Medical image analysis using deep learning algorithms

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: Nov. 7, 2023

In the field of medical image analysis within deep learning (DL), importance employing advanced DL techniques cannot be overstated. has achieved impressive results in various areas, making it particularly noteworthy for healthcare. The integration with enables real-time vast and intricate datasets, yielding insights that significantly enhance healthcare outcomes operational efficiency industry. This extensive review existing literature conducts a thorough examination most recent (DL) approaches designed to address difficulties faced healthcare, focusing on use algorithms analysis. Falling all investigated papers into five different categories terms their techniques, we have assessed them according some critical parameters. Through systematic categorization state-of-the-art such as Convolutional Neural Networks (CNNs), Recurrent (RNNs), Generative Adversarial (GANs), Long Short-term Memory (LSTM) models, hybrid this study explores underlying principles, advantages, limitations, methodologies, simulation environments, datasets. Based our results, Python was frequent programming language used implementing proposed methods papers. Notably, majority scrutinized were published 2021, underscoring contemporaneous nature research. Moreover, accentuates forefront advancements practical applications realm analysis, while simultaneously addressing challenges hinder widespread implementation domains. These discerned serve compelling impetuses future studies aimed at progressive advancement evaluation metrics employed across reviewed articles encompass broad spectrum features, encompassing accuracy, sensitivity, specificity, F-score, robustness, computational complexity, generalizability.

Language: Английский

---

Adventures in data analysis: a systematic review of Deep Learning techniques for pattern recognition in cyber-physical-social systems

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(8), P. 22909 - 22973

Published: Aug. 9, 2023

Language: Английский

---

Breast cancer diagnosis using evolving deep convolutional neural network based on hybrid extreme learning machine technique and improved chimp optimization algorithm

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 87, P. 105492 - 105492

Published: Sept. 28, 2023

Language: Английский

---

Trends in using deep learning algorithms in biomedical prediction systems

Frontiers in Neuroscience, Journal Year: 2023, Volume and Issue: 17

Published: Nov. 9, 2023

In the domain of using DL-based methods in medical and healthcare prediction systems, utilization state-of-the-art deep learning (DL) methodologies assumes paramount significance. DL has attained remarkable achievements across diverse domains, rendering its efficacy particularly noteworthy this context. The integration with health systems enables real-time analysis vast intricate datasets, yielding insights that significantly enhance outcomes operational efficiency industry. This comprehensive literature review systematically investigates latest solutions for challenges encountered healthcare, a specific emphasis on applications domain. By categorizing cutting-edge approaches into distinct categories, including convolutional neural networks (CNNs), recurrent (RNNs), generative adversarial (GANs), long short-term memory (LSTM) models, support vector machine (SVM), hybrid study delves their underlying principles, merits, limitations, methodologies, simulation environments, datasets. Notably, majority scrutinized articles were published 2022, underscoring contemporaneous nature research. Moreover, accentuates forefront advancements techniques practical within realm while simultaneously addressing hinder widespread implementation image segmentation domains. These discerned serve as compelling impetuses future studies aimed at progressive advancement systems. evaluation metrics employed reviewed encompass broad spectrum features, encompassing accuracy, precision, specificity, F-score, adoptability, adaptability, scalability.

Language: Английский

---

A Fast and Light Fingerprint-Matching Model Based on Deep Learning Approaches

Journal of Signal Processing Systems, Journal Year: 2023, Volume and Issue: 95(4), P. 551 - 558

Published: April 1, 2023

Language: Английский

---

MSLEFC: A low-frequency focused underwater acoustic signal classification and analysis system

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 123, P. 106333 - 106333

Published: May 6, 2023

Language: Английский

---

Multilayer Perception-Based Hybrid Spectral Band Selection Algorithm for Aflatoxin B1 Detection Using Hyperspectral Imaging

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(20), P. 9313 - 9313

Published: Oct. 12, 2024

Aflatoxin B1 is a toxic substance in almonds, other nuts, and grains that poses potential serious health risks to humans animals, particularly warm, humid climates. Therefore, it necessary remove aflatoxin before almonds enter the supply chain ensure food safety. Hyperspectral imaging (HSI) rapid, non-destructive method for detecting by analyzing specific spectral data. However, HSI increases data dimensionality often includes irrelevant information, complicating analysis process. These challenges make classification models complex less reliable, especially real-time, in-line applications. This study proposed novel hybrid band selection algorithm detect based on multilayer perceptron (MLP) network weights refinement (W-SR). In process, hyperspectral rank was firstly generated MLP weights. The further updated using confidence matrix. Then, process identified more important spectra from lower-ranked ones through iterative processes. An exhaustive search performed select an optimal subset, consisting of only most significant bands, entire suitable detection industrial environments. experimental results artificially contaminated dataset achieved cross-validation accuracy 98.67% with F1-score 0.982 standard normal variate (SNV) processed four bands. Comparative experiment showed MLPW-SR outperforms baseline methods.

Language: Английский

---

Non-Destructive Detection of Chilled Mutton Freshness Using a Dual-Branch Hierarchical Spectral Feature-Aware Network

Foods, Journal Year: 2025, Volume and Issue: 14(8), P. 1379 - 1379

Published: April 17, 2025

Precise detection of meat freshness levels is essential for food consumer safety and real-time quality monitoring. This study aims to achieve the high-accuracy chilled mutton by integrating hyperspectral imaging with deep learning methods. Although data can effectively capture changes in freshness, sparse raw spectra require optimal processing strategies minimize redundancy. Therefore, this employs a multi-stage approach enhance purity feature spectra. Meanwhile, address issues such as overlapping categories, imbalanced sample distributions, insufficient intermediate features, we propose Dual-Branch Hierarchical Spectral Feature-Aware Network (DBHSNet) detection. First, at interaction stage, PBCA module addresses drawback that global local branches conventional dual-branch framework tend perceive spectral features independently. By enabling effective information exchange bidirectional flow between two branches, injecting positional into each band, model’s awareness sequential bands enhanced. Second, fusion task-driven MSMHA introduced dynamics variation accumulation different metabolites. leveraging multi-head attention cross-scale fusion, model more captures both overall trends fine-grained details. Third, classification output dynamic loss weighting set according training epochs relative losses balance performance, mitigating impact insufficiently discriminative features. The results demonstrate DBHSNet enables precise assessment achieving up 7.59% higher accuracy than methods under same preprocessing conditions, while maintaining superior weighted metrics. Overall, offers novel provides valuable support monitoring cold-chain systems.

Language: Английский

---

Artificial Intelligence Approaches to Modeling Equivalent Circulating Density for Improved Drilling Mud Management

ACS Omega, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Language: Английский

---

Two-dimensional spatial orientation relation recognition between image objects

Engineering Science and Technology an International Journal, Journal Year: 2025, Volume and Issue: 67, P. 102074 - 102074

Published: May 3, 2025

Language: Английский

---