Software-based method for automated intraoperative planning of Schoettle Point in surgical medial patellofemoral ligament reconstruction: A comparative validation study.

BACKGROUND: The aim of the study was to validate a software-based planning method for the Schoettle Point and to evaluate precision and time efficiency of its live overlay on the intraoperative X-ray. METHODS: A software-based method was compared with surgeons' manual planning in an inter- and intrarater study. Subsequently, K-wire placement was performed with and without an overlay of the planning. The time used and the precision achieved were statistically compared. RESULTS: The average deviation between the surgeons (1.68 mm; 2.26 mm) was greater than the discrepancy between the surgeons and the software-based planning (1.30 mm; 1.38 mm). In the intrarater comparison, software-based planning provided consistent results. Live overlay showed a significantly lower positioning error (0.9 ± 0.5 mm) compared with that without overlay (3.0 ± 1.4 mm, p = 0.000; 3.1 ± 1.4 mm, p = 0.001). Live overlay did not achieve a significant time gain (p = 0.393; p = 0.678). CONCLUSION: The software-based planning and live overlay of the Schoettle Point improves surgical precision without negatively affecting time efficiency.

A principled representation of elongated structures using heatmaps.

The detection of elongated structures like lines or edges is an essential component in semantic image analysis. Classical approaches that rely on significant image gradients quickly reach their limits when the structure is context-dependent, amorphous, or not directly visible. This study introduces a principled mathematical description of elongated structures with various origins and shapes. Among others, it serves as an expressive operational description of target functions that can be well approximated by Convolutional Neural Networks. The nominal position of a curve and its positional uncertainty are encoded as a heatmap by convolving the curve distribution with a filter function. We propose a low-error approximation to the expensive numerical integration by evaluating a distance-dependent function, enabling a lightweight implementation with linear time complexity. We analyze the method's numerical approximation error and behavior for different curve types and signal-to-noise levels. Application to surgical 2D and 3D data, semantic boundary detection, skeletonization, and other related tasks demonstrate the method's versatility at low errors.

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

Purpose: Mobile C-arm systems represent the standard imaging devices within the field of spine surgery. In addition to 2D imaging, they allow for 3D scans while preserving unrestricted patient access. For viewing, the acquired volumes are adjusted such that their anatomical standard planes align with the axes of the viewing modality. This difficult and time-consuming step is currently performed manually by the leading surgeon. This process is automatized within this work to improve the usability of C-arm systems. Thereby, the spinal region consisting of multiple vertebrae and the standard planes of all vertebrae being of interest to the surgeon need to be taken into account. Approach: An object detection algorithm based on the you only look once version 3 architecture, adapted to 3D inputs, is compared with a segmentation-based approach employing a 3D U-Net. Both algorithms are trained on a dataset of 440 and tested on 218 spinal volumes. Results: Although the detection-based algorithm is slightly inferior concerning the detection (91% versus 97% accuracy), localization (1.26 mm versus 0.74 mm error) and alignment accuracy (5.00 deg versus 4.73 deg error), it outperforms the segmentation-based one in terms of speed (5 s versus 38 s). Conclusions: Both algorithms show similar good results. However, the speed gain of the detection-based algorithm, resulting in a run time of 5 s, makes it more suitable for usage in an intra-operative scenario.

DL-based inpainting for metal artifact reduction for cone beam CT using metal path length information.

BACKGROUND: Metallic implants, which are inserted into the patient's body during trauma interventions, are the main cause of heavy artifacts in 3D X-ray acquisitions. These artifacts then hinder the evaluation of the correct implant's positioning, thus leading to a disturbed patient's healing process and increased revision rates. PURPOSE: This problem is tackled by so-called metal artifact reduction (MAR) methods. This paper examines possible advances in the inpainting process of such MAR methods to decrease disruptive artifacts while simultaneously preserving important anatomical structures adjacent to the inserted implants. METHODS: In this paper, a learning-based inpainting method for cone-beam computed tomography is proposed that couples a convolutional neural network (CNN) with an estimated metal path length as prior knowledge. Further, the proposed method is solely trained and evaluated on real measured data. RESULTS: The proposed inpainting approach shows advantages over the inpainting method used by the currently clinically approved frequency split metal artifact reduction (fsMAR) method as well as the learning-based state-of-the-art (SOTA) method PConv-Net. The major improvement of the proposed inpainting method lies in the ability to correctly preserve important anatomical structures in those regions adjacent to the metal implants. Especially these regions are highly important for a correct implant's positioning in an intraoperative setup. Using the proposed inpainting, the corresponding MAR volumes reach a mean structural similarity index measure (SSIM) score of 0.9974 and outperform the other methods by up to 6 dB on single slices regarding the peak signal-to-noise ratio (PSNR) score. Furthermore, it can be shown that the proposed method can generalize to clinical cases at hand. CONCLUSIONS: In this paper, a learning-based inpainting network is proposed that leverages prior knowledge about the metal path length of the inserted implant. Evaluations on real measured data reveal an increased overall MAR performance, especially regarding the preservation of anatomical structures adjacent to the inserted implants. Further evaluations suggest the ability of the proposed approach to generalize to clinical cases.

Automatic plane adjustment of orthopedic intraoperative flat panel detector CT-volumes.

Purpose: To assess the result in orthopedic trauma surgery, usually three-dimensional volume data of the treated region is acquired. With mobile C-arm systems, these acquisitions can be performed intraoperatively, reducing the number of required revision surgeries. However, the acquired volumes are typically not aligned to the anatomical regions. Thus, the multiplanar reconstructed (MPR) planes need to be adjusted manually during the review of the volume. To speed up and ease the workflow, an automatic parameterization of these planes is needed. Approach: We present a detailed study of multitask learning (MTL) regression networks to estimate the parameters of the MPR planes. First, various mathematical descriptions for rotation, including Euler angle, quaternion, and matrix representation, are revised. Then, two different MTL network architectures based on the PoseNet are compared with a single task learning network. Results: Using a matrix description rather than the Euler angle description, the accuracy of the regressed normals improves from 7.7 deg to 7.3 deg in the mean value for single anatomies. The multihead approach improves the regression of the plane position from 7.4 to 6.1 mm, whereas the orientation does not benefit from this approach. Thus, the achieved accuracy meets the reported interrater variance in similarly complex body regions of up to 6.3 deg for the normals and up to 9.3 mm for the plane position. Conclusions: The use of a multihead approach with shared features leads to more accurate plane regression compared with the use of individual networks for each task. It also improves the angle estimation for the ankle region. The reported results are in the same range as manual plane adjustments. The use of a combined network with shared parameters requires less memory, which is a great benefit for the implementation of an application for the surgical environment.

Multi-Stage Platform for (Semi-)Automatic Planning in Reconstructive Orthopedic Surgery.

Intricate lesions of the musculoskeletal system require reconstructive orthopedic surgery to restore the correct biomechanics. Careful pre-operative planning of the surgical steps on 2D image data is an essential tool to increase the precision and safety of these operations. However, the plan's effectiveness in the intra-operative workflow is challenged by unpredictable patient and device positioning and complex registration protocols. Here, we develop and analyze a multi-stage algorithm that combines deep learning-based anatomical feature detection and geometric post-processing to enable accurate pre- and intra-operative surgery planning on 2D X-ray images. The algorithm allows granular control over each element of the planning geometry, enabling real-time adjustments directly in the operating room (OR). In the method evaluation of three ligament reconstruction tasks effect on the knee joint, we found high spatial precision in drilling point localization (ε<2.9mm) and low angulation errors for k-wire instrumentation (ε<0.75∘) on 38 diagnostic radiographs. Comparable precision was demonstrated in 15 complex intra-operative trauma cases suffering from strong implant overlap and multi-anatomy exposure. Furthermore, we found that the diverse feature detection tasks can be efficiently solved with a multi-task network topology, improving precision over the single-task case. Our platform will help overcome the limitations of current clinical practice and foster surgical plan generation and adjustment directly in the OR, ultimately motivating the development of novel 2D planning guidelines.