A method and device for symmetrical treatment of soft suspension of the levator aponeurosis of both eyes in double eyelid surgery

Abstract

Embodiments of the present invention relate to a method and device for symmetrically processing the soft suspension of the levator palpebrae superioris aponeurosis of both eyes during double eyelid surgery. The method comprises the following steps: obtaining a user's original facial image, identifying the original facial image based on a feature model to obtain single eyelid features and facial features; obtaining the user's ultrasonic eyelid thickness information; inputting the single eyelid features, facial features, and ultrasonic eyelid thickness information into a generative neural network model to generate a postoperative single eyelid effect image; superimposing the postoperative single eyelid effect image with the original facial image to obtain a postoperative facial effect image; determining the double eyelid surgery procedure based on the postoperative facial effect image selected by the user, and performing the double eyelid surgery. This method enables automated double eyelid surgery.

Description

Technical Field

[0001] The present invention relates to the technical field of double eyelid surgery, and in particular to a method and device for softly suspending and symmetrically processing the levator palpebrae superioris aponeurosis of both eyes during double eyelid surgery. Background Art

[0002] Double eyelid surgery, also known as blepharoplasty or double eyelid surgery, is one of the most common procedures in plastic surgery. Generally speaking, double eyelids visually enlarge the eye contour, add three-dimensionality, make the eye appear larger, and lift the eyelashes, giving a lively and expressive look. There are various surgical methods for double eyelid surgery, the most common of which are incisional and suture methods.

[0003] The incision method is suitable for single eyelids with thicker eyelids or more fat, and single eyelids with inconsistent eye sizes or ptosis. Compared with the buried suture method, it has the disadvantages of longer operation time and longer recovery period, but generally recovery can be achieved in 5-7 days. According to the tissue anatomical structure of the upper eyelid and the surgical method, the incision method can be divided into three categories: hard suspension, soft suspension, and semi-soft suspension. Among them, the soft suspension method is to suture the aponeurosis of the levator palpebrae superioris muscle to the muscle layer of the upper eyelid. When the eyes are open, the contraction of the levator palpebrae superioris muscle drives the muscle layer up, and the latter then drives the upper eyelid skin up to form a double eyelid. This suture is the connection between the muscle aponeurosis and the muscle, which is relatively soft and elastic.

[0004] The buried suture method is suitable for single eyelids with thin eyelid skin and orbicularis oculi muscles, and for those without Mongolian wrinkles and sagging eyelid skin. The disadvantage of buried suture double eyelid surgery is that the results are short-lived.

[0005] With the application of medical robots in hospitals and clinics for medical or auxiliary medical treatment, people are gradually accepting that medical robots can perform or assist in surgery. However, there is currently no relevant automated equipment for double eyelid surgery. Summary of the Invention

[0006] In view of the above problems, the present invention is proposed to provide a method and device for symmetrically treating the soft suspension of the levator palpebrae superioris aponeurosis of both eyes during double eyelid surgery, which overcomes the above problems or at least partially solves the above problems.

[0007] In a first aspect, an embodiment of the present invention provides a method for symmetrically treating the soft suspension of the levator aponeurosis of both eyes during double eyelid surgery, the method comprising the following steps:

[0008] Obtain the user's original facial image, and identify the original facial image based on the feature model to obtain the monolid feature and facial features;

[0009] Obtain the user's ultrasonic eyelid thickness information;

[0010] The single eyelid features, facial features, and ultrasound eyelid thickness information were input into the generative neural network model to generate the postoperative single eyelid effect image;

[0011] The postoperative single eyelid effect image was superimposed on the original facial image to obtain the postoperative facial effect image;

[0012] Determine the surgical method for double eyelid surgery based on the postoperative facial effect image selected by the user and perform the double eyelid surgery;

[0013] The surgical procedure includes the soft hanging incision double eyelid method. When the soft hanging incision double eyelid method is determined to be used based on the postoperative facial effect image selected by the user, the double eyelid surgery includes incising the upper eyelid skin to the orbital septum, removing the orbital septum fat, suturing the medial orbicularis oculi muscle and the plethysmina, and using an electrocoagulation knife to excise and correct the tissue around the surgical suture line, and suturing the outer upper face skin.

[0014] In one embodiment, the feature model is obtained by training with a first training data set, and the training of the feature model is terminated when the loss value between the predicted recognition result output by the feature model and the actual recognition result meets a preset loss condition.

[0015] In one embodiment, the generative neural network model is obtained by training with a second training data set, and the training of the generative neural network model is terminated when the loss value between the postoperative single eyelid effect image generated by the generative neural network model and the postoperative single eyelid real image meets a preset loss condition.

[0016] In a second aspect, an embodiment of the present invention provides a device for softly suspending and symmetrically treating the levator aponeurosis of both eyes during double eyelid surgery, the device comprising:

[0017] A feature extraction module is used to obtain the user's original facial image and identify the original facial image based on the feature model to obtain the single eyelid feature and facial features;

[0018] An eyelid information acquisition module is used to obtain the user's ultrasonic eyelid thickness information;

[0019] A single eyelid effect image generation module is used to input single eyelid features, facial features, and ultrasonic eyelid thickness information into a generative neural network model to generate a postoperative single eyelid effect image;

[0020] A facial effect image generation module is used to superimpose the postoperative single eyelid effect image with the original facial image to obtain a postoperative facial effect image;

[0021] The surgery execution module is used to determine the surgical method of double eyelid surgery based on the postoperative facial effect image selected by the user and perform the double eyelid surgery;

[0022] The surgical procedure includes the soft hanging incision double eyelid method. When the soft hanging incision double eyelid method is determined to be used based on the postoperative facial effect image selected by the user, the surgical execution module is also used to incise the upper eyelid skin to the orbital septum, remove the orbital septum fat, suture the medial orbicularis oculi muscle and the plethysmina, and use an electrocoagulation knife to excise and correct the tissue around the surgical suture line, and suture the outer upper face skin.

[0023] In one embodiment, the feature model is obtained by training with a first training data set, and the training of the feature model is terminated when the loss value between the predicted recognition result output by the feature model and the actual recognition result meets a preset loss condition.

[0024] In one embodiment, the generative neural network model is obtained by training with a second training data set, and the training of the generative neural network model is terminated when the loss value between the postoperative single eyelid effect image generated by the generative neural network model and the postoperative single eyelid real image meets a preset loss condition.

[0025] In an embodiment, the user's original facial image is obtained, and the original facial image is recognized based on a feature model to obtain single eyelid features and facial features; the user's ultrasonic eyelid thickness information is obtained; the single eyelid features, facial features, and ultrasonic eyelid thickness information are input into a generative neural network model to generate a postoperative single eyelid effect image; the postoperative single eyelid effect image is superimposed with the original facial image to obtain a postoperative facial effect image; the double eyelid surgery procedure is determined based on the postoperative facial effect image selected by the user, and the double eyelid surgery is performed; the procedure includes the soft hanging incision double eyelid method, and when the soft hanging incision double eyelid method is determined based on the postoperative facial effect image selected by the user, the double eyelid surgery includes incising the upper eyelid skin to the orbital septum, removing the orbital septum fat, suturing the medial orbicularis oculi muscle and the plethysmia, and using an electrocoagulation knife to excise and correct the tissue around the surgical suture line, and suturing the outer upper facial skin. This method can realize the automated execution of double eyelid surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0027] Figure 1 This is a flow chart of a method for symmetrically processing the soft suspension of the levator aponeurosis of both eyes during double eyelid surgery provided in the first embodiment of the present invention;

[0028] Figure 1A This is the effect picture after suturing the medial orbicularis oculi muscle and the plethysmma during double eyelid surgery;

[0029] Figure 2 This is a structural diagram of a device for constructing a click-through rate prediction model provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0031] Double eyelid surgery, also known as blepharoplasty or double eyelid surgery, is one of the most common procedures in plastic surgery. Generally speaking, double eyelids visually enlarge the eye contour, add three-dimensionality, make the eye appear larger, and lift the eyelashes, giving a lively and expressive look. There are various surgical methods for double eyelid surgery, the most common of which are incisional and suture methods.

[0032] The incision method is suitable for single eyelids with thicker eyelids or more fat, and single eyelids with inconsistent eye sizes or ptosis. Compared with the buried suture method, it has the disadvantages of longer operation time and longer recovery period, but generally recovery can be achieved in 5-7 days. According to the tissue anatomical structure of the upper eyelid and the surgical method, the incision method can be divided into three categories: hard suspension, soft suspension, and semi-soft suspension. Among them, the soft suspension method is to suture the aponeurosis of the levator palpebrae superioris muscle to the muscle layer of the upper eyelid. When the eyes are open, the contraction of the levator palpebrae superioris muscle drives the muscle layer up, and the latter then drives the upper eyelid skin up to form a double eyelid. This suture is the connection between the muscle aponeurosis and the muscle, which is relatively soft and elastic.

[0033] The suture method is suitable for single eyelids with thin eyelid skin and thin orbicularis oculi muscles, and for single eyelids without Mongolian wrinkles and sagging eyelid skin. The disadvantage of buried suture double eyelid surgery is that the effect is short-lived.

[0034] With the application of medical robots in hospitals and clinics for medical or auxiliary medical treatment, people are gradually accepting that medical robots can perform or assist in surgery. However, there is currently no relevant automated equipment for double eyelid surgery.

[0035] To overcome the above problems or at least partially solve the above problems, the present invention provides a method for symmetrically treating the soft suspension of the levator palpebrae superioris aponeurosis of both eyes during double eyelid surgery, which can realize the automated execution of double eyelid surgery. Detailed description is given below through examples.

[0036] Example 1

[0037] Figure 1The present invention provides a method for symmetrically processing the soft suspension of the levator palpebrae superioris muscles during double eyelid surgery, which can be performed by a device for symmetrically processing the soft suspension of the levator palpebrae superioris muscles during double eyelid surgery. The method specifically includes the following steps:

[0038] Step 101: Obtain the original facial image of the user, and identify the original facial image based on a feature model to obtain monolid features and facial features.

[0039] The user's original facial image can be one or more images taken by photographic equipment, cameras, etc. of the user's face according to one or more predetermined perspectives. From the original facial image, single eyelid features and facial features can be obtained, such as the original image of the single eyelid, the width of the palpebral fissure, the distance between the eyebrows and eyes, the distance between the eyes, whether there are bags under the eyes, the height of the nose bridge, etc.

[0040] The feature model is obtained by training with a first training data set. When the loss value between the predicted recognition result output by the feature model and the actual recognition result meets a preset loss condition, the training of the feature model is terminated.

[0041] In one embodiment, it also includes obtaining a first training data set, and then using the first training data set to train the feature model. The first training data set includes original facial image samples and single eyelid feature samples and facial feature samples extracted or calculated by experts based on the original facial images, such as single eyelid original image samples, palpebral fissure width, eyebrow-eye distance, eye-to-eye distance, whether there are bags under the eyes, nose bridge height, etc. After obtaining the first training data set, the feature model can be trained based on the original facial image samples, single eyelid feature samples, and facial feature samples. When the loss value between the predicted recognition result output by the feature model and the actual recognition result meets the preset loss condition, the training of the feature model is terminated. The feature model is used to subsequently identify the original facial image to obtain single eyelid features and facial features.

[0042] Step 102: Obtain the user's ultrasonic eyelid thickness information.

[0043] High-frequency ultrasound can be used to measure the thickness of human skin, fat, muscle, etc. In one embodiment, the user's ultrasonic eyelid thickness information can be directly obtained through an ultrasonic instrument, or by identifying an ultrasonic image taken by an ultrasonic instrument.

[0044] Step 103: Input the single eyelid features, facial features, and ultrasonic eyelid thickness information into a generative neural network model to generate a postoperative single eyelid effect image.

[0045] After obtaining the single eyelid features, facial features, and ultrasonic eyelid thickness information, a postoperative single eyelid effect image can be generated by generating a neural network model.

[0046] The generative neural network model is obtained by training the second training data set. When the loss value between the postoperative single eyelid effect image generated by the generative neural network model and the postoperative single eyelid real image meets the preset loss condition, the training of the generative neural network model is terminated.

[0047] In one embodiment, it also includes obtaining a second training data set, and then using the second training data set to train the generative neural network model. The second training data set includes single eyelid feature samples, facial feature samples, ultrasonic eyelid thickness information samples, and postoperative single eyelid real image samples. After obtaining the second training data set, the generative neural network model can be trained based on the single eyelid feature samples, facial feature samples, ultrasonic eyelid thickness information samples, and postoperative single eyelid real image samples. When the loss value between the postoperative single eyelid effect image generated by the generative neural network model and the postoperative single eyelid real image meets the preset loss condition, the training of the generative neural network model is terminated. The generative neural network model is used to subsequently generate a single eyelid effect image based on the single eyelid features, facial features, and ultrasonic eyelid thickness information.

[0048] Step 104: Superimpose the postoperative single eyelid effect image with the original facial image to obtain a postoperative facial effect image.

[0049] After obtaining the postoperative single eyelid effect image, it can be superimposed with the original facial image to obtain the postoperative facial effect image. When superimposing, the corresponding positions of the single eyelid effect image and the original single eyelid image are first aligned before superimposing, thereby ensuring the fidelity of the superimposed postoperative facial effect image.

[0050] Step 105: Determine the double eyelid surgery procedure based on the postoperative facial effect image selected by the user, and perform the double eyelid surgery.

[0051] The procedure includes a soft hanging incision for double eyelid surgery. When the soft hanging incision is selected based on the user's selected postoperative facial image, the procedure involves incising the upper eyelid skin to the orbital septum, removing orbital fat, suturing the medial orbicularis oculi muscle to the plethysmia, and using an electrocoagulation knife to excise and correct the tissue surrounding the surgical suture line. The skin of the upper face is then sutured on the lateral side. Excision and correction of the tissue surrounding the surgical suture line using an electrocoagulation knife, such as by spot-treatment of excess tissue, can achieve symmetry in the double eyelids and improve the surgical outcome.

[0052] In one embodiment, the surgical procedures may also include hard hanging incision blepharoplasty, semi-soft hanging incision blepharoplasty, buried suture blepharoplasty, etc. The double eyelid surgery may be performed by a surgery execution module, such as a robot.

[0053] In an embodiment, the user's original facial image is obtained, and the original facial image is recognized based on a feature model to obtain single eyelid features and facial features; the user's ultrasonic eyelid thickness information is obtained; the single eyelid features, facial features, and ultrasonic eyelid thickness information are input into a generative neural network model to generate a postoperative single eyelid effect image; the postoperative single eyelid effect image is superimposed with the original facial image to obtain a postoperative facial effect image; the double eyelid surgery procedure is determined based on the postoperative facial effect image selected by the user, and the double eyelid surgery is performed; the procedure includes the soft hanging incision double eyelid method, and when the soft hanging incision double eyelid method is determined based on the postoperative facial effect image selected by the user, the double eyelid surgery includes incising the upper eyelid skin to the orbital septum, removing the orbital septum fat, suturing the medial orbicularis oculi muscle and the plethysmia, and using an electrocoagulation knife to excise and correct the tissue around the surgical suture line, and suturing the outer upper facial skin. This method can realize the automated execution of double eyelid surgery.

[0054] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0055] Example 2

[0056] Figure 2 The second embodiment of the present invention provides a device for symmetrically processing the soft suspension of the levator palpebrae superioris muscles in double eyelid surgery. The device for symmetrically processing the soft suspension of the levator palpebrae superioris muscles in double eyelid surgery may specifically include the following modules:

[0057] The feature extraction module 201 is used to obtain the original facial image of the user, and recognize the original facial image based on the feature model to obtain the monolid feature and facial features.

[0058] The eyelid information acquisition module 202 is used to obtain the user's ultrasonic eyelid thickness information.

[0059] The single eyelid effect image generation module 203 is used to input single eyelid features, facial features, and ultrasonic eyelid thickness information into a generative neural network model to generate a postoperative single eyelid effect image.

[0060] The facial effect image generation module 204 is used to superimpose the postoperative single eyelid effect image with the original facial image to obtain a postoperative facial effect image.

[0061] The surgery execution module 205 is used to determine the surgical procedure for double eyelid surgery based on the postoperative facial effect image selected by the user and perform the double eyelid surgery.

[0062] The surgical procedure includes the soft hanging incision double eyelid method. When the soft hanging incision double eyelid method is determined to be used based on the postoperative facial effect image selected by the user, the surgical execution module is also used to incise the upper eyelid skin to the orbital septum, remove the orbital septum fat, suture the medial orbicularis oculi muscle and the plethysmina, and use an electrocoagulation knife to excise and correct the tissue around the surgical suture line, and suture the outer upper face skin.

[0063] In one embodiment, the feature model is obtained by training with a first training data set, and the training of the feature model is terminated when the loss value between the predicted recognition result output by the feature model and the actual recognition result meets a preset loss condition.

[0064] In one embodiment, the apparatus further includes a first training data set acquisition module configured to acquire a first training data set. The first training data set includes original facial image samples and single eyelid feature samples extracted or calculated by experts based on the original facial images, as well as facial feature samples, such as single eyelid original image samples, palpebral fissure width, eyebrow-eye distance, distance between eyes, presence of under-eye bags, nose bridge height, and the like.

[0065] In one embodiment, the generative neural network model is obtained by training with a second training data set, and the training of the generative neural network model is terminated when the loss value between the postoperative single eyelid effect image generated by the generative neural network model and the postoperative single eyelid real image meets a preset loss condition.

[0066] In one embodiment, the device further includes a second training data set acquisition module configured to acquire a second training data set including single eyelid feature samples, facial feature samples, ultrasonic eyelid thickness information samples, and postoperative single eyelid real image samples.

[0067] The device for symmetrically processing the soft suspension of the levator palpebrae superioris muscle aponeurosis of both eyes during double eyelid surgery provided by an embodiment of the present invention can execute the method for symmetrically processing the soft suspension of the levator palpebrae superioris muscle aponeurosis of both eyes during double eyelid surgery provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0068] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A device for soft suspension and symmetrical treatment of the levator aponeurosis of both eyes during double eyelid surgery, characterized in that: include: A feature extraction module is used to obtain the user's original facial image and identify the original facial image based on the feature model to obtain the single eyelid feature and facial features; An eyelid information acquisition module is used to obtain the user's ultrasonic eyelid thickness information; A single eyelid effect image generation module is used to input single eyelid features, facial features, and ultrasonic eyelid thickness information into a generative neural network model to generate a postoperative single eyelid effect image; A facial effect image generation module is used to superimpose the postoperative single eyelid effect image with the original facial image to obtain a postoperative facial effect image; The surgery execution module is used to determine the surgical method of double eyelid surgery based on the postoperative facial effect image selected by the user and perform the double eyelid surgery; The surgical procedure includes the soft hanging incision double eyelid method. When the soft hanging incision double eyelid method is determined to be used based on the postoperative facial effect image selected by the user, the surgical execution module is also used to incise the upper eyelid skin to the orbital septum, remove the orbital septum fat, suture the medial orbicularis oculi muscle and the plethysmina, and use an electrocoagulation knife to excise and correct the tissue around the surgical suture line, and suture the outer upper face skin.

2. The device according to claim 1, characterized in that: The feature model is obtained by training with a first training data set. When the loss value between the predicted recognition result output by the feature model and the actual recognition result meets a preset loss condition, the training of the feature model is terminated.

3. The device according to claim 2, characterized in that Also includes: The first training data set acquisition module is used to acquire a first training data set.

4. The device according to claim 1, characterized in that: The generative neural network model is obtained by training the second training data set. When the loss value between the postoperative single eyelid effect image generated by the generative neural network model and the postoperative single eyelid real image meets the preset loss condition, the training of the generative neural network model is terminated.

5. The device according to claim 4, characterized in that Also includes: The second training data set acquisition module is used to acquire the second training data set.

Images