CN116869481B - Spine overall structure state detection method based on infrared image and electronic equipment - Google Patents
Spine overall structure state detection method based on infrared image and electronic equipment Download PDFInfo
- Publication number
- CN116869481B CN116869481B CN202310852951.0A CN202310852951A CN116869481B CN 116869481 B CN116869481 B CN 116869481B CN 202310852951 A CN202310852951 A CN 202310852951A CN 116869481 B CN116869481 B CN 116869481B
- Authority
- CN
- China
- Prior art keywords
- acupoint
- spine
- coordinates
- feature point
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims description 34
- 238000001467 acupuncture Methods 0.000 claims description 25
- 238000012360 testing method Methods 0.000 description 12
- 238000012549 training Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 206010039722 scoliosis Diseases 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0073—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by tomography, i.e. reconstruction of 3D images from 2D projections
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
- A61B5/4561—Evaluating static posture, e.g. undesirable back curvature
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
- G06T2207/30012—Spine; Backbone
Abstract
The invention provides a spine overall structure state detection method and electronic equipment based on infrared images, wherein the method comprises the following steps: respectively acquiring infrared images of the left side face, the right side face, the front face and the back face of a trunk area of an object to be detected; acquiring coordinates of corresponding feature points in each infrared image; acquiring a lateral distance difference d based on coordinates of feature points in the left and right images, and acquiring a first frontal comparison slope k based on coordinates of feature points in the frontal image F 1 And a second positive comparison slope k F 2 And acquiring a first back comparison slope k based on coordinates of the feature points in the back image B 1 And a second back comparison slope k B 2 The method comprises the steps of carrying out a first treatment on the surface of the Based on d, k F 1 、k F 2 、k B 1 And k B 2 And determining the overall structure state of the spine of the object to be detected. The invention can detect the whole structure of the spine only based on the whole infrared image, improves the clinical detection efficiency and realizes noninvasive detection, and is particularly suitable for spine detection for children and teenagers.
Description
Technical Field
The invention relates to the field of image processing, in particular to a spine overall structure state detection method based on infrared images and electronic equipment.
Background
Often, the person is in an incorrect posture for a long period of time, resulting in deformation of the overall structure of the spine, such as scoliosis, which is often difficult to judge by the naked eye. In the past, the detection of the overall structure state of the spine is basically carried out by means of an x-ray plate. The X-ray detection cost is high, and the rays can cause a certain degree of damage to the body, so that the X-ray detection method is particularly unsuitable for screening children and teenagers. Thus, there is a need for a low cost and non-invasive spine overall structural condition detection method alternative.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme:
the embodiment of the invention provides a spine overall structure state detection method based on infrared images, which comprises the following steps:
s100, respectively acquiring infrared images of the left side face, the right side face, the front face and the back face of a trunk area of an object to be detected, and obtaining corresponding left side face infrared images, right side face infrared images, front face infrared images and back face infrared images;
s200, acquiring coordinates (x) of a first left-side surface feature point TL1 in the left-side surface infrared image L 1 ，y L 1 ) And the coordinates (x L 2 ，y L 2 ) And acquiring coordinates (x R 1 ，y R 1 ) And the coordinates (x R 2 ，y R 2 )；
S300, acquiring coordinates (x) of a first front feature point TF1 in the front infrared image F 1 ，y F 1 ) Coordinates (x) of the second front feature point TF2 F 2 ，y F 2 ) Coordinates (x) of the third front feature point TF3 F 3 ，y F 3 ) And the coordinates (x F 4 ，y F 4 )；
S400, acquiring coordinates (x) of a first back surface feature point TB1 in the back surface infrared image B 1 ，y B 1 ) Coordinates (x) of the second back surface feature point TB2 B 2 ，y B 2 ) Coordinates (x) of the third back surface feature point TB3 B 3 ，y B 3 ) And the coordinates (x B 4 ，y B 4 )；
S500, acquiring a lateral distance difference d and a first front comparison slope k F 1 Second positive comparison slope k F 2 First back comparison slope k B 1 And a second back comparison slope k B 2 Wherein d= (y) L 1 -y L 2 )-(y R 1 -y R 2 )，k F 1 ＝(y F 1 -y F 2 )/(x F 1 -x F 2 )，k F 2 ＝(y F 3 -y F 4 )/(x F 3 -x F 4 )，k B 1 ＝(y B 1 -y B 2 )/(x B 1 -x B 2 )，k B 2 ＝(y B 3 -y B 4 )/(x B 3 -x B 4 )；
S600, based on the obtained d, k F 1 、k F 2 、k B 1 And k B 2 And determining the overall structure state of the spine of the object to be detected.
The embodiment of the invention also provides an electronic device, which comprises a processor and a non-transitory computer readable storage medium, wherein at least one instruction or at least one section of program is stored in the storage medium, and the at least one instruction or the at least one section of program is loaded and executed by the processor to realize the method.
The invention has at least the following beneficial effects:
the spine overall structure state detection method based on the infrared image provided by the embodiment of the invention can detect the spine overall structure state only based on the infrared image without x-ray films, and can improve the detection efficiency and realize noninvasive detection.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for detecting the overall structure state of a spine based on an infrared image according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The embodiment of the invention provides a spine overall structure state detection method based on infrared images, as shown in fig. 1, the method can comprise the following steps:
s100, respectively acquiring infrared images of the left side face, the right side face, the front face and the back face of a trunk area of an object to be detected, and obtaining corresponding left side face infrared images, right side face infrared images, front face infrared images and back face infrared images.
In the embodiment of the invention, the object to be detected can be a person needing to detect the overall structural state of the spine, and can be preferably children or teenagers. The infrared image can be obtained by shooting through the existing infrared shooting device.
S200, acquiring coordinates (x) of a first left-side surface feature point TL1 in the left-side surface infrared image L 1 ，y L 1 ) And the coordinates (x L 2 ，y L 2 ) And acquiring coordinates (x R 1 ，y R 1 ) And the coordinates (x R 2 ，y R 2 )。
In an exemplary embodiment of the present invention, the first left side feature point may be a left shoulder, a left acupoint, the second left side feature point may be a left acupoint, the first right side feature point may be a right shoulder, a right acupoint, and the second right side feature point may be a right acupoint.
In an exemplary embodiment of the invention, the coordinates of each side feature point may be obtained by marking, for example, a user manually, etc., in the corresponding image. In another exemplary embodiment of the present invention, the coordinates of each of the side feature points may be obtained by a trained feature point recognition model. The framework of the feature point recognition model may be an existing machine learning model or a neural network model, and the specific training process may be the existing technology.
S300, acquiring coordinates (x) of a first front feature point TF1 in the front infrared image F 1 ，y F 1 ) Coordinates (x) of the second front feature point TF2 F 2 ，y F 2 ) Coordinates (x) of the third front feature point TF3 F 3 ，y F 3 ) And the coordinates (x F 4 ，y F 4 )。
In an exemplary embodiment of the present invention, the first front feature point may be a left basin-missing hole, the second front feature point may be a right basin-missing hole, the third front feature point may be a left large horizontal hole, and the fourth front feature point may be a right large horizontal hole.
In an exemplary embodiment of the invention, the coordinates of each front feature point may be obtained by marking, for example, a user manually, etc., in the corresponding image. In another exemplary embodiment of the present invention, the coordinates of each front feature point may be obtained by a trained feature point recognition model. The framework of the feature point recognition model may be an existing machine learning model or a neural network model, and the specific training process may be the existing technology.
S400, acquiring coordinates (x) of a first back surface feature point TB1 in the back surface infrared image B 1 ，y B 1 ) Coordinates (x) of the second back surface feature point TB2 B 2 ，y B 2 ) Coordinates (x) of the third back surface feature point TB3 B 3 ，y B 3 ) And the coordinates (x B 4 ，y B 4 )。
In an exemplary embodiment of the present invention, the first back feature point may be a left Bingshu point, the second back feature point may be a right Bingshu point, the third back feature point may be a left waist eye point, and the fourth back feature point may be a right waist eye point.
In an exemplary embodiment of the invention, the coordinates of each back feature point may be obtained by marking, for example, a user manually, etc., in the corresponding image. In another exemplary embodiment of the present invention, the coordinates of each back surface feature point may be obtained by a trained feature point recognition model. The framework of the feature point recognition model may be an existing machine learning model or a neural network model, and the specific training process may be the existing technology.
S500, acquiring a lateral distance difference d and a first front comparison slope k F 1 Second positive comparison slope k F 2 First back comparison slope k B 1 And a second back comparison slope k B 2 Wherein d= (y) L 1 -y L 2 )-(y R 1 -y R 2 )，k F 1 ＝(y F 1 -y F 2 )/(x F 1 -x F 2 )，k F 2 ＝(y F 3 -y F 4 )/(x F 3 -x F 4 )，k B 1 ＝(y B 1 -y B 2 )/(x B 1 -x B 2 )，k B 2 ＝(y B 3 -y B 4 )/(x B 3 -x B 4 )。
S600, based on the obtained d, k F 1 、k F 2 、k B 1 And k B 2 And determining the overall structure state of the spine of the object to be detected.
Further, S600 specifically includes:
s610, d is compared with a set longitudinal distance thresholdComparing the value d0 to obtain a first comparison result, and respectively comparing k F 1 And k F 2 K B 1 And k B 2 And comparing the set slope threshold k0 to obtain a second comparison result and a third comparison result respectively.
In embodiments of the invention, d0 and k0 may be obtained based on experimentation. Specifically, it can be obtained by the following steps:
s1, respectively acquiring lateral distance differences d1 to dN and a first front comparison slope k of a test object in a normal state confirmed by an expert in the overall structure state of N spines F 11 To k F 1N Second positive comparison slope k F 21 To k F 2N First back comparison slope k B 11 To k B 1N A second backside comparison slope k B 21 To k B 2N The method comprises the steps of carrying out a first treatment on the surface of the Wherein the age distribution of the N subjects is between 2 years and 50 years; dh is the lateral distance difference, k, of the h test object F 1h A first positive comparison slope, k, for the h test object 2 h A second positive comparison slope, k, for the h test object B h A first back comparison slope, k, for the h test object B 2h Comparing the slope for the second back of the h test object, wherein the value of h is 1 to N;
s2, obtaining the maximum one of d1 to dN as d0 and obtaining k F 11 To k F 1N 、k F 21 To k F 2N 、k B 11 To k B 1N K B 21 To k B 2N The largest of (2) is k0. S620, if the first to third comparison results all meet the corresponding set conditions, which indicate that the spine has deformed, such as lateral curvature, then determining that the status of the spine of the object to be detected is an abnormal status; wherein the setting condition corresponding to the first comparison result is d not less than d0, and the setting condition corresponding to the second comparison result is k F 1 And k F 2 At least one of which is greater than or equal to k0, a third comparison junctionThe setting condition corresponding to the fruit is k B 1 And k B 2 At least one of which is greater than or equal to k0.
And S630, if the first to third comparison results do not meet the corresponding set conditions, acquiring the acupuncture point information on the spine in the back infrared image, and determining the overall structure state of the spine of the object to be detected based on the acquired acupuncture point information.
Further, S630 may specifically include:
s631, acquiring the acupuncture point information on the spine in the back infrared image based on the trained spine acupuncture point prediction model to obtain an acupuncture point information set A= { A 1 ，A 2 ，……，A i ，……，A n I-th acupoint information A i ＝(B i ，G i )，B i ID of the ith acupoint, G i G is the position of the ith acupoint i ＝(x i ，y i )，x i And y i The abscissa and the ordinate of the ith acupoint are respectively; wherein y is 1 ＞y 2 ＞……y i ＞……y n I has a value of 1 to n.
In an embodiment of the present invention, the trained spinal acupoint prediction model may be an existing AI model, such as a machine learning model or a neural network model, or the like. The spine whole structure is characterized in that the spine whole structure can be obtained through training of positive samples and negative samples marked with acupoints, wherein the positive samples are back infrared images of the spine whole structure in a normal state, and the negative samples are back infrared images of the spine whole structure in an abnormal state. The specific training process may be prior art.
Those skilled in the art know that the acupoints on the spine may be the governor vessel.
S632, j=2.
S633, if j is less than or equal to n-1, S634 is performed, otherwise S636 is performed.
S634, if |x j -x 0 I > L0, then A j Determining the abnormal acupoints and storing the abnormal acupoints in the current abnormal acupoint record table, and executing S635; otherwise, directly executing S635; l0 is a set lateral distance error threshold, x 0 Is the abscissa of the reference acupoint A 1 Or A n The method comprises the steps of carrying out a first treatment on the surface of the The initial value of the abnormal acupoint record table is empty set.
In embodiments of the invention, L0 may be a test value. Specifically, the method can be obtained by the following steps:
step one, acquiring back infrared images of M spine overall structure states of a test object which is in a normal state through expert confirmation;
respectively obtaining absolute values of distances between any acupoint on the spine of the d-th test object and the abscissa of the reference acupoint in the back infrared image of the d-th test object to obtain a corresponding transverse distance absolute value set Ld= { Ld 1 ，Ld 2 ，……，Ld i ，……，Ld n }；Ld i The absolute value of the distance between the ith acupoint of the d-th test object and the abscissa of the corresponding reference acupoint is 1 to M;
step three, obtaining the maximum value Ld in the Ld max Candidate distance as the d-th test object;
step four, obtaining L1 max To LM max The maximum value of (2) is L0.
S635, set j=j+1; s633 is performed.
S636, taking the current abnormal acupuncture point record table as a target abnormal acupuncture point record table, and executing S637 if the number of abnormal acupuncture points in the target abnormal acupuncture point record table is greater than or equal to a set value; otherwise, determining the spine state of the object to be detected to be a normal state.
In the embodiment of the present invention, the set value may be an empirical value, for example, may be a value greater than or equal to 2.
S637, determining the spine state of the object to be detected as an abnormal state.
Further, in an embodiment of the present invention, S637 further includes:
and displaying the acupoints in the current abnormal acupoint record list in the back infrared image in a set color. Preferably, the set color is also highlighted. Further, in another embodiment of the present invention, S637 further includes:
s6371 based on A 1 、A n And acquiring A from the set acupoint position relation table 2 To A n-1 Reference position a of (2) r 2 To A r n-1 Wherein A is j Reference position G of (2) r j ＝(x r j ，y r j )，x r j And y r j Respectively A j Reference values of the abscissa and the ordinate of (a); wherein the e-th row of the set positional relationship table includes (B e ，P e )，B e ID, P of the e-th acupoint in A e Representing the number of straight-dimension between the e-th acupoint and the reference acupoint, wherein the value of e is 1 to n; wherein x is r j ＝x 0 。
In the embodiment of the invention, P e Based on the theory of traditional Chinese medicine.
Further, y r j ＝y 1 -△y*P j Delta y is the length of the straight dimension, delta y= (y) 1 -y n ) Q, q is A 1 And A n The number of straight-in-between.
S6372, procedure A 1 To A n Displaying in the back infrared image in a first color, A r 2 To A r n-1 And displaying in the back infrared image in a second color.
The first color and the second color may be set based on actual needs, and the present invention is not particularly limited as long as they can be distinguished.
In the embodiment of the invention, by A 1 To A n Displaying in the back infrared image in a first color, A r 2 To A r n-1 The abnormal condition of the spine can be visually known by displaying the spine in the back infrared image with the second color.
Further, S637 further includes:
s6373, forming an acupoint position deviation information table, wherein the ith row of the acupoint position deviation information table comprises%B i ，G r i ，G i ，△G i ) Wherein DeltaG i As the offset information of the ith acupoint, deltaG i ＝(△x i ，△y i ) The transverse offset value Deltax of the ith acupoint i ＝x i -x r i Longitudinal offset value delta y of ith acupoint i ＝y i -y r i 。
And S6374, displaying the acupoint position deviation information table.
According to the embodiment of the invention, the offset degree of the abnormal part of the spine, such as lateral bending, relative to the normal position can be intuitively known by displaying the cheap information table of the positions of the acupuncture points.
Further, in the embodiment of the present invention, S620 further includes:
s6201, acquiring the acupuncture point information on the spine in the back infrared image based on the trained spine acupuncture point prediction model to obtain an acupuncture point information set A= { A 1 ，A 2 ，……，A i ，……，A n I-th acupoint information A i ＝(B i ，G i )，B i ID of the ith acupoint, G i G is the position of the ith acupoint i ＝(x i ，y i )，x i And y i The abscissa and the ordinate of the ith acupoint are respectively; wherein y is 1 ＞y 2 ＞……y i ＞……y n I has a value of 1 to n.
S6202, j=2 is set.
S6203, if j is less than or equal to n-1, executing S6204, otherwise, executing S6206.
S6204 if |x j -x 0 I > L0, then A j Determining abnormal acupoints and storing the abnormal acupoints into a current abnormal acupoint record table, and executing S6205; otherwise, S6205 is directly performed; l0 is a set lateral distance error threshold, x 0 Is the abscissa of the reference acupoint A 1 Or A n The method comprises the steps of carrying out a first treatment on the surface of the The initial value of the abnormal acupoint record table is empty set.
S6205, setting j=j+1; s6203 is performed.
S6206, displaying the acupoints in the current abnormal acupoint record list in the back infrared image in a set color. Preferably, the set color is also highlighted.
Further, in the embodiment of the present invention, S600 further includes:
s640, if g comparison results exist in the first to third comparison results and meet the corresponding setting conditions, outputting prompt information indicating that verification by a user is required. g has a value of 1 or 2.
If 1 or 2 comparison results among the first to third comparison results satisfy the corresponding setting conditions, it is indicated that the pose may be less paired during photographing, and a user such as a doctor is required to perform a verification to confirm the overall structural state of the spine.
Embodiments of the present invention also provide a non-transitory computer readable storage medium that may be disposed in an electronic device to store at least one instruction or at least one program for implementing one of the methods embodiments, the at least one instruction or the at least one program being loaded and executed by the processor to implement the methods provided by the embodiments described above.
Embodiments of the present invention also provide an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
Embodiments of the present invention also provide a computer program product comprising program code for causing an electronic device to carry out the steps of the method according to the various exemplary embodiments of the invention as described in the specification, when said program product is run on the electronic device.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the present disclosure is defined by the appended claims.
Claims (6)
1. An electronic device comprising a processor and a non-transitory computer readable storage medium having at least one instruction or at least one program stored therein, wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement a method for detecting a spine overall structure state based on infrared images, the method comprising the steps of:
s100, respectively acquiring infrared images of the left side face, the right side face, the front face and the back face of a trunk area of an object to be detected, and obtaining corresponding left side face infrared images, right side face infrared images, front face infrared images and back face infrared images;
s200, acquiring coordinates (x) of a first left-side surface feature point TL1 in the left-side surface infrared image L 1 ，y L 1 ) And the coordinates (x L 2 ，y L 2 ) And acquiring coordinates (x R 1 ，y R 1 ) And the coordinates (x R 2 ，y R 2 )；
S300, acquiring coordinates (x) of a first front feature point TF1 in the front infrared image F 1 ，y F 1 ) Coordinates (x) of the second front feature point TF2 F 2 ，y F 2 ) Coordinates (x) of the third front feature point TF3 F 3 ，y F 3 ) And the coordinates (x F 4 ，y F 4 )；
S400, acquiring coordinates (x) of a first back surface feature point TB1 in the back surface infrared image B 1 ，y B 1 ) Coordinates (x) of the second back surface feature point TB2 B 2 ，y B 2 ) Coordinates (x) of the third back surface feature point TB3 B 3 ，y B 3 ) And the coordinates (x B 4 ，y B 4 )；
S500, acquiring a lateral distance difference d and a first front comparison slope k F 1 Second positive comparison slope k F 2 First back comparison slope k B 1 And a second back comparison slope k B 2 Wherein d= (y) L 1 -y L 2 )-(y R 1 -y R 2 )，k F 1 ＝(y F 1 -y F 2 )/(x F 1 -x F 2 )，k F 2 ＝(y F 3 -y F 4 )/(x F 3 -x F 4 )，k B 1 ＝(y B 1 -y B 2 )/(x B 1 -x B 2 )，k B 2 ＝(y B 3 -y B 4 )/(x B 3 -x B 4 )；
S600, based on the obtained d, k F 1 、k F 2 、k B 1 And k B 2 Determining the overall structure state of the spine of the object to be detected;
s600 specifically includes:
s610, comparing d with a set longitudinal distance threshold d0 to obtain a first comparison result, and respectively comparing k F 1 And k F 2 K B 1 And k B 2 Comparing the set slope threshold k0 to obtain a second comparison result and a third comparison result respectively;
s620, if the first to third comparison results all meet the corresponding set conditions, determining that the spine state of the object to be detected is an abnormal state; wherein the setting condition corresponding to the first comparison result is d not less than d0, and the setting condition corresponding to the second comparison result is k F 1 And k F 2 At least one of which is greater than or equal to k0, and the setting condition corresponding to the third comparison result is k B 1 And k B 2 At least one of which is greater than or equal to k0;
s630, if the first to third comparison results do not meet the corresponding set conditions, acquiring the acupuncture point information on the spine in the back infrared image, and determining the overall structure state of the spine of the object to be detected based on the acquired acupuncture point information;
s630 specifically includes:
s631, acquiring the acupuncture point information on the spine in the back infrared image based on the trained spine acupuncture point prediction model to obtain an acupuncture point information set A= { A 1 ，A 2 ，……，A i ，……，A n I-th acupoint information A i ＝(B i ，G i )，B i ID of the ith acupoint, G i G is the position of the ith acupoint i ＝(x i ，y i )，x i And y i The abscissa and the ordinate of the ith acupoint are respectively; wherein y is 1 ＞y 2 ＞……y i ＞……y n I has a value of 1 to n;
s632, set j=2;
s633, if j is less than or equal to n-1, executing S634, otherwise, executing S636;
s634, if |x j -x 0 I > L0, then A j Determining the abnormal acupoints and storing the abnormal acupoints in the current abnormal acupoint record table, and executing S635; otherwise, directly executing S635; l0 is a set lateral distance error threshold, x 0 Is the abscissa of the reference acupoint A 1 Or A n The method comprises the steps of carrying out a first treatment on the surface of the The initial value of the abnormal acupoint record table is an empty set;
s635, set j=j+1; s633 is performed;
s636, taking the current abnormal acupuncture point record table as a target abnormal acupuncture point record table, and executing S637 if the number of abnormal acupuncture points in the target abnormal acupuncture point record table is greater than or equal to a set value; otherwise, determining that the spine state of the object to be detected is a normal state;
s637, determining the spine state of the object to be detected as an abnormal state.
2. The electronic device of claim 1, wherein S637 further comprises:
s6371 based on A 1 、A n And acquiring A from the set acupoint position relation table 2 To A n-1 Reference position a of (2) r 2 To A r n-1 Wherein A is j Reference position G of (2) r j ＝(x r j ，y r j )，x r j And y r j Respectively A j Reference values of the abscissa and the ordinate of (a); wherein the e-th row of the set positional relationship table includes (B e ，P e )，B e ID, P of the e-th acupoint in A e Representing the number of straight-dimension between the e-th acupoint and the reference acupoint, wherein the value of e is 1 to n; wherein x is r j ＝x 0 ；
S6372, procedure A 1 To A n Displaying in the back infrared image in a first color, and displaying A in the back infrared image in a first color r 2 To A r n-1 And displaying in the back infrared image in a second color.
3. The electronic device of claim 2, wherein S637 further comprises:
s6373, forming an acupoint position shift information table, the ith row of the acupoint position shift information table including (B) i ，G r i ，G i ，△G i ) Wherein DeltaG i As the offset information of the ith acupoint, deltaG i ＝(△x i ，△y i ) The transverse offset value Deltax of the ith acupoint i ＝x i -x r i Longitudinal offset value delta y of ith acupoint i ＝y i -y r i ；
And S6374, displaying the acupoint position deviation information table.
4. An electronic device according to claim 2 or 3, characterized in that y r j ＝y 1 -△y*P j Delta y is the length of the straight dimension, delta y= (y) 1 -y n ) Q, q is A 1 And A n The number of straight-in-between.
5. The electronic device of claim 1, wherein S620 further comprises:
s6201, acquiring the acupuncture point information on the spine in the back infrared image based on the trained spine acupuncture point prediction model to obtain an acupuncture point information set A= { A 1 ，A 2 ，……，A r ，……，A n R acupoint information A }, where r ＝(B r ，G r )，B r ID, G of the r-th acupoint r G is the position of the r-th acupoint r ＝(x r ，y r )，x r And y r The abscissa and the ordinate of the r-th acupoint are respectively; wherein y is 1 ＞y 2 ＞……y r ＞……y n R has a value of 1 to n;
s6202, set s=2;
s6203, if S is less than or equal to n-1, executing S6204, otherwise, executing S6206;
s6204 if |x s -x 0 I > L0, then A s Determining abnormal acupoints and storing the abnormal acupoints into a current abnormal acupoint record table, and executing S6205; otherwise, S6205 is directly performed; l0 is a set lateral distance error threshold, x 0 Is the abscissa of the reference acupoint A 1 Or A n The method comprises the steps of carrying out a first treatment on the surface of the The initial value of the abnormal acupoint record table is an empty set;
s6205, set s=s+1; executing S6203;
s6206, displaying the acupoints in the current abnormal acupoint record list in the back infrared image in a set color.
6. The electronic device of claim 1, wherein the first left side feature point is a left shoulder nyin point, the second left side feature point is a left band point, the first right side feature point is a right shoulder nyin point, and the second right side feature point is a right band point;
the first front characteristic points are left basin lacking holes, the second front characteristic points are right basin lacking holes, the third front characteristic points are left large transverse holes, and the fourth front characteristic points are right large transverse holes;
the first back feature point is a left Binshu acupoint, the second back feature point is a right Binshu acupoint, the third back feature point is a left waist eye acupoint, and the fourth back feature point is a right waist eye acupoint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310852951.0A CN116869481B (en) | 2023-07-12 | 2023-07-12 | Spine overall structure state detection method based on infrared image and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310852951.0A CN116869481B (en) | 2023-07-12 | 2023-07-12 | Spine overall structure state detection method based on infrared image and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116869481A CN116869481A (en) | 2023-10-13 |
| CN116869481B true CN116869481B (en) | 2024-02-20 |
Family
ID=88261630
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310852951.0A Active CN116869481B (en) | 2023-07-12 | 2023-07-12 | Spine overall structure state detection method based on infrared image and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116869481B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108151670A (en) * | 2017-12-30 | 2018-06-12 | 北京工业大学 | A kind of back three dimensional symmetry degree evaluating apparatus and method |
| CN113647939A (en) * | 2021-08-26 | 2021-11-16 | 复旦大学 | Artificial intelligence rehabilitation evaluation and training system for spinal degenerative diseases |
| CN113674257A (en) * | 2021-08-26 | 2021-11-19 | 平安科技（深圳）有限公司 | Method, device and equipment for measuring scoliosis angle and storage medium |
| KR20210152279A (en) * | 2020-06-08 | 2021-12-15 | 연세대학교 산학협력단 | Scoliosis Diagnosis Method and System using 3D Depth Camera |
| CN114983396A (en) * | 2022-06-29 | 2022-09-02 | 电子科技大学 | Automatic detection system for scoliosis |
| CN115937319A (en) * | 2023-02-16 | 2023-04-07 | 天河超级计算淮海分中心 | Key point marking method based on X-ray image, electronic equipment and storage medium |
| CN116228727A (en) * | 2023-03-15 | 2023-06-06 | 宜宾显微智能科技有限公司 | Image-based human back epidermis spinal cord detection method and device |
-
2023
- 2023-07-12 CN CN202310852951.0A patent/CN116869481B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108151670A (en) * | 2017-12-30 | 2018-06-12 | 北京工业大学 | A kind of back three dimensional symmetry degree evaluating apparatus and method |
| KR20210152279A (en) * | 2020-06-08 | 2021-12-15 | 연세대학교 산학협력단 | Scoliosis Diagnosis Method and System using 3D Depth Camera |
| CN113647939A (en) * | 2021-08-26 | 2021-11-16 | 复旦大学 | Artificial intelligence rehabilitation evaluation and training system for spinal degenerative diseases |
| CN113674257A (en) * | 2021-08-26 | 2021-11-19 | 平安科技（深圳）有限公司 | Method, device and equipment for measuring scoliosis angle and storage medium |
| CN114983396A (en) * | 2022-06-29 | 2022-09-02 | 电子科技大学 | Automatic detection system for scoliosis |
| CN115937319A (en) * | 2023-02-16 | 2023-04-07 | 天河超级计算淮海分中心 | Key point marking method based on X-ray image, electronic equipment and storage medium |
| CN116228727A (en) * | 2023-03-15 | 2023-06-06 | 宜宾显微智能科技有限公司 | Image-based human back epidermis spinal cord detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116869481A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101944536B1 (en) | System and method for medical diagnosis using neural network | |
| EP2466541A2 (en) | Image processing apparatus, image processing method and image processing program | |
| US20160253798A1 (en) | Image analysis for predicting body weight in humans | |
| US20100128223A1 (en) | Method, algorithm and device for testing visual acuity | |
| CN108888277B (en) | Psychological test method, psychological test system and terminal equipment | |
| KR102043672B1 (en) | System and method for lesion interpretation based on deep learning | |
| EP2470076A2 (en) | Characterizing a physical capability by motion analysis | |
| US11663845B2 (en) | Method and apparatus for privacy protected assessment of movement disorder video recordings | |
| KR20190105180A (en) | Apparatus for Lesion Diagnosis Based on Convolutional Neural Network and Method thereof | |
| Dempere-Marco et al. | The use of visual search for knowledge gathering in image decision support | |
| CN110956636A (en) | Image processing method and device | |
| CN116869481B (en) | Spine overall structure state detection method based on infrared image and electronic equipment | |
| EP3858245B1 (en) | Automatic recognition method for measurement point in cephalo image | |
| Zariffa et al. | Computer vision-based classification of hand grip variations in neurorehabilitation | |
| CN113221815A (en) | Gait identification method based on automatic detection technology of skeletal key points | |
| TWI439253B (en) | Method and system for disease detection using human infrared thermal map | |
| Motoki et al. | Automatic teeth recognition method from dental panoramic images using faster R-CNN and prior knowledge model | |
| TWI663960B (en) | Foot deformity detection model, foot deformity detection system and foot deformity detection method | |
| CN115661101A (en) | Premature infant retinopathy detection system based on random sampling and deep learning | |
| CN116236208A (en) | Multi-lead electrocardio electrode patch positioning method based on human body surface characteristics | |
| CN113284145B (en) | Image processing method and device, computer readable storage medium and electronic device | |
| CN110008995A (en) | Image-recognizing method and system | |
| CN115359548A (en) | Handheld intelligent pupil detection device and detection method | |
| Heo et al. | Development of a robust eye exam diagnosis platform with a deep learning model | |
| CN113870214A (en) | Vein image quality evaluation method and device and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |