Jun Tang

Bio: Jun Tang is an academic researcher. The author has contributed to research in topics: Cobb angle & Volume (compression). The author has an hindex of 1, co-authored 2 publications receiving 6 citations.

Method for automatically measuring Cobb angle

Abstract: The invention discloses a method for automatically measuring a Cobb angle. The method comprises the following steps of step1, preprocessing; step2, carrying out an enhanced watershed segmentation algorithm; step3, extracting each spine center point and fitting a curve; and step4, automatically calculating the Cobb angle. In the method of the invention, upper and lower terminals do not need to be manually established so that the robustness of the algorithm is high, and the method is suitable for operating personnel with less Cobb angle measurement experience; the modes of segmenting-extractingthe center point and fitting the curve are used to represent the curvature of a spine and the method can be further used in the diagnosis of lumbar spondylolisthesis, fracture and other symptoms. Through using the above mode, the curvature of the spine can be effectively and visually displayed. The result of the method is stable and an error is small.

Method and device for measuring spinal curvature

Abstract: The invention provides a method and device for measuring spine bending, and relates to the field of image processing, and the method comprises the steps: firstly, inputting an image of a to-be-detected spine into a pre-trained neural network model, and obtaining a connection line response graph which is used for representing the positions of the upper edge and the lower edge of each spine body andthe coordinate positions of all angular points of each spine body; then, on the basis of the coordinate positions of all the corner points, connecting each upper left corner point with each upper right corner point to obtain a first connection graph, and connecting each upper right corner point with each lower right corner point to obtain a second connection graph; and finally, based on the connection response graph, the first connection graph, the second connection graph and a global optimal criterion, obtaining a real upper line and a real lower line of each spine body. According to the invention, the real upper line and the real lower line of each spine body can be accurately acquired by utilizing the connection response diagram, the first connection diagram, the second connection diagram and the global optimal criterion, and the calculation precision of the Cobb angle is improved.

Spatial information-based intuitionistic fuzzy kernel clustering algorithm for cerebral hemorrhage image segmentation

Abstract: Cerebral hemorrhage is a cardiovascular disease with high mortality and disability rates. In order to measure the hematoma volume of patients with cerebral hemorrhage accurately and quickly, we propose a method that is based on spatial information intuitionistic fuzzy kernel clustering segmentation algorithm. Firstly, the skull structures are removed from cerebral CT images. Then the skull removal images are segmented by the algorithm proposed in this paper. Based on kernel functions, the algorithm adds neighborhood information terms to the objective function, introduces weight factors based on the spatial information, and modifies the membership matrix based on the location information of the hematoma. Finally, the hematoma volume is calculated based on the segmentation results. By measuring the cerebral hemorrhage volume of several patients and analyzing the results, the applicability and effectiveness of this algorithm are validated.

Image processing method and related equipment

Abstract: The embodiment of the invention provides an image processing method and related equipment, and belongs to the technical field of computers. The method comprises the following steps: acquiring a spineimage to be processed; processing the spine image to be processed through a first neural network model, positioning a vertebra region in the spine image to be processed, and obtaining a positioning result; processing the positioning result through a second neural network model to obtain key points on each vertebra region; and obtaining a spinal curvature angle of the spinal image to be processed according to the key points on each vertebral region. The technical scheme of the embodiment of the invention provides an image processing method, which can improve the measurement accuracy of spinal curvature angle measurement.

Spine Cobb angle measurement method and device, readable storage medium and terminal equipment

Abstract: The invention belongs to the technical field of image analysis, and particularly relates to a spine Cobb angle measurement method and device, a computer readable storage medium and terminal equipment.The method comprises the steps of using a pre-trained deep learning network model for carrying out segmentation processing on a spine X-ray image to acquire a segmentation result image, wherein the segmentation result image is a binary image of a spine area and a non-spine area; respectively identifying each spine block from the spine area of the segmentation result map; determining upper and lower end plate straight lines of each spine block; traversing calculation is conducted on the upper end plate straight line and the lower end plate straight line of each spine block, wherein the included angle with the maximum value is determined as the spine Cobb angle. According to the embodiment of the invention, automatic measurement of the spine Cobb angle is truly realized, the required spineCobb angle can be obtained without additional operation of a worker, errors caused by manual or semi-manual measurement of the spine Cobb angle are avoided, and better reliability is achieved.

A scoliosis detection method based on polynomial curve fitting

Abstract: The invention discloses a scoliosis detection and recognition method based on polynomial curve fitting. The method comprises the steps that a machine vision scheme is used for automatically extractingthe center line of a back spine, curve fitting is conducted in combination with back feature points, and cobb angle calculation is conducted. According to the method, the spine center line of a person can be efficiently and accurately obtained through the depth camera, cobb angle calculation is carried out on the spine center line to carry out lateral bending judgment, the labor intensity of manual detection is greatly reduced, and the diagnosis precision is improved. Through cubic polynomial fitting, subsequent processing of the data can be ensured, the situation that higher-order polynomialfitting generates oscillation in actual use and affects the data precision is avoided, and a guarantee is provided for the accuracy of the data.