DG-PPU: Dynamical Graphs based Post-processing of Point Clouds extracted from Knee Ultrasounds

2024-11-12

arXiv.org

AI Summary

Ultrasound-derived 3D point clouds of the knee often suffer from noise due to mislabeling of soft tissue as bone, compromising downstream analysis. Method: This paper proposes a fully automated point cloud post-processing framework based on dynamic graph modeling—the first application of dynamic graph neural networks to ultrasound point cloud denoising. Leveraging the geometric invariance of the knee bone during flexion, the method achieves multi-angle robust filtering by integrating 3D geometric modeling, ultrasound segmentation refinement, and rigid registration. Contribution/Results: Evaluated across three flexion angles, the method achieves a 98.2% false-positive removal rate—surpassing manual curation. It underpins the world’s first ultrasound-driven patellar abnormal trajectory tracking and assessment system, enabling precise, quantitative analysis of anterior knee pain and patellofemoral dynamic instability following total knee arthroplasty.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Graph-based Machine Learning
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Patients undergoing total knee arthroplasty (TKA) often experience non-specific anterior knee pain, arising from abnormal patellofemoral joint (PFJ) instability. Tracking PFJ motion is challenging since static imaging modalities like CT and MRI are limited by field of view and metal artefact interference. Ultrasounds offer an alternative modality for dynamic musculoskeletal imaging. We aim to achieve accurate visualisation of patellar tracking and PFJ motion, using 3D registration of point clouds extracted from ultrasound scans across different angles of joint flexion. Ultrasound images containing soft tissue are often mislabeled as bone during segmentation, resulting in noisy 3D point clouds that hinder accurate registration of the bony joint anatomy. Machine learning the intrinsic geometry of the knee bone may help us eliminate these false positives. As the intrinsic geometry of the knee does not change during PFJ motion, one may expect this to be robust across multiple angles of joint flexion. Our dynamical graphs-based post-processing algorithm (DG-PPU) is able to achieve this, creating smoother point clouds that accurately represent bony knee anatomy across different angles. After inverting these point clouds back to their original ultrasound images, we evaluated that DG-PPU outperformed manual data cleaning done by our lab technician, deleting false positives and noise with 98.2% precision across three different angles of joint flexion. DG-PPU is the first algorithm to automate the post-processing of 3D point clouds extracted from ultrasound scans. With DG-PPU, we contribute towards the development of a novel patellar mal-tracking assessment system with ultrasound, which currently does not exist.

Problem

• Accurate visualization of patellar tracking and PFJ motion.
• Eliminating false positives in 3D point clouds from ultrasounds.
• Automating post-processing of 3D point clouds for knee anatomy.

Innovation

• Dynamic graphs post-process noisy ultrasound point clouds.
• Machine learning enhances knee bone geometry accuracy.
• Automated 3D point cloud cleaning with 98.2% precision.