PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 14, 2026The Journal of the Acoustical Society of America0 citations

Sensor-free ultrasound image-based registration system for liver tumor treatment assessment

View Full Paper
RKRiku KASAGINKNorihiro KoizumiKNKazushi Numata

Key Points

  • To develop a sensor-free registration system for accurately aligning pre- and post-treatment ultrasound images for liver tumor assessment.
  • Utilized a robotically controlled probe to scan the abdomen and create a 3-D vascular model from ultrasound images.
  • Implemented a deep-learning model trained on cross-sectional images to estimate acquisition positions of post-treatment ultrasound images.
  • Conducted rigid point cloud registration to refine initial alignment with the 3-D model.
  • 85.2% of 3000 test images were registered within a 10-mm error margin.
  • Average processing time per image was 0.0782 seconds, demonstrating feasibility for real-time application.

Abstract

In minimally invasive liver tumor treatment without laparotomy, accurate registration between pre- and post-treatment images is essential for evaluating therapeutic effectiveness. Although contrast-enhanced ultrasound is increasingly used postoperatively due to its real-time capability, aligning it precisely with pre-treatment 3-D images remains challenging. Conventional methods often rely on magnetic sensors, which are costly and complex. Hence, a simpler and more affordable sensor-free method is needed. We propose a registration system that uses only ultrasound imaging, a common acoustic diagnostic tool. Before treatment, a robotically controlled probe scans the abdomen, and a 3-D vascular model is built from vessels visualized in ultrasound. Cross-sectional images in various orientations are generated from this model and used to train a deep-learning model. Post-treatment ultrasound images undergo vessel extraction, and the trained model estimates their acquisition positions. Based on this, initial alignment is performed with the 3-D model, followed by rigid point cloud registration to refine it. In evaluations using an abdominal phantom, 85.2% of 3000 test images were registered within a 10-mm error. Average processing time per image was 0.0782 s, demonstrating feasibility for real-time use. This method leverages the real-time nature of ultrasound, offering a promising sensor-free approach for convenient evaluation of therapeutic effectiveness.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

KASAGI et al. (2025) studied this question.

synapsesocial.com/papers/6a0567d2a550a87e60a200behttps://doi.org/10.1121/10.0041382
Ask AI
Helpful
Bookmark
Share
View Full Paper