Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70120
Title: | 結合序列與跨型態學習運用在 3D 生醫影像分割 Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation |
Authors: | Kuan-Lun Tseng 曾冠綸 |
Advisor: | 黃鐘揚(Chung-Yang (Ric) |
Keyword: | 深度學習,影像分割, deep learning,image segmentation, |
Publication Year : | 2018 |
Degree: | 碩士 |
Abstract: | 深度學習如卷積類神經網路在生醫影像上面已經被廣泛的運用而 且取得了突破性的成績。但是多數的方法並沒有採用多種圖像來源或 是僅僅把多種來源當成不同的頻道來使用。為了要把多型態的圖片的 資訊結合起來,本論文提出一個深度學習模型結合跨型態卷積利用在 核磁共振的腦部影像中。我們更利用序列學習中的卷積記憶網路把二 維序列所富涵的資訊結合。整個模型是可以直接做最佳化的,且為了 解決細胞分佈嚴重不平衡的問題我們利用平衡權重的方式來解決。在 BRATS-2015 的資料集中顯示我們的方法是比目前的方法都還要優秀的 Deep learning models such as convolutional neural network have been widely used in 3D biomedical segmentation and achieve state-of-the-art performance. However, most of them often adapt a single modality or stack multiple modalities as different input channels. To better leverage the multi- modalities, we propose a deep encoder-decoder structure with cross-modality convolution layers to incorporate different modalities of MRI data. In addition, we exploit convolutional LSTM to model a sequence of 2D slices, and jointly learn the multi-modalities and convolutional LSTM in an end-to-end manner. To avoid converging to the certain labels, we adopt a re-weighting scheme and two-phase training to handle the label imbalance. Experimental results on BRATS-2015 [13] show that our method outperforms state-of-the- art biomedical segmentation approaches. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70120 |
DOI: | 10.6342/NTU201800241 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 電機工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-107-1.pdf Restricted Access | 1.21 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.