Knowledge Resource Center for Ecological Environment in Arid Area
DOI | 10.1007/978-3-319-75238-9_1 |
Dice Overlap Measures for Objects of Unknown Number: Application to Lesion Segmentation | |
Oguz, Ipek1; Carass, Aaron2,3; Pham, Dzung L.4; Roy, Snehashis4; Subbana, Nagesh1; Calabresi, Peter A.5; Yushkevich, Paul A.1; Shinohara, Russell T.6; Prince, Jerry L.2,3 | |
通讯作者 | Oguz, Ipek |
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 | The Dice overlap ratio is commonly used to evaluate the performance of image segmentation algorithms. While Dice overlap is very useful as a standardized quantitative measure of segmentation accuracy in many applications, it offers a very limited picture of segmentation quality in complex segmentation tasks where the number of target objects is not known a priori, such as the segmentation of white matter lesions or lung nodules. While Dice overlap can still be used in these applications, segmentation algorithms may perform quite differently in ways not reflected by differences in their Dice score. Here we propose a new set of evaluation techniques that offer new insights into the behavior of segmentation algorithms. We illustrate these techniques with a case study comparing two popular multiple sclerosis (MS) lesion segmentation algorithms: OASIS and LesionTOADS. |
英文关键词 | Segmentation Evaluation MS Lesion |
来源出版物 | BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2017 |
ISSN | 0302-9743 |
EISSN | 1611-3349 |
出版年 | 2018 |
卷号 | 10670 |
页码 | 3-14 |
ISBN | 978-3-319-75237-2 |
EISBN | 978-3-319-75238-9 |
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:000432603300001 |
WOS关键词 | MULTIPLE-SCLEROSIS LESIONS ; MRI |
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/2XILL650/307334 |
作者单位 | 1.Univ Penn, Dept Radiol, Philadelphia, PA 19104 USA; 2.Johns Hopkins Univ, Dept Elect & Comp Engn, Baltimore, MD 21218 USA; 3.Johns Hopkins Univ, Dept Comp Sci, Baltimore, MD 21218 USA; 4.Henry M Jackson Fdn Adv Mil Med, CNRM, Bethesda, MD 20817 USA; 5.Johns Hopkins Univ, Dept Neurol, Sch Med, Baltimore, MD 21287 USA; 6.Univ Penn, Dept Biostat & Epidemiol, Philadelphia, PA 19104 USA |
推荐引用方式 GB/T 7714 | Oguz, Ipek,Carass, Aaron,Pham, Dzung L.,et al. Dice Overlap Measures for Objects of Unknown Number: Application to Lesion Segmentation[C]:SPRINGER INTERNATIONAL PUBLISHING AG,2018:3-14. |
条目包含的文件 | 条目无相关文件。 |
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。