DDCNN-F: double decker convolutional neural network 'F' feature fusion as a medical image classification framework DOI Creative Commons
Nirmala Veeramani, Premaladha Jayaraman, R. Krishankumar

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Jan. 5, 2024

Abstract Melanoma is a severe skin cancer that involves abnormal cell development. This study aims to provide new feature fusion framework for melanoma classification includes novel ‘F’ Flag early detection. indicator efficiently distinguishes benign lesions from malignant ones known as melanoma. The article proposes an architecture built in Double Decker Convolutional Neural Network called DDCNN future fusion. network's deck one, (CNN), finds difficult-to-classify hairy images using confidence factor termed the intra-class variance score. These hirsute image samples are combined form Baseline Separated Channel (BSC). By eliminating hair and data augmentation techniques, BSC ready analysis. second trains pre-processed generates bottleneck features. features merged with generated ABCDE clinical bio indicators promote accuracy. Different types of classifiers fed resulting hybrid fused 'F' feature. proposed system was trained ISIC 2019 2020 datasets assess its performance. empirical findings expose strategy exposing achieved specificity 98.4%, accuracy 93.75%, precision 98.56%, Area Under Curve (AUC) value 0.98. approach can accurately identify diagnose fatal outperform other state-of-the-art which attributed Feature framework. Also, this research ascertained improvements several when utilising indicator, highest + 7.34%.

Language: Английский

Diffusion models in medical imaging: A comprehensive survey DOI
Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari

et al.

Medical Image Analysis, Journal Year: 2023, Volume and Issue: 88, P. 102846 - 102846

Published: May 23, 2023

Language: Английский

Citations

264
The Role of Artificial Intelligence in Echocardiography DOI Creative Commons
Timothy Barry, Juan Farina, Chieh‐Ju Chao

et al.

Journal of Imaging, Journal Year: 2023, Volume and Issue: 9(2), P. 50 - 50

Published: Feb. 20, 2023

Echocardiography is an integral part of the diagnosis and management cardiovascular disease. The use application artificial intelligence (AI) a rapidly expanding field in medicine to improve consistency reduce interobserver variability. AI can be successfully applied echocardiography addressing variance during image acquisition interpretation. Furthermore, machine learning aid In realm echocardiography, accurate interpretation largely dependent on subjective knowledge operator. burdened by high dependence level experience operator, greater extent than other imaging modalities like computed tomography, nuclear imaging, magnetic resonance imaging. technologies offer new opportunities for produce accurate, automated, more consistent interpretations. This review discusses as subfield within relation how diagnostic performance echocardiography. also explores published literature outlining value its potential patient care.

Language: Английский

Citations

65
Classification models combined with Boruta feature selection for heart disease prediction DOI Creative Commons

G. Manikandan,

B. Pragadeesh,

V. Manojkumar

et al.

Informatics in Medicine Unlocked, Journal Year: 2024, Volume and Issue: 44, P. 101442 - 101442

Published: Jan. 1, 2024

Cardiovascular disease (CVD), generally called heart illness, is a collective term for various ailments that affect the and blood vessels. Heart primary cause of fatality morbidity in people worldwide, resulting 18 million deaths per year. By identifying those who are most vulnerable to diseases ensuring they receive appropriate care, premature demise can be prevented. Machine learning algorithms now crucial medical field, especially when using databases diagnose diseases. Such efficient data processing techniques applied predict offer much potential accurate prognosis. Therefore, this study compares performance logistic regression, decision tree, support vector machine (SVM) methods with without Boruta feature selection. The Cleveland clinic dataset acquired from Kaggle, which consists 14 features 303 instances, was used investigation. It found selection algorithm, selects six relevant features, improved results algorithms. Among these classification algorithms, regression produced result, an accuracy 88.52 %.

Language: Английский

Citations

45
Deep learning for enhanced brain Tumor Detection and classification DOI Creative Commons
M. Agarwal, Geeta Rani, Ambeshwar Kumar

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102117 - 102117

Published: April 16, 2024

The purpose of this research is to build an automated, robust, intelligent and hybrid system for the early diagnosis classifying brain tumor. To serve purpose, authors propose Auto Contrast Enhancer, Tumor Detector Classifier efficiently provide on-demand contrast improvement poor MRI images classification tumors. classifier accomplishes its task through a two-phase approach. During initial phase, ODTWCHE employed enhance image contrast, facilitating accurate tumours. In subsequent leverages power deep transfer learning, utilizing pre-trained Inception V3 model refine diagnostic process further. tumor classification. Compared state-of-the-art models, including AlexNet, VGG-16, DenseNet-201, VGG-19, GoogLeNet, ResNet-50, proposed showcased outstanding performance by achieving highest accuracy 98.89% on public dataset that consists with varying brightness levels. precise detection achieved multicolored prove system's robustness. article address usage metrics in variety contexts, academia, as well possible problems may result from their improper application. They emphasize how crucial it create measurements align objectives reduce any negative consequences can skew data or allow people manipulate incentives. thorough creating takes into account design considerations, countermeasures unfavorable effects, requirements. paper provides answers creation gives examples metrics' failures many fields. significance understanding goal at hand relate one another, necessity compromise clarity when goals are contradictory incoherent. A comparative analysis existing models further confirms consistently outperforms competition.

Language: Английский

Citations

33
Twelve tips for addressing ethical concerns in the implementation of artificial intelligence in medical education DOI Creative Commons

Russell D’Souza,

Mary Mathew,

Vedprakash Mishra

et al.

Medical Education Online, Journal Year: 2024, Volume and Issue: 29(1)

Published: April 3, 2024

Artificial Intelligence (AI) holds immense potential for revolutionizing medical education and healthcare. Despite its proven benefits, the full integration of AI faces hurdles, with ethical concerns standing out as a key obstacle. Thus, educators should be equipped to address issues that arise ensure seamless sustainability AI-based interventions. This article presents twelve essential tips addressing major in use education. These include emphasizing transparency, bias, validating content, prioritizing data protection, obtaining informed consent, fostering collaboration, training educators, empowering students, regularly monitoring, establishing accountability, adhering standard guidelines, forming an ethics committee implementation AI. By these tips, other stakeholders can foster responsible education, ensuring long-term success positive impact.

Language: Английский

Citations

23
A critical review of machine learning algorithms in maritime, offshore, and oil & gas corrosion research: A comprehensive analysis of ANN and RF models DOI
Md Mahadi Hasan Imran, Shahrizan Jamaludin, Ahmad Faisal Mohamad Ayob

et al.

Ocean Engineering, Journal Year: 2024, Volume and Issue: 295, P. 116796 - 116796

Published: Jan. 30, 2024

Language: Английский

Citations

21
Liquid biopsy for human cancer: cancer screening, monitoring, and treatment DOI Creative Commons
Hao Wang, Yi Zhang, Hao Zhang

et al.

MedComm, Journal Year: 2024, Volume and Issue: 5(6)

Published: May 28, 2024

Currently, tumor treatment modalities such as immunotherapy and targeted therapy have more stringent requirements for obtaining growth information require accurate easy-to-operate detection methods. Compared with traditional tissue biopsy, liquid biopsy is a novel, minimally invasive, real-time tool detecting directly or indirectly released by tumors in human body fluids, which suitable the of new modalities. Liquid has not been widely used clinical practice, there are fewer reviews related applications. This review summarizes applications components (e.g., circulating cells, DNA, extracellular vesicles, etc.) tumorigenesis progression. includes development process techniques biopsies, early screening tumors, detection, guiding therapeutic strategies (liquid biopsy-based personalized medicine prediction response). Finally, current challenges future directions proposed. In sum, this will inspire researchers to use technology promote realization individualized therapy, improve efficacy provide better options patients.

Language: Английский

Citations

21
Enhanced image diagnosing approach in medicine using quantum adaptive machine learning techniques DOI
Sajja Suneel,

R. Krishnamoorthy,

Anandbabu Gopatoti

et al.

Optical and Quantum Electronics, Journal Year: 2024, Volume and Issue: 56(4)

Published: Jan. 30, 2024

Language: Английский

Citations

18
Artificial intelligence for diabetic retinopathy detection: A systematic review DOI Creative Commons
Archana Senapati, Hrudaya Kumar Tripathy, Vandana Sharma

et al.

Informatics in Medicine Unlocked, Journal Year: 2024, Volume and Issue: 45, P. 101445 - 101445

Published: Jan. 1, 2024

The incidence of diabetic retinopathy (DR) has increased at a rapid pace in recent years all over the world. Diabetic eye illness is identified as one most common reasons for vision loss among people. To properly manage DR, there been immense research and exploration state-of-the-art methods using artificial intelligence (AI) enabled models. Specifically, AI-empowered models combine multiple machine learning (ML) deep (DL) based algorithms to improve performance developed system architectures that are commercially utilized detection DR disease. However, these still exhibit several limitations, such computational complexity, low accuracy stage due class imbalance, more time consumption, high maintenance cost. overcome limits, advanced model required accurately predict initial stages. For example, identification disease helps ophthalmologist make an accurate safe diagnosis, thereby, eyesight-related issues may be treated effectively. This study conducted systematic literature review (SLR) provide detailed discussion background retinopathy, its major causes, challenges faced by ophthalmologists detection, possible solutions identifying stage. Also, SLR provides in-depth analysis existing techniques used diagnosis on AI, ML, recently DL-based approaches. Furthermore, this present survey would helpful community receive information approaches along with their significant limitations.

Language: Английский

Citations

16
A Comprehensive Review of Bat Inspired Algorithm: Variants, Applications, and Hybridization DOI Open Access
Mohammad Shehab,

Muhannad A. Abu‐Hashem,

Mohd Khaled Yousef Shambour

et al.

Archives of Computational Methods in Engineering, Journal Year: 2022, Volume and Issue: 30(2), P. 765 - 797

Published: Sept. 21, 2022

Language: Английский

Citations

65