Search
30 articles for “Deep learning segmentation”
-
Survey on Retinal OCT Image Preprocessing, Segmentation, and Deep Learning Based Classification
Abstract: Optical coherence tomography (OCT) is a non-invasive technique that generates high-resolution, detailed cross-sectional images of biological tissues. By utilizing low-coherence interferometry, OCT enables visualization of tissue microstructure with micron-scale resolution, making it useful in various medical fields such as ophthalmology, cardiology, and dermatology. In ophthalmology, OCT is extensively used for diagnosing and monitoring retinal diseases like macular degeneration and diabetic retinopathy, allowing doctors to assess changes in tissue morphology over …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 11, Issue 3, 2024 · pp. 1–9 Read article
-
Image-Based Crack Morphology Characterisation for Electrical Failure Analysis in Conductive Polymer Composites
Abstract: Electrical performance in conductive polymer composites is strongly governed by crack-network evolution, yet failure analysis typically relies on qualitative image inspection or electrical anomaly detection in isolation. This work proposes an end-to-end framework that converts optical/SEM crack imagery into a standardised crack morphology signature and quantitatively links it to electrical degradation indicators. A two-stage learning strategy is adopted: crack-representation pretraining using the public Concrete Crack Images for Classification dataset, followed …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 1375-1386 Read article
-
CNN-Based Wound Segmentation: A Review of Models and Performance Evaluation
Abstract: Deep learning, particularly convolutional neural networks (CNNs), has altered medical image processing by automating and precisely segmenting complex medical pictures. Wound segmentation, a critical application in automated wound assessment, is essential for wound size estimation, classification, and healing progress monitoring. This study presents a comprehensive review of CNN-based wound segmentation models, focusing on their architectures, methodologies, and performance on diverse datasets. Four deep learning models, including two U-Net variants (5-layer …
Published in Current Trends in Signal Processing · Vol. 15, Issue 1, 2025 · pp. 33–46 Read article
-
A Split and Merge UNet: A Deep Learning Assisted UNet Model to Segment Corpus Callosum of Brain for Automatic Autism Detection
Abstract: In recent years, deep learning techniques have shown remarkable performance in various image analysis applications, particularly in the domain of medical image processing. Among these, image segmentation plays a critical role, as it helps in isolating and analyzing specific regions within medical images. The proposed study focuses on segmenting the corpus callosum, a vital structure in the human brain, using a novel optimization technique known as the Split and Merge …
Published in Journal of Multimedia Technology & Recent Advancements · Vol. 11, Issue 3, 2024 · pp. 1–9 Read article
-
Refining Retinal Layer Segmentation in OCT Imaging with Advanced Techniques and Clinical Applications
Abstract: Segmenting retinal layers from Optical Coherence Tomography (OCT) pictures entails locating and separating different retinal layers to offer comprehensive anatomical and pathological information. Age-related macular degeneration, diabetic retinopathy, and glaucoma are among the retinal illnesses for which this procedure is crucial for diagnosis and follow-up. By utilizing preprocessing techniques to improve image quality and applying advanced algorithms—such as intensity-based, gradient-based, and texture-based methods—alongside deep learning approaches, clinicians can accurately measure …
Published in Trends in Opto-electro & Optical Communication · Vol. 14, Issue 2, 2024 · pp. 01–06 Read article
-
Geo AI-Powered Urban Footprints
Abstract: In the contemporary era, building footprints are of paramount importance for accurate and current inventories in the development of infrastructure and geospatial analysis. Traditional methods, relying on manual digitization, were largely unsustainable as the urban regions were growing rapidly. Manual digitization was expensive and lacked geometric precision. This paper introduces an automated, end-to-end GEO AI-powered framework for high-end fidelity building footprint extraction from Google Satellite Data. Our approach for this …
Published in Journal of Remote Sensing & GIS · Vol. 17, Issue 2, 2026 Read article
-
Melanoma Skin Cancer Detection Using Deep Learning
Abstract: Melanoma, a fatal type of skin cancer, is a major global health concern. For better patient outcomes, early and precise detection is essential. A branch of artificial intelligence called deep learning has demonstrated encouraging outcomes in medical image analysis, particularly the identification of skin cancer, in recent years. We present a new method for detecting melanoma skin cancer in this paper by utilizing the ResNet-50 architecture, a deep convolutional neural …
Published in Research and Reviews: Journal of Oncology and Hematology · Vol. 14, Issue 2, 2025 · pp. 1–9 Read article
-
Enhancing Image Classification Performance with Deep Neural Networks
Abstract: Classifying images is useful in many domains, including the study of plant diseases and the analysis of human expressions. Image categorization employing the idea of a “deep neural network” helps to compact otherwise cumbersome photos. It is possible to classify images by using the idea of a “deep neural network”. Self-driving cars, medical diagnosis, automatic translation, etc., all make use of Deep Neural Networks. Recently, excellent results have been achieved …
Published in Journal of Telecommunication, Switching Systems and Networks · Vol. 11, Issue 1, 2024 · pp. 13–23 Read article
-
Automated Microstructure Classification with Class-Specific Segmentation for Titanium Based Composite Materials
Abstract: In engineering, characterisation of microstructure is required to determine and forecast behaviour of titanium alloys. Our proposal in this work has been a deep-learning-based framework in the automatic classification and segmentation of Titanium Based Composite Material. The framework then uses EfficientNetB0 backbone, where we have chosen the backbone to scale the performance of classification and the computational efficiency with the assistance of the transfer learning and the compound scaling. In …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 424–433 Read article
-
Image Processing and Deep CNN-based Automatic Liver Cancer Detection
Abstract: Liver cancer ranks among the leading causes of mortality for people worldwide. In the current situation, manually identifying the cancer tissue is a challenging and timeconsuming task. Treatment planning, response monitoring, tumor load assessment, and prediction are all made possible by the segmentation of liver lesions in CT scans. To address the current problem of liver cancer, the Hybridized Fully Convolutional Neural Network (HFCNN), which has been theoretically modeled, has …
Published in International Journal of Biomedical Innovations and Engineering · Vol. 3, Issue 1, 2025 · pp. 39–41 Read article
-
Advancing Brain Tumor MRI Segmentation
Abstract: Segmentation of brain tumors in MRI scans is an integral part of neuroimaging carried out for diagnostic and therapeutic interventions. Given that manual segmentation is cumbersome and highly variable, there arises a need for automated, more precise segmentation solutions. This project, ‘Machine Learning and Deep Neural Networks to Advance Brain Tumor MRI Segmentation’ will develop a better, efficient, and accurate segmentation model to help clinicians identify brain tumors with greater …
Published in Recent Trends in Electronics Communication Systems · Vol. 12, Issue 2, 2025 · pp. 28–33 Read article
-
Facial Recognition System Utilizing Real-time Deep Learning Techniques
Abstract: This research introduces an openly accessible deep learning-based framework designed for facial recognition. The system encompasses five key stages: face segmentation, detection of facial features, face alignment, embedding, and classification. Deep learning methods are employed for the extraction of fiducial points and embedding within the system. For the classification task, a Support Vector Machine (SVM) is utilized due to its efficiency in both training and inference phases. Notably, the system …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 11, Issue 1, 2024 · pp. 14–20 Read article
-
Role of Artificial Intelligence in Structural Health Monitoring-A Brief Evaluation
Abstract: Artificial intelligence (AI) refers to the capacity of a machine or a computer to ‘think’ or reason in the way a human would, utilizing experience, learned facts, and flexible rules to solve problems that may not fit the standard outlines for a normal algorithm. From this follows the utilization of AI in various sectors, such as the information technology (IT) industry, media, healthcare and medicine, logistics, environmental sustainability, finance, business, …
Published in Journal of Structural Engineering and Management · Vol. 13, Issue 1, 2026 · pp. 34–39 Read article
-
A Comprehensive Review of CNN-Based Framework for Multi-Sign Detection of Diabetic Retinopathy in Fundus Images Using Public Datasets
Abstract: Diabetic retinopathy (DR) is one of the main causes of vision impairment. Blindness prevention and effective treatment depend on early detection. A thorough deep learning-based framework for the automatic segmentation and simultaneous detection of exudates, hemorrhages, and microaneurysms – three important DR indicators – from retinal fundus images is presented in this work. These three pathological signs’ corresponding annotated image patches, along with background (no-sign) areas, were used to train …
Published in Research and Reviews : Journal of Computational Biology · Vol. 14, Issue 3, 2025 · pp. 14–23 Read article
-
Analysis of White Matter, Gray Matter, and Cerebrospinal Fluid Alterations in Neurological Disorders: A Deep Learning Approach
Abstract: This paper investigates the role of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) alterations in the pathophysiology of neurological disorders, including Alzheimer’s disease, Parkinson’s disease, schizophrenia, and epilepsy. By leveraging advanced deep learning methodologies, we aim to automate the segmentation and analysis of brain structures from MRI scans, enabling a more detailed and precise evaluation of their roles in disease progression. These techniques allow for the identification …
Published in Research and Reviews: A Journal of Neuroscience · Vol. 14, Issue 3, 2024 · pp. 21–27 Read article
-
Detection of Brain Tumors from MRI Images Based On Development of Thinking Computer Systems Techniques
Abstract: Brain tumors are one of the common diseases of the nervous system and have great harm to human health, and even lead to death. The detection, segmentation, and extraction of contaminated tumour regions from Magnetic Resonance Imaging (MRI) pictures are major problems; yet, a repetitive and time-consuming task performed by radiologists or clinical experts relies on their experience. The many anatomical structures of the human organ can be imagined using …
Published in Current Trends in Signal Processing Read article
-
An Effective Convolutional Neural Network for Identifying Cancer Blood Disorder Cells Using Microscopic Images
Abstract: Blood, bone marrow, and lymphatic systems are all impacted by hematological cancer is known as a cancer blood disorder. Blood malignancies and various blood disorders pose significant health challenges across all age groups. Early disease detection is essential for effective cancer blood disorder treatment and management. If a blood cancer is not identified in time, it may be hazardous. It results in abnormal white blood cell production by the bone …
Published in Research and Reviews: Journal of Oncology and Hematology · Vol. 13, Issue 2, 2024 · pp. 29–35 Read article
-
The Analysis of Deep Learning-Based Methods for Identifying Diabetic Retinopathy
Abstract: Diabetic retinopathy (DR) is a degenerative eye condition resulting from diabetes mellitus, where high blood glucose levels lead to lesions on the retina. This condition is considered the leading cause of blindness among working-age diabetic patients, particularly in developing countries. As the disease is irreversible, the treatment aims to preserve the patient’s current vision. Early detection is crucial for effective management of DR to maintain vision. One of the main …
Published in Research and Reviews : A Journal of Medical Science and Technology · Vol. 13, Issue 3, 2024 · pp. 15–31 Read article
-
Innovations in Forensic Imaging: Leveraging Deep Learning for Authenticity Verification
Abstract: The advent of digital media has necessitated advancements in forensic imaging, especially for the detection and verification of image authenticity. In this context, digital image forensics plays a critical role in identifying manipulated or counterfeit images. This paper presents a new method that uses deep learning techniques to enhance image forgery detection. The approach utilizes a convolutional neural network (CNN) to automatically learn and recognize the intricate features present in …
Published in Journal of Advances in Shell Programming · Vol. 11, Issue 2, 2024 · pp. 28–33 Read article
-
Ai-Driven Healthcare System for Enhanced Diagnosis and Patient Interaction
Abstract: Deep learning techniques are used in an AI-driven healthcare system to improve disease identification and medical picture analysis. Data collection, preprocessing, model training, and evaluation are all part of the system's systematic workflow. Various deep learning architectures, such as ResNet50, VGG-16, and U-Net, are employed for precise classification and segmentation of medical images. The approach incorporates advanced techniques such as optimization, transfer learning, and data augmentation to significantly enhance the …
Published in Research and Reviews: A Journal of Health Professions · Vol. 15, Issue 2, 2025 Read article