A5050009251- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Screening and Detection
- COVID-19 diagnosis using AI
- Advanced Neural Network Applications
- Vehicle License Plate Recognition
- Artificial Intelligence in Healthcare
- Gastric Cancer Management and Outcomes
- Image Enhancement Techniques
- Advanced Image and Video Retrieval Techniques
- Handwritten Text Recognition Techniques
- Digital Imaging for Blood Diseases
- Image Retrieval and Classification Techniques
- Natural Language Processing Techniques
- Photovoltaic System Optimization Techniques
- Anomaly Detection Techniques and Applications
- Explainable Artificial Intelligence (XAI)
- Image and Signal Denoising Methods
- Power Line Inspection Robots
- Brain Tumor Detection and Classification
- Medical Imaging and Analysis
- Cell Image Analysis Techniques
Gachon University
2020-2024
Abstract Polyps are well-known cancer precursors identified by colonoscopy. However, variability in their size, appearance, and location makes the detection of polyps challenging. Moreover, colonoscopy surveillance removal highly operator-dependent procedures occur a complex organ topology. There exists high missed rate incomplete colonic polyps. To assist clinical reduce rates, automated methods for detecting segmenting using machine learning have been achieved past years. major drawback...
In the last few decades, photovoltaic (PV) power station installations have surged across globe. The output efficiency of these stations deteriorates with passage time due to multiple factors such as hotspots, shaded cell or module, short-circuited bypass diodes, etc. Traditionally, technicians inspect each solar panel in a PV using infrared thermography ensure consistent efficiency. With advancement drone technology, researchers proposed use drones equipped thermal cameras for monitoring....
Computer-aided diagnosis systems developed by computer vision researchers have helped doctors to recognize several endoscopic colorectal diseases more rapidly, which allows appropriate treatment and increases the patient's survival ratio. Herein, we present a robust architecture for image classification using an efficient dilation in Convolutional Neural Network (CNNs). It has high receptive field of view at deep layers increasing decreasing factor preserve spatial details. We argue that...
The incidence of cancer among modern people has recently increased due to various reasons such as eating habits, smoking, and drinking. Therefore, medical image analysis for effective disease diagnosis is considered an extremely important diagnostic tool. In particular, endoscopy used a representative screening method diagnosing diseases the digestive system. However, it quite difficult quickly thoroughly analyze data by relying solely on human vision, with endoscopy. purpose this study was...
Polyps are well-known cancer precursors identified by colonoscopy. However, variability in their size, location, and surface largely affect identification, localisation, characterisation. Moreover, colonoscopic surveillance removal of polyps (referred to as polypectomy ) highly operator-dependent procedures. There exist a high missed detection rate incomplete colonic due variable nature, the difficulties delineate abnormality, recurrence rates, anatomical topography colon. have been several...
Polyp segmentation has accomplished massive triumph over the years in field of supervised learning. However, obtaining a vast number labeled datasets is commonly challenging medical domain. To solve this problem, we employ semi-supervised methods and suitably take advantage unlabeled data to improve performance polyp image segmentation. First, propose an encoder-decoder-based method well suited for with varying shape, size, scales. Second, utilize teacher-student concept training model,...
In this nutshell, we propose a simple, efficient, and explainable deep learning-based U-Net algorithm for the MedAI challenge, focusing on precise segmentation of polyp instrument transparency algorithms. We develop straightforward encoder-decoder-based task above. make an effort to simple network as much possible. Specially, focus input resolution width model find best optimal settings network. perform ablation studies cover aspect.
In polyp segmentation, the latest notable topic revolves around generalization, which aims to develop deep learning-based models capable of learning from single or multiple source domains and applying this knowledge unseen datasets. A significant challenge in real-world clinical settings is suboptimal performance generalized due domain shift. Convolutional neural networks (CNNs) are often biased towards low-level features, such as style impacting generalization. Despite attempts mitigate...
Automatic analysis of colonoscopy images has been an active field research motivated by the importance early detection precancerous polyps. However, detecting polyps during live examination can be challenging due to various factors such as variation skills and experience among endoscopists, lack attentiveness, fatigue leading a high polyp miss-rate. Deep learning emerged promising solution this challenge it assist endoscopists in classifying overlooked abnormalities real time. In addition...
Whole slide imaging is now being used across the world in pathology labs for an accurate diagnosis of biopsy specimens. However, due to large size these images, automatic deep learning-based method highly desirable diagnosing. Herein, we propose a two-step methodology classification and segmentation whole-slide image (WSI). First, patches are extracted from fed into learning based techniques like U-Net with its corresponding mask segmentation. Further, cancerous trained task. During...
The coronavirus disease (COVID-19) highlighted our daily lives recently and caused panic over the world. In parallel, artificial intelligence contributes to presenting solutions cease spread of virus by offering robust deep learning models for detection in chest X-ray images, despite limited data available quality its distribution as we face problem imbalanced often this kind classification. To manage issue, many techniques were presented that aim make dataset homogeneous, increase accuracy...