A New Benchmark and Low Computational Cost Localization Method for Cephalometric Analysis

Manufacturing process of Lithium-ion battery electrode has a direct impact on the resulting practical properties of the cell such as durability, safety and overall performance. In this scenario, together with experimental efforts to understand the correlation between manufacturing process parameters and final overall electrode performance, computational tools have shown the potential to produce insights on the manufacturing properties interdependencies. The ARTISTIC initiative [1] pioneered the development of a series of computational 3D-resolved physics-based models describing each step of the manufacturing process following a sequential pattern, going from the slurry phase, through the drying phase, to produce a calendered electrode. Such physics-based models have the capability to predict how manufacturing parameters impact the electrode microstructure. At the end of each phase the output microstructure is carefully validated with experimental data, assuring that the model is in good agreement with real properties. For the calendering phase, the Discrete Element Method (DEM) is used for the model simulation.One of the main limitations of the DEM simulations is their high computational cost, preventing their direct application in electrode optimization loops. In this matter, and given the great amount of already validated data that was produced in our previous works by using the ARTISTIC model, we take one step forward in the development of a new generation model employing machine learning (ML) techniques to accelerate the physics-based simulations but keeping their accuracy. In this presentation we report a novel time-dependent deep learning (DL) model of the battery electrodes manufacturing process. The DL model is demonstrated for calendering of nickel manganese cobalt (NMC111) electrodes, and trained with time-series data arising from physics-based DEM simulations coming from the ARTISTIC physics-based modeling pipeline [2]. The innovative DL model presented in this work can predict an electrode microstructure evolution over time at a given compression degree during calendering and provide the associated final relaxed electrode microstructure. Here we used the formulation of 96% AM and 4% CBD as a proof of concept.The DL model predictions are validated by comparing data evaluation metrics (e.g., mean square error (MSE) and R2 score) and electrode functional metrics (contact surface area, porosity, diffusivity, and tortuosity factor), showing very good accuracy with respect to the DEM simulations (all the properties are above 90% accurate when compared to target data). Regarding transport properties and given the high accuracy of the DL model to predict tortuosity factor and porosity values we can conclude that the model correctly predicts the effect of the calendering on the transport properties since tortuosity factor and porosity has a high impact on the effective transport properties of Li-ions in the electrolyte. The DL model can remarkably capture the elastic recovery of the electrode upon compression (spring-back phenomenon) and the main 3D electrode microstructure features without using the functional descriptors during its training. In terms of computational cost, the DL model performs a timestep in 15 seconds (wall time) while the DEM model performs an equivalent time step in ∼47 minutes (wall time). Given the DL model significant lower computational cost than the DEM simulations, it paves the way toward quasi-real-time optimization loops of the 3D electrode architecture predicting the calendering conditions to adopt in order to obtain the desired electrode performance. Moreover, we consider that our model has tremendous potential to grow in several aspects such as accuracy and predictability. Therefore, our incoming efforts will be focused on continuing the development of the model and testing it for other formulations and in other manufacturing stages.[1] ARTISTIC Project website. https://www.erc-artistic.eu.[2] D. E. Galvez-Aranda, T. L. Dinh, U. Vijay, F. M. Zanotto, A. A. Franco, Time-Dependent Deep Learning Manufacturing Process Model for Battery Electrode Microstructure Prediction. Adv. Energy Mater. 2024, 2400376. https://doi.org/10.1002/aenm.202400376 Figure 1

The Internet of Things (IoT) holds transformative potential in fields such as power grid optimization, defense networks, and healthcare. However, the constrained processing capacities and resource limitations of IoT networks make them especially susceptible to cyber threats. This study addresses the problem of detecting intrusions in IoT environments by evaluating the performance of deep learning (DL) models under different data and algorithmic conditions. We conducted a comparative analysis of three widely used DL models—Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Bidirectional LSTM (biLSTM)—across four benchmark IoT intrusion detection datasets: BoTIoT, CiCIoT, ToNIoT, and WUSTL-IIoT-2021. Each model was assessed under balanced and imbalanced dataset configurations and evaluated using three loss functions (cross-entropy, focal loss, and dual focal loss). By analyzing model efficacy across these datasets, we highlight the importance of generalizability and adaptability to varied data characteristics that are essential for real-world applications. The results demonstrate that the CNN trained using the cross-entropy loss function consistently outperforms the other models, particularly on balanced datasets. On the other hand, LSTM and biLSTM show strong potential in temporal modeling, but their performance is highly dependent on the characteristics of the dataset. By analyzing the performance of multiple DL models under diverse datasets, this research provides actionable insights for developing secure, interpretable IoT systems that can meet the challenges of designing a secure IoT system.

Background: Mandibular osteoradionecrosis (ORN) is a severe late toxicity of head and neck radiotherapy (RT) characterized by non-healing necrotic bone, with an estimated incidence of 4-8% in the modern IMRT era [1]. Multiple patient, tumor, and treatment factors (e.g., dental extractions, tumor proximity, smoking, and high radiation dose) all contribute to ORN [1,2]. Predictive models that quantify individualized ORN risk could help guide preventive strategies, but there were no validated normal tissue complication probability (NTCP) models for ORN until recently [3]. This study creates a multi-institutional deep learning (DL) model that uses 3D dose distributions ("dosiomic" data) and clinical variables to predict mandibular ORN, with the hypothesis that a large, diverse dataset will improve predictive performance and generalizability. Methods: A retrospective multi-institutional cohort of 1,184 head and neck cancer patients (389 ORN cases) from seven centers was created [4]. Clinical, demographic, and dosimetric information (3D mandibular dose-volume maps and dose-volume histogram metrics) was gathered. The mandibular dose distribution was processed using late fusion convolutional neural network (DenseNet architecture), with clinical risk factors integrated via late fusion. Model training applied 5-fold cross-validation to 80% of the pooled data and was tested on an internal test set (20%) and an external hold-out institution. Performance was evaluated using the area under the ROC curve (AUC), calibration, and F1-score. Results: ORN patients received significantly higher mandibular radiation doses (median D30% and V70Gy), as well as a higher rate of pre-RT dental extractions and smoking [4]. The multi-modal DL model had an internal test AUC of ~0.72 and good calibration, similar to a logistic regression model (AUC ~0.69) [3]. In an independent external cohort, performance was lower (AUC ~0.60), indicating institutional heterogeneity [3]. In terms of discrimination and calibration, a late-fusion DL model performed slightly better than early-fusion and single-modality models [3]. Conclusions: This large-scale study demonstrates the feasibility of predicting ORN risk with multi-institutional data and deep learning. While the DL model performed similarly to traditional models, it offers spatial dose-response insights. Key predictors included mandibular dose-volume metrics (D30%, V70Gy) and dental risk factors [4]. Further research will concentrate on incorporating advanced architectures (e.g., transformers) and addressing domain shifts in order to improve generalizability. This approach shows promise for personalized ORN risk stratification, allowing for tailored prophylactic dental care or adaptive RT planning to reduce ORN in high-risk patients.

This study presents a comprehensive analysis of machine learning techniques for measuring and predicting security in stock markets, comparing the performance of supervised, unsupervised, and deep learning models. Using a diverse dataset from Kaggle that includes historical stock prices, financial news sentiment, company fundamentals, and macroeconomic indicators, we applied feature engineering and rigorous preprocessing methods to optimize model accuracy. The study evaluated Random Forest, Support Vector Machines (SVM), K-Means clustering, and Long Short-Term Memory (LSTM) networks across key performance metrics. Results indicate that Random Forest outperformed other models in classification tasks with an accuracy of 92%, making it highly effective for real-time security assessment. SVM also demonstrated strong classification capabilities, particularly in high-dimensional spaces, with an accuracy of 88%. K-Means and DBSCAN clustering algorithms excelled in anomaly detection, identifying unusual patterns that could signal market irregularities. LSTM models, designed for time-series forecasting, achieved a root mean square error (RMSE) of 1.78, proving their utility in predicting future stock trends but requiring more computational resources.Our findings suggest that a hybrid approach, combining the strengths of supervised and deep learning models, can provide a robust solution for stock market security measurement. By leveraging explainable AI techniques such as SHAP and LIME, we also improved model interpretability, making these predictions more actionable for stakeholders. This research highlights the potential of machine learning in financial security monitoring and supports the growing integration of AI in the finance industry.

BackgroundAcupuncture is a widely practiced traditional therapy, yet safety concerns, particularly needle breakage and retention, remain critical issues that can lead to complications such as infections, organ injury, or chronic pain. This study aimed to develop a deep learning model to monitor acupuncture needle insertion, detect instances of needle breakage, and prevent needle retention, ultimately improving patient safety and treatment outcomes.MethodsA deep learning model based on the YOLOv8 architecture was trained using a dataset comprising 192 images from a commercial image library and 73 clinical images captured during real-world acupuncture sessions. Images were preprocessed through cropping and annotation, and augmented to enhance model generalizability. Five-fold cross-validation was employed to ensure robust performance. Model evaluation metrics included precision, recall, F1 score, and mean average precision (mAP) at Intersection over Union (IoU) thresholds of 50% (mAP@50) and 50–95% (mAP@50–95).ResultsThe model demonstrated strong performance, achieving an average precision of 88.0% and a recall of 82.9%. The mean average precision was 88.6% at mAP@50 and 62.9% at mAP@50–95, indicating high reliability in detecting acupuncture needles across diverse scenarios. These results highlight the potential of the model to enhance clinical safety by minimizing risks associated with needle breakage and retention, regardless of practitioner experience or patient demographics.ConclusionsThe proposed YOLOv8-based deep learning model offers a reliable method for real-time needle monitoring in acupuncture. Its integration into clinical workflows can improve safety and efficiency, especially in underserved regions or settings with less experienced practitioners. Future research should validate the model with larger, more diverse datasets and explore its application in various healthcare settings.Trial registrationNot applicable; this study did not involve a healthcare intervention requiring registration. Data collection adhered to ethical standards with institutional approval (TCHIRB-11310004).

The uncertain yield of crops is one of the major problems the agricultural sector faces today, especially in India. The objective of this paper is to provide an accurate and reliable prediction of crop yield. This will help farmers make decisions that can make their farming more efficient and profitable. We propose a novel deep learning model - an ensemble neural network model using Long Short-Term Memory (LSTMs) and one-dimensional Convolutional Neural Networks (CNNs). We used crop data for over 30 crops from 1997-2015 of all Indian districts. Our model substantially outperforms all other models (Linear Regression, Random Forest, extreme Gradient Boosting (XGB) Regressor, Feed-forward Neural Network (FFNN)) that were tested on accuracy in predicting crop yields. We achieve a correlation coefficient value of over 0.90 and 0.92 for our model for train and test datasets.Our model has several advantages compared to other models. Firstly, it is able to capture the time dependency on temperature and rainfall. Secondly, it is able to work on a large and diverse dataset, unlike most models which only perform well in small regions. Lastly, it is able to use several diverse features - geographical, social, and economic to make a prediction.

Semantic segmentation is a computer vision task that categorizes each pixel in an image into a class or object. Although a number of relevant architectures have been proposed in recent years, they incur the problems like computational cost,large amounts of training data, class imbalance, edge uncertainty, varying sizes of objects, shadow and lighting variations. Such a more number of drawbacks degrades the semantic segmentation performance in terms of accuracy, efficiency and generalization capability. In this work, comprehensive architecture UMV2 for satellite image semantic segmentation is proposed. The UMV2 utilizing a fusion of Unet++ architecture and the lightweight MobileNetV2 encoder deep learning model. The Unet++ architecture, an extension of the widely adopted Unet, is employed for its ability to capture hierarchical features and enhance segmentation performance. Integrating MobileNetV2 as the encoder provides computational efficiency, making the model well-suited for resource- onstrained environments, such as satellite image analysis on edge devices. The proposed model leverages the strengths of both architectures, combining the expressive power of Unet++ with the efficiency of MobileNetV2. Extensive experiments are conducted on a diverse satellite image dataset, evaluating the model’s segmentation accuracy of 0.89, mean IOU of 0.52, precision of 0.80, recall of 0.83 and F1-score of 0.82 with the state of art methods. The results demonstrate the effectiveness of the proposed approach in achieving accurate and efficient satellite image segmentation, making it a promising solution for real-world applications in remote sensing and geospatial analysis.

When fitting statistical models to variables in geoscientific disciplines such as hydrology, it is a customary practice to stratify a large domain into multiple regions (or regimes) and study each region separately. Traditional wisdom suggests that models built for each region separately will have higher performance because of homogeneity within each region. However, each stratified model has access to fewer and less diverse data points. Here, through two hydrologic examples (soil moisture and streamflow), we show that conventional wisdom may no longer hold in the era of big data and deep learning (DL). We systematically examined an effect we call data synergy, where the results of the DL models improved when data were pooled together from characteristically different regions. The performance of the DL models benefited from modest diversity in the training data compared to a homogeneous training set, even with similar data quantity. Moreover, allowing heterogeneous training data makes eligible much larger training datasets, which is an inherent advantage of DL. A large, diverse data set is advantageous in terms of representing extreme events and future scenarios, which has strong implications for climate change impact assessment. The results here suggest the research community should place greater emphasis on data sharing.

Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust algorithms requires a large number of data sets. We sought to train an adversarial model for generating high-quality optic disc images from a large, diverse data set and then assessed the performance of models on generated synthetic images for detecting GON. A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques. Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model's area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image. Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection. Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.

Heatmap regression has become the mainstream methodology for deep learning-based semantic landmark localization, including in facial landmark localization and human pose estimation. Though heatmap regression is robust to large variations in pose, illumination, and occlusion in unconstrained settings, it usually suffers from a sub-pixel localization problem. Specifically, considering that the activation point indices in heatmaps are always integers, quantization error thus appears when using heatmaps as the representation of numerical coordinates. Previous methods to overcome the sub-pixel localization problem usually rely on high-resolution heatmaps. As a result, there is always a trade-off between achieving localization accuracy and computational cost, where the computational complexity of heatmap regression depends on the heatmap resolution in a quadratic manner. In this paper, we formally analyze the quantization error of vanilla heatmap regression and propose a simple yet effective quantization system to address the sub-pixel localization problem. The proposed quantization system induced by the randomized rounding operation 1) encodes the fractional part of numerical coordinates into the ground truth heatmap using a probabilistic approach during training; and 2) decodes the predicted numerical coordinates from a set of activation points during testing. We prove that the proposed quantization system for heatmap regression is unbiased and lossless. Experimental results on popular facial landmark localization datasets (WFLW, 300W, COFW, and AFLW) and human pose estimation datasets (MPII and COCO) demonstrate the effectiveness of the proposed method for efficient and accurate semantic landmark localization. Code is available at http://github.com/baoshengyu/H3R.

Retinal hemorrhage (RH) is a significant clinical finding with various etiologies, necessitating accurate classification for effective management. This study aims to externally validate deep learning (DL) models, specifically FastVit_SA12 and ResNet18, for distinguishing between traumatic and medical causes of RH using diverse fundus photography datasets. A comprehensive dataset was compiled, including private collections from South Korea and Virginia, alongside publicly available datasets such as RFMiD, BRSET, and DeepEyeNet. The models were evaluated on a total of 2661 images, achieving high performance metrics. FastVit_SA12 demonstrated an overall accuracy of 96.99%, with a precision of 0.9935 and recall of 0.9723 for medical cases, while ResNet18 achieved a 94.66% accuracy with a precision of 0.9893. A Grad-CAM analysis revealed that ResNet18 emphasized global vascular patterns, such as arcuate vessels, while FastVit_SA12 focused on clinically relevant areas, including the optic disk and hemorrhagic regions. Medical cases showed localized activations, whereas trauma-related images displayed diffuse patterns across the fundus. Both models exhibited strong sensitivity and specificity, indicating their potential utility in clinical settings for accurate RH diagnosis. This study underscores the importance of external validation in enhancing the reliability and applicability of AI models in ophthalmology, paving the way for improved patient care and outcomes.

INTRODUCTION: In the field of medical imaging, accurate categorization of lung tissue is essential for timely diagnosis and management of lung-related conditions, including cancer. Deep Learning (DL) methodologies have revolutionized this domain, promising improved precision and effectiveness in diagnosing ailments based on image analysis. This research delves into the application of DL models for classifying lung tissue, particularly focusing on histopathological imagery. OBJECTIVES: The primary objective of this study is to explore the deployment of DL models for the classification of lung tissue, emphasizing histopathological images. The research aims to assess the performance of various DL models in accurately distinguishing between different classes of lung tissue, including benign tissue, lung adenocarcinoma, and lung squamous cell carcinoma. METHODS: A dataset comprising 9,000 histopathological images of lung tissue was utilized, sourced from HIPAA compliant and validated sources. The dataset underwent augmentation to ensure diversity and robustness. The images were categorized into three distinct classes and balanced before being split into training, validation, and testing sets. Six DL models - DenseNet201, EfficientNetB7, EfficientNetB5, Vgg19, Vgg16, and Alexnet - were trained and evaluated on this dataset. Performance assessment was conducted based on precision, recall, F1-score for each class, and overall accuracy. RESULTS: The results revealed varying performance levels among the DL models, with EfficientNetB5 achieving perfect scores across all metrics. This highlights the capability of DL in improving the accuracy of lung tissue classification, which holds promise for enhancing diagnosis and treatment outcomes in lung-related conditions. CONCLUSION: This research significantly contributes to understanding the effective utilization of DL models in medical imaging, particularly for lung tissue classification. It emphasizes the critical role of a diverse and balanced dataset in developing robust and accurate models. The insights gained from this study lay the groundwork for further exploration into refining DL methodologies for medical imaging applications, with a focus on improving diagnostic accuracy and ultimately, patient outcomes.

Traditional Convolutional Neural Network (ConvNet, CNN)-based image super-resolution (SR) methods have lower computation costs, making them more friendly for real-world scenarios. However, they suffer from lower performance. On the contrary, Vision Transformer (ViT)-based SR methods have achieved impressive performance recently, but these methods often suffer from high computation costs and model storage overhead, making them hard to meet the requirements in practical application scenarios. In practical scenarios, an SR model should reconstruct an image with high quality and fast inference. To handle this issue, we propose a novel CNN-based Efficient Residual ConvNet enhanced with structural Re-parameterization (RepECN) for a better trade-off between performance and efficiency. A stage-to-block hierarchical architecture design paradigm inspired by ViT is utilized to keep the state-of-the-art performance, while the efficiency is ensured by abandoning the time-consuming Multi-Head Self-Attention (MHSA) and by re-designing the block-level modules based on CNN. Specifically, RepECN consists of three structural modules: a shallow feature extraction module, a deep feature extraction, and an image reconstruction module. The deep feature extraction module comprises multiple ConvNet Stages (CNS), each containing 6 Re-Parameterization ConvNet Blocks (RepCNB), a head layer, and a residual connection. The RepCNB utilizes larger kernel convolutions rather than MHSA to enhance the capability of learning long-range dependence. In the image reconstruction module, an upsampling module consisting of nearest-neighbor interpolation and pixel attention is deployed to reduce parameters and maintain reconstruction performance, while bicubic interpolation on another branch allows the backbone network to focus on learning high-frequency information. The extensive experimental results on multiple public benchmarks show that our RepECN can achieve 2.5∼5× faster inference than the state-of-the-art ViT-based SR model with better or competitive super-resolving performance, indicating that our RepECN can reconstruct high-quality images with fast inference.

Cyberbullying, a pervasive issue in the digital age, poses threats to individuals’ well-being across various attributes such as religion, age, ethnicity, and gender. This research employs artificial intelligence to detect cyberbullying instances in Twitter data, utilizing both traditional and deep learning models. The study repurposes the Sentiment140 dataset, originally intended for sentiment analysis, for the nuanced task of cyberbullying detection. Ethical considerations guide the dataset transformation process, ensuring responsible AI development. The Naive Bayes algorithm demonstrates commendable precision, recall, and accuracy, showcasing its efficacy. The Bi-LSTM model, leveraging deep learning capabilities, exhibits nuanced cyberbullying detection. The study also underscores limitations, emphasizing the need for refined models and diverse datasets.

We present a comprehensive theoretical framework analyzing the relationship between data distributions and fairness guarantees in equitable deep learning. Our work establishes novel theoretical bounds that explicitly account for data distribution heterogeneity across demographic groups, while introducing a formal analysis framework that minimizes expected loss differences across these groups. We derive comprehensive theoretical bounds for fairness errors and convergence rates, and characterize how distributional differences between groups affect the fundamental trade-off between fairness and accuracy. Through extensive experiments on diverse datasets across various modalities (image, tabular data, and text), including FairVision (eye disease detection), CheXpert (pleural effusion detection), HAM10000 (skin lesion classification), FairFace (facial attribute recognition), ACS Income (income prediction), CivilComments-WILDS (toxic comment detection), we validate our theoretical findings and demonstrate that differences in feature distributions across demographic groups significantly impact model fairness, with performance disparities particularly pronounced in racial categories. The theoretical bounds we derive corroborate these empirical observations, providing insights into the fundamental limits of achieving fairness in deep learning models when faced with heterogeneous data distributions. This work advances our understanding of fairness in AI-based diagnosis systems and provides a theoretical foundation for developing more equitable algorithms. Motivated by these theoretical insights, particularly the link between feature distribution shifts and fairness gaps, we propose Fairness-Aware Regularization (FAR), a practical training objective that directly minimizes inter-group discrepancies in feature centroids and covariances to improve equitable performance. We validate the effectiveness of FAR across all datasets considered in this study, consistently observing improvements in overall AUC, ES-AUC, and subgroup performance. The code for analysis is publicly available via https://github.com/Harvard-Ophthalmology-AI-Lab/fairness guarantees.