Cascaded Inner-Outer Clip Retformer for Ultrasound Video Object Segmentation

计算机视觉 计算机科学 人工智能 分割 图像分割 对象(语法) 放射科 医学
作者
Jialu Li,Lei Zhu,Zhaohu Xing,Baoliang Zhao,Ying Hu,Faqin Lv,Q. Wang
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:29 (12): 8876-8889 被引量:3
标识
DOI:10.1109/jbhi.2024.3464732
摘要

Computer-aided ultrasound (US) imaging is an important prerequisite for early clinical diagnosis and treatment. Due to the harsh ultrasound (US) image quality and the blurry tumor area, recent memory-based video object segmentation models (VOS) achieve frame-level segmentation by performing intensive similarity matching among the past frames which could inevitably result in computational redundancy. In this paper, we first build a larger annotated benchmark dataset for breast lesion segmentation in ultrasound videos, then we propose a lightweight clip-level VOS framework for achieving higher segmentation accuracy while maintaining the speed. Then an Inner-Outer Clip Retformer is proposed to extract spatial-temporal tumor features in parallel. Specifically, the proposed Outer Clip Retformer extracts the tumor movement feature from past video clips to locate the current clip tumor position, while the Inner Clip Retformer detailedly extracts current tumor features that can produce more accurate segmentation results. Then a Clip Contrastive loss function is further proposed to align the extracted tumor features along both the spatial-temporal dimensions to improve the segmentation accuracy. In addition, the Global Retentive Memory is proposed to maintain the complementary tumor features with lower computing resources which can generate coherent temporal movement features. In this way, our model can significantly improve the spatial-temporal perception ability without increasing a large number of parameters, achieving more accurate segmentation results while maintaining a faster segmentation speed. Finally, we conduct extensive experiments to evaluate our proposed model on several video object segmentation datasets, the results show that our framework outperforms state-of-the-art segmentation methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
香蕉觅云应助王二采纳,获得10
刚刚
勤劳冰烟完成签到,获得积分10
1秒前
害羞的新之完成签到 ,获得积分10
1秒前
1秒前
1秒前
科研通AI6.4应助QDU采纳,获得10
1秒前
三人行发布了新的文献求助10
1秒前
坦率豆芽完成签到,获得积分10
1秒前
ATYS完成签到,获得积分10
2秒前
陈含章完成签到,获得积分10
2秒前
2秒前
言非离完成签到,获得积分10
2秒前
2秒前
lilly发布了新的文献求助30
3秒前
3秒前
3秒前
852应助长情雪兰采纳,获得10
3秒前
梦泊发布了新的文献求助10
3秒前
4秒前
4秒前
4秒前
万能图书馆应助叶白山采纳,获得10
5秒前
5秒前
5秒前
黎敏完成签到,获得积分10
6秒前
合作发布了新的文献求助10
6秒前
夜月残阳完成签到,获得积分10
6秒前
6秒前
6秒前
坦率豆芽发布了新的文献求助10
7秒前
花菜完成签到 ,获得积分10
7秒前
7秒前
一栗籽发布了新的文献求助50
7秒前
ATYS发布了新的文献求助10
8秒前
8秒前
大白兔发布了新的文献求助10
8秒前
李科研完成签到,获得积分10
8秒前
孙一斤发布了新的文献求助10
8秒前
8秒前
三人行完成签到,获得积分10
8秒前
高分求助中
卤化钙钛矿人工突触的研究 1000
Engineering for calcareous sediments : proceedings of the International Conference on Calcareous Sediments, Perth 15-18 March 1988 / edited by R.J. Jewell, D.C. Andrews 1000
Wolffs Headache and Other Head Pain 9th Edition 1000
Continuing Syntax 1000
Signals, Systems, and Signal Processing 510
Cardiac structure and function of elite volleyball players across different playing positions 500
CLSI H26-A2 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 物理 内科学 复合材料 催化作用 物理化学 光电子学 电极 细胞生物学 基因 无机化学
热门帖子
关注 科研通微信公众号,转发送积分 6242122
求助须知:如何正确求助?哪些是违规求助? 8066055
关于积分的说明 16834998
捐赠科研通 5320156
什么是DOI,文献DOI怎么找? 2832952
邀请新用户注册赠送积分活动 1810534
关于科研通互助平台的介绍 1666851