Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention

计算机科学 一般化 合成数据 人工智能 探测器 深度学习 机器学习 训练集 模式识别(心理学) 数学 电信 数学分析
作者
Ruixin Wang,Jinghang Wang,Wei Zhao,Xiaohui Liu,Guoping Tan,Jun Liu,Zhiyuan Wang
出处
期刊:Diagnostics [Multidisciplinary Digital Publishing Institute]
卷期号:15 (15): 1926-1926
标识
DOI:10.3390/diagnostics15151926
摘要

Objectives: Automatic tip localization is critical in ultrasound (US)-guided interventions. Although deep learning (DL) has been widely used for precise tip detection, existing methods are limited by the availability of real puncture data and expert annotations. Methods: To address these challenges, we propose a novel method that uses synthetic US puncture data to pre-train DL-based tip detectors, improving their generalization. Synthetic data are generated by fusing clinical US images of healthy controls with tips created using generative DL models. To ensure clinical diversity, we constructed a dataset from scans of 20 volunteers, covering 20 organs or anatomical regions, obtained with six different US machines and performed by three physicians with varying expertise levels. Tip diversity is introduced by generating a wide range of synthetic tips using a denoising probabilistic diffusion model (DDPM). This method synthesizes a large volume of diverse US puncture data, which are used to pre-train tip detectors, followed by subsequently training with real puncture data. Results: Our method outperforms MSCOCO pre-training on a clinical puncture dataset, achieving a 1.27–7.19% improvement in AP0.1:0.5 with varying numbers of real samples. State-of-the-art detectors also show performance gains of 1.14–1.76% when applying the proposed method. Conclusions: The experimental results demonstrate that our method enhances the generalization of tip detectors without relying on expert annotations or large amounts of real data, offering significant potential for more accurate visual guidance during US-guided interventions and broader clinical applications.
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
刚刚
今后的应助被氟锑酸采纳,获得10
刚刚
10349发布了新的文献求助10
刚刚
Cc完成签到 ,获得积分10
刚刚
1秒前
Akim的应助被标致的灵槐采纳,获得30
1秒前
1秒前
可爱凤梨完成签到,获得积分10
2秒前
3秒前
领导范儿的应助被熙可檬采纳,获得10
4秒前
无花果的应助被好的呢采纳,获得10
4秒前
科目三的应助被科研的麦兜采纳,获得10
5秒前
呆头鹅发布了新的文献求助10
5秒前
Ray的应助被郭竞阳采纳,获得10
5秒前
酷波er的应助被丝绒采纳,获得10
6秒前
沉静向梦完成签到,获得积分20
6秒前
66的应助被曲奇采纳,获得10
6秒前
7秒前
7秒前
lazyp发布了新的文献求助10
7秒前
斯文问旋发布了新的文献求助10
7秒前
小雪绛完成签到,获得积分10
7秒前
ding的应助被YU采纳,获得10
8秒前
9秒前
9秒前
10秒前
果冻发布了新的文献求助10
10秒前
10秒前
无花果的应助被ZHAO采纳,获得10
10秒前
10秒前
11秒前
11秒前
11秒前
赘婿的应助被freak采纳,获得10
11秒前
11秒前
11秒前
11秒前
12秒前
12秒前
852的应助被斯文问旋采纳,获得10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 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 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8164555
求助须知:如何正确求助?哪些是违规求助? 9558341
关于积分的说明 21745170
捐赠科研通 7755092
什么是DOI,文献DOI怎么找? 3428591
关于科研通互助平台的介绍 2553128
邀请新用户注册赠送积分活动 2473151