Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 26, 2025

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

Multi-needle Localization with Attention U-Net in US-guided HDR Prostate Brachytherapy.

Yupei Zhang¹, Yang Lei¹, Richard L J Qiu¹

¹Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, USA.

Medical Physics

|March 11, 2020

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

LANet: A Lightweight and Accurate Balanced Network Based on State Space Models for Real-Time Semantic Segmentation.

IEEE transactions on neural networks and learning systems·2026

Same author

Molecular characterization of Blastocystis sp., Cryptosporidium spp., and Giardia spp. in Eld's deer (Rucervus eldii) and their forest rangers in Hainan, China.

Parasites & vectors·2026

Same author

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026

Same author

<sup>18</sup>F-Fluciclovine or <sup>68</sup>Ga-PSMA-11 PET/CT-guided Salvage Radiotherapy Changes in Postprostatectomy Biochemical Recurrence: Secondary Analysis of the EMPIRE-2 Trial.

Radiology·2026

Same author

A digital twin framework for adaptive treatment planning in radiotherapy.

Physics in medicine and biology·2026

Same author

Gut Microbiome Associations With Depressive Symptoms in Women With Gynecologic Cancer: A Longitudinal Study.

Biological research for nursing·2026

A new deep learning method accurately segments needles in 3D transrectal ultrasound (TRUS) for high dose rate (HDR) prostate brachytherapy, improving radiation plan quality.

Area of Science:

Medical Imaging
Artificial Intelligence
Radiation Oncology

Background:

High dose rate (HDR) prostate brachytherapy relies on precise needle placement for effective radiation delivery.
Current ultrasound (US) imaging limitations, including low signal-to-noise ratio (SNR), hinder real-time multi-needle segmentation in 3D transrectal US (TRUS).
Accurate real-time needle localization is crucial for assessing radiation dose distribution and improving treatment outcomes.

Purpose of the Study:

To develop a deep learning-based method for accurate and real-time segmentation of multiple needles in 3D TRUS images.
To enable real-time dose mapping by overcoming the challenge of multi-needle segmentation in US imaging.
To enhance the quality of radiation treatment plans and patient outcomes in HDR prostate brachytherapy.

Keywords:

deep learning multi-needle localization prostate brachytherapy total variation regularization ultrasound images

More Related Videos

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

A New Technique for Treating Low-risk Prostate Cancer—Super Active Surveillance

A New Technique for Treating Low-risk Prostate Cancer—Super Active Surveillance

Published on: November 7, 2025

Related Experiment Videos

Last Updated: Dec 26, 2025

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

A New Technique for Treating Low-risk Prostate Cancer—Super Active Surveillance

A New Technique for Treating Low-risk Prostate Cancer—Super Active Surveillance

Published on: November 7, 2025

Main Methods:

A U-Net based deep learning model incorporating attention gates and total variation (TV) regularization was developed.
The network was trained using deep supervision on 3D TRUS patches with manual needle annotations as ground truth.
The model was evaluated on its ability to localize and segment HDR needles, comparing shaft and tip errors against manual segmentation and state-of-the-art methods.

Main Results:

The proposed method achieved 96% needle detection rate across 23 patients.
Mean errors for needle shaft and tip localization were 0.290 ± 0.236 mm and 0.442 ± 0.831 mm, respectively.
The method demonstrated significant improvement over existing U-Net and deeply supervised attention U-Net models (P < 0.05).

Conclusions:

A novel segmentation method precisely localizes multiple needles in 3D TRUS for HDR prostate brachytherapy.
3D needle rendering aids clinicians in evaluating needle placement accuracy.
This advancement facilitates the development of real-time dose assessment tools, potentially improving HDR prostate brachytherapy quality and outcomes.