Patent•
Method for automatically measuring Cobb angle
25 Sep 2018-
TL;DR: In this article, a method for automatically measuring the Cobb angle of a lumbar spondylolisthesis, fracture and other symptoms is presented, which is suitable for operating personnel with less Cobb angle measurement experience.
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.
Citations
More filters
Patent•
19 Mar 2019
TL;DR: In this article, the authors proposed a method and device for measuring spine bending, which 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 and the coordinate positions of all angular points of each body body; then, on the basis of the coordinate position of all the corner points, connecting each upper left corner
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.
4 citations
Patent•
05 Nov 2019
TL;DR: In this article, an image processing method was proposed to improve the measurement accuracy of spinal curvature angle measurement, which can improve the quality of the image and improve the accuracy of the estimation.
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.
2 citations
Patent•
27 Aug 2019
TL;DR: In this paper, a pre-trained deep learning network model was used to perform segmentation on a spine X-ray image to acquire a segmentation result image, wherein the segmentation image is a binary image of a spine area and a non-spine area.
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.
1 citations
Patent•
18 Jun 2019
TL;DR: In this paper, a machine vision scheme is used for automatically extracting the center line of a back spine, curve fitting is conducted in combination with back feature points, and cobb angle calculation is conducted.
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.
Patent•
08 Oct 2020
TL;DR: In this article, a pre-trained deep learning network model was used to perform segmentation processing on a spine X-ray image to obtain a segmentation result image, the segmentation image being a binary image of a spine area and a non-spine area, respectively identifying each spinal block, and determining the angle with the largest value to be a spine Cobb angle.
Abstract: A spine Cobb angle measurement method and apparatus, a readable storage medium, and a terminal device, relating to the technical field of image analysis, the method comprising: using a pre-trained deep learning network model to perform segmentation processing on a spine X-ray image to obtain a segmentation result image (S201), the segmentation result image being a binary image of a spine area and a non-spine area; from the spine area of the segmentation result image, respectively identifying each spinal block (S202); respectively determining the upper and lower endplate straight line of each spinal block (S203); performing a traversal calculation on the upper and lower endplate straight line of each spinal block, and determining the angle with the largest value to be a spine Cobb angle (S204). The present method implements automatic measurement of a spine Cobb angle in a true sense, and can obtain the required spine Cobb angle without needing staff to perform additional operations, avoiding errors introduced by manual or semi-manual methods of performing spine Cobb angle measurement, and having good reliability.
References
More filters
Patent•
22 Mar 2007TL;DR: An image processing method for automatically analyzing the spine in a radiograph is described in this article. But this method requires the radiograph image to be acquired in digital form, and it is not suitable for the use in medical applications.
Abstract: An image processing method for automatically analyzing the spine in a radiograph. The methods includes the steps of acquiring the radiographic image in digital form; detecting the spine midline in the radiograph, locating vertebra and pedicle along the spine midline, and calculating geometrical data of the spine in the radiograph.
31 citations
Patent•
21 Aug 2006TL;DR: In this article, the authors proposed a method for detecting the curvature of a spine and computing at least one of a first angle or a second angle based on the line of the curvatures of the spine.
Abstract: A method for providing automatic detection of curvature of a spine and computation of specific angles in images of the spine includes automatically displaying the curvature of the spine as a line in an image of the spine, and computing at least one of a first angle or a second angle based on the line of the curvature of the spine.
10 citations
Patent•
07 Nov 2017
TL;DR: Sunflower disease recognition method based on a random forest method is proposed in this paper, which can recognize four common diseases of sunflower leaves including powdery mildew, bacterial leaf spot, black spot, and downy mildow and comprises steps of: A: Disease image acquisition in which an acquired leaf image color is required to be as close as possible to the color of a leaf itself; B: disease image processing in which a processing method suitable for sunflower disease image recognition is used; C: disease segmentation, in order to select an optimal color image segmentation method
Abstract: The invention discloses a sunflower disease recognition method based on a random forest method. The sunflower disease recognition method can recognize four common diseases of sunflower leaves including powdery mildew, bacterial leaf spot, black spot, and downy mildew and comprises steps of: A: disease image acquisition in which an acquired leaf image color is required to be as close as possible to the color of a leaf itself; B: disease image processing in which a processing method suitable for sunflower disease image recognition is used; C: disease image segmentation in which an optimal color image segmentation method is selected by analyzing and comparing various image segmentation methods; D: disease image feature extraction in which parameters such as the color feature and the texture feature of the disease image are extracted for research; and E: disease recognition and diagnosis in which the sunflower disease is diagnosed and recognized by using the random forest method. The sunflower disease recognition method mainly solves the subjectivity, the limitation, and the fuzziness of eye determination and difficulty in new disease determination in a process of disease recognition, improves the accuracy of diseases recognition, and provides agricultural workers with good help for recognizing and preventing sunflower diseases.
9 citations
Patent•
12 Feb 2014
TL;DR: In this article, a method for calculating the amount of spine deformation by using the second coordinate information was proposed, which can be calculated automatically according to the predetermined spine X-ray images and the coordinate information of a plurality of points inside.
Abstract: The invention discloses a spine X-ray image processing method and system. The method includes utilizing a second spine X-ray image to perform rectification on a first spine X-ray image and obtain space conversion information of the first spine X-ray image; acquiring second coordinate information of rectified predetermined points according to the space conversion information and first coordinate information at least a pair of predetermined points on the edges of a spine in the first spine X-ray image; calculating and outputting the amount of spine deformation by utilizing the second coordinate information. According to the method and device, the amount of spine deformation can be calculated automatically according to the predetermined spine X-ray images and the coordinate information of a plurality of points inside, influences on calculation results by manual operation can be reduced, and the calculation results can be more accurate.
6 citations
Patent•
15 Dec 2017
TL;DR: In this paper, a measurement method of the scoliosis angle of the back of a human body based on computer vision is proposed, which includes the steps of acquiring a back depth image of a person by using a depth camera and preprocessing the back depth images of the human body; then performing triangulation processing by using the Lawson algorithm to obtain a three-dimensional reconstruction model of the person's back.
Abstract: The invention discloses a measurement method of the scoliosis angle of the back of a human body based on computer vision. The measurement method includes the steps of acquiring a back depth image of a human body by using a depth camera and preprocessing the back depth image of the human body; then performing triangulation processing by using a Lawson algorithm to obtain a three-dimensional reconstruction model of the back of the human body; constructing a contour map of the back surface profile of the human body and combining with the characteristics of a contour line to find a central line of the back of the human body; performing integer interpolation on the central line of the back to obtain the curvature of each point on the central line of the back; solving the length of the spine trunk by the use of anatomical landmark points and obtaining a spine body length expression; and finally substituting into a correlation model to reconstruct a spine central line three-dimensional curve. The reconstruction accuracy is greatly increased, and the reconstruction effect is excellent.
5 citations