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

<b>Objectives</b>: 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. <b>Methods&l...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruixin Wang, Jinghang Wang, Wei Zhao, Xiaohui Liu, Guoping Tan, Jun Liu, Zhiyuan Wang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/15/1926
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849407680749240320
author Ruixin Wang
Jinghang Wang
Wei Zhao
Xiaohui Liu
Guoping Tan
Jun Liu
Zhiyuan Wang
author_facet Ruixin Wang
Jinghang Wang
Wei Zhao
Xiaohui Liu
Guoping Tan
Jun Liu
Zhiyuan Wang
author_sort Ruixin Wang
collection DOAJ
description <b>Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: Our method outperforms MSCOCO pre-training on a clinical puncture dataset, achieving a 1.27–7.19% improvement in AP<sub>0.1:0.5</sub> 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. <b>Conclusions:</b> 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.
format Article
id doaj-art-5c516f77c70a4065bc6a6fe282e98beb
institution Kabale University
issn 2075-4418
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-5c516f77c70a4065bc6a6fe282e98beb2025-08-20T03:35:58ZengMDPI AGDiagnostics2075-44182025-07-011515192610.3390/diagnostics15151926Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided InterventionRuixin Wang0Jinghang Wang1Wei Zhao2Xiaohui Liu3Guoping Tan4Jun Liu5Zhiyuan Wang6Department of Radiology, The Second Xiangya Hospital, Central South University, Changsha 410011, ChinaDepartment of Radiology, The Second Xiangya Hospital, Central South University, Changsha 410011, ChinaDepartment of Radiology, The Second Xiangya Hospital, Central South University, Changsha 410011, ChinaThe First People’s Hospital of Kunshan, Affiliated Kunshan Hospital of Jiangsu University, Suzhou 215300, ChinaCollege of Computer and Software, Hohai University, Nanjing 211100, ChinaDepartment of Radiology, The Second Xiangya Hospital, Central South University, Changsha 410011, ChinaDepartment of Ultrasound, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013, China<b>Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: Our method outperforms MSCOCO pre-training on a clinical puncture dataset, achieving a 1.27–7.19% improvement in AP<sub>0.1:0.5</sub> 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. <b>Conclusions:</b> 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.https://www.mdpi.com/2075-4418/15/15/1926needle tip detectionultrasound-guided interventionsdata synthesisgenerative deep learning
spellingShingle Ruixin Wang
Jinghang Wang
Wei Zhao
Xiaohui Liu
Guoping Tan
Jun Liu
Zhiyuan Wang
Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention
Diagnostics
needle tip detection
ultrasound-guided interventions
data synthesis
generative deep learning
title Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention
title_full Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention
title_fullStr Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention
title_full_unstemmed Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention
title_short Enhancing Tip Detection by Pre-Training with Synthetic Data for Ultrasound-Guided Intervention
title_sort enhancing tip detection by pre training with synthetic data for ultrasound guided intervention
topic needle tip detection
ultrasound-guided interventions
data synthesis
generative deep learning
url https://www.mdpi.com/2075-4418/15/15/1926
work_keys_str_mv AT ruixinwang enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention
AT jinghangwang enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention
AT weizhao enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention
AT xiaohuiliu enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention
AT guopingtan enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention
AT junliu enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention
AT zhiyuanwang enhancingtipdetectionbypretrainingwithsyntheticdataforultrasoundguidedintervention