Deep Learning Methodology Research Articles

RUL forecasting for wind turbine predictive maintenance based on deep learning

Predictive maintenance (PdM) is increasingly pursued to reduce wind farm operation and maintenance costs by accurately predicting the remaining useful life (RUL) and strategically scheduling maintenance. However, the remoteness of wind farms often renders current methodologies ineffective, as they fail to provide a sufficiently reliable advance time window for maintenance planning, limiting PdM's practicality. This study introduces a novel deep learning (DL) methodology for future-RUL forecasting. By employing a multi-parametric attention-based DL approach that bypasses feature engineering, thereby minimizing the risk of human error, two models—ForeNet-2d and ForeNet-3d—are proposed. These models successfully forecast the RUL for seven multifaceted wind turbine (WT) failures with a 2-week forecast window. The most precise forecast deviated by only 10 minutes from the actual RUL, while the least accurate prediction deviated by 1.8 days, with most predictions being off by only a few hours. This methodology offers a substantial time frame to access remote WTs and perform necessary maintenance, thereby enabling the practical implementation of PdM.

Targeting ATP catalytic activity of chromodomain helicase CHD1L for the anticancer inhibitor discovery

CHD1L functions as an ATP-dependent chromatin remodeling enzyme, featuring an ATPase catalytic domain activated by double-stranded DNA. Its involvement in critical aspects of cancer progression, such as drug resistance and epithelial-mesenchymal transition, underscores its potential as a promising therapeutic target for cancer treatment. In this study, we have pioneered an innovative approach that integrates multiple deep learning methodologies alongside biochemical and cellular experiments to identify promising inhibitors of CHD1L. Through virtual screening of over 1.5 million small molecule compounds, we carefully curated a set of 36 candidate compounds and rigorously evaluated the top 13 candidates. Our findings establish the lead compound C071–0684 as a potent anticancer agent with a novel molecular backbone, demonstrating remarkable efficacy against colorectal and breast cancer cells targeting CHD1L. This compound exhibited a comparable effect on ATPase activity and binding affinity with CHD1Li 6.11, highlighting its superior pharmacological potential. These results provide valuable insights and pave the way for the discovery and development of CHD1L-targeted therapeutics, holding great promise for cancer patients.

Enhancing soil nitrogen measurement via visible-near infrared spectroscopy: Integrating soil particle size distribution with long short-term memory models

Good quality of soil nitrogen data, which is essential for the advancement of both enhanced agricultural management and ecological environment, traditionally depends on labor intensive chemical procedures. Visible near-infrared (Vis-NIR) spectroscopy, acknowledged for its efficiency, environmental compatibility and rapidity, merges as a promising alternative. However, the effectiveness of Vis-NIR measurement models are significantly compromised by soil particle size distribution (PSD), presenting a substantial challenge in improving the measurement accuracy and reliability. Here an innovative deep learning methodology that integrates PSD with Vis-NIR spectroscopy was proposed for the measurement of nitrogen content in soil samples. By leveraging the LUCAS dataset, different strategies for integrating PSD with Vis-NIR spectral data in deep learning models were explored, revealing that our proposed InSGraL framework, which incorporated mixed features of PSD and spectra as LSTM inputs achieves superior performance. Compared to models utilizing solely Vis-NIR data, InSGraL exhibits a 39.47 % reduction in RMSE and a 42.55 % decrease in MAE, and demonstrates robust performance across various land cover types, achieving an R2 of 0.94 on grassland samples. Moreover, Shapley Additive exPlanations (SHAP) analysis revealed that incorporating PSD modifies the spectral input importance distribution, effectively mitigating spectral interference from particle size while highlighting critical wavelengths previously obscured. This study provides an innovative modeling strategy to mitigate the influence of PSD by integrating it within deep learning framework using Vis-NIR, contributing a deeper understanding of the relationship between PSD and Vis-NIR spectra for the measurement of nitrogen content and offering an effective means to attain soil nitrogen data.

Dynamic entrainment: A deep learning and data-driven process approach for synchronization in the Hodgkin-Huxley model.

Resonance and synchronized rhythm are significant phenomena observed in dynamical systems in nature, particularly in biological contexts. These phenomena can either enhance or disrupt system functioning. Numerous examples illustrate the necessity for organs within the human body to maintain their rhythmic patterns for proper operation. For instance, in the brain, synchronized or desynchronized electrical activities can contribute to neurodegenerative conditions like Huntington's disease. In this paper, we utilize the well-established Hodgkin-Huxley (HH) model, which describes the propagation of action potentials in neurons through conductance-based mechanisms. Employing a "data-driven" approach alongside the outputs of the HH model, we introduce an innovative technique termed "dynamic entrainment." This technique leverages deep learning methodologies to dynamically sustain the system within its entrainment regime. Our findings show that the results of the dynamic entrainment technique match with the outputs of the mechanistic (HH) model.

Transformers-based architectures for stroke segmentation: a review

Stroke remains a significant global health concern, necessitating precise and efficient diagnostic tools for timely intervention and improved patient outcomes. The emergence of deep learning methodologies has transformed the landscape of medical image analysis. Recently, Transformers, initially designed for natural language processing, have exhibited remarkable capabilities in various computer vision applications, including medical image analysis. This comprehensive review aims to provide an in-depth exploration of the cutting-edge Transformer-based architectures applied in the context of stroke segmentation. It commences with an exploration of stroke pathology, imaging modalities, and the challenges associated with accurate diagnosis and segmentation. Subsequently, the review delves into the fundamental ideas of Transformers, offering detailed insights into their architectural intricacies and the underlying mechanisms that empower them to effectively capture complex spatial information within medical images. The existing literature is systematically categorized and analyzed, discussing various approaches that leverage Transformers for stroke segmentation. A critical assessment is provided, highlighting the strengths and limitations of these methods, including considerations of performance and computational efficiency. Additionally, this review explores potential avenues for future research and development.

Do LSTM memory states reflect the relationships in reduced-complexity sandy shoreline models

Equilibrium-based models are a transparent method of modelling shoreline change, though often too simplistic to capture complex dynamics. Conversely, deep learning methodologies offer greater predictive power at the expense of transparency. In this research we scrutinize the internal workings of an LSTM shoreline model. A regression-based probe is used to show that cell state vectors, responsible for past-to-future information flow, autonomously generate equilibrium-like information akin to the physics-based equilibrium term of the ShoreFor model, Ωeq. The variation in probe skill throughout training is tracked to show that at 5 of 6 transects, the LSTM was able to meaningfully acquire equilibrium information (ΣΔR2 = 0.3–0.6). The results of this work offer evidence that an LSTM may model shoreline change with internal methods that are consistent with the current understanding of coastal shoreline dynamics. These physically meaningful representations emphasize the importance of co-evolution between machine learning and physics-based approaches moving forward.

A Review on Deep Learning Approaches and Optimization Techniques For Political Security Threat Prediction

In an era of complex geopolitical dynamics and evolving security threats, the accurate prediction and proactive management of political security risks are imperative. This article provides a comprehensive review of the application of deep learning methodologies and optimization techniques to enhance political security threat prediction. Beginning with analyzing the dynamic landscape of political security threats, the paper emphasizes the necessity for adaptive, data-driven predictive tools. It then delves into the fundamentals of deep learning, elucidating core principles, notable architectural frameworks, and their diverse applications across domains. Expanding upon this foundation, the study evaluates the suitability of deep learning models for addressing the multifaceted challenges associated with political security threat prediction. To maximize the utility of these models, the article explores optimization techniques encompassing hyperparameter tuning, transfer learning, and ensemble strategies, assessing their effectiveness in fine-tuning predictions and bolstering the resilience of threat prediction systems. This review involved the utilization of four journal databases: IEEE, Science Direct, Association for Computing Machinery (ACM), and SpringerLink. We analyzed and examined 39 articles, paying close attention to the different patterns and techniques found within the chosen research framework. Through a critical synthesis of existing research, this review offers insights into the strengths, limitations, and future directions of deep learning-based political security threat prediction, contributing to the ongoing discourse on leveraging artificial intelligence for safeguarding global stability and security.

GC-WIR : 3D global coordinate attention wide inverted ResNet network for pulmonary nodules classification

PurposeCurrently, deep learning methods for the classification of benign and malignant lung nodules encounter challenges encompassing intricate and unstable algorithmic models, limited data adaptability, and an abundance of model parameters.To tackle these concerns, this investigation introduces a novel approach: the 3D Global Coordinated Attention Wide Inverted ResNet Network (GC-WIR). This network aims to achieve precise classification of benign and malignant pulmonary nodules, leveraging its merits of heightened efficiency, parsimonious parameterization, and robust stability.MethodsWithin this framework, a 3D Global Coordinate Attention Mechanism (3D GCA) is designed to compute the features of the input images by converting 3D channel information and multi-dimensional positional cues. By encompassing both global channel details and spatial positional cues, this approach maintains a judicious balance between flexibility and computational efficiency. Furthermore, the GC-WIR architecture incorporates a 3D Wide Inverted Residual Network (3D WIRN), which augments feature computation by expanding input channels. This augmentation mitigates information loss during feature extraction, expedites model convergence, and concurrently enhances performance. The utilization of the inverted residual structure imbues the model with heightened stability.ResultsEmpirical validation of the GC-WIR method is performed on the LUNA 16 dataset, yielding predictions that surpass those generated by previous models. This novel approach achieves an impressive accuracy rate of 94.32%, coupled with a specificity of 93.69%. Notably, the model’s parameter count remains modest at 5.76M, affording optimal classification accuracy.ConclusionFurthermore, experimental results unequivocally demonstrate that, even under stringent computational constraints, GC-WIR outperforms alternative deep learning methodologies, establishing a new benchmark in performance.

A survey of deep causal models and their industrial applications

The notion of causality assumes a paramount position within the realm of human cognition. Over the past few decades, there has been significant advancement in the domain of causal effect estimation across various disciplines, including but not limited to computer science, medicine, economics, and industrial applications. Given the continous advancements in deep learning methodologies, there has been a notable surge in its utilization for the estimation of causal effects using counterfactual data. Typically, deep causal models map the characteristics of covariates to a representation space and then design various objective functions to estimate counterfactual data unbiasedly. Different from the existing surveys on causal models in machine learning, this review mainly focuses on the overview of the deep causal models based on neural networks, and its core contributions are as follows: (1) we cast insight on a comprehensive overview of deep causal models from both timeline of development and method classification perspectives; (2) we outline some typical applications of causal effect estimation to industry; (3) we also endeavor to present a detailed categorization and analysis on relevant datasets, source codes and experiments.

An ensemble machine learning model assists in the diagnosis of gastric ectopic pancreas and gastric stromal tumors

ObjectiveTo develop an ensemble machine learning (eML) model using multiphase computed tomography (MPCT) for distinguishing between gastric ectopic pancreas (GEP) and gastric stromal tumors (GIST) in lesions < 3 cm.MethodsIn this study, we retrospectively collected MPCT images from 138 patients between April 2017 and June 2023 across two centers. Cohort 1 comprised 94 patients divided into a training cohort and an internal validation cohort, while the 44 patients from Cohort 2 constituted the external validation cohort. Deep learning (DL) models were constructed based on the lesion region, and radiomics features were extracted to develop radiomics models, which were later integrated into the fusion model. Model performance was assessed through the analysis of the area under the receiver operating characteristic curve (AUROC). The diagnostic efficacy of the optimal model was compared with that of a radiologist. Additionally, the radiologist with the assistance of the eML model provides a secondary diagnosis, to assess the potential clinical value of the model.ResultsAfter evaluation using an external validation cohort, the radiomics model demonstrated the highest performance in the venous phase, achieving AUROC of 0.87. The DL model showed optimal performance in the non-contrast phase, with AUROC of 0.81. The eML achieved the best performance across all models, with AUROC of 0.90. The use of eML-assisted analysis resulted in a significant improvement in the junior radiologist’s accuracy, rising from 0.77 to 0.93 (p < 0.05). However, the senior radiologist’s accuracy, while improving from 0.86 to 0.95, did not exhibit a statistically significant difference.ConclusioneML model based on MPCT can effectively distinguish between GEPs and GISTs < 3 cm.Critical relevance statementThe multiphase CT-based fusion model, incorporating radiomics and DL technology, proves effective in distinguishing between GEP and gastric stromal tumors, serving as a valuable tool to enhance diagnoses and offering references for clinical decision-making.Key PointsNo studies yet differentiated these tumors via radiomics or DL.Radiomics and DL methodologies unveil potentially distinct phenotypes within lesions.Quantitative analysis on CT for GIST and ectopic pancreas.Ensemble learning aids accurate diagnoses, assisting treatment decisions.Graphical

Sentiment Mining in E-Commerce

Sentiment analysis is crucial for comprehending customer feedback and enhancing workplace culture, as well as improving products and services. By employing natural language processing (NLP) techniques to meticulously analyze this feedback, organizations can identify specific areas that require improvement, address employee issues, and cultivate a positive work environment. These deep learning models powered by NLP offer invaluable tools for HR and sales departments in the e-commerce sector, enabling them to track sentiment trends among employees and users over time and implement targeted interventions. Focusing on the e-commerce industry, this study employs NLP-driven deep learning methodologies to analyze both employee and user feedback, with the objective of identifying underlying sentiments. The proposed framework leverages these advanced techniques to categorize user feedback into positive, negative, or neutral sentiments. This approach aims to develop a robust and effective system for sentiment analysis, providing significant insights that can help drive organizational improvements and enhance customer satisfaction. The key steps of this framework include data collection, NLP-enhanced feature extraction, sentiment detection, and final classification using finite-state automata. The effectiveness of this NLP-centric approach was tested on diverse datasets of customer feedback collected from an e-commerce industry. Evaluation metrics such as accuracy, precision, and recall were utilized to assess the performance of the system. The results demonstrate the effectiveness of the proposed framework, achieving a 93.75% accuracy rate and surpassing existing benchmark methods. The outcomes of this study are particularly consequential for the e-commerce sector, offering them a strategic advantage in refining their product portfolios and cultivating a more dynamic workplace culture

MEG AND PET IMAGES-BASED BRAIN TUMOR DETECTION USING KAPUR’S OTSU SEGMENTATION AND SOOTY OPTIMIZED MOBILENET CLASSIFICATION

Deep learning techniques have revolutionized medical image analysis recently, particularly in brain tumor (BT) detection. A comprehensive overview of the advancements and challenges associated with employing deep learning methodologies for the accurate and timely detection of BT. This work proposes a novel brain hybrid hexagonal mobile network (BH2Mnet) to identify benign and malignant tumors using MEG and PET images. An adaptive bilateral filter (ABF) is used as a de-noising for input images to eliminate noise artifacts. Eliminating the skull and outer cortical regions, a process known as "skull stripping" is utilized to enhance the number of training images. The de-noised images are segmented to detect the BT using Kapur's Otsu threshold (KOT) algorithm. Based on these segmented tumors, hexagonal feature sets with and without segmentation masks are produced using hybrid hexagonal features (HHF). Finally, the Sooty optimization-based MobileNet classifier is employed to classify the BT into benign, malignant cases. It was determined that the proposed BH2Mnet approach was 99.21 % accurate in classifying data. According to the proposed BH2Mnet NS-CNN, the total accuracy is enhanced by 1.67 %, 2.69 %, and 4.11 % compared to hybrid DAE, BFC, Deep CNN, and Neutrosophy.

Pulmonary Nodule Detection, Segmentation and Classification Using Deep Learning: A Comprehensive Literature Review

Lung cancer is a leading cause of cancer-related deaths worldwide, emphasizing the significance of early detection. Computer-aided diagnostic systems have emerged as valuable tools for aiding radiologists in the analysis of medical images, particularly in the context of lung cancer screening. A typical pipeline for lung cancer diagnosis involves pulmonary nodule detection, segmentation, and classification. Although traditional machine learning methods have been deployed in the previous years with great success, this literature review focuses on state-of-the-art deep learning methods. The objective is to extract key insights and methodologies from deep learning studies that exhibit high experimental results in this domain. This paper delves into the databases utilized, preprocessing steps applied, data augmentation techniques employed, and proposed methods deployed in studies with exceptional outcomes. The reviewed studies predominantly harness cutting-edge deep learning methodologies, encompassing traditional convolutional neural networks (CNNs) and advanced variants such as 3D CNNs, alongside other innovative approaches such as Capsule networks and transformers. The methods examined in these studies reflect the continuous evolution of deep learning techniques for pulmonary nodule detection, segmentation, and classification. The methodologies, datasets, and techniques discussed here collectively contribute to the development of more efficient computer-aided diagnostic systems, empowering radiologists and dfhealthcare professionals in the fight against this deadly disease.

A Deep Learning-Enhanced Compartmental Model and Its Application in Modeling Omicron in China.

The mainstream compartmental models require stochastic parameterization to estimate the transmission parameters between compartments, whose calculation depend upon detailed statistics on epidemiological characteristics, which are expensive, economically and resource-wise, to collect. In addition, infectious diseases spread in three dimensions: temporal, spatial, and mobile, i.e., they affect a population through not only the time progression of infection, but also the geographic distribution and physical mobility of the population. However, the parameterization process for the mainstream compartmental models does not effectively capture the spatial and mobile dimensions. As an alternative, deep learning techniques are utilized in estimating these stochastic parameters with greatly reduced dependency on data particularity and with a built-in temporal-spatial-mobile process that models the geographic distribution and physical mobility of the population. In particular, we apply DNN (Deep Neural Network) and LSTM (Long-Short Term Memory) techniques to estimate the transmission parameters in a customized compartmental model, then feed the estimated transmission parameters to the compartmental model to predict the development of the Omicron epidemic in China over the 28 days for the period between 4 June and 1 July 2022. The average levels of predication accuracy of the model are 98% and 92% for the number of infections and deaths, respectively. We establish that deep learning techniques provide an alternative to the prevalent compartmental modes and demonstrate the efficacy and potential of applying deep learning methodologies in predicting the dynamics of infectious diseases.

Design, Building and Deployment of Smart Applications for Anomaly Detection and Failure Prediction in Industrial Use Cases

This paper presents a comparative analysis of deep learning techniques for anomaly detection and failure prediction. We explore various deep learning architectures on an IoT dataset, including recurrent neural networks (RNNs, LSTMs and GRUs), convolutional neural networks (CNNs) and transformers, to assess their effectiveness in anomaly detection and failure prediction. It was found that the hybrid transformer-GRU configuration delivers the highest accuracy, albeit at the cost of requiring the longest computational time for training. Furthermore, we employ explainability techniques to elucidate the decision-making processes of these black box models and evaluate their behaviour. By analysing the inner workings of the models, we aim at providing insights into the factors influencing failure predictions. Through comprehensive experimentation and analysis on sensor data collected from a water pump, this study contributes to the understanding of deep learning methodologies for anomaly detection and failure prediction and underscores the importance of model interpretability in critical applications such as prognostics and health management. Additionally, we specify the architecture for deploying these models in a real environment using the RAI4.0 metamodel, meant for designing, configuring and automatically deploying distributed stream-based industrial applications. Our findings will offer valuable guidance for practitioners seeking to deploy deep learning techniques effectively in predictive maintenance systems, facilitating informed decision-making and enhancing reliability and efficiency in industrial operations.

DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search.

A growing number of deep learning (DL) methodologies have recently been developed to design novel compounds and expand the chemical space within virtual libraries. Most of these neural network approaches design molecules to specifically bind a target based on its structural information and/or knowledge of previously identified binders. Fewer attempts have been made to develop approaches for de novo design of virtual libraries, as synthesizability of generated molecules remains a challenge. In this work, we developed a new Monte Carlo Search (MCS) algorithm, DrugSynthMC (Drug Synthesis using Monte Carlo), in conjunction with DL and statistical-based priors to generate thousands of interpretable chemical structures and novel drug-like molecules per second. DrugSynthMC produces drug-like compounds using an atom-based search model that builds molecules as SMILES, character by character. Designed molecules follow Lipinski's "rule of 5″, show a high proportion of highly water-soluble nontoxic predicted-to-be synthesizable compounds, and efficiently expand the chemical space within the libraries, without reliance on training data sets, synthesizability metrics, or enforcing during SMILES generation. Our approach can function with or without an underlying neural network and is thus easily explainable and versatile. This ease in drug-like molecule generation allows for future integration of score functions aimed at different target- or job-oriented goals. Thus, DrugSynthMC is expected to enable the functional assessment of large compound libraries covering an extensive novel chemical space, overcoming the limitations of existing drug collections. The software is available at https://github.com/RoucairolMilo/DrugSynthMC.

Physics-informed neural network for volumetric sound field reconstruction of speech signals

Recent developments in acoustic signal processing have seen the integration of deep learning methodologies, alongside the continued prominence of classical wave expansion-based approaches, particularly in sound field reconstruction. Physics-informed neural networks (PINNs) have emerged as a novel framework, bridging the gap between data-driven and model-based techniques for addressing physical phenomena governed by partial differential equations. This paper introduces a PINN-based approach for the recovery of arbitrary volumetric acoustic fields. The network incorporates the wave equation to impose a regularization on signal reconstruction in the time domain. This methodology enables the network to learn the physical law of sound propagation and allows for the complete characterization of the sound field based on a limited set of observations. The proposed method’s efficacy is validated through experiments involving speech signals in a real-world environment, considering varying numbers of available measurements. Moreover, a comparative analysis is undertaken against state-of-the-art frequency domain and time domain reconstruction methods from existing literature, highlighting the increased accuracy across the various measurement configurations.

Optimal techno-economic assessment of isolated microgrid integrated with fast charging stations using radial basis deep learning

The global transportation electrification commerce sector is now booming. Stakeholders are paying an increased attention to the integration of electric vehicles and electric buses into the transportation networks. As a result, there is an urgent need to invest in public charging infrastructure, particularly for fast charging facilities. Consequently, and to complete the portfolio of the green environment, these fast-charging stations (FCSs) are designed using 100% of renewable energy sources (RESs). Thus, this paper proposes an optimization model for the techno-economic assessment of FCSs comprising photovoltaic and wind turbines with various energy storage devices (ESDs). In this regard, the FCS performance is evaluated using flywheels and super capacitors due to their high-power density and charging/discharging cycles and rates. Then, optimal sizing of these distributed generators is attained considering diverse technical and economical key performance indicators. Afterwards, the problem gets more sophisticated by investigating the effect of RES’s uncertainties on the selection criterion of the FCS’s components, design and capacity. Eventually, as an effort dedicated to an online energy management approach, a deep learning methodology based on radial basis network (RBN) is implemented, validated, and carried out. In stark contrast to conventional optimization approaches, RBN demonstrates its superiority by obtaining the optimum solutions in a relatively short amount of time.

Exploring the Combination of Computer Vision and Surgical Neuroanatomy: A Workflow Involving Artificial Intelligence for the Identification of Skull Base Foramina

The skull base is a complex region in neurosurgery, featuring numerous foramina. Accurate identification of these foramina is imperative to avoid intraoperative complications and to facilitate educational progress in neurosurgical trainees. The intricate landscape of the skull base often challenges both clinicians and learners, necessitating innovative identification solutions. We aimed to develop a computer vision model that automates the identification and labeling of the skull base foramina from various image formats, enhancing surgical planning and educational outcomes. We employed a deep learning methodology, specifically using a convolutional neural network architecture. Our model was trained on a dataset comprising of 3560 high-resolution, annotated images of the skull base, taken from various perspectives and lighting conditions to ensure model generalizability. Model performance was quantitatively assessed using precision and recall metrics. The convolutional neural network model demonstrated strong performance, achieving an average precision of 0.77. At a confidence threshold of 0.28, the model reached an optimal precision of 90.4% and a recall of 89.6%. Validation on an independent test set of images corroborated the model's capability to consistently and accurately identify and label multiple skull base foramina across diverse imaging scenarios. This study successfully introduces a highly accurate computer vision model tailored for the identification of skull base foramina, illustrating the model's potential as a transformative tool in anatomical education and intraoperative structure visualization. The findings suggest promising avenues for future research into automated anatomical recognition models, suggesting a trajectory toward increasingly sophisticated aids in neurosurgical operations and education.

Can incorporating image resolution into neural networks improve kidney tumor classification performance in ultrasound images?

Deep learning has been widely used in ultrasound image analysis, and it also benefits kidney ultrasound interpretation and diagnosis. However, the importance of ultrasound image resolution often goes overlooked within deep learning methodologies. In this study, we integrate the ultrasound image resolution into a convolutional neural network and explore the effect of the resolution on diagnosis of kidney tumors. In the process of integrating the image resolution information, we propose two different approaches to narrow the semantic gap between the features extracted by the neural network and the resolution features. In the first approach, the resolution is directly concatenated with the features extracted by the neural network. In the second approach, the features extracted by the neural network are first dimensionally reduced and then combined with the resolution features to form new composite features. We compare these two approaches incorporating the resolution with the method without incorporating the resolution on a kidney tumor dataset of 926 images consisting of 211 images of benign kidney tumors and 715 images of malignant kidney tumors. The area under the receiver operating characteristic curve (AUC) of the method without incorporating the resolution is 0.8665, and the AUCs of the two approaches incorporating the resolution are 0.8926 (P < 0.0001) and 0.9135 (P < 0.0001) respectively. This study has established end-to-end kidney tumor classification systems and has demonstrated the benefits of integrating image resolution, showing that incorporating image resolution into neural networks can more accurately distinguish between malignant and benign kidney tumors in ultrasound images.