Sci Rep. 2024 Mar 19;14(1):6525. doi: 10.1038/s41598-024-57227-3.

ABSTRACT

The rise of bots that mimic human behavior represents one of the most pressing threats to healthy information environments on social media. Many bots are designed to increase the visibility of low-quality content, spread misinformation, and artificially boost the reach of brands and politicians. These bots can also disrupt civic action coordination, such as by flooding a hashtag with spam and undermining political mobilization. Social media platforms have recognized these malicious bots' risks and implemented strict policies and protocols to block automated accounts. However, effective bot detection methods for Spanish are still in their early stages. Many studies and tools used for Spanish are based on English-language models and lack performance evaluations in Spanish. In response to this need, we have developed a method for detecting bots in Spanish called Botcheck. Botcheck was trained on a collection of Spanish-language accounts annotated in Twibot-20, a large-scale dataset featuring thousands of accounts annotated by humans in various languages. We evaluated Botcheck's performance on a large set of labeled accounts and found that it outperforms other competitive methods, including deep learning-based methods. As a case study, we used Botcheck to analyze the 2021 Chilean Presidential elections and discovered evidence of bot account intervention during the electoral term. In addition, we conducted an external validation of the accounts detected by Botcheck in the case study and found our method to be highly effective. We have also observed differences in behavior among the bots that are following the social media accounts of official presidential candidates.

PMID:38499853 | DOI:10.1038/s41598-024-57227-3

Sci Rep. 2024 Mar 18;14(1):6473. doi: 10.1038/s41598-024-57247-z.

ABSTRACT

Antioxidant peptides (AOPs) are highly valued in food and pharmaceutical industries due to their significant role in human function. This study introduces a novel approach to identifying robust AOPs using a deep generative model based on sequence representation. Through filtration with a deep-learning classification model and subsequent clustering via the Butina cluster algorithm, twelve peptides (GP1-GP12) with potential antioxidant capacity were predicted. Density functional theory (DFT) calculations guided the selection of six peptides for synthesis and biological experiments. Molecular orbital representations revealed that the HOMO for these peptides is primarily localized on the indole segment, underscoring its pivotal role in antioxidant activity. All six synthesized peptides exhibited antioxidant activity in the DPPH assay, while the hydroxyl radical test showed suboptimal results. A hemolysis assay confirmed the non-hemolytic nature of the generated peptides. Additionally, an in silico investigation explored the potential inhibitory interaction between the peptides and the Keap1 protein. Analysis revealed that ligands GP3, GP4, and GP12 induced significant structural changes in proteins, affecting their stability and flexibility. These findings highlight the capability of machine learning approaches in generating novel antioxidant peptides.

PMID:38499731 | DOI:10.1038/s41598-024-57247-z

IEEE Trans Vis Comput Graph. 2024 Mar 18;PP. doi: 10.1109/TVCG.2024.3378309. Online ahead of print.

ABSTRACT

Mesh denoising is a crucial technology that aims to recover a high-fidelity 3D mesh from a noise-corrupted one. Deep learning methods, particularly graph convolutional networks (GCNs) based mesh denoisers, have demonstrated their effectiveness in removing various complex real-world noises while preserving authentic geometry. However, it is still a quite challenging work to faithfully regress uncontaminated normals and vertices on meshes with irregular topology. In this paper, we propose a novel pipeline that incorporates two parallel normal-aware and vertex-aware branches to achieve a balance between smoothness and geometric details while maintaining the flexibility of surface topology. We introduce ResGEM, a new GCN, with multi-scale embedding modules and residual decoding structures to facilitate normal regression and vertex modification for mesh denoising. To effectively extract multi-scale surface features while avoiding the loss of topological information caused by graph pooling or coarsening operations, we encode the noisy normal and vertex graphs using four edge-conditioned embedding modules (EEMs) at different scales. This allows us to obtain favorable feature representations with multiple receptive field sizes. Formulating the denoising problem into a residual learning problem, the decoder incorporates residual blocks to accurately predict true normals and vertex offsets from the embedded feature space. Moreover, we propose novel regularization terms in the loss function that enhance the smoothing and generalization ability of our network by imposing constraints on normal consistency. Comprehensive experiments have been conducted to demonstrate the superiority of our method over the state-of-the-art on both synthetic and real-scanned datasets.

PMID:38498760 | DOI:10.1109/TVCG.2024.3378309

IEEE Trans Biomed Eng. 2024 Mar 18;PP. doi: 10.1109/TBME.2024.3378508. Online ahead of print.

ABSTRACT

OBJECTIVE: Growing attention has been paid recently to electrocardiogram (ECG) based obstructive sleep apnea (OSA) detection, with some progresses been made on this topic. However, the lack of data, low data quality, and incomplete data labeling hinder the application of deep learning to OSA detection, which in turn affects the overall generalization capacity of the network.

METHODS: To address these issues, we propose the ResT-ECGAN framework. It uses a one-dimensional generative adversarial network (ECGAN) for sample generation, and integrates it into ResTNet for OSA detection. ECGAN filters the generated ECG signals by incorporating the concept of fuzziness, effectively increasing the amount of high-quality data. ResT-Net not only alleviates the problems caused by deepening the network but also utilizes multihead attention mechanisms to parallelize sequence processing and extract more valuable OSA detection features by leveraging contextual information.

RESULTS: Through extensive experiments, we verify that ECGAN can effectively improve the OSA detection performance of ResT-Net. Using only ResT-Net for detection, the accuracy on the Apnea-ECG and private databases is 0.885 and 0.837, respectively. By adding ECGAN-generated data augmentation, the accuracy is increased to 0.893 and 0.848, respectively.

CONCLUSION AND SIGNIFICANCE: Comparing with the state-of-the-art deep learning methods, our method outperforms them in terms of accuracy. This study provides a new approach and solution to improve OSA detection in situations with limited labeled samples.

PMID:38498752 | DOI:10.1109/TBME.2024.3378508

IEEE J Biomed Health Inform. 2024 Mar 18;PP. doi: 10.1109/JBHI.2024.3377631. Online ahead of print.

ABSTRACT

Drug combination therapy is crucial in cancer treatment, but accurately predicting drug synergy remains a challenge due to the complexity of drug combinations. Machine learning and deep learning models have shown promise in drug combination prediction, but they suffer from issues such as gradient vanishing, overfitting, and parameter tuning. To address these problems, the deep drug synergy prediction network, named as EDNet is proposed that leverages a modified triangular mutation-based differential evolution algorithm. This algorithm evolves the initial connection weights and architecture-related attributes of the deep bidirectional mixture density network, improving its performance and addressing the aforementioned issues. EDNet automatically extracts relevant features and provides conditional probability distributions of output attributes. The performance of EDNet is evaluated over two well-known drug synergy datasets, NCI-ALMANAC and deep-synergy. The results demonstrate that EDNet outperforms the competing models. EDNet facilitates efficient drug interactions, enhancing the overall effectiveness of drug combinations for improved cancer treatment outcomes.

PMID:38498748 | DOI:10.1109/JBHI.2024.3377631

IEEE Trans Neural Syst Rehabil Eng. 2024 Mar 18;PP. doi: 10.1109/TNSRE.2024.3377698. Online ahead of print.

ABSTRACT

The utilization of deep learning techniques for decoding visual perception images from brain activity recorded by functional magnetic resonance imaging (fMRI) has garnered considerable attention in recent research. However, reconstructed images from previous studies still suffer from low quality or unreliability. Moreover, the complexity inherent to fMRI data, characterized by high dimensionality and low signal-to-noise ratio, poses significant challenges in extracting meaningful visual information for perceptual reconstruction. In this regard, we proposes a novel neural decoding model, named the hierarchical semantic generative adversarial network (HS-GAN), inspired by the hierarchical encoding of the visual cortex and the homology theory of convolutional neural networks (CNNs), which is capable of reconstructing perceptual images from fMRI data by leveraging the hierarchical and semantic representations. The experimental results demonstrate that HS-GAN achieved the best performance on Horikawa2017 dataset (histogram similarity: 0.447, SSIM-Acc: 78.9%, Peceptual-Acc: 95.38%, AlexNet(2): 96.24% and AlexNet(5): 94.82%) over existing advanced methods, indicating improved naturalness and fidelity of the reconstructed image. The versatility of the HS-GAN was also highlighted, as it demonstrated promising generalization capabilities in reconstructing handwritten digits, achieving the highest SSIM (0.783±0.038), thus extending its application beyond training solely on natural images.

PMID:38498745 | DOI:10.1109/TNSRE.2024.3377698

IEEE Trans Neural Syst Rehabil Eng. 2024 Mar 18;PP. doi: 10.1109/TNSRE.2024.3378112. Online ahead of print.

ABSTRACT

Balanced posture without dizziness is achieved via harmonious coordination of visual, vestibular, and somatosensory systems. Specific frequency bands of center of pressure (COP) signals during quiet standing are closely related to the sensory inputs of the sensorimotor system. In this study, we proposed a deep learning-based novel protocol using the COP signal frequencies to estimate the equilibrium score (ES), a sensory system contribution. Sensory organization test was performed with normal controls (n=125), patients with Meniere's disease (n=72) and vestibular neuritis (n=105). The COP signals preprocessed via filtering, detrending and augmenting during quiet standing were converted to frequency domains utilizing Short-time Fourier Transform. Four different types of CNN backbone including GoogleNet, ResNet-18, SqueezeNet, and VGG16 were trained and tested using the frequency transformed data of COP and the ES under conditions #2 to #6. Additionally, the 100 original output classes (1 to 100 ESs) were encoded into 50, 20, 10 and 5 sub-classes to improve the performance of the prediction model. Absolute difference between the measured and predicted ES was about 1.7 (ResNet-18 with encoding of 20 sub-classes). The average error of each sensory analysis calculated using the measured ES and predicted ES was approximately 1.0%. The results suggest that the sensory system contribution of patients with dizziness can be quantitatively assessed using only the COP signal from a single test of standing posture. This study has potential to reduce balance testing time (spent on six conditions with three trials each in sensory organization test) and the size of computerized dynamic posturography (movable visual surround and force plate), and helps achieve the widespread application of the balance assessment.

PMID:38498740 | DOI:10.1109/TNSRE.2024.3378112

Plants (Basel). 2024 Feb 14;13(4):522. doi: 10.3390/plants13040522.

ABSTRACT

Phenological studies have a crucial role in the global change context. The Mediterranean basin constitutes a key study site since strong climate change impacts are expected, particularly in mountain areas such as Sierra Nevada, where we focus. Specifically, we delve into phenological changes in endemic vascular plants over time by analysing data at three scales: entire massif, altitudinal ranges, and particular species, seeking to contribute to stopping biodiversity loss. For this, we analysed 5262 samples of 2129 herbarium sheets from Sierra Nevada, dated from 1837 to 2019, including reproductive structure, complete collection date, and precise location. We found a generalized advancement in phenology at all scales, and particularly in flowering onset and flowering peak. Thus, plants flower on average 11 days earlier now than before the 1970s. Although similar trends have been confirmed for many territories and species, we address plants that have been studied little in the past regarding biotypes and distribution, and which are relevant for conservation. Thus, we analysed phenological changes in endemic plants, mostly threatened, from a crucial hotspot within the Mediterranean hotspot, which is particularly vulnerable to global warming. Our results highlight the urgency of phenological studies by species and of including ecological interactions and effects on their life cycles.

PMID:38498521 | DOI:10.3390/plants13040522

Oral Radiol. 2024 Mar 18. doi: 10.1007/s11282-024-00741-x. Online ahead of print.

ABSTRACT

OBJECTIVES: The aim of this study was to develop an assessment tool for automatic detection of dental caries in periapical radiographs using convolutional neural network (CNN) architecture.

METHODS: A novel diagnostic model named ResNet + SAM was established using numerous periapical radiographs (4278 images) annotated by medical experts to automatically detect dental caries. The performance of the model was compared to the traditional CNNs (VGG19, ResNet-50), and the dentists. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique shows the region of interest in the image for the CNNs.

RESULTS: ResNet + SAM demonstrated significantly improved performance compared to the modified ResNet-50 model, with an average F1 score of 0.886 (95% CI 0.855-0.918), accuracy of 0.885 (95% CI 0.862-0.901) and AUC of 0.954 (95% CI 0.924-0.980). The comparison between the performance of the model and the dentists revealed that the model achieved higher accuracy than that of the junior dentists. With the assist of the tool, the dentists achieved superior metrics with a mean F1 score of 0.827 and the interobserver agreement for dental caries is enhanced from 0.592/0.610 to 0.706/0.723.

CONCLUSIONS: According to the results obtained from the experiments, the automatic assessment tool using the ResNet + SAM model shows remarkable performance and has excellent possibilities in identifying dental caries. The use of the assessment tool in clinical practice can be of great benefit as a clinical decision-making support in dentistry and reduce the workload of dentists.

PMID:38498223 | DOI:10.1007/s11282-024-00741-x

Strahlenther Onkol. 2024 Mar 18. doi: 10.1007/s00066-024-02221-x. Online ahead of print.

ABSTRACT

OBJECTIVE: This study aims to examine the ability of deep learning (DL)-derived imaging features for the prediction of radiation pneumonitis (RP) in locally advanced non-small-cell lung cancer (LA-NSCLC) patients.

MATERIALS AND METHODS: The study cohort consisted of 90 patients from the Fudan University Shanghai Cancer Center and 59 patients from the Affiliated Hospital of Jiangnan University. Occurrences of RP were used as the endpoint event. A total of 512 3D DL-derived features were extracted from two regions of interest (lung-PTV and PTV-GTV) delineated on the pre-radiotherapy planning CT. Feature selection was done using LASSO regression, and the classification models were built using the multilayered perceptron method. Performances of the developed models were evaluated by receiver operating characteristic curve analysis. In addition, the developed models were supplemented with clinical variables and dose-volume metrics of relevance to search for increased predictive value.

RESULTS: The predictive model using DL features derived from lung-PTV outperformed the one based on features extracted from PTV-GTV, with AUCs of 0.921 and 0.892, respectively, in the internal test dataset. Furthermore, incorporating the dose-volume metric V30Gy into the predictive model using features from lung-PTV resulted in an improvement of AUCs from 0.835 to 0.881 for the training data and from 0.690 to 0.746 for the validation data, respectively (DeLong p < 0.05).

CONCLUSION: Imaging features extracted from pre-radiotherapy planning CT using 3D DL networks could predict radiation pneumonitis and may be of clinical value for risk stratification and toxicity management in LA-NSCLC patients.

CLINICAL RELEVANCE STATEMENT: Integrating DL-derived features with dose-volume metrics provides a promising noninvasive method to predict radiation pneumonitis in LA-NSCLC lung cancer radiotherapy, thus improving individualized treatment and patient outcomes.

PMID:38498173 | DOI:10.1007/s00066-024-02221-x

Med Biol Eng Comput. 2024 Mar 18. doi: 10.1007/s11517-024-03026-x. Online ahead of print.

ABSTRACT

Segmentation of tumors in ultrasound (US) images of the breast is a critical issue in medical imaging. Due to the poor quality of US images and the varying specifications of US machines, segmentation and classification of abnormalities present difficulties even for trained radiologists. The paper aims to introduce a novel AI-based hybrid model for US segmentation that offers high accuracy, requires relatively smaller datasets, and is capable of handling previously unseen data. The software can be used for diagnostics and the US-guided biopsies. A unique and robust hybrid approach that combines deep learning (DL) and multi-agent artificial life (AL) has been introduced. The algorithms are verified on three US datasets. The method outperforms 14 selected state-of-the-art algorithms applied to US images characterized by complex geometry and high level of noise. The paper offers an original classification of the images and tests to analyze the limits of the DL. The model has been trained and verified on 1264 ultrasound images. The images are in the JPEG and PNG formats. The age of the patients ranges from 22 to 73 years. The 14 benchmark algorithms include deformable shapes, edge linking, superpixels, machine learning, and DL methods. The tests use eight-region shape- and contour-based evaluation metrics. The proposed method (DL-AL) produces excellent results in terms of the dice coefficient (region) and the relative Hausdorff distance H3 (contour-based) as follows: the easiest image complexity level, Dice = 0.96 and H3 = 0.26; the medium complexity level, Dice = 0.91 and H3 = 0.82; and the hardest complexity level, Dice = 0.90 and H3 = 0.84. All other metrics follow the same pattern. The DL-AL outperforms the second best (Unet-based) method by 10-20%. The method has been also tested by a series of unconventional tests. The model was trained on low complexity images and applied to the entire set of images. These results are summarized below. (1) Only the low complexity images have been used for training (68% unknown images): Dice = 0.80 and H3 = 2.01. (2) The low and the medium complexity images have been used for training (51% unknown images): Dice = 0.86 and H3 = 1.32. (3) The low, medium, and hard complexity images have been used for training (35% unknown images): Dice = 0.92 and H3 = 0.76. These tests show a significant advantage of DL-AL over 30%. A video demo illustrating the algorithm is at http://tinyurl.com/mr4ah687 .

PMID:38498125 | DOI:10.1007/s11517-024-03026-x

J Am Med Inform Assoc. 2024 Mar 18:ocae049. doi: 10.1093/jamia/ocae049. Online ahead of print.

ABSTRACT

OBJECTIVES: Metabolic disease in children is increasing worldwide and predisposes a wide array of chronic comorbid conditions with severe impacts on quality of life. Tools for early detection are needed to promptly intervene to prevent or slow the development of these long-term complications.

MATERIALS AND METHODS: No clinically available tools are currently in widespread use that can predict the onset of metabolic diseases in pediatric patients. Here, we use interpretable deep learning, leveraging longitudinal clinical measurements, demographical data, and diagnosis codes from electronic health record data from a large integrated health system to predict the onset of prediabetes, type 2 diabetes (T2D), and metabolic syndrome in pediatric cohorts.

RESULTS: The cohort included 49 517 children with overweight or obesity aged 2-18 (54.9% male, 73% Caucasian), with a median follow-up time of 7.5 years and mean body mass index (BMI) percentile of 88.6%. Our model demonstrated area under receiver operating characteristic curve (AUC) accuracies up to 0.87, 0.79, and 0.79 for predicting T2D, metabolic syndrome, and prediabetes, respectively. Whereas most risk calculators use only recently available data, incorporating longitudinal data improved AUCs by 13.04%, 11.48%, and 11.67% for T2D, syndrome, and prediabetes, respectively, versus models using the most recent BMI (P < 2.2 × 10-16).

DISCUSSION: Despite most risk calculators using only the most recent data, incorporating longitudinal data improved the model accuracies because utilizing trajectories provides a more comprehensive characterization of the patient's health history. Our interpretable model indicated that BMI trajectories were consistently identified as one of the most influential features for prediction, highlighting the advantages of incorporating longitudinal data when available.

PMID:38497983 | DOI:10.1093/jamia/ocae049

J Am Med Inform Assoc. 2024 Mar 18:ocae050. doi: 10.1093/jamia/ocae050. Online ahead of print.

ABSTRACT

OBJECTIVE: Passive monitoring of touchscreen interactions generates keystroke dynamic signals that can be used to detect and track neurological conditions such as Parkinson's disease (PD) and psychomotor impairment with minimal burden on the user. However, this typically requires datasets with clinically confirmed labels collected in standardized environments, which is challenging, especially for a large subject pool. This study validates the efficacy of a self-supervised learning method in reducing the reliance on labels and evaluates its generalizability.

MATERIALS AND METHODS: We propose a new type of self-supervised loss combining Barlow Twins loss, which attempts to create similar feature representations with reduced feature redundancy for samples coming from the same subject, and a Dissimilarity loss, which promotes uncorrelated features for samples generated by different subjects. An encoder is first pre-trained using this loss on unlabeled data from an uncontrolled setting, then fine-tuned with clinically validated data. Our experiments test the model generalizability with controls and subjects with PD on 2 independent datasets.

RESULTS: Our approach showed better generalization compared to previous methods, including a feature engineering strategy, a deep learning model pre-trained on Parkinsonian signs, and a traditional supervised model.

DISCUSSION: The absence of standardized data acquisition protocols and the limited availability of annotated datasets compromise the generalizability of supervised models. In these contexts, self-supervised models offer the advantage of learning more robust patterns from the data, bypassing the need for ground truth labels.

CONCLUSION: This approach has the potential to accelerate the clinical validation of touchscreen typing software for neurodegenerative diseases.

PMID:38497957 | DOI:10.1093/jamia/ocae050

Elife. 2024 Mar 18;12:RP90502. doi: 10.7554/eLife.90502.

ABSTRACT

Intravital microscopy has revolutionized live-cell imaging by allowing the study of spatial-temporal cell dynamics in living animals. However, the complexity of the data generated by this technology has limited the development of effective computational tools to identify and quantify cell processes. Amongst them, apoptosis is a crucial form of regulated cell death involved in tissue homeostasis and host defense. Live-cell imaging enabled the study of apoptosis at the cellular level, enhancing our understanding of its spatial-temporal regulation. However, at present, no computational method can deliver robust detection of apoptosis in microscopy timelapses. To overcome this limitation, we developed ADeS, a deep learning-based apoptosis detection system that employs the principle of activity recognition. We trained ADeS on extensive datasets containing more than 10,000 apoptotic instances collected both in vitro and in vivo, achieving a classification accuracy above 98% and outperforming state-of-the-art solutions. ADeS is the first method capable of detecting the location and duration of multiple apoptotic events in full microscopy timelapses, surpassing human performance in the same task. We demonstrated the effectiveness and robustness of ADeS across various imaging modalities, cell types, and staining techniques. Finally, we employed ADeS to quantify cell survival in vitro and tissue damage in mice, demonstrating its potential application in toxicity assays, treatment evaluation, and inflammatory dynamics. Our findings suggest that ADeS is a valuable tool for the accurate detection and quantification of apoptosis in live-cell imaging and, in particular, intravital microscopy data, providing insights into the complex spatial-temporal regulation of this process.

PMID:38497754 | DOI:10.7554/eLife.90502

J Biomol Struct Dyn. 2024 Mar 18:1-6. doi: 10.1080/07391102.2024.2326671. Online ahead of print.

ABSTRACT

Endothelial cells produce a semipermeable barrier known as the blood-brain barrier (BBB) to keep undesired chemicals out of the central nervous system (CNS). However, this barrier also restricts the exploration of potential new medications due to insufficient exposure. To address this challenge, machine learning (ML) algorithms can be useful to predict the BBB permeability of chemical compounds. Support vector machines, continuous neural networks, and deep learning approaches have been used to identify compounds that can penetrate the BBB. However, predicting BBB permeability based solely on chemical structure can be difficult. In the current research, we developed an ML model using a large dataset to predict BBB permeability, which could be used for early-stage drug screening of potential CNS medications. Our artificial neural network ANN algorithm exhibited an accuracy of 0.94, specificity of 0.83, sensitivity of 0.97, AUC of 0.96, and MCC of 0.83. These metrics suggest that our model has a high accuracy rate in predicting BBB permeability and therefore has the potential to advance drug discovery efforts in the CNS. This study's outcomes demonstrate the potential for ML models to predict BBB permeability accurately, aiding in the identification of new CNS therapeutic options.Communicated by Ramaswamy H. Sarma.

PMID:38497749 | DOI:10.1080/07391102.2024.2326671

ACS Omega. 2024 Feb 27;9(10):12027-12036. doi: 10.1021/acsomega.3c09735. eCollection 2024 Mar 12.

ABSTRACT

With the increasingly widespread application of deep learning technology in the field of coal mines, the image recognition of mine water inrush has become a hot research topic. Underground environments are complex, and images have a high noise and low brightness. Additionally, mine water inrush is accidental, and few actual image samples are available. Therefore, this paper proposes an algorithm that recognizes mine water inrush images based on few-shot deep learning. According to the characteristics of images with coal wall water seepage, a bilinear neural network was used to extract the image features and enhance the network's fine-grained image recognition. First, features were extracted using a bilinear convolutional neural network. Second, the network was pre-trained based on cosine similarity. Finally, the network was fine-tuned for the predicted image. For single-line feature extraction, the method is compared with big data and few-shot learning. According to the experimental results, the recognition rate reaches 95.2% for few-shot learning based on a bilinear neural network, thus demonstrating its effectiveness.

PMID:38496943 | PMC:PMC10938431 | DOI:10.1021/acsomega.3c09735

Heliyon. 2024 Mar 10;10(6):e27937. doi: 10.1016/j.heliyon.2024.e27937. eCollection 2024 Mar 30.

ABSTRACT

BACKGROUND: Coronary artery disease (CAD) in type 2 diabetes mellitus (T2DM) patients often presents diffuse lesions, with extensive calcification, and it is time-consuming to measure coronary artery calcium score (CACS).

OBJECTIVES: To explore the predictive ability of deep learning (DL)-based CACS for obstructive CAD and hemodynamically significant CAD in T2DM.

METHODS: 469 T2DM patients suspected of CAD who accepted CACS scan and coronary CT angiography between January 2013 and December 2020 were enrolled. Obstructive CAD was defined as diameter stenosis ≥50%. Hemodynamically significant CAD was defined as CT-derived fractional flow reserve ≤0.8. CACS was calculated with a fully automated method based on DL algorithm. Logistic regression was applied to determine the independent predictors. The predictive performance was evaluated with area under receiver operating characteristic curve (AUC).

RESULTS: DL-CACS (adjusted odds ratio (OR): 1.005; 95% CI: 1.003-1.006; P ＜ 0.001) was significantly associated with obstructive CAD. DL-CACS (adjusted OR:1.003; 95% CI: 1.002-1.004; P ＜ 0.001) was also an independent predictor for hemodynamically significant CAD. The AUCs, sensitivities, specificities, positive predictive values and negative predictive values of DL-CACS for obstructive CAD and hemodynamically significant CAD were 0.753 (95% CI: 0.712-0.792), 75.9%, 66.5%, 74.8%, 67.8% and 0.769 (95% CI: 0.728-0.806), 80.7%, 62.1%, 59.6% and 82.3% respectively. It took 1.17 min to perform automated measurement of DL-CACS in total, which was significantly less than manual measurement of 1.73 min (P ＜ 0.001).

CONCLUSIONS: DL-CACS, with less time-consuming, can accurately and effectively predict obstructive CAD and hemodynamically significant CAD in T2DM.

PMID:38496873 | PMC:PMC10944251 | DOI:10.1016/j.heliyon.2024.e27937

Heliyon. 2024 Feb 28;10(6):e27178. doi: 10.1016/j.heliyon.2024.e27178. eCollection 2024 Mar 30.

ABSTRACT

The progress of deep learning technology has made image classification an important application field. Image style classification is a complex task involving the recognition of the whole picture, including the recognition of salient features and detailed features. This study is based on the ResNet algorithm and has improved its Resnet 50 version with excellent performance. In the model architecture, we introduce blur pool operation and replace the traditional Relu function with Celu activation function. In addition, the triplet attention mechanism was integrated to further enhance the model performance. Through a series of experiments, it is found that the improved ResNet50 model has the highest classification accuracy of 80.6% on large-scale image data sets, which is 11.7% higher than the traditional ResNet50 model. In terms of recognition of similar style images, the model incorporating triplet attention demonstrated higher average accuracy (74%) and recall (82%). This improvement has achieved certain results and has certain technical reference value for various styles of image classification fields.

PMID:38496868 | PMC:PMC10944206 | DOI:10.1016/j.heliyon.2024.e27178

Heliyon. 2024 Mar 8;10(6):e27894. doi: 10.1016/j.heliyon.2024.e27894. eCollection 2024 Mar 30.

ABSTRACT

Faults in photovoltaic (PV) modules may occur due to various environmental and physical factors. To prevent faults and minimize investment losses, fault diagnosis is crucial to ensure uninterrupted power production, extended operational lifespan, and a high level of safety in PV modules. Recent advancements in inspection techniques and instrumentation have significantly reduced the cost and time required for inspections. A novel stacking-based ensemble approach was performed in the present study for the accurate classification of PV module visible faults. The present study utilizes AlexNet (a pre-trained network) to extract image features from the aerial images of PV modules with the aid of MATLAB software. Furthermore, J48 algorithm was applied to perform the feature selection task to determine the most relevant features. The features derived as output from the J48 algorithm were passed onto train eight base classifiers namely, Naïve Bayes, logistic regression (LR), J48, random forest (RF), multilayer perceptron (MLP), logistic model tree (LMT), support vector machines (SVM) and k-nearest neighbors (kNN). The best performing five classifiers on the front run with higher classification accuracies were selected to formulate three categories of stacking ensemble groups as follows: (i) three-class ensemble (SVM, kNN, and LMT), (ii) four-class ensemble (SVM, kNN, LMT, and RF), and (iii) five-class ensemble (SVM, kNN, LMT, RF, and MLP). A comparison in the performance of the aforementioned stacked ensembles was evaluated with different meta classifiers. The obtained results infer that the four-class stacking ensemble model (SVM, kNN, LMT, and RF) with RF as the predictor achieved the highest possible classification accuracy of 99.04%.

PMID:38496862 | PMC:PMC10944267 | DOI:10.1016/j.heliyon.2024.e27894

J Pathol Inform. 2024 Feb 15;15:100368. doi: 10.1016/j.jpi.2024.100368. eCollection 2024 Dec.

ABSTRACT

Soft tissue tumors (STTs) pose diagnostic and therapeutic challenges due to their rarity, complexity, and morphological overlap. Accurate differentiation between benign and malignant STTs is important to set treatment directions, however, this task can be difficult. The integration of machine learning and artificial intelligence (AI) models can potentially be helpful in classifying these tumors. The aim of this study was to investigate AI and machine learning tools in the classification of STT into benign and malignant categories. This study consisted of three components: (1) Evaluation of whole-slide images (WSIs) to classify STT into benign and malignant entities. Five specialized soft tissue pathologists from different medical centers independently reviewed 100 WSIs, representing 100 different cases, with limited clinical information and no additional workup. The results showed an overall concordance rate of 70.4% compared to the reference diagnosis. (2) Identification of cell-specific parameters that can distinguish benign and malignant STT. Using an image analysis software (QuPath) and a cohort of 95 cases, several cell-specific parameters were found to be statistically significant, most notably cell count, nucleus/cell area ratio, nucleus hematoxylin density mean, and cell max caliper. (3) Evaluation of machine learning library (Scikit-learn) in differentiating benign and malignant STTs. A total of 195 STT cases (156 cases in the training group and 39 cases in the validation group) achieved approximately 70% sensitivity and specificity, and an AUC of 0.68. Our limited study suggests that the use of WSI and AI in soft tissue pathology has the potential to enhance diagnostic accuracy and identify parameters that can differentiate between benign and malignant STTs. We envision the integration of AI as a supportive tool to augment the pathologists' diagnostic capabilities.

PMID:38496781 | PMC:PMC10940995 | DOI:10.1016/j.jpi.2024.100368