Special Issue(24-14): AI-Driven OCT Image Analysis for Automated Disease Detection and Classification.

SPECIAL ISSUE PROPOSAL

AI-Driven OCT Image Analysis for Automated Disease Detection and Classification

The evaluation and interpretation of optics coherence tomography in retinal science has greatly progressed to advances in computer vision, which is defined as the field of expertise that teaches computers to understand digital images using both artificial intelligence (AI) and traditional techniques. The field of deep learning in computational neuroscience has a prospect for improving diagnosis, classification, and management in personal and population settings. Deep learning is predicated on the ability to recognise images using pre-existing information. Diabetic retinopathy is a slowly developing health issue that frequently progresses silently without obvious symptoms. Damage to the retinal blood vessels is a major factor in this condition. Optical coherence tomography, or OCT, has become the preferred noninvasive imaging modality for quickly and precisely identifying diabetic retinopathy.

Still, these techniques have three main drawbacks: first, their black box attributes make it difficult for medical professionals to fully trust the results they produce instantly; second, their lack of exactness makes it difficult to apply those techniques to complex and clinical cases; and third, the size and complexity of the models and works that are currently available for OCT classification make them more difficult to use in immediate applications by requiring a significant amount of memory and processing power. A process for improving the features that can be recovered from optical coherence tomography images using a cognitive network by evaluating the images using image processing technologies. The algorithms already in use that rely on fundus photography and optical coherent tomography imaging have already surpassed human evaluators in diagnosis accuracy. More exploration of artificial intelligence (AI) in ophthalmology is being conducted as a result of the rising incidence and burden of eye illnesses worldwide, as well as the increasing usage of sophisticated imaging technologies for ophthalmic inspection, such as fundus cameras and optical coherence tomography (OCT). Numerous research groups have created automated analytic algorithms for the purpose of identifying and diagnosing eye disorders.

In this context, the integration of AI with medical image analysis represents a significant accomplishment, providing a deep understanding of an individual's anatomy and physiography using the complex interpretation of visual data. The combination of AI and medical imaging has accelerated the creation of advanced methods of great importance for disease diagnosis, prognosis, and treatment planning. AI-enabled medical imaging techniques have proven to be exceptionally effective at automating processes that were previously susceptible to personality and variations. This special issue of computer vision, which is identified as the branch of science that enables computers to interpret digital images using both traditional and artificial intelligence (AI) methods, has made great strides in the processing and interpretation of optical coherence tomography (OCT) in retinal imaging.

TOPICS INCLUDE, BUT ARE NOT LIMITED TO:

• Transfer learning-powered artificial intelligence model for image-based medical diagnostics
• Assessment of Intelligent Systems in OCT Image-Based Retinal Screening
• Artificial learning and image processing in computerised images and optical coherence tomography
• Possible uses of artificial intelligence for corneal disease image interpretation
• Harnessing Artificial Intelligence to Help Doctors Interpret Medical Images An Overview
• Deterioration with special image preprocessing utilising optical coherence tomography
• Intelligent technology utilisation for corneal disease diagnosis and treatment
• AI's prognostic promise in ophthalmology: using retinal imaging to predict systemic diseases
• Image analysis using artificial intelligence in dermatology: present advancements and potential directions
• Unauthorised fundus image registration using AI-driven generalised exponential transformation methods
• Deep learning applications for the detection, categorisation, and management of  degeneration

GUEST EDITORS

Dr.Abdul Aziz

Universidad de Zaragoza, Zaragoza, Spain.

Email ID: [email protected], [email protected] 

Research Link:  https://scholar.google.com/citations?user=BB0FCKwAAAAJ&hl=en 

Official Webpage: https://i3a.unizar.es/es/investigadores/abdul-aziz 

Professional Summary: Dr.Abdul Aziz received his Bachelor’s degree in computer science from the COMSATS Institute of Information Technology, Lahore, Pakistan, in 2013, and Master’s degree in computer science from the National University of Computer and Emerging Sciences, Karachi, Pakistan, in 2018. He is currently working at the University of Zaragoza, within the Advanced Information Systems Laboratory (IAAA) of the Aragon Institute of Engineering Research (I3A). 

Research Interests: Open (Linked) Data, Open Data Portals, Open Government Data, Data Science, Information Retrieval 

Dr.Moiz Khan Sherwani

University of Copenhagen, Denmark

Email ID: [email protected] 

Research Link:  https://scholar.google.it/citations?user=uDlA1JgAAAAJ&hl=en 

Professional Summary: Dr.Moiz Khan Sherwani received my PhD in Computer Science (Artificial Intelligence in Medicine) from University of Calabria. Currently, he is working at University of Copenhagen. His previous research scope was based on the image synthesis, diagnosis, infection segmentation in medical images (MRI, CT, and other image modalities). He is currently working on machine learning approaches applied over multi-omics data. His main activities include data analysis of genomics data and applying ML models to predict, classify and implement algorithms to solve the biological questions within the context.

Research Interests: Machine Learning, Natural Language Processing, Data Mining and Knowledge Discovery, Text Analysis, Data Science, Medical Image Analysis, Medical Imaging, Medical and Biomedical Image Processing, Deep learning in Biomedical data, Machine Learning on Multi-omics data, Graph databases, Artificial Intelligence

Dr.Waseem Akram

Khalifa University, UAE

Email ID: [email protected] 

Research Link: https://www.researchgate.net/profile/Waseem-Akram 

Professional Summary: Waseem Akram has expertise and experience in both software development as well as in research. He is working on the control and guidance of autonomous underwater vehicles for the visual inspection of underwater assets. Apart from this, he is also working on agent-based modelling, complex networks modelling, machine learning, computer vision and deep learning-based research projects.

Research Interests: Complex Networks, Agent-Based Modeling, Smart Grid, Marine vehicles, Fault Tolerance, Underwater Acoustics, Complex Adaptive Systems, Marine Inspection, Marine Aquaculture.

TENTATIVE DATES

Submission Deadline: 31th December, 2024

Authors Notification: 25th March, 2025

Revised Version Submission: 25th May, 2025

Final Decision Notification: 05th Aug, 2025