Graph Convolutional Networks For Disease Mapping and Classification in Healthcare DOI
Rakesh Kumar, Devvret Verma,

J. Relin Francis Raj

et al.

Published: Dec. 29, 2023

In the context of healthcare, this study investigates use Graph A convolutional Networks (GCNs) for disease mapping along with classification. Based on an interpretivist philosophical thought, a descriptive design alongside secondary data collection is used in deductive manner. The research creates strong framework sickness mapping, assesses how well GCNs adapt to varied health information, and compares their effectiveness more conventional machine learning techniques order determine suitable they are. An investigation conducted into understanding GCN-based diagnosis models, offering valuable perspectives decision-making procedures. findings support improved diagnostic precision, wellinformed treatment planning, precision medical treatments. emphasis when applying results procedures connection systems that provide decision support, ongoing improvement. importance model interpretability, ability be general as realworld integration highlighted by critical analysis. Developing interpretability strategies addressing ethical issues are among recommendations. ensure responsible deployment, future work ought concentrate improving GCN architectures, integrating multi-modal information advocating interdisciplinary collaboration.

Language: Английский

A model for skin cancer using combination of ensemble learning and deep learning DOI Creative Commons
Mehdi Hosseinzadeh, Dildar Hussain, Firas Muhammad Zeki Mahmood

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(5), P. e0301275 - e0301275

Published: May 31, 2024

Skin cancer has a significant impact on the lives of many individuals annually and is recognized as most prevalent type cancer. In United States, an estimated annual incidence approximately 3.5 million people receiving diagnosis skin underscores its widespread prevalence. Furthermore, prognosis for afflicted with advancing stages experiences substantial decline in survival rates. This paper dedicated to aiding healthcare experts distinguishing between benign malignant cases by employing range machine learning deep techniques different feature extractors selectors enhance evaluation metrics. this paper, transfer models are employed extractors, metrics, selection layer designed, which includes diverse such Univariate, Mutual Information, ANOVA, PCA, XGB, Lasso, Random Forest, Variance. Among models, DenseNet-201 was selected primary extractor identify features from data. Subsequently, Lasso method applied selection, utilizing approaches MLP, RF, NB. To optimize accuracy precision, ensemble methods were best-performing models. The study provides sensitivity rates 87.72% 92.15%, respectively.

Language: Английский

Citations

6
Precision Lesion Analysis and Classification in Dermatological Imaging through Advanced Convolutional Architectures DOI Creative Commons

Shake Ibna Abir,

Shaharina Shoha,

Sarder Abdulla Al Shiam

et al.

Journal of Computer Science and Technology Studies, Journal Year: 2024, Volume and Issue: 6(5), P. 168 - 180

Published: Dec. 11, 2024

In this study, six convolutional neural network (CNN) architectures, VGG16, Inception-v3, ResNet, MobileNet, NasNet, and EfficientNet are tested on classifying dermatological lesions. The research preprocesses features extracts skin lesions data to achieve an accurate lesion classification in employing two benchmark datasets, HAM10000 ISIC-2019. CNN models then extract from the filtered, resized images (uniform dimensions: 128 × 3 pixels). These results show that consistently achieves higher accuracy, precision, recall, F1-score than any other model melanoma, basal cell carcinoma actinic keratoses, with 94.0%, 92.0%, 93.8%, respectively. competitive performance of NasNet is also demonstrated for eczema psoriasis. This study concludes proper preprocessing optimized architecture important image classification. promising, however, challenges such as imbalance datasets requirement larger ethically gathered exist. For future work, dataset diversity will be improved, along generalization, through interdisciplinary collaboration advanced architectures.

Language: Английский

Citations

4
Artificial Intelligence-Driven Multidirectional Curvelet Analysis for Enganced Skin Cancer Detection DOI
Abdul Razak Mohamed Sikkander,

V. V. Lakshmi,

G. Theivanathan

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Skin Lesions as Signs of Neuroenhancement in Sport DOI Creative Commons
S A Popescu, Roman Popescu, Vlad Mihai Voiculescu

et al.

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 315 - 315

Published: March 17, 2025

Background: Neuroenhancement in sports, through pharmacological and non-pharmacological methods, is a complex highly debated topic with no definitive regulatory framework established by the World Anti-Doping Agency (WADA). The hypothesis that dermatological changes could serve as observable biomarkers for neurodoping introduces novel promising approach to detecting understanding physiological impacts of cognitive enhancers athletes. As methods become increasingly sophisticated, developing objective, reliable, non-invasive detection strategies imperative. Utilizing signs diagnostic tool internal neurophysiological offer critical insights into safety, fairness, ethical considerations enhancement competitive sports. A systematic correlation between skin manifestations, timeline practices, intensity provide healthcare professionals valuable tools monitoring athletes’ health ensuring strict compliance anti-doping regulations. Methods: Due limited body research on this topic, review literature was conducted, spanning from 2010 31 December 2024, using databases such PubMed, Science Direct, Google Scholar. This study followed 2020 PRISMA guidelines included English-language articles published within specified period, focusing lesions adverse reactions neuroenhancement methods. employed targeted keywords, including “skin AND rivastigmine”, galantamine”, donepezil”, memantine”, transcranial direct electrical stimulation”. Given scarcity studies directly addressing search criteria were broadened include associated brain stimulation. Eighteen relevant identified analyzed. Results: rivastigmine patches most used method neuroenhancement, pruritic (itchy) frequent effect. Donepezil fewer primarily non-pruritic reactions. Among current stimulation (tDCS) notably linked burns, due inadequate electrode–skin contact, prolonged exposure, or excessive intensity. These findings suggest specific manifestations potential indicators practices Conclusions: Although demonstrate distinctive side effects might signal neurodoping, lack robust clinical data involving athletes limits ability draw conclusions. Athletes who engage without medical supervision are at an elevated risk systemic Skin lesions, therefore, represent early marker inappropriate use overuse cognitive-enhancing drugs neuromodulation therapies. emphasize need focused establish validated neurodoping. contribute significantly ongoing neuroethical discourse regarding legitimacy safety

Language: Английский

Citations

0
A Bibliometric Review of Deep Learning Approaches in Skin Cancer Research DOI Creative Commons
Catur Supriyanto, Abu Salam, Junta Zeniarja

et al.

Computation, Journal Year: 2025, Volume and Issue: 13(3), P. 78 - 78

Published: March 19, 2025

Early detection of skin cancer is crucial for successful treatment and improved patient outcomes. Medical images play a vital role in this process, serving as the primary data source both traditional modern diagnostic approaches. This study aims to provide an overview significant medical highlight developments use deep learning early diagnosis. The scope survey includes in-depth exploration state-of-the-art methods, evaluation public datasets commonly used training validation, bibliometric analysis recent advancements field. focuses on publications Scopus database from 2019 2024. search string find articles by their abstracts, titles, keywords, several datasets, like HAM ISIC, ensuring relevance topic. Filters are applied based year, document type, language. identified 1697 articles, predominantly comprising journal conference proceedings. shows that number has increased over past five years. growth driven not only developed countries but also developing countries. Dermatology departments various hospitals advancing methods. In addition identifying publication trends, reveals underexplored areas encourage new explorations using VOSviewer Bibliometrix applications.

Language: Английский

Citations

0
Enhancing skin lesion classification: a CNN approach with human baseline comparison DOI Creative Commons
Deep Ajabani, Zaffar Ahmed Shaikh, Amr Yousef

et al.

PeerJ Computer Science, Journal Year: 2025, Volume and Issue: 11, P. e2795 - e2795

Published: April 15, 2025

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high-confidence CNN while replacing low-confidence outputs expert assessments to enhance diagnostic accuracy. A model utilizing EfficientNetB3 backbone is trained datasets from ISIC-2019 and ISIC-2020 SIIM-ISIC melanoma classification challenges evaluated a 150-image test set. model’s are compared against 69 experienced medical professionals. Performance assessed using receiver operating characteristic (ROC) curves area under curve (AUC) metrics, alongside analysis resource costs. baseline achieves AUC 0.822, slightly below performance experts. However, improves true positive rate 0.782 reduces false 0.182, delivering better minimal involvement. offers scalable, resource-efficient solution address variability in image analysis, effectively harnessing complementary strengths humans CNNs.

Language: Английский

Citations

0
Skin Cancer Diagnosis (SCD) Using EfficientNet-Wavelet and Gray Wolf Optimization (GWO) DOI

Ali Abesi,

Amir Ali Bengari,

Khabiba Abdiyeva

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Bayesian‐Edge system for classification and segmentation of skin lesions in Internet of Medical Things DOI Creative Commons
Shahid Naseem, Muhammad Awais Anwar, Muhammad Faheem

et al.

Skin Research and Technology, Journal Year: 2024, Volume and Issue: 30(8)

Published: July 31, 2024

Abstract Background Skin diseases are severe diseases. Identification of these depends upon the abstraction atypical skin regions. The segmentation is essential to rheumatologists in risk impost and for valuable vital decision‐making. lesion from images a crucial step toward achieving this goal—timely exposure malignancy psoriasis expressively intensifies persistence ratio. Defies occur when people presume they have without accurately precisely incepted. However, analyzing at runtime big challenge due truncated distinction visual similarity between malignance non‐malignance lesions. images' different shapes, contrast, vibrations make challenging. Recently, various researchers explored applicability deep learning models segmentation. Materials methods This paper introduces lesions model that integrates two intelligent methodologies: Bayesian inference edge intelligence. In model, we deal with intelligence utilize texture features enhances segmentation's accuracy efficiency. Results We analyze our work along several dimensions, including input data (datasets, preprocessing, synthetic generation), design (architecture, modules), evaluation aspects (data annotation requirements performance). discuss dimensions seminal works systematic viewpoint examine how influenced current trends. Conclusion summarize previously used techniques comprehensive table facilitate comparisons. Our experimental results show Bayesian‐Edge networks can boost diagnostic performance by up 87.80% incurring additional parameters heavy computation.

Language: Английский

Citations

3
Enhancing Skin Lesion Detection: A Multistage Multiclass Convolutional Neural Network-Based Framework DOI Creative Commons
Muhammad Umair Ali,

Majdi Khalid,

Hanan Alshanbari

et al.

Bioengineering, Journal Year: 2023, Volume and Issue: 10(12), P. 1430 - 1430

Published: Dec. 15, 2023

The early identification and treatment of various dermatological conditions depend on the detection skin lesions. Due to advancements in computer-aided diagnosis machine learning approaches, learning-based lesion analysis methods have attracted much interest recently. Employing concept transfer learning, this research proposes a deep convolutional neural network (CNN)-based multistage multiclass framework categorize seven types In first stage, CNN model was developed classify images into two classes, namely benign malignant. second then used with further lesions five subcategories (melanocytic nevus, actinic keratosis, dermatofibroma, vascular) malignant (melanoma basal cell carcinoma). frozen weights developed-trained correlated benefited using same type for subclassification classes. proposed technique improved classification accuracy online ISIC2018 dataset by up 93.4% class identification. Furthermore, high 96.2% achieved both Sensitivity, specificity, precision, F1-score metrics validated effectiveness framework. Compared existing models described literature, approach took less time train had higher rate.

Language: Английский

Citations

7
Recent advancements using machine learning & deep learning approaches for diabetes detection: a systematic review DOI Creative Commons
Neha Katiyar, Hardeo Kumar Thakur, Anindya Ghatak

et al.

e-Prime - Advances in Electrical Engineering Electronics and Energy, Journal Year: 2024, Volume and Issue: 9, P. 100661 - 100661

Published: June 28, 2024

Nowadays, Diabetes Mellitus is one of the significant health challenges that affects many people across world. Early detection will help in preventing complications, i.e., kidney disease, nerve damage, eye etc. Over past few years, several Machine Learning and Deep techniques have been applied for early Mellitus. The paper provides reviews on various mellitus. review criteria mainly focus five topics: diabetes dataset, methods used, performance metrics, limitations work, overall status diabetic research. objective this to provide a comprehensive prediction applying be helpful sources researchers healthcare field.

Language: Английский

Citations

2