Skin Cancer Detection and Classification Using Neural Network Algorithms: A Systematic Review

Diagnostics, Journal Year: 2024, Volume and Issue: 14(4), P. 454 - 454

Published: Feb. 19, 2024

In recent years, there has been growing interest in the use of computer-assisted technology for early detection skin cancer through analysis dermatoscopic images. However, accuracy illustrated behind state-of-the-art approaches depends on several factors, such as quality images and interpretation results by medical experts. This systematic review aims to critically assess efficacy challenges this research field order explain usability limitations highlight potential future lines work scientific clinical community. study, was carried out over 45 contemporary studies extracted from databases Web Science Scopus. Several computer vision techniques related image video processing diagnosis were identified. context, focus process included algorithms employed, result accuracy, validation metrics. Thus, yielded significant advancements using deep learning machine algorithms. Lastly, establishes a foundation research, highlighting contributions opportunities improve effectiveness learning.

Language: Английский

---

Review of Federated Learning and Machine Learning-Based Methods for Medical Image Analysis

Big Data and Cognitive Computing, Journal Year: 2024, Volume and Issue: 8(9), P. 99 - 99

Published: Aug. 28, 2024

Federated learning is an emerging technology that enables the decentralised training of machine learning-based methods for medical image analysis across multiple sites while ensuring privacy. This review paper thoroughly examines federated research applied to analysis, outlining technical contributions. We followed guidelines Okali and Schabram, a methodology, produce comprehensive summary discussion literature in information systems. Searches were conducted at leading indexing platforms: PubMed, IEEE Xplore, Scopus, ACM, Web Science. found total 433 papers selected 118 them further examination. The findings highlighted on applying neural network cardiology, dermatology, gastroenterology, neurology, oncology, respiratory medicine, urology. main challenges reported ability models adapt effectively real-world datasets privacy preservation. outlined two strategies address these challenges: non-independent identically distributed data privacy-enhancing methods. offers reference overview those already working field introduction new topic.

Language: Английский

---

Utility of artificial intelligence in dermatology: Challenges and perspectives

IP Indian Journal of Clinical and Experimental Dermatology, Journal Year: 2025, Volume and Issue: 11(1), P. 1 - 9

Published: Feb. 8, 2025

Medicine is entering a transformative era with disruptive technologies such as virtual reality, genomic prediction, data analytics, personalized medicine, stem cell therapy, 3-D printing, and nanorobotics. Dermatology significantly impacted by these advancements, particularly through artificial intelligence (AI). AI, defined devices performing functions typically requiring human intelligence, plays an increasingly prominent role in healthcare. John McCarthy coined the term AI 1956. In dermatology, aids diagnosis, treatment planning, understanding diseases across communities. Machine learning deep learning, subsets of require extensive datasets robust analysis to improve accuracy performance. AI's integration into dermatology revolutionizing field enabling precision, reducing errors, minimizing staffing needs. tools support dermatologists diagnosing treating various conditions, from psoriasis acne dermatitis ulcers. Convolutional neural networks (CNNs) enhance classification skin lesions, while predictive models optimize strategies based on patient data. extends oncology, where it improves cancer detection image histopathological assessment. Despite its potential, faces challenges quality, representativeness, algorithm transparency, ethical considerations. Addressing biases, standardizing imaging protocols, enhancing human-machine collaboration are crucial for maximizing benefits. holds immense promise offering innovative solutions care diagnostic accuracy. The future includes advancements vision-language models, federated precision medicine approaches. Overcoming related privacy, regulatory standards, model evaluation essential successful clinical practice. Collaborative efforts among stakeholders vital drive progress realize full potential ultimately improving outcomes globally.

Language: Английский

---

Symmetry in Privacy-Based Healthcare: A Review of Skin Cancer Detection and Classification Using Federated Learning

Symmetry, Journal Year: 2023, Volume and Issue: 15(7), P. 1369 - 1369

Published: July 5, 2023

Skin cancer represents one of the most lethal and prevalent types observed in human population. When diagnosed its early stages, melanoma, a form skin cancer, can be effectively treated cured. Machine learning algorithms play crucial role facilitating timely detection aiding accurate diagnosis appropriate treatment patients. However, implementation traditional machine approaches for disease is impeded by privacy regulations, which necessitate centralized processing patient data cloud environments. To overcome challenges associated with privacy, federated emerges as promising solution, enabling development privacy-aware healthcare systems diagnosis. This paper presents comprehensive review that examines obstacles faced conventional explores integration context privacy-conscious prediction systems. It provides discussion on various datasets available performance comparison techniques lesion prediction. The objective to highlight advantages offered potential addressing concerns realm

Language: Английский

---

Asynchronous Federated Learning for Improved Cardiovascular Disease Prediction Using Artificial Intelligence

Diagnostics, Journal Year: 2023, Volume and Issue: 13(14), P. 2340 - 2340

Published: July 11, 2023

Healthcare professionals consider predicting heart disease an essential task and deep learning has proven to be a promising approach for achieving this goal. This research paper introduces novel method called the asynchronous federated cardiac prediction (AFLCP), which combines dataset neural networks (DNNs) with technique. The proposed employs asynchronously updating parameters of DNNs incorporates temporally weighted aggregation technique enhance accuracy convergence central model. To evaluate effectiveness AFLCP method, two datasets various DNN architectures are tested, results demonstrate that outperforms baseline in terms both communication cost model accuracy.

Language: Английский

---

Towards trustworthy AI-driven leukemia diagnosis: A hybrid Hierarchical Federated Learning and explainable AI framework

Informatics in Medicine Unlocked, Journal Year: 2025, Volume and Issue: unknown, P. 101618 - 101618

Published: Jan. 1, 2025

Language: Английский

---

From challenges and pitfalls to recommendations and opportunities: Implementing federated learning in healthcare

Medical Image Analysis, Journal Year: 2025, Volume and Issue: 101, P. 103497 - 103497

Published: Feb. 14, 2025

Federated learning holds great potential for enabling large-scale healthcare research and collaboration across multiple centers while ensuring data privacy security are not compromised. Although numerous recent studies suggest or utilize federated based methods in healthcare, it remains unclear which ones have clinical utility. This review paper considers analyzes the most up to May 2024 that describe healthcare. After a thorough review, we find vast majority appropriate use due their methodological flaws and/or underlying biases include but limited concerns, generalization issues, communication costs. As result, effectiveness of is significantly To overcome these challenges, provide recommendations promising opportunities might be implemented resolve problems improve quality model development with

Language: Английский

---

Deep Multilevel Feature Fusion: An Xception-Based Framework Enhanced by Assorted Attention Mechanism for Improved Melanoma Diagnosis

International Journal of Scientific Research in Computer Science Engineering and Information Technology, Journal Year: 2025, Volume and Issue: 11(1), P. 3635 - 3644

Published: Feb. 25, 2025

Melanoma DiagnosisArtificial Intelligence (AI), Machine Learning (ML), and Deep (DL) have a game-changing potential in melanoma diagnosis treatment. Utilizing these technologies can tremendously increase the accuracy efficiency of detection as they rely on algorithms neural networks to process large volumes data quickly accurately like never before. The DMFFX(Deep Multilevel Feature Fused Xception) for feature extraction model, followed by segmentation model AAMBCS(Assorted Attention Mechanism based Convolutional Segmentation), shows contribution AI improving image quality diagnostic accuracy. By employing DEECO (Differential Evolution Based Enhanced Colour Optimization) preprocessing Xception network enhance results, classification processes become more potent efficient, resulting accurate reliable results. study emphasizes critical role early enhancing patient outcomes survival rates. AI-powered present many benefits offering standard evaluations that reduce human element opportunity error. While developments are promising, researchers field healthcare need work overcoming challenges research gaps identified deliver real-time technology healthcare.

Language: Английский

---

SoK: Federated Learning and Unlearning for Medical Image Analysis

Expert Systems, Journal Year: 2025, Volume and Issue: 42(6)

Published: May 6, 2025

ABSTRACT Medical image analysis is a critical component of modern healthcare, enabling accurate disease diagnosis and effective patient treatment. However, the process fraught with challenges, including inter‐ intra‐observer variability, time constraints, data‐related issues such as privacy, heterogeneity accessibility. Within this framework, Federated Learning (FL) has emerged promising solution, allowing collaborative model training across distributed healthcare entities without sharing sensitive data. This study provides comprehensive Systematization Knowledge (SoK) review FL its extension, Unlearning (FU), within context medical analysis. enables privacy‐preserving, decentralised training, while FU addresses ‘Right To Be Forgotten’, ensuring compliance data protection regulations like GDPR HIPAA. We explore opportunities challenges FU, detailing their methodologies, frameworks, datasets, evaluation metrics. The highlights potential to enhance diagnostic accuracy, improve care, foster trust in AI‐driven systems. also identify research gaps propose future directions for advancing imaging, emphasising need interdisciplinary collaboration development dedicated frameworks. Thus, aims bridge gap between theoretical advancements practical applications, paving way more robust privacy‐compliant AI models healthcare.

Language: Английский

---

Federated Averaging Optimization for Efficient Skin Cancer Image Analysis

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 3794 - 3803

Published: Jan. 1, 2025

Language: Английский

---