Cited 0 time in webofscience Cited 0 time in scopus

Retinal OCT Image Segmentation Using Semi-supervised Learning with Generative Adversarial Networks

Title
Retinal OCT Image Segmentation Using Semi-supervised Learning with Generative Adversarial Networks
Translated Title
적대적 생성 모델을 이용한 반지도학습 기반의 안구 OCT 영상 영역화
Authors
Gyeongmin Lee
DGIST Authors
Lee, Gyeongmin; Kung, JaehaPark, Sanghyun
Advisor(s)
박상현
Co-Advisor(s)
Jaeha Kung
Issue Date
2020
Available Date
2020-06-23
Degree Date
2020-02
Type
Thesis
Description
Optical coherence tomography, Generative adversarial network, Weakly-supervised learning, Semi-supervised learning, Segmentation
Abstract
Optical coherence tomography (OCT) is a three-dimensional imaging technique with micrometer resolution by irradiating a laser to optical scattering media such as tissues of living organisms, and can acquire images in depth direction. In particular, it is mainly used in the medical field. This is because, unlike the radiation-based imaging technique or the method of injecting a contrast agent and imaging it, it is a non-invasive method that does not affect the patient and there is little preparation time in imaging. In ophthalmology, OCT can image retinal layers to predict prognosis of vision and other eye diseases. Also, by continuously photographing the OCT, blood flow in the retina may be measured by imaging a fluid flowing in a certain area of ​​the retina, which is associated with various diseases such as diabetes. But analyzing these images is time-consuming and there are differences in the results among doctors. In this paper, we propose 1) CAM generation using Attention-based multiple instance learning (AMIL). After dividing the images into patch units, we design a model that learns the importance of the patches that contribute to the classification, and generate CAMs of the patch units using the trained parameters to calculate the contributions. The CAM thus obtained shows the shape of the object better than the conventional CAM through the whole image-based learning and is similar to the actual label, so it is used when training the segmentation model with a few labelled data. And 2) based on the Generative Adversarial Network (GAN) structure, which learns the generator and discriminator repeatedly as a method for learning the zoning model using a few labelled data and the AMIL-based CAM generated by the technique of 1). We propose a segmentation model. The proposed method was applied to the OCT image provided by Yeungnam University and the OCT dataset published in kaggle. Thus, the proposed weak label generation method showed better performance than the existing CAM method or AMIL method. In addition, the proposed GAN-based method shows that the data using a small amount of accurate label and the weak label created by the proposed method improves the performance by about 2% compared to the learning using only a small amount of accurate label.
Table Of Contents
I. INTRODUCTION 1 1. introduction 1 2. Related works 2 3. Contributions 3 II. BACKGROUND 5 1. Weakly-supervised learning 5 2. Generative adversarial network 7 III. METHOD 8 1. Class activation mapping using attention-based multiple instance learning 9 2. Semi-supervised learning with generative adversarial network 11 IV. RESULTS 14 1. Dataset 14 2. Implementation details 14 3. Results 15 V. Conclusion 18 Reference 19
URI
http://dgist.dcollection.net/common/orgView/200000285620
http://hdl.handle.net/20.500.11750/11969
DOI
10.22677/Theses.200000285620
Degree
Master
Department
Robotics Engineering
University
DGIST
Related Researcher
  • Author Kung, Jaeha Intelligent Digital Systems Lab
  • Research Interests 딥러닝, 가속하드웨어, 저전력 하드웨어, 고성능 시스템
Files:
There are no files associated with this item.
Collection:
Department of Robotics EngineeringThesesMaster


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE