Real-Time Reconstruction of 3D Bone Models via Very-Low-Dose Protocols

TL;DR

This paper presents SSR-KD, an AI framework that reconstructs accurate 3D bone models from biplanar X-rays in 30 seconds, reducing radiation and manual effort, and enabling intraoperative use.

Contribution

The introduction of SSR-KD, a semi-supervised AI method that produces high-quality 3D bone models from low-dose X-rays, bypassing CT and manual delineation.

Findings

Reconstructed bone models have an average error under 1.0 mm.

Models are generated in 30 seconds, significantly faster than traditional methods.

Reconstructed models are clinically comparable to CT-based models.

Abstract

Patient-specific bone models are essential for designing surgical guides and preoperative planning, as they enable the visualization of intricate anatomical structures. However, traditional CT-based approaches for creating bone models are limited to preoperative use due to the low flexibility and high radiation exposure of CT and time-consuming manual delineation. Here, we introduce Semi-Supervised Reconstruction with Knowledge Distillation (SSR-KD), a fast and accurate AI framework to reconstruct high-quality bone models from biplanar X-rays in 30 seconds, with an average error under 1.0 mm, eliminating the dependence on CT and manual work. Additionally, high tibial osteotomy simulation was performed by experts on reconstructed bone models, demonstrating that bone models reconstructed from biplanar X-rays have comparable clinical applicability to those annotated from CT. Overall, our approach accelerates the process, reduces radiation exposure, enables intraoperative guidance, and significantly improves the practicality of bone models, offering transformative applications in orthopedics.