doi: 10.62486/latia202474

 

ORIGINAL

 

Advancing Medical Image Analysis: The Role of Adaptive Optimization Techniques in Enhancing COVID-19 Detection, Lung Infection, and Tumor Segmentation

 

Avances en el análisis de imágenes médicas: el papel de las técnicas de optimización adaptativa para mejorar la detección de la COVID-19, la infección pulmonar y la segmentación de tumores

 

Muhyeeddin Alqaraleh1  *, Mowafaq Salem Alzboon2  *, Mohammad Subhi Al-Batah2  *, Mutaz Abdel Wahed2  *

 

1Faculty of Information Technology, Zarqa University, Zarqa, Jordan.              

2Faculty of Information Technology, Jadara University, Irbid, Jordan.

 

Cite as: Muhyeeddin A, Mowafaq SA, Al-Batah MS, Mutaz AW. Advancing Medical Image Analysis: The Role of Adaptive Optimization Techniques in Enhancing COVID-19 Detection, Lung Infection, and Tumor Segmentation. LatIA. 2024; 2:74. https://doi.org/10.62486/latia202474

 

Submitted: 01-02-2024                   Revised: 12-05-2024                   Accepted: 07-10-2024                 Published: 08-10-2024

 

Editor: Dr. Rubén González Vallejo

 

Corresponding auhtor: Muhyeeddin Alqaraleh *

 

ABSTRACT

 

Artificial intelligence (AI) holds significant potential to revolutionize healthcare by improving clinical practices and patient outcomes. This research explores the integration of AI in healthcare, focusing on methodologies such as machine learning, natural language processing, and computer vision, which enable the extraction of valuable insights from complex medical imaging and clinical data. Through a comprehensive literature review, the study highlights AI’s practical applications in diagnostics, treatment planning, and predicting patient outcomes. Additionally, ethical issues, data privacy, and legal frameworks are examined, emphasizing the importance of responsible AI usage in healthcare. The findings demonstrate AI’s ability to enhance diagnostic accuracy, streamline administrative tasks, and optimize resource allocation, leading to personalized treatments and more efficient healthcare management. However, challenges remain, including data quality, algorithm transparency, and ethical concerns, which must be addressed to ensure safe and effective AI deployment. Continued research, collaboration between healthcare professionals and AI experts, and the development of robust regulatory frameworks are essential for maximizing AI’s benefits while minimizing risks. This research underscores the transformative potential of AI in healthcare and stresses the need for a multidisciplinary approach to address the ethical and regulatory complexities involved in its widespread adoption.

 

Keywords: Artificial Intelligence in Healthcare; AI Applications in Medicine; Predictive Analytics in Healthcare; Precision Medicine; Algorithmic Bias; Ethical Issues in AI.

 

RESUMEN

 

La inteligencia artificial (IA) tiene un potencial significativo para revolucionar la atención médica al mejorar las prácticas clínicas y los resultados de los pacientes. Esta investigación explora la integración de la IA en la atención médica, centrándose en metodologías como el aprendizaje automático, el procesamiento del lenguaje natural y la visión artificial, que permiten la extracción de información valiosa de imágenes médicas complejas y datos clínicos. A través de una revisión exhaustiva de la literatura, el estudio destaca las aplicaciones prácticas de la IA en el diagnóstico, la planificación del tratamiento y la predicción de los resultados de los pacientes. Además, se examinan cuestiones éticas, la privacidad de los datos y los marcos legales, enfatizando la importancia del uso responsable de la IA en la atención médica. Los hallazgos demuestran la capacidad de la IA para mejorar la precisión del diagnóstico, agilizar las tareas administrativas y optimizar la asignación de recursos, lo que conduce a tratamientos personalizados y una gestión de la atención médica más eficiente. Sin embargo, siguen existiendo desafíos, incluida la calidad de los datos, la transparencia de los algoritmos y las preocupaciones éticas, que deben abordarse para garantizar una implementación segura y eficaz de la IA. La investigación continua, la colaboración entre los profesionales de la salud y los expertos en IA y el desarrollo de marcos regulatorios sólidos son esenciales para maximizar los beneficios de la IA y minimizar los riesgos. Esta investigación subraya el potencial transformador de la IA en la atención médica y destaca la necesidad de un enfoque multidisciplinario para abordar las complejidades éticas y regulatorias involucradas en su adopción generalizada.

 

Palabras clave: Inteligencia Artificial en el Ámbito Sanitario; Aplicaciones de la IA en la Medicina; Análisis Predictivo en el Ámbito Sanitario; Medicina de Precisión; Sesgo Algorítmico; Cuestiones Éticas en la IA.

 

 

 

INTRODUCTION

The integration of artificial intelligence (AI) into healthcare represents a paradigm shift that has the potential to revolutionize clinical operations and patient care. Initially introduced in the 20th century, AI systems, while limited in scope, laid the foundation for the rapid advancement and adoption of AI in medicine. As we progress into the 21st century, AI applications in healthcare have expanded significantly. Modern AI systems are now capable of handling predictive analytics, supporting real-time surgical assistance, and enhancing precision medicine by tailoring treatments to genetic profiles. Furthermore, AI plays a crucial role in public health, aiding in disease regulation at unprecedented scales.(1)

The growth of AI in healthcare has been shaped by technological advancements and key developments, particularly in algorithmic design for processing complex clinical data. With improvements in computing power and machine learning techniques, AI systems can now analyze vast datasets autonomously, leading to more accurate diagnoses, personalized treatment plans, and better patient outcomes.(2)

However, the increasing use of AI in healthcare brings ethical challenges, including concerns about data privacy, algorithmic bias, and the potential displacement of clinical professionals. This study aims to explore both the benefits and ethical considerations associated with AI in healthcare, using case studies and recent research to provide a comprehensive analysis of its transformative impact. The research will also highlight the need for responsible AI applications and guide future studies and policies toward fostering a more equitable and sustainable healthcare system.(3)

 

Related work

Increasing diagnosis accuracy and illness monitoring requires healthcare reform. This paper highlights how PSO-ACO optimisation and swarm intelligence might alter healthcare by improving medical image analysis and disease surveillance. What makes these strategies revolutionary in healthcare? This essay highlights PSO-ACO optimisation and swarm intelligence’s strengths and healthcare applications. Researchers study how PSO-ACO optimisation and swarm intelligence improve clinical image evaluation and disease surveillance. The report evaluates the literature, examining strategies’ benefits and downsides and their healthcare applications. The overview highlights this location’s concerns and future directions, emphasising new research and development. This extensive review reveals how PSO-ACO optimisation and swarm intelligence could change healthcare. These methods may revolutionise medical image analysis and disease surveillance.(4)

In the fourth industrial revolution, healthcare is one of the fastest-growing sectors. Human-powered, lengthy, and error-prone methods are used by most healthcare professionals. The current paradigm, new scientific results, technology preparedness, supervised machine learning (SML) possibilities in numerous healthcare businesses, and ethical considerations are discussed in this study. Disease diagnosis, personalised medicine, clinical trials, non-invasive image analysis, drug discovery, patient care services, remote patient monitoring, hospital data, nanotechnology, learning-based automation, and explainable AI are evaluated. To grasp non-invasive therapeutic architecture, medical imaging analysis is examined technically. This study also highlights new AI and SML innovations that will benefit healthcare. SML-based systems need data quality awareness because healthcare is data-heavy and knowledge management is essential. Today, biomedical and healthcare SML requires expertise, data quality awareness for data-intensive studies, and a knowledge-centric health management system. Ethics and other AI and SML consequences must be considered in the pros and cons. The findings of this work will aid academics and industry in SML research in healthcare and biomedical domains.(5)

NLP and medical imaging advancements have substantially increased deep-learning model applications. These advances have improved data comprehension and raised awareness of cutting-edge structures and their practical applications. Medical imaging researchers recognize the limitations of focusing exclusively on images and the importance of multimodal inputs. This discipline suffers from inadequate literature reviews. Contemporary research perspectives, structures, tasks, datasets, and performance measurements are examined in this work. To provide academics and healthcare professionals with a comprehensive summary of academic studies and logical insights to guide future research, we also provide a concise assessment of capability future paths.(6,7)

Deep mastering models have improved thanks to NLP and scientific imaging. These improvements have increased data comprehension and knowledge of modern structures’ practical possibilities. Medical imaging experts recognise the limitations of image-only research and the value of multimodal inputs. Poor literature reviews hurt this field. Field research designs, tasks, datasets, and performance indicators are examined in this study. We also provide a succinct description of future directions to give academics and healthcare practitioners a complete understanding of academic research and logical insights to inspire future study.(8)

In recent years, medical image fusion has become a thorough analytical approach with numerous modification techniques. Medical image fusion improves photo quality and accuracy by combining images from multiple modalities. This field encompasses picture processing, laptop vision, pattern recognition, machine learning, and AI. Large clinical programs have employed clinical image fusion to help clinicians understand lesions by combining scientific photos from multiple modalities. Grey Wolf rules with several learning models reduce squared errors and optimise the process using weighted entropy and picture fusion. The necessary results were achieved by hybridising DWT and DCT. GWO-RNN is a unique unsupervised classification fusion using Principle Component Analysis, Grey Wolf Optimisation, and a Recurrent Neural Network. Model for multimodal paintings with structural and sparse constraints. Eigenvalues, eigenvectors, and correlation and covariance analysis make photo fusion more exact and adaptable. Matlab simulates the suggested workbench’s peak sign-to-noise ratio, suggested rectangle error, correlation, and accuracy to compare it to current approaches. Proposed workbench beats all performance benchmarks and reduces computational overhead.(9)

Diagnoses and treatments require medical pictures. Algorithms that identify and remove superfluous medical imaging data segment anatomy. Effectiveness of these algorithms will affect subsequent processing. Many studies have examined medical picture segmentation algorithms and their applications. These studies lack medical image segmentation bibliometric analysis. Medical image segmentation technology academic publishing was examined in this bibliometric analysis. WoS Core Collection and Scopus provided data. In five categories—annual publications, nationalities, top authors, publication sources, and keywords—quantitative analysis created essential visual maps of publication patterns. In qualitative analysis, medical picture segmentation approaches and research trends were investigated. We examined the top 49 annual citation publications. Results/finds. This analysis indicated a significant year-over-year rise in publications. The US, China, and India are key. These are largely conference papers but few top journal articles. Keyword analysis suggests deep-learning medical image segmentation algorithms are being developed. Reviews, segmentation algorithm articles, and others were included. The majority of publications in these three categories focused on segmentation algorithms, while deep learning neural network-based techniques were frontiers. Finally, our bibliometric study informs medical image segmentation research goals. Researchers should study deep learning neural network medical image segmentation.(10)

Medical imaging analysis and diagnosis involve image segmentation. Convolutional neural networks are promising and accurate. However, training these networks requires substantial annotated datasets. Expert annotations are costly; crowdsourcing is better. We already examined the best crowd labour allocation for annotation number and quality. Photo segmentation is tiresome, but this study makes it fun. This method gives users fun activities and good annotations. In our study, we introduce gamified crowdsourcing for medical image segmentation. We examine the most sophisticated research incentives and offer two gamification solutions for picture segmentation. Finally, we propose an integrated game concept that combines both approaches and offers the following incentives: (a) points or scoring to reward precise segmentations immediately, (b) a leaderboard or rankings system to accumulate scores for long-term motivation, (c) badges or achievements to visually represent users’ segmentation proficiency, and (d) levels to show users’ progress. We describe the prototype’s early implementation and how the game concept matches our study.(10)

We analyze profound classifier performance differences. We find significant variance in classifiers’ ability to segment individuals across medical imaging modalities and protected features. Importantly, we show that this trait indicates algorithmic bias. After substantial theoretical and empirical investigation, we found a correlation between subgroup separability, disparities, and a deterioration in performance when models are trained on systematic bias, such as underdiagnosis. Our research on how models develop bias offers new insights for fair medical imaging artificial intelligence.(11)

Advanced computer vision capabilities of vision transformers changed medical image analysis. Modern hybrid-/transformer-based methods emphasise on transformers’ ability to capture massive interdependencies, ignoring their computer complexity, expensive training, and redundant dependency. This research proposes adaptive pruning in transformers for medical picture segmentation and develops APFormer, a lightweight, efficient hybrid network. This is the first medical image processing transformer pruning study. Many critical components boost APFormer’s performance. Self-regularized self-attention (SSA) enhances dependence convergence, GRPE learns location, and adaptive pruning minimises computations and perceptual information. Self-attention and position embedding are done separately by SSA and GRPE utilising well-converged dependence and Gaussian heatmap distributions. This aids transformer trimming and training. Adjusting gate control parameters prunes transformer model adaptively. It reduces queries and dependencies and improves speed. APFormer outperforms state-of-the-art segmentation algorithms with fewer parameters and lower GFLOPs in many studies on two datasets. Ablation results show that adaptive pruning can be used as a plug-and-play component to improve hybrid/transformer-based approaches.(12)

Federation learning (FL) lets hospitals construct deep learning models for medical picture segmentation using independent patient data. Federated learning (FL) fails with non-iid data, like medical photos. This work starts with a theoretical FL technique analysis to discover model aggregation difficulties when training on non-iid data. Federated cross-learning (FedCross) is suggested as a simple and effective solution to this difficult challenge. Unlike FL alternatives, FedCross trains the global model sequentially and round-robin across consumers. All training phase model aggregation is abolished. FedCrossEns improves performance and matches centralised learning by combining FedCross with ensemble learning. We test extensively on public databases. For non-iid data, FedCross training outperforms FL techniques in experiments. FedCrossEns enhances segmentation and assesses model uncertainty, proving our inventions’ therapeutic potential.(13)

Medical photos contain private patient information. These photos must be preserved. This paper presents secure and effective medical image encryption and decryption. The method uses DNA, tent, logistic maps, SHA-256, and MD5 hashes. The suggested method generates a key using picture and metadata hash methods. The key complements the image. The black backdrop generates unnecessary DNA encoded sequences, therefore rotate and permute the medical image’s first two most crucial bit-planes. Final component: logistic map-based dynamic DNA rules encode and decode DNA for each 2-bit pixel value. Tent map and XOR confuse-diffuse. Simulations and security analysis show the proposed technique outperforms current encryption methods. A correlation coefficient of 6,66617e-7 and a large critical space of 2624 show this. Common attacks like chosen/known-plaintext and cropping/noise can also be defended by the suggested device.(14)

Summary Healthcare is altered by CNNs, which increase prediction, diagnosis, and decision-making. Convolutional Neural Networks (CNNs) are important in medical image processing and are simplified in this article for scientists. Convolutional Neural Networks (CNNs) enable laptop vision and data analysis. Understanding how synthetic intelligence models work will help doctors as it becomes more integrated into healthcare. Radiography, histology, and scientific images benefit from CNNs. Radiography hired CNNs to automate pneumonia, pulmonary embolism, and rectal cancer assessments. Histology classified colorectal polyps, stomach epithelial tumours, and other cancers using CNNs. CNNs could detect ocular, cutaneous, and stomach/colorectal polyps during endoscopic treatments. They assist surgeons analyse anatomy and demonstrate safe laparoscopic dissection areas. Clinical image evaluation with CNNs improves diagnostic precision, workflow efficiency, and picture processing, improving patient and healthcare outcomes.(15,16)

AI has changed medical imaging analysis. This paper describes a complex scientific imaging generation employing AI to analyse photos regularly. Photo category, object identity, and segmentation on the platform use ResNet50, YOLOv5l, and Res50-U-Net. The automated pipeline effectively classifies and sends scientific photos to essential analysis modules. MRI brain photos segment tumours and X-rays show abnormalities. This study found that AI improves scientific picture judgement in three levels. Scientific diagnostics and medical care benefit from type, detection, and segmentation. Computerised photo analysis distinguishes the platform from modern technology. Clinicians get insights and reduce subjectivity in guiding judgement with AI, revolutionising medical imaging.(17)

Rapid technological advances and new studies require healthcare privacy and record protection. Avoid storing too much clinical data. Recently, medical data and steganography lossless compression has been extensively researched. Enhanced steganography, wavelet reconstruction (WT), and lossless compression protect garage performance and privacy. This study secures and retains huge patient data images, allowing pharmacologists to store twice as much data in a comprehensive repository. This study focusses secure storage, fast image service, and cheap computation. This study adds patient data to medical images and safeguard shield images using rapid knight tour (KT) and discrete WT (DWT). Lossless packet compression optimises and reduces memory. JPEG compresses more than PNG. Hi-resolution images are 7 %–7,5 % and 30 %–37 % compressed. The model improves compression ratio and percentage beyond others. The projected compression ratio is 35 %–60 %, but averages 7,8 %–8,6 %. Our research improves data security and image quality over current methods. Photos are processed faster and preserved when resized.(18)

Objective Lesions and anatomical characteristics are measured using clinical medical image analysis. This can improve medical diagnosis and prognosis. Historically, qualified physicians or medical physicists did these arduous tasks, but low productivity and discrimination hindered them. In the last decade, various machine-learning methods have automated picture analysis. Compared to supervised and unsupervised learning methods, medical image analysis rarely uses reinforcement learning. This review study forms the basis for future research. Importance Many medical analysts don’t comprehend or use reinforcement learning in clinical settings, despite its popularity. Lack of well-structured non-computer scientist review articles may contribute. Not all medical image analysis reinforcement learning models are reviewed. Instead, reinforcement learning helps readers analyse medical images. Methodology and Results We curated PubMed and Google Scholar. Due to a dearth of relevant papers, we included many good recent preprints. Articles were thoroughly vetted and categorised by image analysis issues. This article covers reinforcement learning basics and popular models. We then evaluated reinforcement learning models’ medical image processing uses. Conclusion: reinforcement learning system limits and potential enhancements.(19)

 

Technological overview

Artificial intelligence technologies

AI technology in healthcare is mostly used for device learning, deep learning, and herbal language processing. These technologies improve many healthcare delivery variables in different ways.(20)

A.  Machine Learning (ML): Algorithms analyse data and produce predictions or selections based on facts. ML is widely utilised in healthcare for predictive analytics and screening for disease outbreaks and patient decline. In diagnostic imaging, algorithms scan pictures to find tumours and fractures faster than humans.(21)

B.   Deep Learning (DL): A subset of device reading, deep mastering studies complex statistics using layered neural networks. Pathology, which reads complex tissue samples, has advanced with this generation. Deep analysis enhances robotic surgical operations by providing precision guidance based on real-time data at particular operation step.(22)

C.   Natural Language Processing (NLP): This technology enables computers to comprehend and interpret human language, making it crucial in healthcare for handling unstructured data like scientific notes and records. It extracts impacted character records, allows personalised care, and improves file-heavy approaches.(23)

 

Current applications

Current AI healthcare applications are large and transformational, affecting diagnosis, treatment guidelines, and character tracking:

A.  Scientific diagnostics are being transformed by AI structures, particularly those that use deep learning. AI systems can accurately detect diabetic retinopathy in retinal imaging and malignant tumours in radiology scans. This method no longer improves diagnosis accuracy but greatly reduces analysis time.(24)

B.   therapy Recommendations: AI is being used in medical selection support to provide therapy guidelines. These technologies compare patient records to massive databases of studies and case histories to suggest customised treatments. IBM’s Watson for Health employs cognitive generation to analyse based and unstructured statistics in clinical notes and reports to assist most cancer patients choose more effective treatments.(25)

C.  AI technology is used in remote patient monitoring to assess non-stop care outside of traditional scientific settings. AI-enabled wearable health gadgets can detect early health issues and warn healthcare providers. Disease management and geriatric care require regular tracking, therefore this program is invaluable.(26)

AI’s healthcare transformation potential is much greater than these instances. AI is best at streamlining operational efficiency, improving patient outcomes, and enabling more responsive, unique, and patient-centered clinical practices.(27)

 

Future directions for AI in healthcare

Artificial intelligence (AI) in healthcare is evolving, providing new hospital therapy interventions and controls. To maximise AI’s healthcare potential, we must understand evolving technology, refine integration tactics, and provide robust ethical frameworks.(28)

 

Innovations on the horizon

AI in healthcare has a bright future that could improve patient outcomes and care agency performance:

Predictive Analytics for Personalised Medicine: AI can analyse large datasets to forecast health risks and scientific impacts. This age allows customised treatments based on genetic profiles, lifestyle factors, and unique personal trends, improving efficacy and reducing negative effects.(29)

AI-powered Genomic Sequencing: AI can help identify disease-related genetic markers. This innovation allows for more accurate diagnosis and treatment of complex diseases like most malignancies.(30)

AI-progressed robot surgery allows minimally invasive procedures for greater precision and faster recovery. AI-driven robot systems can meet people’s rehabilitation goals with customised treatment plans that improve outcomes.(31)

AI-powered virtual fitness aides can monitor health and offer real-time recommendations. These assistants must handle ongoing issues, ensure treatment adherence, and assist in fitness crises.

Mental Health Applications: AI will revolutionise highbrow fitness care by delivering real-time counselling, measuring treatment improvement, and forecasting intellectual fitness crises. These programs may also wish to improve mental fitness resource accessibility and efficacy.(32)

 

Strategies for integration

AI integration into modern healthcare systems requires many strategic moves:

Increasing Interoperability and Data Standards: Healthcare IT structures need universal facts and better interoperability. For actual AI software, these enhancements will enable green fitness statistic update and evaluation.(33)

Complete Workforce Training: Healthcare professionals need AI equipment training and knowledge about their operating thoughts, boundaries, and capability biases. They can successfully integrate AI insights into scientific decision-making with this understanding.

Patient Engagement: AI in healthcare requires patient engagement. Patients should understand AI generation and its benefits and be involved in making decisions about AI use in their health facility treatment.(34)

AI infrastructure must be invested in by healthcare institutions. The most spartan computational power and crucial data protection mechanisms protect affected person records.

 

Ethical Framework Development

As AI becomes more prevalent in healthcare, ethical frameworks are needed. These frameworks should address numerous fundamental issues:

Transparency: Ethical guidelines should make AI systems transparent so patients and healthcare providers can understand decisions. Transparency builds confidence and allows informed consent.

Privacy and Security: AI systems must protect affected individuals’ data. This involves preventing unauthorised facts from being admitted and maintaining fact integrity.(35)

Addressing Bias and Ensuring Fairness: Ethical guidelines include finding, stopping, and correcting AI algorithm biases to provide fair and honest treatment for all patients, regardless of history.

Clear Accountability: AI in healthcare requires clear duty norms. This includes assigning responsibility for AI alternatives’ outcomes and handling capability errors and unfavourable events. The future of AI in healthcare is bright, but it requires careful navigation to maximise advantages while minimising hazards. The healthcare organisation may use AI to improve patient care, results, and ethics by focussing on cutting-edge innovations, strategic integration, and morality. These endeavours will chart AI’s healthcare trajectory and social impact.(36)

 

REFERENCES

1. Al-shanableh N, Alzyoud M, Al-husban RY, Alshanableh NM, Al-Oun A, Al-Batah MS, et al. Advanced Ensemble Machine Learning Techniques for Optimizing Diabetes Mellitus Prognostication: A Detailed Examination of Hospital Data. Data Metadata. 2024;3:363.

 

2. Al-Batah MS, Alzboon MS, Alzyoud M, Al-Shanableh N. Enhancing Image Cryptography Performance with Block Left Rotation Operations. Appl Comput Intell Soft Comput. 2024;2024(1):3641927.

 

3. Alzboon M, Alomari SA, Al-Batah MS, Banikhalaf M. The characteristics of the green internet of things and big data in building safer, smarter, and sustainable cities. Int J Eng \& Technol. 2017;6(3):83–92.

 

4. Simran, Singh J. A Comprehensive Survey of PSO-ACO Optimization and Swarm Intelligence in Healthcare: Implications for Medical Image Analysis and Disease Surveillance. 2023 3rd Asian Conf Innov Technol. 2023;

 

5. Roy S, Roy S, Meena T, Meena T, Lim S-J, Lim S-J. Demystifying Supervised Learning in Healthcare 4.0: A New Reality of Transforming Diagnostic Medicine. Diagnostics. 2022;

 

6. Eldin WS, Kaboudan A. AI-Driven Medical Imaging Platform: Advancements in Image Analysis and Healthcare Diagnosis. J ACS Adv Comput Sci. 2023;

 

7. Fu S, Fu S, Zhang M, Zhang M, Zhang M, Zhang M, et al. Advancements of Medical Image Enhancement in Healthcare Applications. J Healthc Eng. 2018;

 

8. Liu Z, Liu Z, He M, He M, Jiang Z, Jiang Z, et al. Survey on natural language processing in medical image analysis. J Cent South Univ Med Sci. 2022;

 

9. Prathipa SR, Ramadevi R. Feature Level Medical Image Fusion with Deep Learning. 2023 Int Conf Evol Algorithms Soft Comput Tech. 2023;

 

10. Zhang B, Zhang B, Rahmatullah B, Rahmatullah B, Wang SL, Wang SL, et al. A bibliometric of publication trends in medical image segmentation: Quantitative and qualitative analysis. J Appl Clin Med Phys. 2021;

 

11. Wang Y, Li Z, Mei J, Wei Z, Liu L, Wang C, et al. SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation. Int Conf Med Image Comput Comput Interv. 2023;

 

12. Lin X, Yu L, Cheng K-T, Yan Z. The Lighter the Better: Rethinking Transformers in Medical Image Segmentation Through Adaptive Pruning. IEEE Trans Med Imaging. 2023;

 

13. Xu X, Chen T, Deng H, Kuang T, Barber JC, Kim D, et al. Federated Cross Learning for Medical Image Segmentation. Int Conf Med Imaging with Deep Learn. 2022;

 

14. Aouissaoui I, Aouissaoui I, Bakir T, Bakir T, Sakly A, Sakly A. Robustly correlated key-medical image for DNA-chaos based encryption. Iet Image Process. 2021;

 

15. Kourounis G, Elmahmudi A, Thomson B, Hunter J, Ugail H, Wilson C. Computer image analysis with artificial intelligence: a practical introduction to convolutional neural networks for medical professionals. Postgrad Med J. 2023;

 

16. Janssens J, Lazendic S, Huang S, Pižurica A. Multimodal Extension of the ML-CSC Framework for Medical Image Segmentation. Int Symp Image Signal Process Anal. 2021;

 

17. Liu Y, Liu Y, Zhang M, Zhang M, Zhong Z, Zhong Z, et al. A novel adaptive cubic quasi‐newton optimizer for deep learning based medical image analysis tasks, validated on detection of COVID‐19 and segmentation for COVID‐19 lung infection, liver tumor, and optic disc/cup. Med Phys. 2022;

 

18. Xue X, Marappan R, Raju SK, Raghavan R, Rajan R, Khalaf OI, et al. Modelling and Analysis of Hybrid Transformation for Lossless Big Medical Image Compression. Bioengineering. 2023;

 

19. Hu M, Zhang J, Matkovic L, Liu T, Yang X. Reinforcement learning in medical image analysis: Concepts, applications, challenges, and future directions. J Appl Clin Med Phys. 2022;

 

20. Alzboon MS. Internet of things between reality or a wishing-list: a survey. Int J Eng \& Technol. 2018;7(2):956–61.

 

21. Alqaraleh M, Alzboon MS, Al-Batah MS, Wahed MA, Abuashour A, Alsmadi FH. Harnessing Machine Learning for Quantifying Vesicoureteral Reflux: A Promising Approach for Objective Assessment. Int J Online \& Biomed Eng. 2024;20(11).

 

22. Al-Batah MS, Alzboon MS, Alazaidah R. Intelligent Heart Disease Prediction System with Applications in Jordanian Hospitals. Int J Adv Comput Sci Appl. 2023;14(9):508–17.

 

23. Alzboon MS, Al-Batah MS. Prostate Cancer Detection and Analysis using Advanced Machine Learning. Int J Adv Comput Sci Appl. 2023;14(8):388–96.

 

24. Al-Batah M, Zaqaibeh B, Alomari SA, Alzboon MS. Gene Microarray Cancer classification using correlation based feature selection algorithm and rules classifiers. Int J online Biomed Eng. 2019;15(8):62–73.

 

25. Alzboon MS. Survey on Patient Health Monitoring System Based on Internet of Things. Inf Sci Lett. 2022;11(4):1183–90.

 

26. Alzboon MS, Bader AF, Abuashour A, Alqaraleh MK, Zaqaibeh B, Al-Batah M. The Two Sides of AI in Cybersecurity: Opportunities and Challenges. In: Proceedings of 2023 2nd International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2023. 2023.

 

27. Alzboon MS, Al-Batah M, Alqaraleh M, Abuashour A, Bader AF. A Comparative Study of Machine Learning Techniques for Early Prediction of Diabetes. In: 2023 IEEE 10th International Conference on Communications and Networking, ComNet 2023 - Proceedings. 2023. p. 1–12.

 

28. Alzboon MS, Aljarrah E, Alqaraleh M, Alomari SA. Nodexl Tool for Social Network Analysis. Vol. 12, Turkish Journal of Computer and Mathematics Education. 2021.

 

29. Alzboon M. Semantic Text Analysis on Social Networks and Data Processing: Review and Future Directions. Inf Sci Lett. 2022;11(5):1371–84.

 

30. Alzboon MS, Al-Batah M, Alqaraleh M, Abuashour A, Bader AF. A Comparative Study of Machine Learning Techniques for Early Prediction of Prostate Cancer. In: 2023 IEEE 10th International Conference on Communications and Networking, ComNet 2023 - Proceedings. 2023. p. 1–12.

 

31. Alzboon MS, Qawasmeh S, Alqaraleh M, Abuashour A, Bader AF, Al-Batah M. Machine Learning Classification Algorithms for Accurate Breast Cancer Diagnosis. In: 2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023. 2023.

 

32. Al Tal S, Al Salaimeh S, Ali Alomari S, Alqaraleh M. The modern hosting computing systems for small and medium businesses. Acad Entrep J. 2019;25(4):1–7.

 

33. Alzboon MS, Al-Batah MS, Alqaraleh M, Abuashour A, Bader AFH. Early Diagnosis of Diabetes: A Comparison of Machine Learning Methods. Int J online Biomed Eng. 2023;19(15):144–65.

 

34. Alomari SA, Alqaraleh M, Aljarrah E, Alzboon MS. Toward achieving self-resource discovery in distributed systems based on distributed quadtree. J Theor Appl Inf Technol. 2020;98(20):3088–99.

 

35. Alzboon MS, Qawasmeh S, Alqaraleh M, Abuashour A, Bader AF, Al-Batah M. Pushing the Envelope: Investigating the Potential and Limitations of ChatGPT and Artificial Intelligence in Advancing Computer Science Research. In: 2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023. 2023.

 

36. Ahmad A, Alzboon MS, Alqaraleh MK. Comparative Study of Classification Mechanisms of Machine Learning on Multiple Data Mining Tool Kits. Am J Biomed Sci Res 2024 [Internet]. 2024;22(1):577–9. Available from: www.biomedgrid.com

 

FINANCING

Currently, there are no available financing sources designated for this project. This absence of financial support underscores the need for strategic planning to identify potential funding avenues that could facilitate the successful implementation and advancement of the initiative.

 

CONFLICT OF INTEREST

The authors declare that the research was conducted without any commercial or financial relationships that could be construed as a potential conflict of interest.

 

AUTHOR CONTRIBUTIONS

Conceptualization: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Data curation: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Formal Analysis: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Research: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Methodology: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Project management: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Validation: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Drafting – original draft: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.

Writing - proofreading and editing: Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah, Mutaz Abdel Wahed.