The bilateral filter is a classical technique for edge‐preserving smoothing. It has been widely used as an effective image denoising approach to remove Gaussian noise. The performance of bilateral filtering highly depends on the accuracy of its range distance estimation, which is used for pixel‐neighbourhood similarity measurement. However, in the conventional bilateral filtering approach, estimating the range distance directly from noisy observation results in the degradation of denoising performance. To address this issue, the authors propose a novel bilateral filtering scheme with a dual‐range kernel, which provides a more robust range of distance estimation at various noise levels compared with existing methods. To further improve the denoising performance, they employ a linear model to retrieve the remaining image details from the method noise and add them back to the denoised image by employing an optimal approach based on Stein's unbiased risk estimate. Experiments on standard test images demonstrate that the proposed method outperforms conventional bilateral filter and its major state‐of‐the‐art variants.
Objective. Robot-assisted pedicle screw placement in spinal surgery can reduce the complications associated with the screw placement and reduce the hospital return counts due to malfunctions. However, it requires accurate planning for a high-quality procedure. The state-of-the-art technologies reported in the literature either ignore the anatomical variations across vertebrae or require substantial human interactions. We present an improved approach that achieves pedicle screw path planning through multiple projections of a numerically re-oriented vertebra with the estimated posture. Approach. We proposed an improved YOLO-type neural network model (YOLOPOSE3D) to estimate the posture of a vertebra before pedicle path planning. In YOLOPOSE3D, the vertebral posture is given as a rotation quaternion and 3D location coordinates by optimizing the intersection over union of the vertebra with the predicted posture and the actual posture. Then, a new local coordinate system is established for the vertebra based on the estimated posture. Finally, the optimal pedicle screw path trajectory is determined from the multiple projections of the vertebra in the local coordinates. Main results. The experimental results in difficult cases of scoliosis showed that the new YOLOPOSE3D network could accurately detect the location and posture of the vertebra with average translation and orientation errors as small as 1.55 mm and 2.55°. The screw path planning achieved 83.1% success rate without breaking the pedicle cortex for the lumbar vertebral L1–L5, which is better than that of a doctor’s manual planning, 82.4%. With the clinical class A requirement to allow less than 2 mm out of the pedicle cortex, the success rate achieved nearly 100%. Significance. The proposed YOLOPOSED3D method can accurately determine the vertebral postures. With the improved posture prior, better clinical outcomes can be achieved for pedicle screw placement in spine internal fixation procedures.
Background. Cancer stem cell (CSC) promotes angiogenesis which plays an important role in tumor occurrence, growth, and metastasis. Accurately, quantifying the tumor vasculature can help understanding CSC characteristics and improve cancer diagnosis, therapy planning, and evaluation. The objective of this study is to present a method for improved angiogenesis assessment. Methods. We proposed a three-dimensional microvessel density (3D MVD) to evaluate tumor angiogenesis and tested it in animal models. Six male Balb/c nude mice were divided into normal group and tumor group. The mice in tumor group were orthotopically implanted human gastric cancer, cell line BGC-823. The phase-contrast images were collected at Shanghai Synchrotron Radiation Facility BL13W beamline, which has much higher soft-tissue contrast and spatial resolution than conventional X-ray. After volume reconstruction and vessel extraction, the 3D models of the angiogenesis were established for MVD calculation. Results. The results showed that the proposed 3D MVD is positively correlated with the pathological changes of the microvessels. It took the advantage of high resolution of the phase-contrast imaging and added three-dimensional information to the existing MVD measure. Conclusions. Our study presents a feasible approach for better understanding of tumor angiogenesis. It may provide doctors and scientists a better tool for cancer investigation and improving medical outcomes.
Background: For the spinal internal fixation procedures, connecting rods to the pedicle screws are commonly used in all spinal segments from the cervical to sacral spine. So far, we have only seen single vertebral screw trajectory planning methods in literatures. Joint screw placements in multi‐level vertebrae with the constraint of an ipsilateral connecting rod are not considered.Purpose: In this paper, a screw trajectory planning method that considers screw‐rod joint system with both multi‐level vertebral constraints and individual vertebral safety tolerance are proposed.Methods: The proposed method addresses three challenging constraints jointly for multi‐level vertebral fixation with pedicle screws. First, a cylindrical screw safe passage model is suggested instead of a unique mathematical optimal trajectory for a single pedicle. Second, the flexible screw cap accessibility model is also included. Third, the connecting rod is modeled to accommodate the spine contour and support the needed gripping capacity. The retrospective clinical data of relative normal shape spines from Beijing Jishuitan hospital were used in the testing. The screw trajectories from the existing methods based on single vertebra and the proposed method based on multi‐level vertebrae optimization are calculated and compared.Results: The results showed that the calculated screw placements by the proposed method can achieve 88% success rate without breaking the pedicle cortex and 100% in clinical class A quality (allow less than 2 mm out of the pedicle cortex) compared to 86.1% and 99.1%, respectively, with the existing methods. Expert evaluation showed that the screw path trajectories and the connecting rod calculated by the new method satisfied the clinical implantation requirements.Conclusions: The new screw planning approach that seeks an overall optimization for multi‐level vertebral fixation is feasible and more advantageous for clinical use than the single vertebral approaches.
13 February 2025 in Expert Systems with Applications
Anti-vascular endothelial growth factor (anti-VEGF) therapy is effective for reducing the severity level of diabetic retinopathy (DR). However, it is difficult to determine the in vivo spatial and temporal expression of VEGF in the DR retina at an early stage. Here, we report a quantitatively fluorescence molecular imaging and image analysis method by creating a VEGF targeted fluorescence imaging probe, which can potentially detect and predict anti-VEGF treatment response. Moreover, the ex vivo multiscale fluorescence imaging demonstrated the spatial correlation between VEGF relative expression and vascular abnormalities in two and three dimensions. It revealed that VEGF was mainly abnormally expressed at the bifurcation of the microvessels, which advances the knowledge of the DR progression by molecular fluorescence imaging. Our study has the potential to achieve early detection of DR disease, provide more insight into understanding anti-VEGF treatment, and may help stratify patients based on the molecular imaging of retinal VEGF.