by using receiver operating characteristic curve (ROC) analysis.

RESULTS: The total training time of EfficientNetV2-S was about 6 h. For differentiating of F1-2 vs F3, the accuracy, sensitivity and specificity of EfficientNetV2-S model were 96.2 %, 96.4 % and 96.0 % in the test set. The AUC in test set was 0.559. The accuracy, sensitivity and specificity were 82.1 %, 74.5 % and 89.6 % in the test set by using EfficientNetV2-S model to differentiate F1-2 vs F3-4, and the AUC in test set were 0.763. For differentiating F1-3 vs F4, the accuracy, sensitivity and specificity of EfficientNetV2-S model were 71.5 %, 73.4 % and 69.5 % in the test set. The AUC was 0.553 in test set. For differentiating F1-2 vs F4, the accuracy, sensitivity and specificity of our model were 84.3 %, 80.2 % and 88.3 % in the test set, and the AUC was 0.715, respectively. For differentiating F3 vs F4, the accuracy, sensitivity and specificity of EfficientNetV2-S model were 92.5 %, 89.1 % and 95.6 % in the test set, and the AUC was 0.696 in the test set.

CONCLUSIONS: The EfficientNetV2-S models based on multi-parametric MRI had the feasibility for staging of liver fibrosis because they showed high training speed and diagnostic performance in our study.

PMID:39165928 | PMC:PMC11334657 | DOI:10.1016/j.heliyon.2024.e35115

iScience. 2024 Jul 22;27(8):110545. doi: 10.1016/j.isci.2024.110545. eCollection 2024 Aug 16.

ABSTRACT

Both mental health and mental illness unfold in complex and unpredictable ways. Novel artificial intelligence approaches from the area of dynamical systems reconstruction can characterize such dynamics and help understand the underlying brain mechanisms, which can also be used as potential biomarkers. However, applying deep learning to model dynamical systems at the individual level must overcome numerous computational challenges to be reproducible and clinically useful. In this study, we performed an extensive analysis of these challenges using generative modeling of brain dynamics from fMRI data as an example and demonstrated their impact on classifying patients with schizophrenia and major depression. This study highlights the tendency of deep learning models to identify functionally unique solutions during parameter optimization, which severely impacts the reproducibility of downstream predictions. We hope this study guides the future development of individual-level generative models and similar machine learning approaches aimed at identifying reproducible biomarkers of mental illness.

PMID:39165842 | PMC:PMC11334782 | DOI:10.1016/j.isci.2024.110545

Ophthalmol Sci. 2024 Jun 13;4(6):100563. doi: 10.1016/j.xops.2024.100563. eCollection 2024 Nov-Dec.

ABSTRACT

OBJECTIVE: To quantitatively predict children's and adolescents' spherical equivalent (SE) by leveraging their variable-length historical vision records.

DESIGN: Retrospective analysis.

PARTICIPANTS: Eight hundred ninety-five myopic children and adolescents aged 4 to 18 years, with a complete ophthalmic examination and retinoscopy in cycloplegia prior to spectacle correction, were enrolled in the period from January 1, 2008 to July 1, 2023 at the University Hospital "Sveti Duh," Zagreb, Croatia.

METHODS: A novel modification of time-aware long short-term memory (LSTM) was used to quantitatively predict children's and adolescents' SE within 7 years after diagnosis.

MAIN OUTCOME MEASURES: The utilization of extended gate time-aware LSTM involved capturing temporal features within irregularly sampled time series data. This approach aligned more closely with the characteristics of fact-based data, increasing its applicability and contributing to the early identification of myopia progression.

RESULTS: The testing set exhibited a mean absolute prediction error (MAE) of 0.10 ± 0.15 diopter (D) for SE. Lower MAE values were associated with longer sequence lengths, shorter prediction durations, older age groups, and low myopia, while higher MAE values were observed with shorter sequence lengths, longer prediction durations, younger age groups, and in premyopic or high myopic individuals, ranging from as low as 0.03 ± 0.04 D to as high as 0.45 ± 0.24 D.

CONCLUSIONS: Extended gate time-aware LSTM capturing temporal features in irregularly sampled time series data can be used to quantitatively predict children's and adolescents' SE within 7 years with an overall error of 0.10 ± 0.15 D. This value is substantially lower than the threshold for prediction to be considered clinically acceptable, such as a criterion of 0.75 D.

FINANCIAL DISCLOSURES: The author(s) have no proprietary or commercial interest in any materials discussed in this article.

PMID:39165695 | PMC:PMC11334700 | DOI:10.1016/j.xops.2024.100563

Ophthalmol Sci. 2024 May 17;4(6):100552. doi: 10.1016/j.xops.2024.100552. eCollection 2024 Nov-Dec.

ABSTRACT

OBJECTIVE: Vision transformers (ViTs) have shown promising performance in various classification tasks previously dominated by convolutional neural networks (CNNs). However, the performance of ViTs in referable diabetic retinopathy (DR) detection is relatively underexplored. In this study, using retinal photographs, we evaluated the comparative performances of ViTs and CNNs on detection of referable DR.

DESIGN: Retrospective study.

PARTICIPANTS: A total of 48 269 retinal images from the open-source Kaggle DR detection dataset, the Messidor-1 dataset and the Singapore Epidemiology of Eye Diseases (SEED) study were included.

METHODS: Using 41 614 retinal photographs from the Kaggle dataset, we developed 5 CNN (Visual Geometry Group 19, ResNet50, InceptionV3, DenseNet201, and EfficientNetV2S) and 4 ViTs models (VAN_small, CrossViT_small, ViT_small, and Hierarchical Vision transformer using Shifted Windows [SWIN]_tiny) for the detection of referable DR. We defined the presence of referable DR as eyes with moderate or worse DR. The comparative performance of all 9 models was evaluated in the Kaggle internal test dataset (with 1045 study eyes), and in 2 external test sets, the SEED study (5455 study eyes) and the Messidor-1 (1200 study eyes).

MAIN OUTCOME MEASURES: Area under operating characteristics curve (AUC), specificity, and sensitivity.

RESULTS: Among all models, the SWIN transformer displayed the highest AUC of 95.7% on the internal test set, significantly outperforming the CNN models (all P < 0.001). The same observation was confirmed in the external test sets, with the SWIN transformer achieving AUC of 97.3% in SEED and 96.3% in Messidor-1. When specificity level was fixed at 80% for the internal test, the SWIN transformer achieved the highest sensitivity of 94.4%, significantly better than all the CNN models (sensitivity levels ranging between 76.3% and 83.8%; all P < 0.001). This trend was also consistently observed in both external test sets.

CONCLUSIONS: Our findings demonstrate that ViTs provide superior performance over CNNs in detecting referable DR from retinal photographs. These results point to the potential of utilizing ViT models to improve and optimize retinal photo-based deep learning for referable DR detection.

FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

PMID:39165694 | PMC:PMC11334703 | DOI:10.1016/j.xops.2024.100552

Sci Rep. 2024 Aug 20;14(1):19285. doi: 10.1038/s41598-024-70175-2.

ABSTRACT

Age-related macular degeneration (AMD) and diabetic macular edema (DME) are significant causes of blindness worldwide. The prevalence of these diseases is steadily increasing due to population aging. Therefore, early diagnosis and prevention are crucial for effective treatment. Classification of Macular Degeneration OCT Images is a widely used method for assessing retinal lesions. However, there are two main challenges in OCT image classification: incomplete image feature extraction and lack of prominence in important positional features. To address these challenges, we proposed a deep learning neural network model called MSA-Net, which incorporates our proposed multi-scale architecture and spatial attention mechanism. Our multi-scale architecture is based on depthwise separable convolution, which ensures comprehensive feature extraction from multiple scales while minimizing the growth of model parameters. The spatial attention mechanism is aim to highlight the important positional features in the images, which emphasizes the representation of macular region features in OCT images. We test MSA-NET on the NEH dataset and the UCSD dataset, performing three-class (CNV, DURSEN, and NORMAL) and four-class (CNV, DURSEN, DME, and NORMAL) classification tasks. On the NEH dataset, the accuracy, sensitivity, and specificity are 98.1%, 97.9%, and 98.0%, respectively. After fine-tuning on the UCSD dataset, the accuracy, sensitivity, and specificity are 96.7%, 96.7%, and 98.9%, respectively. Experimental results demonstrate the excellent classification performance and generalization ability of our model compared to previous models and recent well-known OCT classification models, establishing it as a highly competitive intelligence classification approach in the field of macular degeneration.

PMID:39164445 | DOI:10.1038/s41598-024-70175-2

Sci Rep. 2024 Aug 20;14(1):19330. doi: 10.1038/s41598-024-69173-1.

ABSTRACT

Smart elevators provide substantial promise for time and energy management applications by utilizing cutting edge artificial intelligence and image processing technology. In order to improve operating efficiency, this project designs an elevator system that uses the YOLO model for object detection. Compared to traditional methods, our results show a 15% improvement in wait times and a 20% reduction in energy use. Due to the elevator's increased accuracy and dependability, users' qualitative feedback shows a high degree of pleasure. These results imply that intelligent elevator systems can make a significant contribution to more intelligent building management. Due to the elevator's increased accuracy and dependability, users' qualitative feedback shows a high degree of pleasure. These results imply that intelligent elevator systems can make a significant contribution to more intelligent building management. The successful integration of artificial intelligence (AI) and image processing technologies in elevator systems presents a promising foundation for future research and development. Further advancements in object detection algorithms, such as refining YOLO models for even higher accuracy and real-time adaptability, hold potential to enhance operational efficiency. Integrating smart elevators more deeply into IoT networks and building management systems could enable comprehensive energy management strategies and real-time decision-making. Predictive maintenance models tailored to elevator components could minimize downtime and optimize service schedules, enhancing overall reliability. Additionally, exploring adaptive user interfaces and personalized scheduling algorithms could further elevate user satisfaction by tailoring elevator interactions to individual preferences. Sustainable practices, including energy-efficient designs and integration of renewable energy sources, represent crucial avenues for reducing environmental impact. Addressing security concerns through advanced encryption and access control mechanisms will be essential for safeguarding sensitive data in smart elevator systems.

PMID:39164299 | DOI:10.1038/s41598-024-69173-1

Nat Commun. 2024 Aug 20;15(1):7136. doi: 10.1038/s41467-024-51433-3.

ABSTRACT

Untargeted metabolomic analysis using mass spectrometry provides comprehensive metabolic profiling, but its medical application faces challenges of complex data processing, high inter-batch variability, and unidentified metabolites. Here, we present DeepMSProfiler, an explainable deep-learning-based method, enabling end-to-end analysis on raw metabolic signals with output of high accuracy and reliability. Using cross-hospital 859 human serum samples from lung adenocarcinoma, benign lung nodules, and healthy individuals, DeepMSProfiler successfully differentiates the metabolomic profiles of different groups (AUC 0.99) and detects early-stage lung adenocarcinoma (accuracy 0.961). Model flow and ablation experiments demonstrate that DeepMSProfiler overcomes inter-hospital variability and effects of unknown metabolites signals. Our ensemble strategy removes background-category phenomena in multi-classification deep-learning models, and the novel interpretability enables direct access to disease-related metabolite-protein networks. Further applying to lipid metabolomic data unveils correlations of important metabolites and proteins. Overall, DeepMSProfiler offers a straightforward and reliable method for disease diagnosis and mechanism discovery, enhancing its broad applicability.

PMID:39164279 | DOI:10.1038/s41467-024-51433-3

Immunity. 2024 Aug 15:S1074-7613(24)00371-6. doi: 10.1016/j.immuni.2024.07.022. Online ahead of print.

ABSTRACT

Despite decades of antibody research, it remains challenging to predict the specificity of an antibody solely based on its sequence. Two major obstacles are the lack of appropriate models and the inaccessibility of datasets for model training. In this study, we curated >5,000 influenza hemagglutinin (HA) antibodies by mining research publications and patents, which revealed many distinct sequence features between antibodies to HA head and stem domains. We then leveraged this dataset to develop a lightweight memory B cell language model (mBLM) for sequence-based antibody specificity prediction. Model explainability analysis showed that mBLM could identify key sequence features of HA stem antibodies. Additionally, by applying mBLM to HA antibodies with unknown epitopes, we discovered and experimentally validated many HA stem antibodies. Overall, this study not only advances our molecular understanding of the antibody response to the influenza virus but also provides a valuable resource for applying deep learning to antibody research.

PMID:39163866 | DOI:10.1016/j.immuni.2024.07.022

Med. 2024 Aug 14:S2666-6340(24)00307-6. doi: 10.1016/j.medj.2024.07.025. Online ahead of print.

ABSTRACT

BACKGROUND: Digital subtraction angiography (DSA) devices are commonly used in numerous interventional procedures across various parts of the body, necessitating multiple scans per procedure, which results in significant radiation exposure for both doctors and patients. Inspired by generative artificial intelligence techniques, this study proposes GenDSA, a large-scale pretrained multi-frame generative model-based real-time and low-dose DSA imaging system.

METHODS: GenDSA was developed to generate 1-, 2-, and 3-frame sequences following each real frame. A large-scale dataset comprising ∼3 million DSA images from 27,117 patients across 10 hospitals was constructed to pretrain, fine-tune, and validate GenDSA. Two other datasets from 25 hospitals were used for evaluation. Objective evaluations included SSIM and PSNR. Five interventional radiologists independently assessed the quality of the generated frames using the Likert scale and visual Turing test. Scoring consistency among the radiologists was measured using the Kendall coefficient of concordance (W). The Fleiss' kappa values were used for inter-rater agreement analysis for visual Turing tests.

FINDINGS: Using only one-third of the clinical radiation dose, videos generated by GenDSA were perfectly consistent with real videos. Objective evaluations demonstrated that GenDSA's performance (PSNR = 36.83, SSIM = 0.911, generation time = 0.07 s/frame) surpassed state-of-the-art algorithms. Subjective ratings and statistical results from five doctors indicated no significant difference between real and generated videos. Furthermore, the generated videos were comparable to real videos in overall quality (4.905 vs. 4.935) and lesion assessment (4.825 vs. 4.860).

CONCLUSIONS: With clear clinical and translational values, the developed GenDSA can significantly reduce radiation damage to both doctors and patients during DSA-guided procedures.

FUNDING: This study was supported by the National Key R&D Program and the National Natural Science Foundation of China.

PMID:39163857 | DOI:10.1016/j.medj.2024.07.025

Genome Biol. 2024 Aug 20;25(1):227. doi: 10.1186/s13059-024-03369-6.

ABSTRACT

BACKGROUND: The design of nucleotide sequences with defined properties is a long-standing problem in bioengineering. An important application is protein expression, be it in the context of research or the production of mRNA vaccines. The rate of protein synthesis depends on the 5' untranslated region (5'UTR) of the mRNAs, and recently, deep learning models were proposed to predict the translation output of mRNAs from the 5'UTR sequence. At the same time, large data sets of endogenous and reporter mRNA translation have become available.

RESULTS: In this study, we use complementary data obtained in two different cell types to assess the accuracy and generality of currently available models for predicting translational output. We find that while performing well on the data sets on which they were trained, deep learning models do not generalize well to other data sets, in particular of endogenous mRNAs, which differ in many properties from reporter constructs.

CONCLUSIONS: These differences limit the ability of deep learning models to uncover mechanisms of translation control and to predict the impact of genetic variation. We suggest directions that combine high-throughput measurements and machine learning to unravel mechanisms of translation control and improve construct design.

PMID:39164757 | DOI:10.1186/s13059-024-03369-6

BMC Public Health. 2024 Aug 20;24(1):2251. doi: 10.1186/s12889-024-19605-4.

ABSTRACT

The association between built environment and physical activity has been recognized. However, how and to what extent microscale streetscapes are related to running activity remains underexplored, partly due to the lack of running data in large urban areas. Moreover, few studies have examined the interactive effects of macroscale built environment and microscale streetscapes. This study examines the main and interactive effects of the two-level environments on running intensity, using 9.73 million fitness tracker data from Keep in Shanghai, China. Results of spatial error model showed that: 1) the explanatory power of microscale streetscapes was higher than that of macroscale built environment with R2 of 0.245 and 0.240, respectively, which is different from the prior finding that R2 is greater for macroscale built environment than for microscale streetscape; 2) sky and green view indexes were positively associated with running intensity, whereas visual crowdedness had a negative effect; 3) there were negative interactions of land use Herfindahl-Hirschman index with sky and green view indexes, while a positive interaction was observed for visual crowdedness. To conclude, greener, more open and less visually crowded streetscapes, can promote running behavior and enhance the benefits of land use mix as well. The findings highlight the importance of streetscapes in promoting running behavior, instead of a supplement to macroscale built environment.

PMID:39164681 | DOI:10.1186/s12889-024-19605-4

BMC Bioinformatics. 2024 Aug 20;25(1):269. doi: 10.1186/s12859-024-05894-4.

ABSTRACT

BACKGROUND: Fluorescence microscopy (FM) is an important and widely adopted biological imaging technique. Segmentation is often the first step in quantitative analysis of FM images. Deep neural networks (DNNs) have become the state-of-the-art tools for image segmentation. However, their performance on natural images may collapse under certain image corruptions or adversarial attacks. This poses real risks to their deployment in real-world applications. Although the robustness of DNN models in segmenting natural images has been studied extensively, their robustness in segmenting FM images remains poorly understood RESULTS: To address this deficiency, we have developed an assay that benchmarks robustness of DNN segmentation models using datasets of realistic synthetic 2D FM images with precisely controlled corruptions or adversarial attacks. Using this assay, we have benchmarked robustness of ten representative models such as DeepLab and Vision Transformer. We find that models with good robustness on natural images may perform poorly on FM images. We also find new robustness properties of DNN models and new connections between their corruption robustness and adversarial robustness. To further assess the robustness of the selected models, we have also benchmarked them on real microscopy images of different modalities without using simulated degradation. The results are consistent with those obtained on the realistic synthetic images, confirming the fidelity and reliability of our image synthesis method as well as the effectiveness of our assay.

CONCLUSIONS: Based on comprehensive benchmarking experiments, we have found distinct robustness properties of deep neural networks in semantic segmentation of FM images. Based on the findings, we have made specific recommendations on selection and design of robust models for FM image segmentation.

PMID:39164632 | DOI:10.1186/s12859-024-05894-4

Nat Immunol. 2024 Aug 20. doi: 10.1038/s41590-024-01888-9. Online ahead of print.

ABSTRACT

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and mRNA vaccination induce robust CD4+ T cell responses. Using single-cell transcriptomics, here, we evaluated CD4+ T cells specific for the SARS-CoV-2 spike protein in the blood and draining lymph nodes (dLNs) of individuals 3 months and 6 months after vaccination with the BNT162b2 mRNA vaccine. We analyzed 1,277 spike-specific CD4+ T cells, including 238 defined using Trex, a deep learning-based reverse epitope mapping method to predict antigen specificity. Human dLN spike-specific CD4+ follicular helper T (TFH) cells exhibited heterogeneous phenotypes, including germinal center CD4+ TFH cells and CD4+IL-10+ TFH cells. Analysis of an independent cohort of SARS-CoV-2-infected individuals 3 months and 6 months after infection found spike-specific CD4+ T cell profiles in blood that were distinct from those detected in blood 3 months and 6 months after BNT162b2 vaccination. Our findings provide an atlas of human spike-specific CD4+ T cell transcriptional phenotypes in the dLNs and blood following SARS-CoV-2 vaccination or infection.

PMID:39164479 | DOI:10.1038/s41590-024-01888-9

Commun Eng. 2024 Aug 20;3(1):110. doi: 10.1038/s44172-024-00252-x.

ABSTRACT

The value of luxury goods, particularly investment-grade gemstones, is influenced by their origin and authenticity, often resulting in differences worth millions of dollars. Traditional methods for determining gemstone origin and detecting treatments involve subjective visual inspections and a range of advanced analytical techniques. However, these approaches can be time-consuming, prone to inconsistencies, and lack automation. Here, we propose GEMTELLIGENCE, a novel deep learning approach enabling streamlined and consistent origin determination of gemstone origin and detection of treatments. GEMTELLIGENCE leverages convolutional and attention-based neural networks that combine the multi-modal heterogeneous data collected from multiple instruments. The algorithm attains predictive performance comparable to expensive laser-ablation inductively-coupled-plasma mass-spectrometry analysis and expert visual examination, while using input data from relatively inexpensive analytical methods. Our methodology represents an advancement in gemstone analysis, greatly enhancing automation and robustness throughout the analytical process pipeline.

PMID:39164470 | DOI:10.1038/s44172-024-00252-x

J Imaging Inform Med. 2024 Aug 20. doi: 10.1007/s10278-024-01221-8. Online ahead of print.

ABSTRACT

In clinical practice, the anatomical classification of pulmonary veins plays a crucial role in the preoperative assessment of atrial fibrillation radiofrequency ablation surgery. Accurate classification of pulmonary vein anatomy assists physicians in selecting appropriate mapping electrodes and avoids causing pulmonary arterial hypertension. Due to the diverse and subtly different anatomical classifications of pulmonary veins, as well as the imbalance in data distribution, deep learning models often exhibit poor expression capability in extracting deep features, leading to misjudgments and affecting classification accuracy. Therefore, in order to solve the problem of unbalanced classification of left atrial pulmonary veins, this paper proposes a network integrating multi-scale feature-enhanced attention and dual-feature extraction classifiers, called DECNet. The multi-scale feature-enhanced attention utilizes multi-scale information to guide the reinforcement of deep features, generating channel weights and spatial weights to enhance the expression capability of deep features. The dual-feature extraction classifier assigns a fixed number of channels to each category, equally evaluating all categories, thus alleviating the learning bias and overfitting caused by data imbalance. By combining the two, the expression capability of deep features is strengthened, achieving accurate classification of left atrial pulmonary vein morphology and providing support for subsequent clinical treatment. The proposed method is evaluated on datasets provided by the People's Hospital of Liaoning Province and the publicly available DermaMNIST dataset, achieving average accuracies of 78.81% and 83.44%, respectively, demonstrating the effectiveness of the proposed approach.

PMID:39164454 | DOI:10.1007/s10278-024-01221-8