OBJECTIVE: Respiratory motion-induced displacement of internal organs poses a significant challenge in image-guided radiation therapy, particularly affecting liver landmark tracking accuracy.
METHODS: Addressing this concern, we propose a self-supervised method for robust landmark tracking in long liver ultrasound sequences. Our approach leverages a Siamese-based context-aware correlation filter network, trained by using the consistency loss between forward tracking and back verification. By effectively utilizing both labeled and unlabeled liver ultrasound images, our model, Siam-CCF , mitigates the impact of speckle noise and artifacts on ultrasonic image tracking by a context-aware correlation filter. Additionally, a fusion strategy for template patch feature helps the tracker to obtain rich appearance information around the point-landmark.
RESULTS: Siam-CCF achieves a mean tracking error of 0.79 ± 0.83 mm at a frame rate of 118.6 fps, exhibiting a superior speed-accuracy trade-off on the public MICCAI 2015 Challenge on Liver Ultrasound Tracking (CLUST2015) 2D dataset. This performance won the 5th place on the CLUST2015 2D point-landmark tracking task.
CONCLUSIONS: Extensive experiments validate the effectiveness of our proposed approach, establishing it as one of the top-performing techniques on the CLUST2015 online leaderboard at the time of this submission.

The presence of respiratory motion not only degrades the reconstructed image but also limits the utilization of anatomical priors in emission tomography. In this study, we explore the potential application of a joint motion estimation and penalized image reconstruction algorithm using anatomical priors in gated time-of-flight positron emission tomography/computed tomography (PET/CT). The algorithm is able to warp both the activity image and the attenuation map to align them with the measured data with the facilitation of anatomical information contained in the attenuation map. Five patient datasets, three acquired in single-bed position and two acquired in whole-body continuous-bed-motion mode, are included. For each patient, the attenuation map is derived from a breath-hold CT. The Parallel Levels Sets (PLS) is chosen as a representative anatomical prior. In addition to demonstrating the reliability of the estimated motion and the benefits of incorporating anatomical prior, preliminary results also indicate that the algorithm shows the potential to reconstruct an activity image in the space corresponding to that of the attenuation map, which could be applied to address the potential misalignment issue in applications involving multiple PET acquisitions but a single CT.

OBJECTIVE: Percutaneous image-guided interventions are commonly used for the diagnosis and treatment of cancer. In practice, physiological breathing-induced motion increases the difficulty of accurately inserting needles into tumors without impairing the surrounding vital structures. In this work, we propose a data-driven patient-specific hierarchical respiratory motion estimation framework to accurately estimate the position of a tumor and surrounding vital tissues in real time.
METHODS: The motion of optical markers attached to the chest or abdomen skin is used as a surrogate signal to estimate tumor motion based on ɛ-support vector regression (ɛ-SVR). With the estimated tumor motion as the input, a novel respiratory motion model is developed to estimate the diffeomorphic deformation field of the whole organ (liver or lung) without intraoperative, iterative optimization computations. The respiratory motion model of the whole organ is established in Lie algebra space based on the kriging algorithm to ensure that the estimated deformation field is diffeomorphic, optimal, and unbiased. Preoperative prior knowledge for modeling the motion of whole organs is obtained by deformation registration between four-dimensional computed tomography (4D CT) images using a hybrid diffeomorphic registration method.
CONCLUSIONS: Experimental results on an in vivo beagle dog show that the minimum value of the determinant of the Jacobian of the estimated deformation field is greater than zero, so the estimated deformation field of the whole liver with our method is diffeomorphic. The mean position error of the tumor is 1.2 mm corresponding to a mean accuracy improvement of 76.5%, and the mean position error of the whole liver is 2.1 mm, corresponding to a mean accuracy improvement of 37.9%. The experimental results based on public human subject data show that the mean position error of the tumor is 1.1 mm, corresponding to a mean accuracy improvement of 83.1%, and the mean position error of the whole lung is 2.1 mm, corresponding to a mean accuracy improvement of 41.4%. The positioning errors for the tumor and whole organ are hierarchical and consistent with clinical demand.

Improving the quality of image-guided radiation therapy requires the tracking of respiratory motion in ultrasound sequences. However, the low signal-to-noise ratio and the artifacts in ultrasound images make it difficult to track targets accurately and robustly. In this study, we propose a novel deep learning model, called a Cascaded One-shot Deformable Convolutional Neural Network (COSD-CNN), to track landmarks in real time in long ultrasound sequences. Specifically, we design a cascaded Siamese network structure to improve the tracking performance of CNN-based methods. We propose a one-shot deformable convolution module to enhance the robustness of the COSD-CNN to appearance variation in a meta-learning manner. Moreover, we design a simple and efficient unsupervised strategy to facilitate the network\'s training with a limited number of medical images, in which many corner points are selected from raw ultrasound images to learn network features with high generalizability. The proposed COSD-CNN has been extensively evaluated on the public Challenge on Liver UltraSound Tracking (CLUST) 2D dataset and on our own ultrasound image dataset from the First Affiliated Hospital of Sun Yat-sen University (FSYSU). Experiment results show that the proposed model can track a target through an ultrasound sequence with high accuracy and robustness. Our method achieves new state-of-the-art performance on the CLUST 2D benchmark set, indicating its strong potential for application in clinical practice.