Abstract
In this paper, we present a fully automatic solution for denoting bone configuration on two-dimensional images. A dataset of 300 X-ray images of children’s knee joints was collected. The strict experimental protocol established in this study increased the difficulty of post-processing. Therefore, we tackled the problem of obtaining reliable information from medical image data of insufficient quality. We proposed a set of features that unambiguously denoted configuration of the bone on the image, namely the femur. It was crucial to define the features that were independent of age, since age variability of subjects was high. Subsequently, we defined image keypoints directly corresponding to those features. Their positions were used to determine the coordinate system denoting femur configuration. A complex keypoint detector was proposed, composed of two different estimator architectures: gradient-based and based on the convolutional neural network. The positions of the keypoints were used to determine the configuration of the femur on each image frame. The overall performance of both estimators working in parallel was evaluated using X-ray images from the publicly available LERA dataset.
Highlights
In recent years, robotics have largely influenced medical practices [1]
We specified the feature set that unambiguously determines femur configuration, the defined corresponding image keypoints, and we constructed femur coordinate system derived from those features
The performance of the algorithm was evaluated on new data and achieved satisfactory results
Summary
Robotics have largely influenced medical practices [1]. Artificial intelligence, miniaturization, and computer power all contribute to the widespread usage of robots in medicine. Proper extraction of important features from the data is necessary to maintain the benefits of the aforementioned systems. One example of such application is a robotic rehabilitation aid that is able to track the movement path of the real healthy joint. We propose an automatic solution to detect key features, i.e., keypoints, on medical images. The main contribution of this paper can be summarized as follows: Selection of image features that unambiguously define the configuration of the bone on the X-ray image, given the troublesome specification of the image data. We provide a complete solution to obtain femur configuration on two-dimensional X-ray images. From an artificial intelligence point of view, we provide the optimal estimator architecture to solve a regression task for medical images
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
