Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge

S Ali, N Ghatwary, D Jha, E Isik-Polat, G Polat… - Scientific Reports, 2024 - nature.com
Polyps are well-known cancer precursors identified by colonoscopy. However, variability in
their size, appearance, and location makes the detection of polyps challenging. Moreover …

Improving the computer-aided estimation of ulcerative colitis severity according to mayo endoscopic score by using regression-based deep learning

G Polat, HT Kani, I Ergenc… - Inflammatory Bowel …, 2023 - academic.oup.com
Background Assessment of endoscopic activity in ulcerative colitis (UC) is important for
treatment decisions and monitoring disease progress. However, substantial inter-and …

A stacking-based artificial intelligence framework for an effective detection and localization of colon polyps

C Albuquerque, R Henriques, M Castelli - Scientific Reports, 2022 - nature.com
Polyp detection through colonoscopy is a widely used method to prevent colorectal cancer.
The automation of this process aided by artificial intelligence allows faster and improved …

Class distance weighted cross-entropy loss for ulcerative colitis severity estimation

G Polat, I Ergenc, HT Kani, YO Alahdab, O Atug… - Annual Conference on …, 2022 - Springer
In scoring systems used to measure the endoscopic activity of ulcerative colitis, such as
Mayo endoscopic score or Ulcerative Colitis Endoscopic Index Severity, levels increase with …

Sources of performance variability in deep learning-based polyp detection

TN Tran, TJ Adler, A Yamlahi, E Christodoulou… - International Journal of …, 2023 - Springer
Purpose Validation metrics are a key prerequisite for the reliable tracking of scientific
progress and for deciding on the potential clinical translation of methods. While recent …

Evaluation and analysis of different aggregation and hyperparameter selection methods for federated brain tumor segmentation

E Isik-Polat, G Polat, A Kocyigit, A Temizel - … MICCAI Brainlesion Workshop, 2021 - Springer
Availability of large, diverse, and multi-national datasets is crucial for the development of
effective and clinically applicable AI systems in the medical imaging domain. However …

Improving classification performance of endoscopic images with generative data augmentation

ÜM Çağlar - 2022 - open.metu.edu.tr
The performance of a supervised deep learning model is highly dependent on the quality
and variety of the images in the training dataset. In some applications, it may be impossible …

[PDF][PDF] StackBox: An improved framework for precise polyp detection

C Albuquerque, R Henriques, M Castelli - 2022 - run.unl.pt
Polyp detection through colonoscopy is a widely used method to prevent colorectal cancer.
The automation of this process aided by arti cial intelligence allows faster and improved …

ACTIVE LEARNING BASED SYNTHETIC SAMPLE SELECTION FOR ENDOSCOPIC IMAGE CLASSIFICATION

A İnci - 2022 - open.metu.edu.tr
Many people suffer from Ulcerative Colitis (UC), which is a chronic inflammatory bowel
disease. UC exhibits itself as ulcers, inflammation, and sores in the colon. In order to provide …

Object Detection in Medical Imaging

CIA Albuquerque - 2023 - search.proquest.com
Artificial Intelligence, assisted by deep learning, has emerged in various fields of our society.
These systems allow the automation and the improvement of several tasks, even …