消息
×
loading..
Multimodal Local Representation Learning For Multi-Task Blastocyst Assessment
2024-10
会议录名称IEEE SYMPOSIUM ON BIOMEDICAL IMAGING 2024
ISSN1945-7928
发表状态已发表
DOI10.1109/ISBI56570.2024.10635863
摘要Blastocyst assessment is a critical step to influence the live birth rate in the in vitro fertilization (IVF) treatment. We propose a pioneer multimodal local representation learning framework that leverages both visual and textual information, which provides a comprehensive and automatic assessment of blastocyst quality. The model redefines the blastocyst assessment as an image-text retrieval multi-task, assessing two main blastocyst components, the inner cell mass (ICM) and trophoblast (TE), respectively. By learning local representation, our approach captures the fine-grained similarity between text descriptions and image patches, enhancing the accuracy and interpretability of the assessment model. The experimental results are promising, achieving accuracy 89.1% for ICM and 91.6% for TE respectively. Furthermore, this proposed local representation learning framework may extend to other multi-task biomedical imaging applications.
会议录编者/会议主办者AI2D Center ; et al. ; Therapanacea ; Thermo Fisher Scientific ; United Imaging Intelligence ; Verasonics
关键词Adversarial machine learning Cell culture Contrastive Learning Image representation Image retrieval Multi-task learning Biomedical images Blastocyst assessment Image texts Image-text retrieval Learning frameworks Multi tasks Multi-modal Multi-task model Multimodal local representation Text retrieval
会议名称21st IEEE International Symposium on Biomedical Imaging, ISBI 2024
会议地点Athens, Greece
会议日期27-30 May 2024
URL查看原文
收录类别EI
语种英语
出版者IEEE Computer Society
EI入藏号20243717024919
EI主题词Medical imaging
EISSN1945-8452
EI分类号101.1 ; 101.3 ; 101.7 ; 102.2.1 ; 1101.2 ; 1106.3.1 ; 746 Imaging Techniques
原始文献类型Conference article (CA)
来源库IEEE
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/378350
专题信息科学与技术学院_硕士生
创意与艺术学院_PI研究组(P)_谢广平组
创意与艺术学院_PI研究组(P)_杨锐组
创意与艺术学院_PI研究组(P)_武颖娜组
共同第一作者Zhang J(张军); Xie GP(谢广平)
通讯作者Ni N(倪娜)
作者单位
1.上海科技大学
2.西安交通大学第一附属医院
第一作者单位上海科技大学
通讯作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Zhang J,Zheng BZ,Ni N,et al. Multimodal Local Representation Learning For Multi-Task Blastocyst Assessment[C]//AI2D Center, et al., Therapanacea, Thermo Fisher Scientific, United Imaging Intelligence, Verasonics:IEEE Computer Society,2024.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zhang J(张军)]的文章
[Zheng BZ(郑博中)]的文章
[Ni N(倪娜)]的文章
百度学术
百度学术中相似的文章
[Zhang J(张军)]的文章
[Zheng BZ(郑博中)]的文章
[Ni N(倪娜)]的文章
必应学术
必应学术中相似的文章
[Zhang J(张军)]的文章
[Zheng BZ(郑博中)]的文章
[Ni N(倪娜)]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。