Method, device and program product for constructing enophthalmos pathology assessment model

Abstract

The present invention belongs to the field of intelligent medical treatment, and specifically relates to a method, device, and program product for constructing an enophthalmos lesion volume assessment model. The method comprises: obtaining an image set of an enophthalmos patient; annotating the image set to obtain the orbital tissue area boundaries of the healthy side and the affected side, wherein the orbital tissue includes the eyeball, orbital fat, and any one or more of the following: extraocular muscles, optic nerve, cornea, and lacrimal gland; extracting the orbital tissue volumes of the healthy side and the affected side based on the orbital tissue area boundaries, and calculating the orbital tissue volume changes of the affected and healthy sides; using the image set as a training data set, and the orbital tissue volume changes as a prediction target input into a neural network model, and obtaining an enophthalmos lesion volume assessment model after training. The present application takes into account the changes in the finely divided orbital tissue volume, and at the same time integrates the relative volume changes, so as to more accurately quantify the amount of enophthalmos lesions and achieve better correction effects after surgery.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical care, and more specifically, to a method, device, medium and program product for constructing an enophthalmos lesion volume assessment model. Background Art

[0002] Post-traumatic enophthalmos (PE) refers to the necrosis and adhesion of part of the orbital cavity due to injury, orbital tumor resection / radiotherapy, etc., which leads to the eyeball moving backward, outward and downward at the equator due to the loss of orbital volume and / or the increase of orbital cavity volume, resulting in the eyeball visually sinking and retracting. Currently, this condition is usually confirmed by the following diagnostic criteria in ophthalmological evaluation: (1) Clinical examination: using external observation and manual detection of the position of the eyeball; (2) Imaging examination: mainly using CT or MRI scans to evaluate the structural changes in the orbit and the relative position of the eyeball; (3) Quantitative measurement: using exophthalmometer to quantify the protrusion of the eyeball. Retraction outside the normal range is considered to be concave. It is generally believed that a retraction of more than 2 mm compared with the contralateral eyeball is clinically significant.

[0003] Currently, sunken eyes are usually treated by injecting fillers to correct the protrusion of the eyeball; at this time, a necessary technical problem is how to determine the amount of filler to be filled.

[0004] In the existing technology, CT imaging is used to assist in analyzing the orbital volume of patients with orbital bone fractures and to calculate the empirical formula for orbital volume filling and correction of eyeball protrusion. Studies have shown that there is a direct correlation between orbital volume and enophthalmos, mainly based on the relationship between the orbital volume ratio (OVR), that is, the ratio of the volume of the damaged orbit to the volume of the normal orbit and the degree of enophthalmos (PE), that is, the empirical formula method: the greater the increase in OV, the more severe the PE. On average, the OV increases by 1cm. 3 It will cause PE to increase by 0.80mm. This situation is mainly applicable to the eyeball sunken caused by orbital fractures leading to the increase of bony orbital volume. The filling amount at this time is determined according to the measured increase of bony orbital volume. The orbital cavity volume increases by 1cm. 3This will result in a reduction of approximately 0.8mm in eyeball extrusion. The injection volume is determined by estimating the degree of orbital volume increase based on the preoperative measurement of eyeball extrusion. However, scholars have also discovered the limitations of following empirical formulas: due to the large individual differences in eyeball depression, the variability between observers in clinical evaluation is greater than that in radiological evaluation, which has certain limitations and is more variable in clinical evaluation. At the same time, current technology relies on traditional formulas, which are difficult to adapt to complex trauma situations (surgery, radiotherapy, etc.) and are not suitable for patients with both bony orbital volume enlargement and orbital soft tissue atrophy. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method for constructing an enophthalmos volume change evaluation model. By accurately extracting the volume of orbital tissue that affects enophthalmos and simultaneously considering the changes in orbital volume and orbital tissue volume, a more accurate quantification of the ideal filling volume of the eye socket during filling treatment for patients with enophthalmos can be achieved.

[0006] The present application (first aspect) discloses a method for constructing an enophthalmos pathology assessment model, comprising:

[0007] S1: Acquire an image set of a patient with enophthalmos, wherein the image set includes images of the healthy eye and the affected eye; S2: Annotate the image set to obtain the boundaries of the orbital tissue regions of the healthy and affected sides, wherein the orbital tissue includes the eyeball, orbital fat, and any one or more of the following: extraocular muscles, optic nerve, cornea, and lacrimal gland;

[0008] S3: Based on the orbital tissue area boundary, the orbital tissue volumes of the healthy side and the affected side are extracted respectively, and the orbital tissue volume changes of the affected side and the healthy side are calculated;

[0009] S4: The image set is used as a training data set, and the orbital tissue volume change is used as a prediction target to input into a neural network model for training to obtain an enophthalmos lesion volume assessment model.

[0010] Furthermore, the extraocular muscles include one or more of the following: medial rectus muscle, lateral rectus muscle, superior rectus muscle, inferior rectus muscle, superior oblique muscle, and inferior oblique muscle.

[0011] Furthermore, the method also includes: performing three-dimensional reconstruction based on the image set and the annotated orbital tissue area boundaries to obtain the three-dimensional boundaries of the orbital tissue; extracting the orbital tissue volumes of the healthy side and the affected side based on the three-dimensional boundaries of the orbital tissue, and calculating the changes in the orbital tissue volumes of the affected side and the healthy side.

[0012] Furthermore, the method further comprises: marking the orbital boundary during labeling, extracting the orbital volume and orbital tissue volume of the healthy side and the affected side respectively based on the orbital boundary and the orbital tissue area boundary, and calculating the orbital volume change and orbital tissue volume change of the affected side and the healthy side;

[0013] Calculating the relative volume change between the affected side and the healthy side based on the orbital volume change and the orbital tissue volume change;

[0014] The image set is used as a training data set, and the relative volume change is used as a prediction target to input into a neural network model, and after training, an eye lesion relative volume change evaluation model is obtained.

[0015] Furthermore, the relative volume change is expressed as:

[0016] RVD=ΔV orbital -ΔV content

[0017] Where RVD represents the relative volume change, ΔV orbital Indicates the change in orbital volume; ΔV content represents the volume change of orbital tissue,

[0018] ΔV orbital The calculation method is expressed as:

[0019] ΔV orbital =V affected -V healthy

[0020] Where, ΔV orbital Indicates the change in orbital volume, V affected represents the orbital volume of the affected side, V healthy represents the orbital volume of the healthy side;

[0021] ΔV content The calculation method is expressed as:

[0022] ΔV content =V affected-content -V healthy-content

[0023] Where, ΔV content Indicates the volume change of orbital tissue, V affected V represents the volume of the orbital cavity tissue on the affected side. healthy represents the volume of orbital cavity tissue on the healthy side.

[0024] The second aspect of the present application discloses a system for constructing an enophthalmos pathology assessment model, comprising:

[0025] An acquisition module is used to acquire an image set of a patient with enophthalmos, wherein the image set includes images of the healthy side and the affected side of the eye socket;

[0026] Annotation module: used for annotating the image set to obtain the orbital tissue area boundaries of the healthy side and the affected side, wherein the orbital tissue includes the eyeball, orbital fat and any one or more of the following: extraocular muscles, optic nerve, cornea, and lacrimal gland;

[0027] Pathological volume calculation module: used to extract the orbital cavity tissue volumes of the healthy side and the affected side based on the orbital cavity tissue area boundary, and calculate the orbital cavity tissue volume changes of the affected side and the healthy side;

[0028] Model training module: used to use the image set as a training data set, and the orbital tissue volume change as a prediction target input into the neural network model to obtain an orbital tissue volume change evaluation model after training. The orbital tissue volume change evaluation model is an enophthalmos lesion volume evaluation model.

[0029] At the same time, this application discloses the application method of the constructed model:

[0030] A method for calculating the amount of intraocular lesions, characterized in that the method comprises:

[0031] Obtain images of patients with enophthalmos;

[0032] The image of the enophthalmos patient is input into any one of the above-mentioned enophthalmos lesion volume assessment models or any one of the above-mentioned enophthalmos lesion relative volume models to obtain the patient's enophthalmos lesion volume.

[0033] A method for calculating the filling amount for treating enophthalmos, characterized in that the method comprises:

[0034] The amount of enophthalmos in the patient is obtained based on the calculation method of the amount of intraocular lesions;

[0035] The filler volume during filling treatment is determined based on the volume of the enophthalmos lesion and the properties of the filler.

[0036] Furthermore, the method also includes: determining the volume of filler during filling treatment based on the change in the volume of the enophthalmos.

[0037] A third aspect of the present application discloses a computer device comprising: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute any step of the above-mentioned method for constructing a model for evaluating the amount of enophthalmos lesions, or the method for calculating the amount of endophthalmos lesions or the method for calculating the amount of filling for enophthalmos treatment.

[0038] In a fourth aspect, the present application discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements any step of the method for constructing an enophthalmos lesion amount assessment model described above, or the method for calculating the amount of intraocular lesions or the method for calculating the amount of filling for enophthalmos treatment.

[0039] In a fifth aspect, the present application discloses a computer program product, comprising a computer program, which, when executed by a processor, implements any step of the above-mentioned method for constructing a model for evaluating the change in volume of the enophthalmos, or a step of the method for calculating the volume of intraocular lesions or the method for calculating the filling amount for enophthalmos treatment.

[0040] This application has the following beneficial effects:

[0041] (1) Previous volumetric analyses of enophthalmos have not considered the impact of various orbital tissue volumes on enophthalmos. This application achieves precise quantification of orbital tissue volume by finely marking the tissues that affect enophthalmos, providing an accurate measurement of the filling amount for filling treatment surgery.

[0042] (2) Reconstructing orbital tissue based on fine annotations through 3D reconstruction technology makes the quantification of orbital tissue volume more accurate than image-delineated ROIs;

[0043] (3) In the past, only the changes in orbital volume were focused on in the treatment of enophthalmos. The enophthalmos caused by the changes in orbital volume was corrected by filling. The present application comprehensively considers the changes in orbital volume and the changes in the orbital cavity tissue, measures the changes in the relative volume of the orbit through bidirectional changes, and determines the filling amount during the filling treatment based on the changes in the relative volume. The quantification is more accurate and can achieve better correction effects after surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 This is a schematic diagram of the method flow provided by the first aspect of the embodiment of the present invention;

[0046] Figure 2 is a schematic diagram of a program product provided by the second aspect of an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0048] Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention;

[0049] Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention;

[0050] Figure 6A This is a schematic diagram of one step of 3D annotation provided by an embodiment of the present invention;

[0051] Figure 6B This is a schematic diagram of the second step of 3D annotation provided by an embodiment of the present invention;

[0052] Figure 6C This is a schematic diagram of step three of 3D annotation provided by an embodiment of the present invention;

[0053] Figure 6D This is a schematic diagram of a 3D annotation result provided by an embodiment of the present invention;

[0054] Figure 6E is a schematic diagram of a labeled reconstructed 3D image provided by an embodiment of the present invention;

[0055] Figure 7 This is a schematic diagram of marking orbital tissue provided by an embodiment of the present invention;

[0056] Figure 8 is a schematic diagram of an eyeball sunken image provided by an embodiment of the present invention;

[0057] Figure 9 is a schematic diagram of a volume measurement calculation provided by an embodiment of the present invention;

[0058] Figure 10 Schematic diagram of a reconstructed healthy orbit and an affected orbit provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0060] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0062] Figure 1 1 is a flow chart of a method for constructing an enophthalmos pathology estimation model provided by an embodiment of the present invention. Specifically, the method includes the following steps:

[0063] S101: Acquire an image set of an enophthalmos patient, wherein the image set includes images of the healthy side and the affected side of the eye socket;

[0064] S102: labeling the image set to obtain the orbital tissue area boundaries of the healthy side and the affected side, wherein the orbital tissue includes the eyeball, orbital fat, and any one or more of the following: extraocular muscles, optic nerve, cornea, and lacrimal gland;

[0065] S103: extracting the orbital cavity tissue volumes of the healthy side and the affected side based on the orbital cavity tissue region boundary, and calculating the orbital cavity tissue volume changes of the affected side and the healthy side;

[0066] S104: Using the image set as a training data set and the orbital tissue volume change as a prediction target, inputting the neural network model into the training to obtain a constructed enophthalmos lesion volume assessment model.

[0067] Currently, there are no reports at home or abroad on the application of precise tracing and quantitative assessment of orbital soft tissue volume based on CT / MRI data in the treatment of enophthalmos. The application of relevant soft tissue quantification is limited to non-traumatic diseases, such as patients with thyroid-associated eye disease. The characteristic of thyroid-associated orbitopathy (TAO) is proptosis due to increased volume of orbital fat and extraocular muscles.

[0068] Through clinical research on enophthalmos, the present applicant found that the core cause of enophthalmos deformity includes not only changes in orbital volume due to bony changes, but also changes in soft tissue volume within the orbital cavity due to trauma. Therefore, in order to further accurately evaluate the filling amount during filling treatment, the present applicant has done the following important work.

[0069] In some embodiments, we have innovatively manually traced more than 20 important orbital tissues (eyeball, optic nerve, extraocular muscles, etc.) ( Figure 7 As shown in the figure, we have completed the annotation of orbital soft tissue and calculation of orbital filling volume in 26 cases (26 eyes). Manual tracing took about 2 hours for each case and each eye, which was time-consuming. However, through manual tracing, we found that we have achieved accurate measurement of orbital soft tissue volume, and the obtained orbital filling volume is more in line with clinical reality.

[0070] The important orbital tissues related to sunken eyes include one or more of the following: extraocular muscles (6 on each side, for a total of 12), cornea (1 on each side, for a total of 2), optic nerve (1 on each side, for a total of 2), lacrimal gland (1 on each side, for a total of 2), eyeball (1 on each side, for a total of 2), and orbital fat (1 on each side, for a total of 2), totaling 22 types.

[0071] The extraocular muscles include the medial rectus, lateral rectus, superior rectus, inferior rectus, superior oblique, and inferior oblique muscles; there are 6 on each side, for a total of 12 on the left and right sides.

[0072] In some embodiments, the annotations include: eyeball, orbital fat.

[0073] In some embodiments, the annotations include: eyeball, orbital fat, cornea, optic nerve.

[0074] In some embodiments, the labels include: eyeball, orbital fat, cornea, optic nerve, lacrimal gland, eyeball.

[0075] In some embodiments, the labels include: cornea, optic nerve, lacrimal gland, eyeball, orbital fat.

[0076] In some embodiments, the labels include: cornea, optic nerve, lacrimal gland, eyeball, orbital fat, and extraocular muscles.

[0077] In some embodiments, the marking method is as follows Figure 7 As shown in the figure, the orbital tissues of the left eye and the right eye are marked respectively, with a total of 22 marked objects, such as Figure 7 As shown in Table 1:

[0078] Table 1 Orbital cavity tissue

[0079] Orbital tissue of the left eye Orbital tissue of the right eye Left eye lens / eyeball Right eye lens / eyeball Left optic nerve Right optic nerve Left tear gland Right lacrimal gland Left orbital fat Right orbital fat Left cornea Right cornea Left superior rectus muscle Right superior rectus muscle Left inferior rectus muscle Right inferior rectus muscle Left medial rectus muscle Right medial rectus muscle left lateral rectus muscle Right lateral rectus muscle Left superior oblique muscle Right superior oblique muscle Left inferior oblique muscle Right inferior oblique muscle

[0080] like Figure 6A 、6B 6C shows an example of annotation. We perform annotation on the CT image in the 3D reconstruction software. The annotated window is the upper left window, which displays the transverse section of the head image. The upper right window is the 3D window, which displays the reconstructed 3D image and orbital tissue after annotation. The lower left window displays the coronal section of the image.

[0081] After marking is completed, Figure 6D As shown, the 3D image corresponding to the CT image is obtained through 3D reconstruction, and the annotation is reflected in the reconstructed 3D image as follows: the annotated 3D orbital cavity tissue, and the annotated reconstructed 3D image can be seen by zooming in ( Figure 6E ) as shown.

[0082] In some embodiments, the proposed orbital filling volume is calculated based on the annotated reconstructed 3D image, wherein the calculation of the proposed filling volume only measures the difference in soft tissue volume between the affected side and the healthy side, and the calculation method is expressed as:

[0083] ΔV content =V affected-content -V healthy-content

[0084] Where, ΔV content Represents the volume change of orbital tissue, which is also our proposed filling volume, V affected V represents the volume of the orbital cavity tissue on the affected side. healthy represents the volume of orbital cavity tissue on the healthy side;

[0085] In some embodiments, the calculation of the proposed orbital cavity filling volume not only measures the difference in soft tissue volume between the affected and healthy sides, but also takes into account the difference in orbital volume caused by bony changes. In this case, the proposed orbital cavity filling volume is a relative volume change, expressed as:

[0086] RVD=ΔV orbital -ΔV content

[0087] Where RVD represents the relative volume change, ΔV orbital Indicates the change in orbital volume; ΔV content represents the volume change of orbital tissue, where

[0088] ΔV orbital The calculation method is expressed as:

[0089] ΔV orbital =V affected -V healthy

[0090] Where, ΔV orbital Indicates the change in orbital volume, V affected represents the orbital volume of the affected side, Vhealthy represents the orbital volume of the healthy side;

[0091] Since the above manual tracing is very slow, in order to improve the efficiency of extracting the orbital soft tissue volume by tracing, we use the image data of the completed manual tracing samples as the training set data, and the results of manual tracing as the output of the neural network to train the orbital soft tissue automatic segmentation model.

[0092] Then, we increased the sample size and first used the orbital soft tissue automatic segmentation model to preliminarily depict the orbital soft tissue to improve efficiency. Then, we manually corrected the orbital soft tissue depiction to reduce the depiction error and extract more simulated filling volume.

[0093] In some embodiments, in order to automatically extract the proposed filling volume, we use the image dataset as the training set data, and the extracted orbital tissue volume change as the label or training target of the deep learning model. After iterative training, we obtain a trained orbital tissue volume change model. The enophthalmos lesion volume assessment model we refer to here is this trained orbital tissue volume change model. The orbital tissue volume change model can output the orbital tissue volume change based on the newly input image of the enophthalmos patient, so that the doctor can determine the filling amount during filling treatment.

[0094] In some embodiments, the intended filling amount during treatment is the change in orbital tissue volume.

[0095] In some embodiments, we use the image dataset as the training set data, and the extracted orbital volume change as the label or training target of the deep learning model. After iterative training, a trained orbital volume change model is obtained. The enophthalmos lesion volume assessment model we refer to here is this trained orbital volume change model. The orbital volume change model can output the orbital volume change based on the newly input image of the enophthalmos patient, so that the doctor can determine the filling amount during filling treatment.

[0096] In some embodiments, the volume to be filled during treatment is the volume of the enophthalmos lesion, that is, the change in orbital volume.

[0097] Furthermore, the doctor can obtain the orbital tissue volume change and orbital volume change of the new patient to be tested based on the orbital tissue volume change model and the orbital volume change model, thereby obtaining the relative volume change of the orbit. The doctor determines the filling amount based on the relative volume change during filling treatment.

[0098] In some embodiments, the volume to be filled during treatment is the volume of the enophthalmos lesion, that is, the relative volume change.

[0099] In some embodiments, we use the image dataset as the training set data, and use the orbital relative volume change extracted from the training set data as the label or training target of the deep learning model. After iterative training, a trained orbital relative volume change model is obtained. The enophthalmos lesion volume assessment model we refer to here is this trained orbital relative volume change model. The orbital relative volume change model can output the orbital relative volume change based on the newly input image of the enophthalmos patient, so that the doctor can determine the filling amount during filling treatment.

[0100] In some embodiments, the volume to be filled during treatment is the volume of the enophthalmos lesion, that is, the relative volume change.

[0101] In some embodiments, due to different tolerances of patients to fillers and differences in the therapeutic effects of fillers, the actual filling amount used for treatment is obtained by correcting the lesion volume output by the model during actual treatment.

[0102] In this application, 3D digital technology is used to quantitatively analyze the volume of orbital soft tissue in patients with post-traumatic enophthalmos deformity, thereby achieving precise correction of enophthalmos deformity.

[0103] This study is based on the integration of medical and engineering cutting-edge technology. It innovatively applies a modified manual tracing and segmentation calculation method to quantitatively evaluate the pre-filled volume of the orbital cavity in patients with post-traumatic enophthalmos. It then trains a model to accurately correct enophthalmos caused by complex traumas such as training injuries or combat trauma. There have been no related reports at home or abroad.

[0104] For patients with complex post-traumatic enophthalmos deformity who have both orbital volume loss and orbital cavity volume enlargement, accurate quantitative filling can be achieved while predicting the treatment effect.

[0105] In some embodiments, the research methods include:

[0106] 1. Case collection: 80 patients (80 eyes) with post-traumatic enophthalmos deformity who required autologous particulate fat grafting were enrolled in the Department of Orbital Surgery, Department of Ophthalmology, the Third Medical Center, PLA General Hospital. The experimental group had the expected filling volume calculated using 3D quantification by digital manual tracing, while the control group had the expected filling volume calculated using the classical formula.

[0107] 2. Project Implementation:

[0108] Complete preoperative examination (orbital CT, MRI, visual acuity test, exophthalmos measurement, and accurate physical examination),

[0109] Preliminarily determine the location and range of eye adhesion, eye position, eye movement and degree of strabismus, and evaluate the visual acuity and visual function of the affected eye.

[0110] 3. Tracing method: Before and after surgery, 24 orbital structures, including the extraocular muscles, eyeball, and optic nerve, were manually traced and segmented using the VECTRA M3 3D Slicer based on CT Dicom data.

[0111] The volume of orbital soft tissue filling was quantitatively evaluated preoperatively.

[0112] 4. Reduce manual tracing errors: Three doctors with more than 10 years of clinical experience in orbital surgery manually traced the volume and took the average value (preliminary training).

[0113] In some embodiments, the training set and the volume corresponding to the marked orbital tissue structure are obtained through the above research, thereby calculating the change in the volume of the tissue in the affected orbit;

[0114] The training set images are input into the convolutional neural network to predict the change in the volume of the tissue in the orbital cavity on the affected side. The predicted value is compared with the measured value to reduce the error between the predicted value and the measured value for the optimization purpose. For example, the loss function adopts the MSE function, and the iteration is stopped after it is iterated and optimized for a certain number of times or the error is less than the expected value to obtain an eyeball sunken filling volume evaluation model. For new patients with eyeball sunken eyes, their eye images are input into the eyeball sunken filling volume evaluation model, and the estimated change in the volume of the tissue in the orbital cavity on the affected side is output. In the filling treatment of patients with orbital sunken eyes, the estimated change in the volume of the tissue in the orbital cavity on the affected side is used as the reference value for the surgical filling volume for treatment.

[0115] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device 2000 may include: one or more processors 2010, and one or more memories 2020; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, they may execute the method described above.

[0116] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, operations, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor can be a microprocessor or any conventional processor, etc., and can be an X86 architecture or an ARM architecture.

[0117] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented, as non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0118] For example, the method or apparatus according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as the ROM 3030 or the hard disk 3070, may store various data or files used for processing and / or communication of the method provided in the present disclosure, as well as program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0119] The embodiment of the present invention further provides a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium 4000 provided in an embodiment of the present invention, and computer-readable instructions 4010 are stored on the computer storage medium 4020. When the computer-readable instructions 4010 are executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0120] The present disclosure also provides a computer program product or a computer program, which implements the steps of the above method when executed by a processor, such as Figure 2 As shown, the computer program product or computer program includes:

[0121] Acquisition module 201: used to acquire an image set of a patient with enophthalmos, wherein the images in the image set include the orbits of the healthy side and the affected side;

[0122] Annotation module 202 is used to annotate the image set to obtain the orbital tissue area boundaries of the healthy side and the affected side, wherein the orbital tissue includes the eyeball, orbital fat, and any one or more of the following: extraocular muscles, optic nerve, cornea, and lacrimal gland;

[0123] The pathological volume calculation module 203 is used to extract the orbital tissue volumes of the healthy side and the affected side based on the orbital tissue region boundary, and calculate the orbital tissue volume changes of the affected side and the healthy side;

[0124] Model training module 204: used to input the image set as a training data set and the orbital tissue volume change as a prediction target into a neural network model to obtain a constructed enophthalmos lesion volume assessment model after training.

[0125] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0126] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented, as non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0127] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0129] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0131] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will appreciate that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for constructing an enophthalmos lesion assessment model, characterized in that: The method comprises: S1: obtaining an image set of a patient with enophthalmos, wherein the image set includes images of a healthy eye and an affected eye; S2: labeling the image set to obtain the orbital tissue area boundaries of the healthy side and the affected side, and labeling the orbital boundaries during labeling. The orbital tissue includes the eyeball, orbital fat, and any one or more of the following: extraocular muscles, optic nerve, cornea, and lacrimal gland; S3: extracting the orbital volume and orbital tissue volume of the healthy side and the affected side based on the orbital boundary and the orbital cavity tissue area boundary, respectively, and calculating the orbital volume change and orbital cavity tissue volume change of the affected side and the healthy side; and calculating the relative volume change between the affected side and the healthy side based on the orbital volume change and orbital cavity tissue volume change; S4: The image set is used as a training data set, and the relative volume change is used as a prediction target to input into a neural network model, and then a relative volume assessment model for enophthalmos lesions is obtained after training.

2. The method for constructing an enophthalmos lesion assessment model according to claim 1, characterized in that: The extraocular muscles include one or more of the following: medial rectus muscle, lateral rectus muscle, superior rectus muscle, inferior rectus muscle, superior oblique muscle, and inferior oblique muscle.

3. The method for constructing an enophthalmos lesion assessment model according to claim 1, characterized in that: The method further includes: performing three-dimensional reconstruction based on the image set and the annotated orbital cavity tissue region boundary to obtain the three-dimensional boundaries of the orbital cavity tissue; extracting the orbital cavity tissue volumes of the healthy side and the affected side based on the three-dimensional boundaries of the orbital cavity tissue, and calculating the orbital cavity tissue volume changes of the affected side and the healthy side.

4. The method for constructing an enophthalmos lesion assessment model according to claim 1, wherein: The orbital cavity tissue volume change is the difference between the orbital cavity tissue volumes of the healthy side and the affected side.

5. The method for constructing an enophthalmos lesion assessment model according to claim 1, wherein: The orbital cavity tissue volume change is expressed as: ΔV content =V affected-content -V healthy-content Where, ΔV content Indicates the volume change of orbital tissue, V affected V represents the volume of the orbital cavity tissue on the affected side. healthy represents the volume of orbital cavity tissue on the healthy side.

6. The method for constructing an enophthalmos lesion assessment model according to claim 1, wherein: The relative volume change is expressed as: RVD=ΔV orbital -ΔV content Where RVD represents the relative volume change, ΔV orbital Indicates the change in orbital volume; ΔV content Indicates the volume change of orbital tissue.

7. The method for constructing an enophthalmos lesion assessment model according to claim 1, characterized in that: The change in orbital volume is expressed as: ΔV orbital =V affected -V healthy Where, ΔV orbital Indicates the change in orbital volume, V affected represents the orbital volume of the affected side, V healthy represents the orbital volume of the healthy side.

8. A method for calculating the amount of enophthalmos, characterized in that: The method comprises: Obtain images of patients with enophthalmos; The image of the patient with enophthalmos is input into the enophthalmos lesion relative volume assessment model constructed by the method according to any one of claims 1 to 7 to obtain the patient's enophthalmos lesion volume.

9. A method for calculating the filling amount for enophthalmos treatment, characterized in that: The method comprises: Obtaining the amount of enophthalmos lesion of the patient according to the method of claim 8; The filler volume during filling treatment is determined based on the amount of enophthalmos and the properties of the filler.

10. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; and the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images