Hui Tang

Objective. Real-time x-ray fluoroscopy (XRF) is widely used for navigating coronary interventions. X-ray coronary angiography (XCA) is needed to facilitate the interventional procedure, resulting in excessive consumption of iodinated contrast agents. To reduce the contrast consumption, the vessel masks derived from XCA images are overlaid on XRF images, assuming periodic heartbeats. To address the two-dimensional (2D) nature of XCA limits, using 3D/2D coronary artery registration, centerlines with depth information derived from three-dimensional (3D) coronary computed tomography angiography (CCTA) can provide the necessary depth guidance and discriminate vessel overlapping. However, the existing tree-aligning feature-based registration strategy suffers from the error accumulation introduced by cascading multi-step processes or time-consuming limitation of iterative optimization in the 3D/2D tree alignment step. Approach. In this work, we propose an intensity-based end-to-end 3D/2D tree alignment method to address these limitations by removing the image-to-graph modality transformation in the intraoperative pipeline. Specifically, we design AlignNet for the intensity-based 3D/2D tree alignment, RegisNet for the centerline registration with graph regularization. AlignNet and RegisNet are trained using a cost-efficient supervised learning strategy based on large-scale simulated coronary deformations. Three cascaded end-to-end networks including nnUnet, AlignNet, and RegisNet are integrated into the intraoperative pipeline. Main results. Numerical simulations involving qualitative and quantitative analyses of large-scale CCTA–XCA samples achieved a mean registration error of 0.42 mm. Clinical validation using paired CCTA–XCA data from six patients achieved a mean registration error of 0.359 mm and a mean processing speed of 16.3 fps. In addition, validation using one paired CCTA–XCA–XRF case demonstrated the feasibility of generating depth-guided coronary roadmaps for interventional navigation. Significance. These results demonstrate that the proposed technique has the potential to achieve accurate and real-time depth-guided coronary intervention navigation, and it is valuable for subsequent multi-center clinical studies.

Vertebral landmark localization in computed tomography (CT) volumes is crucial for spinal pathological diagnosis, postoperative assessment and surgical planning. However, vertebral localization within high-resolution three-dimensional CT volumes still poses prominent challenges. This study introduces a novel two-stage deep learning framework that effectively addresses challenges such as large spatial spans and high morphological similarity of vertebrae. The first stage employs the improved squeeze and excitation V-Net (ISE-VNet) for coarse segmentation of the spinal column. The second stage utilizes a 3D spatial-generalized differential spatial-to-numerical transform (DSNT) module for precise localization of individual vertebrae. Our framework significantly improves identification rates from 81.15% to 96.32% and reduces localization errors from 7.6 mm to 2.1 mm, outperforming state-of-the-art methods. This approach provides a robust solution for clinical vertebral landmark localization in 3D medical images. This design effectively enables efficient and focused analysis of vertebral local regions and it holds significant value in both scientific research and clinical practice.

Computed tomography (CT) scanners are widely used to obtain detailed internal images in clinical diagnosis. Highly attenuated metallic implants resulting from strong and energy-dependent attenuation cause metal artifacts in CT scanning. However, current supervised deep network-based metal artifact reduction (MAR) methods hardly generalize in clinical diagnosis and treatment because of difficult acquisition for the paired artifact-affected and artifact-free data. In addition, these deep model-based methods cannot ensure the sinogram-domain data consistency for the exact metal trace inpainting. To address the above problems, we propose an UnsuPervised sinoGRam-domAin Data-consistEnt network for MAR, i.e., UPGRADE-Net. First, UPGRADE-Net fully leverages the prior knowledge to guide the generative conditional diffusion model for fine-grained metal trace inpainting. Second, without the artifact-free ground truth, a deep unsupervised MAR framework in the reverse process is constructed to contextually learn the known background data distribution for the unknown metal trace restoration in sinogram-domain. Third, to further maintain the sinogram-domain data consistency, two physics-based consistency constraint loss functions, including conjugate-ray and accumulation-ray consistency loss, are designed for the conjugate point constraint and the accumulation constraint. The proposed UPGRADE-Net is trained and evaluated on a publicly available dataset and a clinical dataset. Extensive experimental results validate that the proposed method outperforms the state-of-the-art competing methods for MAR.

In the field of medical image processing, vascular image segmentation plays a crucial role in clinical diagnosis, treatment planning, prognosis, and medical decision-making. Accurate and automated segmentation of vascular images can assist clinicians in understanding the vascular network structure, leading to more informed medical decisions. However, manual annotation of vascular images is time-consuming and challenging due to the fine and low-contrast vascular branches, especially in the medical imaging domain where annotation requires specialized knowledge and clinical expertise. Data-driven deep learning models struggle to achieve good performance when only a small number of annotated vascular images are available. To address this issue, this paper proposes a novel Conditional Virtual Imaging (CVI) framework for few-shot vascular image segmentation learning. The framework combines limited annotated data with extensive unlabeled data to generate high-quality images, effectively improving the accuracy and robustness of segmentation learning. Our approach primarily includes two innovations: First, aligned image-mask pair generation, which leverages the powerful image generation capabilities of large pre-trained models to produce high-quality vascular images with complex structures using only a few training images; Second, the Dual-Consistency Learning (DCL) strategy, which simultaneously trains the generator and segmentation model, allowing them to learn from each other and maximize the utilization of limited data. Experimental results demonstrate that our CVI framework can generate high-quality medical images and effectively enhance the performance of segmentation models in few-shot scenarios. Our code will be made publicly available online.

Ultrasound probe calibration is crucial for precise spatial mapping in ultrasound-guided surgical navigation and free-hand 3D ultrasound imaging as it establishes the rigid-body transformation between the ultrasound image plane and an external tracking sensor. However, the existing methods often rely on manual feature point selection and exhibit limited robustness to outliers, resulting in reduced accuracy, reproducibility, and efficiency. To address these limitations, we propose a fully automated calibration framework that leverages the geometric priors of an N-wire phantom to achieve reliable recognition. The method incorporates a robust feature point extraction algorithm and integrates a hybrid outlier rejection strategy based on the Random Sample Consensus (RANSAC) algorithm. The experimental evaluations demonstrate sub-millimeter accuracy (<0.6 mm) across varying imaging depths, with the calibration process completed in under two minutes and exhibiting high repeatability. These results suggest that the proposed framework provides a robust, accurate, and time-efficient solution for ultrasound probe calibration, with strong potential for clinical integration.