Search

Elbow computerized tomography (CT) scans have been widely applied for describing elbow morphology. To enhance the objectivity and efficiency of clinical diagnosis, an automatic method to recognize, segment, and reconstruct elbow joint bones is proposed in this study. The method involves three steps: initially, the humerus, ulna, and radius are automatically recognized based on the anatomical features of the elbow joint, and the prompt boxes are generated. Subsequently, elbow MedSAM is obtained through transfer learning, which accurately segments the CT images by integrating the prompt boxes. After that, hole-filling and object reclassification steps are executed to refine the mask. Finally, three-dimensional (3D) reconstruction is conducted seamlessly using the marching cube algorithm. To validate the reliability and accuracy of the method, the images were compared to the masks labeled by senior surgeons. Quantitative evaluation of segmentation results revealed median intersection over union (IoU) values of 0.963, 0.959, and 0.950 for the humerus, ulna, and radius, respectively. Additionally, the reconstructed surface errors were measured at 1.127, 1.523, and 2.062 mm, respectively. Consequently, the automatic elbow reconstruction method demonstrates promising capabilities in clinical diagnosis, preoperative planning, and intraoperative navigation for elbow joint diseases.

The existing three-dimensional (3D) x-ray reconstruction methods for lung cancer tissue reconstruct the investigated objects based on a series of two-dimensional (2D) image sections and a chosen 3D reconstruction algorithm. However, because these procedures apply the same segmentation method for all 2D image sections, they may not achieve the optimal segmentation for each section. As a result, the reconstructed 3D images have limited spatial resolution. Furthermore, the existing 3D reconstruction method is time-consuming and results in a limited time resolution. This research presents an innovation of 3D reconstruction by reformulating two main components of the method. First, a validity index for fuzzy clustering is used to obtain the optimal segmentations of any 2D x-ray image. The process is realized by automatically determining the optimal number of clusters for the image. Second, unlike the existing 3D reconstruction methods, a fast-FCM algorithm is used to speed up the 2D image segmenting process, thereby raising the time resolution of the 3D reconstruction process. With the aid of commonly used VTK software, the proposed method has been used to visualize four classes of typical lung cancer tissues: adenocarcinoma, large cell carcinoma, small cell carcinoma, and squamous cell carcinoma. Experimental results validate the effectiveness and efficiency of the proposed algorithm. Thus, the method contributes a useful tool for x-ray-based 3D image reconstruction. [ABSTRACT FROM AUTHOR]

This paper focuses on the application of a multi- camera imaging system for three-dimensional (3-D) visualization and quantitative characterization of the flame front structures of a turbulent flame. The 2-D images of the flame front are captured simultaneously using identical monochromatic CCD cameras from three different directions around the flame. Dedicated computing algorithms have been developed to reconstruct the 3-D structures of the flame front using various image processing techniques such as edge detection, contour extraction, and mesh generation. A set of flame parameters, including ignition points, ignition volume, ignition surface area, and circularity, is determined from the models generated to characterize the flame front. Results obtained under a range of combustion conditions demonstrate the capability of the system for 3-D quantitative characterization of flame front structures. [ABSTRACT FROM AUTHOR]