Arid
DOI10.1007/978-3-319-75238-9_4
Joint Intensity Fusion Image Synthesis Applied to Multiple Sclerosis Lesion Segmentation
Fleishman, Greg M.1; Valcarcel, Alessandra2; Pham, Dzung L.3; Roy, Snehashis3; Calabresi, Peter A.4; Yushkevich, Paul1; Shinohara, Russell T.2; Oguz, Ipek1
通讯作者Fleishman, Greg M.
会议名称3rd International Workshop on Brain-Lesion (BrainLes) held jointly at the Conference on Medical Image Computing for Computer Assisted Intervention (MICCAI)
会议日期SEP 14, 2017
会议地点Quebec City, CANADA
英文摘要

We propose a new approach to Multiple Sclerosis lesion segmentation that utilizes synthesized images. A new method of image synthesis is considered: joint intensity fusion (JIF). JIF synthesizes an image from a library of deformably registered and intensity normalized atlases. Each location in the synthesized image is a weighted average of the registered atlases; atlas weights vary spatially. The weights are determined using the joint label fusion (JLF) framework. The primary methodological contribution is the application of JLF to MRI signal directly rather than labels. Synthesized images are then used as additional features in a lesion segmentation task using the OASIS classifier, a logistic regression model on intensities from multiple modalities. The addition of JIF synthesized images improved the Dice-Sorensen coefficient (relative to manually drawn gold standards) of lesion segmentations over the standard model segmentations by 0.0462 +/- 0.0050 (mean +/- standard deviation) at optimal threshold over all subjects and 10 separate training/testing folds.


来源出版物BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2017
ISSN0302-9743
EISSN1611-3349
出版年2018
卷号10670
页码43-54
ISBN978-3-319-75237-2
EISBN978-3-319-75238-9
出版者SPRINGER INTERNATIONAL PUBLISHING AG
类型Proceedings Paper
语种英语
国家USA
收录类别CPCI-S
WOS记录号WOS:000432603300004
WOS关键词STATISTICAL ESTIMATION ; ATLAS
WOS类目Computer Science, Theory & Methods ; Clinical Neurology ; Neurosciences ; Neuroimaging
WOS研究方向Computer Science ; Neurosciences & Neurology
资源类型会议论文
条目标识符http://119.78.100.177/qdio/handle/2XILL650/307337
作者单位1.Univ Penn, Dept Radiol, Philadelphia, PA 19104 USA;
2.Univ Penn, Dept Biostat & Epidemiol, Philadelphia, PA 19104 USA;
3.Henry M Jackson Fdn Adv Mil Med, CNRM, Bethesda, MD 20817 USA;
4.Johns Hopkins Univ, Sch Med, Dept Neurol, Baltimore, MD 21287 USA
推荐引用方式
GB/T 7714
Fleishman, Greg M.,Valcarcel, Alessandra,Pham, Dzung L.,et al. Joint Intensity Fusion Image Synthesis Applied to Multiple Sclerosis Lesion Segmentation[C]:SPRINGER INTERNATIONAL PUBLISHING AG,2018:43-54.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Fleishman, Greg M.]的文章
[Valcarcel, Alessandra]的文章
[Pham, Dzung L.]的文章
百度学术
百度学术中相似的文章
[Fleishman, Greg M.]的文章
[Valcarcel, Alessandra]的文章
[Pham, Dzung L.]的文章
必应学术
必应学术中相似的文章
[Fleishman, Greg M.]的文章
[Valcarcel, Alessandra]的文章
[Pham, Dzung L.]的文章
相关权益政策
暂无数据
收藏/分享

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。