Introduction

Surgical planning requires the identification of anatomical landmarks on medical images pre, intra, and post-procedures. Landmark detection on X-rays is thus an important, though time intensive, step to ensure good surgical outcomes. The operative workflow can be made more efficient by using machine learning approaches to automate the detection of landmarks. These models could also assist with the development of robotic surgical procedures, as robotic approaches to surgery require the robotic device to orient itself to the patient's anatomy. Previously described models are effective, but complex, making it difficult for landmark identification to occur in real-time in a robotic system.

Objectives

We propose a streamlined approach to landmark detection on pelvis radiographs that achieves similar accuracy to gold-standard manual annotations.

Methods

To train and evaluate the network, 902 pelvic radiographs (382 Outlet view, 520 AP view) were annotated with 22 landmarks and split into training (n = 700), validation (n = 99), and testing (n = 103) set. A U-Net architecture with five encoding layers and five decoding layers was used. Landmark labels were converted into 128 × 128 × 22 heatmap array by placing a Gaussian blur filter (5% of image size) over each landmark in order to generate a single 128 × 128 layer of the array, thus generating the 22 layers of the overall heatmap array with one landmark heatmap on each layer. Each layer was an array of 0 except a circular Gaussian around the area of the landmark. A 256 × 256 array representing the image was fed into the U-Net architecture, which outputted a 128 × 128 × 22 heatmap array. Intersection over union loss was used to train the network.

Results

Following training for 100 epochs, the algorithm was able to predict the position of 22 clinically relevant landmarks with an average error of 2.36±.5 mm compared to ground-truth annotations made by trained experts and musculoskeletal radiologists with experience in pelvic scan analysis. The network was able to accurately determine the position of relevant landmarks. It was able to do this despite highly variable contrast and brightness in the dataset. Prediction accuracy was invariant to view (AP: 2.27±.51 mm, Outlet: 2.45±.64 mm). A prediction took 1.13±.07 seconds.

Conclusions

The network is able to rapidly provide accurate femoral landmarks on a radiograph of the pelvis. This will allow for the automation of numerous clinically relevant measurements. Additionally, an important avenue of further research is exploring whether automated use of these measurements can aid in the prediction of femur fractures in machine learning models.

中文翻译：

---

骨盆 X 射线自动股骨标志检测

介绍

手术计划需要在手术前、手术中和手术后识别医学图像上的解剖标志。因此，X 射线上的地标检测是确保良好手术结果的重要步骤，尽管时间密集。通过使用机器学习方法来自动检测地标，可以提高操作工作流程的效率。这些模型还可以帮助开发机器人手术程序，因为机器人手术方法需要机器人设备将自己定位到患者的解剖结构。先前描述的模型是有效的，但很复杂，因此很难在机器人系统中实时进行地标识别。

目标

我们提出了一种简化的方法来检测骨盆 X 光片上的地标，该方法可以达到与黄金标准手动注释相似的准确度。

方法

为了训练和评估网络，902 张盆腔 X 光片（382 个出口视图，520 个 AP 视图）被注释了 22 个地标，并分为训练（n = 700）、验证（n = 99）和测试（n = 103）组。使用了具有五个编码层和五个解码层的 U-Net 架构。通过在每个地标上放置一个高斯模糊滤波器（图像大小的 5%），将地标标签转换为 128 × 128 × 22 热图阵列，以生成阵列的单个 128 × 128 层，从而生成整体的 22 层热图数组，每一层都有一个地标热图。除了围绕地标区域的圆形高斯外，每一层都是一个 0 数组。一个代表图像的 256 × 256 数组被输入到 U-Net 架构中，该架构输出了一个 128 × 128 × 22 的热图数组。使用联合损失的交集来训练网络。

结果

经过 100 个 epoch 的训练，该算法能够预测 22 个临床相关标志的位置，平均误差为 2.36±.5 毫米，与训练有素的专家和具有盆腔扫描分析经验的肌肉骨骼放射科医生所做的真实注释相比。该网络能够准确地确定相关地标的位置。尽管数据集中的对比度和亮度变化很大，但它能够做到这一点。预测精度不变（AP：2.27±.51 mm，出口：2.45±.64 mm）。预测耗时 1.13±.07 秒。

结论

该网络能够在骨盆 X 光片上快速提供准确的股骨标志。这将允许许多临床相关测量的自动化。此外，进一步研究的一个重要途径是探索这些测量的自动使用是否有助于预测机器学习模型中的股骨骨折。