Publications
Detailed Information
3D Convolutional Neural Networks for Brain Tumor Segmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 유석인 | - |
dc.contributor.author | 신동준 | - |
dc.date.accessioned | 2017-07-14T02:34:49Z | - |
dc.date.available | 2017-07-14T02:34:49Z | - |
dc.date.issued | 2016-02 | - |
dc.identifier.other | 000000132980 | - |
dc.identifier.uri | https://hdl.handle.net/10371/122655 | - |
dc.description | 학위논문 (석사)-- 서울대학교 대학원 : 컴퓨터공학부, 2016. 2. 유석인. | - |
dc.description.abstract | Brain Tumor segmentation aims to separating the different tumor tissues (solid
or active tumor, edema, and necrosis) from normal brain tissue: gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). In brain tumor studies, the existence of abnormal tissues may be easily detectable most of the time. However, accurate and reproducible segmentation and characterization of abnormalities are not straightforward. Even for experienced doctors, precise detection of tumor in MR image makes a long business. In recently years, Convolutional Neural Networks (CNNs) often obtain incredible results in problems to extract information from complex and high-dimensional inputs, for which useful features are not obvious to be identified from the structured design. In this thesis, we propose a new model for brain tumor segmentation in Magnetic Resonance Imaging (MRI) by adapting multiple dimension feature combination. First, we preprocessed original MRI meta-image in several way because MRI meta-image has much information not only brain tissue and tumor but also unnecessary noise, skull, biased intensity. Second, we built two dimensional multi-channel non-pooling convolutional neural networks. It is not common model because almost convolutional neural networks models have focused on natural image classification. But in medical image processing, low level accurate segmentation is important than high level abstract. Finally, we built a three-dimensional convolutional neural networks by combination of 2 dimensional model data and compare its result with 2 dimensional CNNs result. The method was evaluated on BRATS 2013 (Brain Tumor Segmentation 2013) data set. This data set provided via the Virtual Skeleton Database (VSD). Experiment results on respective datasets show the proposed algorithm works successfully and combination of coordinate plane information improve performance in three-dimensional segmentation problem | - |
dc.description.tableofcontents | Chapter 1 Introduction 1
Chapter 2 Previous work 6 2.1 Preprocess 7 2.1.1 Image de-noising 7 2.1.2 Skull-stripping 7 2.1.3 Intensity normalization 8 2.2 Segmentation 9 2.2.1 Threshold-based methods 9 2.2.2 Region-based methods 10 2.2.3 Pixel classication methods 10 2.2.4 Model based methods 11 Chapter 3 Proposed approach 12 3.1 Preprocessing 12 3.1.1 Bias correction 12 3.1.2 Normalization 13 3.2 3D Multipolar CNN 13 Chapter 4 Experiment 17 4.1 Environment 17 4.2 Result Evaluation 18 4.3 Runtime Evaluation 20 Chapter 5 Conculsion 22 5.1 Summary of the Work 22 5.2 Future Work 22 Bibliography 24 요약 29 | - |
dc.format | application/pdf | - |
dc.format.extent | 3926812 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | CNN | - |
dc.subject | MRI | - |
dc.subject | segmentation | - |
dc.subject.ddc | 621 | - |
dc.title | 3D Convolutional Neural Networks for Brain Tumor Segmentation | - |
dc.type | Thesis | - |
dc.contributor.AlternativeAuthor | Dongjun Shin | - |
dc.description.degree | Master | - |
dc.citation.pages | 39 | - |
dc.contributor.affiliation | 공과대학 컴퓨터공학부 | - |
dc.date.awarded | 2016-02 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.