DENTAL PANORAMIC AND BITEWING X-RAY IMAGE SEGMENTATION USING U-NET AND TRANSFORMER NETWORKS

Download

Mete_Can_Kaya_thesis.pdf

Date

2023-1-23

Author

KAYA, METE CAN

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

426
views

460
downloads

With the advancement in medical imaging systems, and the underlying software platforms, diagnostics success in medicine improved significantly. Even though automatized systems are essential tools for diagnostic success, medical professional opinion is still used a lot, especially in dentistry. In the area of dentistry, x-ray images are wildly used for diagnostic purposes, i.e. to find caries, the location of embedded wisdom teeth, the health of the bone structure, etc. The dentist uses contrast and region-based information to evaluate these images. However, evaluation can be time-consuming, and it is not foolproof. In the literature, several studies exist on automatic detection from dental panoramic or bitewing images separately. Different then these studies, in this thesis, a transformer-based model is used for the segmentation of teeth using both panoramic and bitewing images. The proposed model achieved similar results on a panoramic dataset with state-of-the-art models while achieving %90 accuracy on the bitewing dataset.

Subject Keywords

Dental image, Segmentation, Transformers

URI

https://hdl.handle.net/11511/102047

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation Polat, Görkem; Işık Polat, Ece; Koçyiğit, Altan; Temizel, Alptekin (2021-9-27) 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, forming a global model by bringing these datasets together at a central location, comes along with various data privacy and ownership problems. To alleviate these problems, several recent studies focus on the federated learning paradigm, a distributed learning approach for decentralized data. Federated learning leverages all the ...
Integrated circuit design for flip-chip bonded capacitive micromachined ultrasonic transducers Maadi, Muhammad; Bayram, Barış; Department of Electrical and Electronics Engineering (2013) In previous decades, the applications of ultrasound technologies in medical imaging and therapeutic systems have significantly increased. In conventional ultrasound systems, the transducer array is separated from the electronic instrumentation with multicore physical cabling. However, connection cables make the system too bulky and degrade the receive sensitivity in ultrasound 3D imaging applications because of the capacitance of long cables. The interface electronics for phased array ultrasound systems (im...
Development of a Visio-Haptic Integrated Dental Training Simulation System Konukseven, Erhan İlhan; Önder, Mustafa Turgut; Mumcuoğlu, Ünal Erkan (2010-08-01) The use of haptic devices in the medical field has become widespread in the last decade. In this study, a visio-haptic dental training system is developed using haptic and stereoscopic devices. Several advantages are offered by such a simulation system, including effective learning without any fear of making mistakes on a patient, possibility of repeating various dental operations, ease of evaluating student performance, and low-cost dental training even without an instructor. In this study, the biomechanic...
Optimum Design of 6R Passive Haptic Robotic Arm for Implant Surgery Yılmaz, Serkan; Konukseven, Erhan İlhan (2010-07-10) The aim of this research was to design an optimum 6R passive haptic robotic arm (PHRA) to work in a limited workspace during dental implant surgery. Misplacement of an implant during dental surgery causes longer recuperation periods and functional disorders. In this study, a passive guidance robot arm was designed as a surgical aid tool for a dentist during the operation to reduce the surgical complications. Optimum design of a 6R robot is a complex issue since minimum energy has to be consumed while maximu...
Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods Işın, Ali; Direkoğlu, Cem; Şah, Melike (Elsevier BV; 2016) Brain tumor segmentation is an important task in medical image processing. Early diagnosis of brain tumors plays an important role in improving treatment possibilities and increases the survival rate of the patients. Manual segmentation of the brain tumors for cancer diagnosis, from large amount of MRI images generated in clinical routine, is a difficult and time consuming task. There is a need for automatic brain tumor image segmentation. The purpose of this paper is to provide a review of MRI-based brain ...

Citation Formats

M. C. KAYA, “DENTAL PANORAMIC AND BITEWING X-RAY IMAGE SEGMENTATION USING U-NET AND TRANSFORMER NETWORKS,” M.S. - Master of Science, Middle East Technical University, 2023.