DG-PPU: Dynamical Graphs based Post-processing of Point Clouds extracted from Knee Ultrasounds
Injune Hwang, Karthik Saravanan, Caterina V Coralli, S Jack Tu, Stephen J Mellon
TL;DR
The paper tackles the challenge of visualizing patellofemoral joint motion after total knee arthroplasty by leveraging ultrasound-derived 3D point clouds, which are corrupted by mislabelled soft tissue. It introduces DG-PPU, a dynamical-graphs-based post-processing method built on DGCNN to denoise and smooth point clouds across knee flexion angles, improving bone geometry fidelity for subsequent registration. DG-PPU achieves a mean precision of about $98.2 ext{\%}$ across angles and demonstrates robustness on partial scans, supporting real-time potential for patellar-tracking assessment with ultrasound. The approach is positioned to integrate with the CATMAUS pipeline, with future work focusing on broader validation and exploring DCP-based registration to complete a clinical PFJ tracking system.
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.