ACTIVE LEARNING BASED SYNTHETIC SAMPLE SELECTION FOR ENDOSCOPIC IMAGE CLASSIFICATION

Download
2022-9-2
İnci, Alperen
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 proper treatment, an expert physician needs to assess the severity of the disease. However, physicians have disagreements on the severity of the disease in terms of the widely used Mayo scoring. This brings in the need for reliable and au- tomated methods. Even though automated disease diagnosis using medical imaging has become a trending topic, labeling data in the medical field requires the agreement of a committee of experts and this is a limiting factor in obtaining a sufficient amount and variety of data for robust model training. Although generative data augmenta- tion methods have been proven to increase data diversity and quality, directly adding synthetic samples may not contribute to a model’s performance, and may even result in a performance drop. Some of these generated samples might be unrealistic, or already have been learned by the model and predicted with a high confidence score. In this thesis, we propose generation of a synthetic data pool, a subset of which is then selected and used for training. The data pool is created by generating samples with different truncation parameters. Then, active learning approaches are adopted to select informative synthetic samples among these samples in the data pool for model training. The results show that the results are favorable, and the performance is more stable compared to the baseline method and random selection of generated samples.

Suggestions

In vivo pain relief effectiveness of an analgesic-anesthetic carrying biodegradable controlled release rod systems
Sendil-Keskin, D; Altunay, H; Wise, DL; Hasırcı, Vasıf Nejat (2003-01-01)
Pain is the most common and feared symptom for patients, especially those with cancer. Treatment of chronic pain with conventional ways of medication usually fails with increasing severity of the pain. New approaches enabling the prolonged provision of pain relievers are required. We designed a controlled release system of pain relievers, mainly for opioids (morphine, M, codeine, C, and hydromorphone, HM), and a local anesthetic (bupivacaine, BP) in the form Of poly(L-lactide-colycolide) (PLGA) rods. The ef...
Psychological distress in rheumatoid arthritis patients: An evaluation within the conservation of resources theory
Dirik, Gulay; Karancı, Ayşe Nuray (2010-01-01)
Rheumatoid arthritis (RA) is a chronic disease, which can lead to considerable psychological distress. The present study evaluated anxiety and depression symptoms for this chronic and painful illness within the framework of the conservation of resources (COR) theory. Coping strategies, coping self-efficacy, religiousness and social support are very important personal resources, which have been found to protect individuals from psychological distress. The aim of the present study was to examine the predictiv...
Large Eddy Simulation of Blood Flow Inside Vessels for Acoustic Diagnosis of Atherosclerosis
Sert, Cüneyt; Yazıcıoğlu, Yiğit (2018-10-20)
Atherosclerosis is a cardiovascular disease, in which plaque builds up inside a blood vessel, narrowing it down and forming a stenosis that adversely affects flow. Because of the constriction, turbulent flow occurs at the post-stenotic region, which leads pressure fluctuations on the vessel wall. The murmur caused by this interaction propagates through the surrounding tissue and reaches the skin surface. These sounds emitted from the stenosed vessels are evaluated as a sign of stenosis. In this study, large...
Early alterations in myocardia and vessels of the diabetic rat heart: an FTIR microspectroscopic study
Toyran, Neslihan; Lasch, Peter; Naumann, Dieter; Turan, Belma; Severcan, Feride (2006-08-01)
Diabetes mellitus is associated with a high incidence and poor prognosis of cardiovascular disease. The aim of the present study was to examine the effect of relatively short-term (5 weeks) Type I diabetes on the left ventricle, the right ventricle and the vessel (vein) on the left ventricle of the myocardium, at molecular level by FTIR (Fourier-transform infrared) microspectroscopy. The rats were categorized into two groups: control group (for the left ventricle myocardium, n = 8; for the right ventricle m...
Social construction of "pseudo disease" in Turkey: Clinicians' practice of "giving diagnosis", patiens' voices from "subject positions"
Usubütün, Seda; Aksu, Meral; Department of Psychology (2003)
Pseudo diseases" that will be explored in that study are Undifferentiated Somatoform Disorder (USD), Fibromyalgia Syndrome (FMS) and Chronic Fatigue Syndrome (CFS). CFS is a diagnostic label that is not currently used in Turkish medical practice. In order to document the latency or absence of CFS diagnosis in our context, 108 medical specialists from Neurology, Infectious Diseases, Physical Treatment and Rehabilitation, and Psychiatry were asked to read a case scenario of a possible CFS patient and to give ...
Citation Formats
A. İnci, “ACTIVE LEARNING BASED SYNTHETIC SAMPLE SELECTION FOR ENDOSCOPIC IMAGE CLASSIFICATION,” M.S. - Master of Science, Middle East Technical University, 2022.