A5055226892- Colorectal Cancer Screening and Detection
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- AI in cancer detection
- Privacy-Preserving Technologies in Data
- Face and Expression Recognition
- Brain Tumor Detection and Classification
- Gastrointestinal Bleeding Diagnosis and Treatment
- Domain Adaptation and Few-Shot Learning
- Adversarial Robustness in Machine Learning
- Mycobacterium research and diagnosis
- Lung Cancer Diagnosis and Treatment
- Gastrointestinal disorders and treatments
- Digital Imaging for Blood Diseases
- Esophageal Cancer Research and Treatment
- Currency Recognition and Detection
- Microscopic Colitis
- Gastric Cancer Management and Outcomes
- Artificial Intelligence in Healthcare and Education
- Remote-Sensing Image Classification
- Advanced Neural Network Applications
- Inflammatory Bowel Disease
- Biomedical and Engineering Education
- Machine Learning in Healthcare
- Advanced Image and Video Retrieval Techniques
Middle East Technical University
2021-2024
The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems suggest pathway for clinical translation of technologies. Whilst widely used diagnostic treatment tool hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence multi-class artefacts that hinder their visual interpretation, 2) difficulty identifying subtle...
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...
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...
Assessment of endoscopic activity in ulcerative colitis (UC) is important for treatment decisions and monitoring disease progress. However, substantial inter- intraobserver variability grading impairs the assessment. Our aim was to develop a computer-aided diagnosis system using deep learning reduce subjectivity improve reliability assessment.The cohort comprises 11 276 images from 564 patients who underwent colonoscopy UC. We propose regression-based approach evaluation UC according Mayo...
The number of international benchmarking competitions is steadily increasing in various fields machine learning (ML) research and practice. So far, however, little known about the common practice as well bottlenecks faced by community tackling questions posed. To shed light on status quo algorithm development specific field biomedical imaging analysis, we designed an survey that was issued to all participants challenges conducted conjunction with IEEE ISBI 2021 MICCAI conferences (80 total)....
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment validation used algorithms, but relatively little attention has been given practical pitfalls when using specific a task. These typically related (1) disregard inherent metric properties, such as behaviour in presence class...
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces mortality by 20% compared to traditional chest radiography. Therefore, CT has started be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in scan can up 600. computer-aided-detection (CAD) systems are very important faster and more accurate assessment data. In this study, we proposed framework analyzes...
Assessing disease severity involving ordinal classes, where each class represents increasing levels of severity, benefit from loss functions that account for this structure. Traditional categorical functions, like Cross-Entropy (CE), often perform suboptimally in these scenarios. To address this, we propose a novel function, Class Distance Weighted (CDW-CE), which penalizes misclassifications more harshly when classes are farther apart. We evaluated CDW-CE on the Labeled Images Ulcerative...
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces mortality by 20% compared to traditional chest radiography. Therefore, CT has started be used widely all across the world. However, analyzing these images is a serious burden for radiologists. In this study, we propose novel and simple framework analyzes screenings convolutional neural networks (CNNs) false positives. Our shows even non-complex architectures are very powerful classify...
Endoscopic imaging is commonly used to diagnose Ulcerative Colitis (UC) and classify its severity. It has been shown that deep learning based methods are effective in automated analysis of these images can potentially be aid medical doctors. Unleashing the full potential depends on availability large amount labeled images; however, obtaining labeling quite challenging. In this paper, we propose a active generative augmentation method. The method involves generating number synthetic samples...
Endoscopic imaging is commonly used to diagnose Ulcerative Colitis (UC) and classify its severity. It has been shown that deep learning based methods are effective in automated analysis of these images can potentially be aid medical doctors. Unleashing the full potential depends on availability large amount labeled images; however, obtaining labeling quite challenging. In this paper, we propose a active generative augmentation method. The method involves generating number synthetic samples...
In scoring systems used to measure the endoscopic activity of ulcerative colitis, such as Mayo score or Ulcerative Colitis Endoscopic Index Severity, levels increase with severity disease activity. Such relative ranking among scores makes it an ordinal regression problem. On other hand, most studies use categorical cross-entropy loss function train deep learning models, which is not optimal for this study, we propose a novel function, class distance weighted (CDW-CE), that respects order...
Aims Multilayer artificial neural networks are intelligence (AI) algorithms with high predictive power that allow processing large volumes of data sets. Ulcerative colitis (UC) Endoscopic Mayo Score (EMS) is a subjective assessment varies between the endoscopists (1, 2). Our aim was to develop an AI algorithm evaluate endoscopist-independent EMS accuracy and minimize subjectivity.