Computer-assisted contralateral side comparison of the ankle joint using flat panel technology

Abstract

Purpose Reduction and osteosynthesis of ankle fractures is a challenging surgical procedure when it comes to the verification of the reduction result. Evaluation is conducted using intra-operative imaging of the injured ankle and depends on the expertise of the surgeon. Studies suggest that intra-individual variance of the ankle bone shape and pose is considerably lower than the inter-individual variance. It stands to reason that the information gain from the healthy contralateral side can help to improve the evaluation. Method In this paper, an assistance system is proposed that provides a side-to-side view of the two ankle joints for visual comparison and instant evaluation using only one 3D C-arm image. Two convolutional neural networks (CNN) are employed to extract the relevant image regions and pose information of each ankle so that they can be aligned with each other. A first U-Net uses a sliding window to predict the location of each ankle. The standard plane estimation is formulated as segmentation problem so that a second U-Net predicts the three viewing planes for alignment. Results Experiments were conducted to assess the accuracy of the individual steps on 218 unilateral ankle datasets as well as the overall performance on 7 bilateral ankle datasets. The experiments on unilateral ankles yield a median position-to-plane error of $$0.73\pm 1.36$$ 0.73 ± 1.36 mm and a median angular error between 2.98$$^\circ $$ ∘ and 3.71$$^\circ $$ ∘ for the plane normals. Conclusion Standard plane estimation via segmentation outperforms direct pose regression. Furthermore, the complete pipeline was evaluated including ankle detection and subsequent plane estimation on bilateral datasets. The proposed pipeline enables a direct contralateral side comparison without additional radiation. This has the potential to ease and improve the intra-operative evaluation for the surgeons in the future and reduce the need for revision surgery.

Clinical observation on the treatment of ankle fracture with buttress plate and traditional internal fixation and its effect on GQOLI-74 score and Baird-Jackson score

“…Compared with the traditional open reduction treatment, the former method had shortened postoperative fracture healing time, more ideal clinical effect, and more satisfied long-term knee function recovery and range of motion. 18 Based on the imaging findings of reduction and bone healing as well as the Baird-Jackson score, Zhou et al concluded that the posterolateral approach of compression plate hollow screw internal fixation is an effective method for reduction and fixation of large posterior malleolus fractures. 19 This is consistent with the conclusion of this study.…”

Robotic Technology in Foot and Ankle Surgery: A Comprehensive Review

“…In the realm of CAS, one system has proposed the use of a neural network, or U-Net, to extract relevant image regions from one 3D C-arm image to provide contralateral side comparison of the non-injured ankle joint during reduction of ankle fractures [ 37 ] ( Figure 4 ). However, this study is limited, given a patient population with similar body mass indices and the fact that use of this technology as a correctional tool does not account for larger position changes, or offsets.…”

“…Based on this ROI extracted, a second U-Net predicts three binary images that represent the planes of the ROI. Reprinted with permission from [ 37 ]. Copyright 2021 Springer Link.…”

Fast 3D YOLOv3 based standard plane regression of vertebral bodies in intra-operative CBCT volumes

“…In contrast, Thomas et al 2 . developed an assistance system that provides a side-to-side view of a patient’s ankle joints for visual comparison and evaluation for intra-operative CBCT volumes.…”

“…For this purpose, we present a novel algorithm based on the YOLOv3 architecture and adapted for 3D inputs that regresses the standard planes in addition to the vertebrae surrounding bounding box parameters. To evaluate the model, we create a reference model by adapting the approach of Thomas et al 2 . to enable the regression of the standard planes for multiple vertebrae within an input volume.…”