A novel aggregated coefficient ranking based feature selection strategy for enhancing the diagnosis of breast cancer classification using machine learning

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 4, 2025

Abstract Effective Breast cancer (BC) analysis is crucial for early prognosis, controlling recurrence, timely medical intervention, and determining appropriate treatment procedures. Additionally, it plays a significant role in optimizing mortality rates among women with breast increasing the average lifespan of patients. This can be achieved by performing effective critical feature BC picking superlative features through ranking-based Feature Selection (FS). Various authors have developed strategies relying on single FS, but this approach may not yield excellent results could lead to various consequences, including time storage complexity issues, inaccurate results, poor decision-making, difficult interpretation models. Therefore, data facilitate development robust ranking methodology selection. To solve these problems, paper suggests new method called Aggregated Coefficient Ranking-based (ACRFS), which based tri chracteristic behavioral criteria. strategy aims significantly improve an Attribute Subset (ASSS). The proposed utilized computational problem solvers such as chi-square, mutual information, correlation, rank-dense methods. work implemented introduced using Wisconsin-based applied Synthetic Minority Oversampling Technique (SMOTE) obtained subset. Later, we employed models decision trees, support vector machines, k-nearest neighbors, random forests, stochastic gradient descent, Gaussian naive bayes determine type cancer. classification metrics accuracy, precision, recall, F1 score, kappa Matthews coefficient were evaluate effectiveness suggested ACRFS approach. has demonstrated superior outcomes fewer minimal complexity.

Language: Английский

---

Breast cancer classification based on hybrid CNN with LSTM model

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 5, 2025

Breast cancer (BC) is a global problem, largely due to shortage of knowledge and early detection. The speed-up process detection classification crucial for effective treatment. Medical image analysis methods computer-aided diagnosis can enhance this process, providing training assistance less experienced clinicians. Deep Learning (DL) models play great role in accurately detecting classifying the huge dataset, especially when dealing with large medical images. This paper presents novel hybrid model DL combined Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) binary breast on two datasets available at Kaggle repository. CNNs extract mammographic features, including spatial hierarchies malignancy patterns, whereas LSTM networks characterize sequential dependencies temporal interactions. Our method combines these structures improve accuracy resilience. We compared proposed other models, such as CNN, LSTM, Gated Recurrent Units (GRUs), VGG-16, RESNET-50. CNN-LSTM achieved superior performance accuracies 99.17% 99.90% respective datasets. uses prediction evaluation metrics accuracy, sensitivity, specificity, F-score, AUC curve. results showed that our classifiers others second dataset.

Language: Английский

---

A review on fault detection and diagnosis of industrial robots and multi-axis machines

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102397 - 102397

Published: June 11, 2024

- Industrial Robots and Multi-axis Machines have become increasingly popular in recent years, a diverse range of industries. These complex expensive machines are vulnerable to variety problems that could put the robot or its surroundings danger. To keep system running, these issues must be discovered diagnosed quickly. Although numerous related review papers been increasing over time, none describe techniques fault diagnosis isolation (FDI) for smart manufacturing industrial robotic systems their rotating components. This work reviews this issue expands discussion existing cover FDI Multi DOF robots. The study excludes some types autonomous robots like multi-robot systems, swarms, UAVs out our domain while including associated components involved such as gearbox, actuators, controllers. A few previous studies discussed current-signature data-driven approaches but either single motor, actuator, one joint not whole manipulator faults. literature outcome concluded methods can identify faults only two DOFs it is advisable present an approach repetitive benefit from limitations conducting on automatic enhanced by reference mathematical model each task.

Language: Английский

---

Applications of artificial intelligence-enabled robots and chatbots in ophthalmology: recent advances and future trends

Current Opinion in Ophthalmology, Journal Year: 2024, Volume and Issue: 35(3), P. 238 - 243

Published: Jan. 22, 2024

Purpose of review Recent advances in artificial intelligence (AI), robotics, and chatbots have brought these technologies to the forefront medicine, particularly ophthalmology. These been applied diagnosis, prognosis, surgical operations, patient-specific care It is thus both timely pertinent assess existing landscape, recent advances, trajectory trends AI, AI-enabled robots, findings Some developments integrated AI enabled robotics with procedures More recently, large language models (LLMs) like ChatGPT shown promise augmenting research capabilities diagnosing ophthalmic diseases. may portend a new era doctor-patient-machine collaboration. Summary Ophthalmology undergoing revolutionary change research, clinical practice, interventions. Ophthalmic chatbot based on LLMs are converging create digital Collectively, future which conventional knowledge will be seamlessly improve patient experience enhance therapeutic outcomes.

Language: Английский

---

Modified U-Net with attention gate for enhanced automated brain tumor segmentation

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 2, 2025

Language: Английский

---

Deep Convolutional Neural Networks in Medical Image Analysis: A Review

Information, Journal Year: 2025, Volume and Issue: 16(3), P. 195 - 195

Published: March 3, 2025

Deep convolutional neural networks (CNNs) have revolutionized medical image analysis by enabling the automated learning of hierarchical features from complex imaging datasets. This review provides a focused CNN evolution and architectures as applied to analysis, highlighting their application performance in different fields, including oncology, neurology, cardiology, pulmonology, ophthalmology, dermatology, orthopedics. The paper also explores challenges specific outlines trends future research directions. aims serve valuable resource for researchers practitioners healthcare artificial intelligence.

Language: Английский

---

A systematic review of deep learning techniques for generating synthetic CT images from MRI data

Polish Journal of Medical Physics And Engineering, Journal Year: 2025, Volume and Issue: 31(1), P. 20 - 38

Published: March 1, 2025

Abstract Introduction: This systematic review evaluates various studies on deep learning algorithms for generating synthetic CT images from MRI data, focusing challenges in image quality and accuracy current generation methods. Magnetic resonance imaging (MRI) is increasingly important clinical settings due to its detailed visualization noninvasive nature, making it a valuable tool advancing patient care identifying new areas research. Materials Methods: In this study we conducted thorough search across several databases identify published between January 2009 2024 using generate (sCT) radiotherapy. The focused peer-reviewed, English-language excluded unpublished, non-English, irrelevant studies. Data methods, input modalities, anatomical sites were extracted analyzed result-based synthesis approach. categorized 84 by site, following PRISMA guidelines summarizing the findings. Results: U-Net model most frequently used with 34 articles highlighting effectiveness capturing fine details, Conditional GANs are also widely used, while Cycle-GANs Pix2pix effective translation tasks. Significant differences performance metrics, such as MAE PSNR, observed regions models, variability among different approaches. Conclusion: underscores need continued refinement standardization approaches medical address metrics models.

Language: Английский

---

A review of convolutional neural network based methods for medical image classification

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 185, P. 109507 - 109507

Published: Dec. 3, 2024

Language: Английский

---

Quantifying Soybean Defects: A Computational Approach to Seed Classification Using Deep Learning Techniques

Agronomy, Journal Year: 2024, Volume and Issue: 14(6), P. 1098 - 1098

Published: May 22, 2024

This paper presents a computational approach for quantifying soybean defects through seed classification using deep learning techniques. To differentiate between good and defective seeds quickly accurately, we introduce lightweight defect identification network (SSDINet). Initially, the labeled dataset is developed processed proposed contour detection (SCD) algorithm, which enhances quality of images performs segmentation, followed by SSDINet. The network, SSDINet, consists convolutional neural depthwise convolution blocks, squeeze-and-excitation making lightweight, faster, more accurate than other state-of-the-art approaches. Experimental results demonstrate that SSDINet achieved highest accuracy, 98.64%, with 1.15 M parameters in 4.70 ms, surpassing existing models. research contributes to advancing techniques agricultural applications offers insights into practical implementation systems control industry.

Language: Английский

---

An Optimized Role-Based Access Control Using Trust Mechanism in E-Health Cloud Environment

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 138813 - 138826

Published: Jan. 1, 2023

In today’s world, services are improved and advanced in every field of life. Especially the health sector, information technology (IT) plays a vigorous role electronic (e-health). To achieve benefits from e-health, its cloud-based implementation is necessary. With this environment’s multiple benefits, privacy security loopholes exist. As number users grows, Electronic Healthcare System’s (EHS) response time becomes slower. This study presented trust mechanism for access control (AC) known as role-based (RBAC) to address issue. method observes user’s behavior assigns roles based on it. The AC module has been implemented using SQL Server, an administrator develops controls with EHS modules. validate value, A .net-based framework introduced. e-health proposed research ensures that can protect their data intruders other threats.

Language: Английский

---