CN111833298B - Skeletal development grade detection method and terminal equipment - Google Patents
Skeletal development grade detection method and terminal equipment Download PDFInfo
- Publication number
- CN111833298B CN111833298B CN202010498270.5A CN202010498270A CN111833298B CN 111833298 B CN111833298 B CN 111833298B CN 202010498270 A CN202010498270 A CN 202010498270A CN 111833298 B CN111833298 B CN 111833298B
- Authority
- CN
- China
- Prior art keywords
- target
- classification result
- bone
- classification results
- target classification
- 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
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
Abstract
The invention is suitable for the technical field of bone age detection, and provides a bone development grade detection method and terminal equipment, wherein the bone development grade detection method comprises the following steps: acquiring a target bone image, inputting the target bone image into a bone development grade classification model for identification, and obtaining a plurality of classification results and confidence degrees corresponding to the classification results respectively; determining the reliability of the target classification result according to a first preset number of classification results with the confidence degrees ranked in the front and a target classification result with the highest confidence degree in the plurality of classification results; if the target classification result is reliable, determining a bone development grade corresponding to the target bone image according to the target classification result; and if the target classification result is unreliable, correcting the target classification result, and determining the bone development grade corresponding to the target bone image according to the corrected target classification result. The invention introduces a reliability judgment mechanism on the basis of the existing skeletal development grade classification model, and corrects the reliability judgment mechanism, thereby effectively improving the accuracy of skeletal development grade detection and being suitable for clinical application.
Description
Technical Field
The invention belongs to the technical field of bone age detection, and particularly relates to a bone development grade detection method and terminal equipment.
Background
The bone age is short for the bone age, and the bone age evaluation can accurately reflect the growth development level and the maturity of an individual. The method not only can determine the biological age of the children, but also can know the growth and development potential and the sexual maturity trend of the children as soon as possible through the bone age, also can predict the adult height of the children through the bone age, and the determination of the bone age also has great help for diagnosing some pediatric endocrine diseases.
With the development of computer vision technology, people try to adopt deep learning to realize intelligent identification of bone age in recent years. Compared with the traditional manual research and judgment method, the method has the advantages that the efficiency is greatly improved, but the clinical application requirements cannot be met in the aspect of precision.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and a terminal device for detecting bone development levels, so as to solve the problem that in the prior art, the accuracy of intelligent bone age identification by deep learning is not sufficient, and the requirements of clinical application cannot be met.
The first aspect of the embodiments of the present invention provides a method for detecting a skeletal development grade, including:
acquiring a target bone image, inputting the target bone image into a bone development grade classification model for identification, and obtaining a plurality of classification results and confidence degrees corresponding to the classification results respectively;
selecting a first preset number of classification results and target classification results from the multiple classification results; the first preset number of classification results is that the classification results of the previous first preset number are arranged in the plurality of classification results according to the sequence of the confidence degrees from large to small, and the target classification result is the classification result with the highest confidence degree in the plurality of classification results
Determining the reliability of the target classification result according to the classification results of the first preset number and the confidence coefficient of the target classification result;
if the target classification result is reliable, determining a bone development grade corresponding to the target bone image according to the target classification result;
and if the target classification result is unreliable, correcting the target classification result, and determining the bone development grade corresponding to the target bone image according to the corrected target classification result.
A second aspect of the embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the bone development level detection method as provided in the first aspect of the embodiments of the present invention.
A third aspect of the embodiments of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the bone development level detection method according to the first aspect of the embodiments of the present invention. The embodiment of the invention provides a skeletal development grade detection method, which comprises the following steps: acquiring a target bone image, inputting the target bone image into a bone development grade classification model for identification, and obtaining a plurality of classification results and confidence coefficients corresponding to the classification results respectively; determining the reliability of the target classification result according to a first preset number of classification results which are ranked in the front according to the sequence confidence degrees from big to small in the plurality of classification results and the target classification result with the highest confidence degree; if the target classification result is reliable, determining a bone development grade corresponding to the target bone image according to the target classification result; and if the target classification result is unreliable, correcting the target classification result, and determining the bone development grade corresponding to the target bone image according to the corrected target classification result. According to the bone age detection method, a reliability judgment mechanism is introduced on the basis of the existing bone age detection model and is corrected, so that the accuracy of bone age detection is effectively improved, the method is more suitable for clinical application, and the working efficiency of doctors is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a method for detecting skeletal development grade according to an embodiment of the present invention;
FIG. 2 is a schematic view of a human hand skeleton;
FIG. 3 is a schematic view of a skeletal development grade detection apparatus provided by an embodiment of the present invention;
fig. 4 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Referring to fig. 1, an embodiment of the present invention provides a method for detecting bone development levels, including:
step S101: acquiring a target bone image, inputting the target bone image into a bone development grade classification model for identification, and obtaining a plurality of classification results and confidence coefficients corresponding to the classification results respectively;
step S102: selecting a first preset number of classification results and target classification results from the multiple classification results; the first preset number of classification results is that the classification results of the previous first preset number are arranged in the plurality of classification results according to the sequence of the confidence degrees from large to small, and the target classification result is the classification result with the highest confidence degree in the plurality of classification results;
step S103: determining the reliability of the target classification result according to the classification results of the first preset number and the confidence coefficient of the target classification result;
step S104: if the target classification result is reliable, determining a bone development grade corresponding to the target bone image according to the target classification result;
step S105: and if the target classification result is unreliable, correcting the target classification result, and determining the bone development grade corresponding to the target bone image according to the corrected target classification result.
According to the bone development grade detection method provided by the embodiment of the invention, a reliability evaluation mechanism is introduced on the basis of the prior art bone age intelligent identification, a bone development grade classification model is adopted to identify a target bone image, and compared with the traditional method of outputting only one identification result, the method provided by the embodiment of the invention obtains a plurality of classification results identified by the bone development grade classification model and confidence degrees corresponding to the classification results respectively, and takes the classification result with the highest confidence degree as the target classification result, so as to judge the reliability of the target classification result. Furthermore, a correction mechanism is introduced in the embodiment of the invention, and if the target classification result is unreliable, the target classification result is corrected, so that the bone development grade corresponding to the target bone image is obtained. The bone development grade identification method provided by the embodiment of the invention has the advantages that the accuracy is effectively improved, the method is more suitable for clinical application, and the working efficiency of doctors is effectively improved. Wherein, the target bone image is an X-ray film of the bone to be detected.
In some embodiments, the classification result is a RUS-CHN bone age standard, and step S103 may include:
step S1031: determining whether the target classification result has a suffix;
step S1032: if the target classification result has no suffix, executing a first operation based on the classification results of the first preset number and the confidence coefficient of the target classification result to obtain the reliability of the target classification result;
step S1033: if the target classification result has a suffix, determining a target bone age standard;
step S1034: if the target bone age standard is the RUS-CHN bone age standard, executing a first operation based on a first preset number of classification results and the confidence coefficient of the target classification results to obtain the reliability of the target classification results;
step S1035: and if the target bone age standard is the TW3 bone age standard, executing a second operation based on the first preset number of classification results to obtain the reliability of the target classification result.
Currently, the international more common bone age standard is TW3 bone age standard, which is divided into 9 classes, including classes 0, 1, 2, 3, 4, 5, 6, 7, and 8. According to the current generation Chinese children as samples, a RUS-CHN bone age standard which is more suitable for the current generation children is provided, the standard is in contact with the international general method, is compatible with the TW3 bone age standard, and is divided into 15 grades comprising 0, 1, 2, 3, 4, 5-0, 5-2, 6, 7-0, 7-2, 8-0, 8-1, 8-2, 8-3 and 8-4 grades. Wherein, for example, 5-2 is a suffix level and the suffix is 2; 4 is no suffix rating.
Because the RUS-CHN bone age standard is compatible with the TW3 bone age standard, the RUS-CHN bone age standard is adopted to train a bone development grade classification model in the embodiment of the invention, the classification result is the RUS-CHN bone age standard, and the compatibility is higher. The target bone age standard is a standard of a bone development grade required to be output by a user, and can be an RUS-CHN bone age standard or a TW3 bone age standard. The level of the RUS-CHN bone age standard without a suffix can be common to the level of the TW3 bone age standard, and thus, it is first determined whether or not the target classification result has a suffix, and if no suffix is found, the same method can be applied regardless of the target bone age standard. If the target classification result has a suffix, the grades of the two grades of standards are not universal and are processed by different methods.
In some embodiments, the performing a first operation based on the first preset number of classification results and the confidence of the target classification result to obtain the reliability of the target classification result may include:
determining whether the confidence of the target classification result is greater than a confidence threshold;
if the confidence of the target classification result is greater than the confidence threshold, the target classification result is reliable;
if the confidence of the target classification result is not greater than the confidence threshold, determining whether the grades of the classification results of the first preset number are continuous;
if the grades of the first preset number of classification results are continuous, the target classification result is reliable;
if the grades of the first preset number of classification results are not continuous, the target classification result is unreliable.
The confidence threshold is obtained according to experience, and if the confidence of the target classification result is greater than the confidence threshold, the confidence of the target classification result is higher and more accurate, and the target classification result is reliable. And if the confidence coefficient of the target classification result is not high enough, judging that the target classification result is unreliable. Further, whether the grades of the first preset number of classification results are continuous or not is determined, for example, the first preset number may be 2, that is, the classification results of the first preset number are two grades with the highest confidence level and the next highest confidence level in the multiple classification results, if the two grades are continuous, it is indicated that the overall trends of the classification results are consistent, and the confidence level of the target classification result is higher, and it is determined that the target classification result is reliable.
In some embodiments, the performing the second operation based on the first preset number of classification results to obtain the reliability of the target classification result may include:
determining whether the levels of the first preset number of classification results are continuous;
if the grades of the first preset number of classification results are continuous, the target classification result is reliable;
if the grades of the first preset number of classification results are not continuous, the target classification result is unreliable.
In some embodiments, determining a bone development level corresponding to the target bone image according to the target classification result includes:
if the target bone age standard is the RUS-CHN bone age standard, taking the target classification result as a bone development grade corresponding to the target bone image;
if the target bone age standard is the TW3 bone age standard, determining whether the target classification result has a suffix;
if the target classification result has a suffix, removing the suffix of the target classification result and taking the removed suffix as a bone development grade corresponding to the target bone image;
and if the target classification result has no suffix, taking the target classification result as the bone development grade corresponding to the target bone image.
Since the TW3 bone age standard is broader than the RUS-CHN bone age standard, and the target classification result is the RUS-CHN bone age standard, if the bone development grade required by the user is the TW3 bone age standard, the target classification result of the RUS-CHN bone age standard can be directly used as the bone development grade of the TW3 bone age standard after the suffix is removed. For example, if the target bone development level is 8 to 3, the level 8 with the suffix 3 removed may be directly used as the bone development level of the target bone image.
In some embodiments, the same method may be used to determine the bone development level corresponding to the target bone image according to the corrected target classification result.
In some embodiments, the target bone is any one of thirteen metacarpophalangeal bones of a human hand, and the correcting the target classification result may include:
determining target classification results corresponding to twelve metacarpophalangeal bones except the target bone in the thirteen metacarpophalangeal bones;
and correcting the target classification result corresponding to the target bone image according to the target classification results corresponding to the twelve metacarpophalangeal bones.
In some embodiments, in order to improve the detection accuracy, the reliability of twelve metacarpophalangeal bones except for the target bone may be determined according to the methods in steps S101 to S103, and the target classification result corresponding to the target metacarpophalangeal bone is corrected by using the reliable metacarpophalangeal bones and the corresponding target classification result.
In some embodiments, correcting the target classification result corresponding to the target bone image according to the target classification results corresponding to the twelve metacarpophalangeal bones may include:
determining a first quantity of target classification results of the twelve metacarpophalangeal bones in a first grade range and a second quantity of target classification results in a second grade range;
if the first quantity is larger than the second quantity, selecting a second preset quantity of classification results from the plurality of classification results, and taking the classification result with the highest grade in the second preset quantity of classification results as a corrected target classification result; the second preset number of classification results is that the classification results of the previous second preset number are arranged in the plurality of classification results according to the sequence of confidence degrees from high to low;
if the first quantity is not larger than the second quantity, selecting a second preset quantity of classification results from the plurality of classification results, and taking the classification result with the lowest grade in the second preset quantity of classification results as a corrected target classification result;
wherein the second preset number is greater than the first preset number; the levels in the first range of levels are each greater than the levels in the second range of levels.
Referring to fig. 2, the bones of the human hand include 13 metacarpal phalanges, 1, radius, 2, ulna, 3, metacarpal bones I, 4, metacarpal bones III, 5, metacarpal bones V, 6, proximal phalanges I, 7, proximal phalanges III, 8, proximal phalanges V, 9, middle phalanges III, 10, middle phalanges V, 11, distal phalanges I, 12, distal phalanges III, and 13, distal phalanges V. Because the development of each skeleton of the human body is consistent, when the target classification result is unreliable, the target metacarpophalangeal bones can be corrected through the other twelve metacarpophalangeal bones, and the skeleton development grade trend of the twelve metacarpophalangeal bones is determined. Dividing the RUS-CHN bone age criteria into two parts, the first ranking range may include: 7-0, 7-2, 8-0, 8-1, 8-2, 8-3, 8-4, and the second rank range may include: 0, 1, 2, 3, 4, 5-0, 5-2 and 6, if the bone development grades of the twelve metacarpophalangeal bones are mostly in the first grade range, which indicates that the bone development of the person tends to be high grade, selecting the highest grade in the second preset number of classification results before the confidence degree ranking of the target bone image as a new target classification result; otherwise, if the skeleton development grades of the twelve metacarpophalangeal bones are mostly in the second grade range, the lowest grade in the second preset quantity of classification results is selected as the target classification result. For example, the second preset number may be 3, that is, the second preset number of classification results is 3 classification results with the highest confidence rank among the plurality of classification results.
In some embodiments, the first predetermined number is 2 and the second predetermined number is 3.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Referring to fig. 3, an embodiment of the present invention further provides a bone development grade detection apparatus, including:
the identification module 21 is configured to obtain a target bone image, input the target bone image into a bone development level classification model, and identify the target bone image to obtain a plurality of classification results and confidence levels corresponding to the plurality of classification results;
the parameter determining module 22 is used for selecting a first preset number of classification results and target classification results from the multiple classification results; the first preset number of classification results is that the classification results of the previous first preset number are arranged in the plurality of classification results according to the sequence of the confidence degrees from large to small, and the target classification result is the classification result with the highest confidence degree in the plurality of classification results
The reliability judging module 23 is configured to determine the reliability of the target classification result according to the first preset number of classification results and the confidence of the target classification result;
the first detection result determining module 24 is configured to determine, if the target classification result is reliable, a bone development level corresponding to the target bone image according to the target classification result;
and the second detection result determining module 25 is configured to correct the target classification result if the target classification result is unreliable, and determine a bone development level corresponding to the target bone image according to the corrected target classification result.
In some embodiments, the classification result is a RUS-CHN bone age standard, and the reliability determining module 23 may include:
suffix determination unit 231: determining whether the target classification result has a suffix;
the first judgment unit 232: if the target classification result has no suffix, executing a first operation based on the classification results of the first preset number and the confidence coefficient of the target classification result to obtain the reliability of the target classification result;
second determination section 233: if the target classification result has a suffix, determining a target bone age standard;
third judging unit 234: if the target bone age standard is the RUS-CHN bone age standard, executing a first operation based on a first preset number of classification results and the confidence coefficient of the target classification results to obtain the reliability of the target classification results;
fourth judging unit 235: and if the target bone age standard is the TW3 bone age standard, executing a second operation based on the first preset number of classification results to obtain the reliability of the target classification result.
In some embodiments, performing the first operation to obtain the reliability of the target classification result may include:
determining whether the confidence of the target classification result is greater than a confidence threshold;
if the confidence of the target classification result is greater than the confidence threshold, the target classification result is reliable;
if the confidence degree of the target classification result is not greater than the confidence degree threshold value, determining whether the levels of the classification results of the first preset number are continuous;
if the grades of the first preset number of classification results are continuous, the target classification result is reliable;
if the grades of the first preset number of classification results are not continuous, the target classification result is unreliable.
In some embodiments, performing the second operation to obtain the reliability of the target classification result may include:
determining whether the levels of the first preset number of classification results are continuous;
if the grades of the first preset number of classification results are continuous, the target classification result is reliable;
and if the grades of the classification results of the first preset number are not continuous, the target classification result is unreliable.
In some embodiments, the first detection result determining module 24 may include:
fifth judging unit 241: if the target bone age standard is the RUS-CHN bone age standard, taking the target classification result as a bone development grade corresponding to the target bone image;
sixth judging section 242: if the target bone age standard is the TW3 bone age standard, determining whether the target classification result has a suffix;
the seventh judging unit 243: if the target classification result has a suffix, removing the suffix of the target classification result and taking the removed suffix as a bone development grade corresponding to the target bone image;
eighth judging unit 244: and if the target classification result has no suffix, taking the target classification result as the bone development grade corresponding to the target bone image.
In some embodiments, the target bone is any one of thirteen metacarpophalangeal bones of the human hand, and the second detection result determining module 25 may include:
the auxiliary parameter determining unit 251 is used for determining target classification results corresponding to twelve metacarpophalangeal bones except the target bone in the thirteen metacarpophalangeal bones;
the correction unit 252: and correcting the target classification result corresponding to the target bone image according to the target classification results corresponding to the twelve metacarpophalangeal bones.
In some embodiments, the correction unit 252 may include:
rank range determination subunit 2521: determining a first quantity of target classification results of the twelve metacarpophalangeal bones in a first grade range and a second quantity of target classification results in a second grade range;
first judgment subunit 2522: if the first quantity is larger than the second quantity, selecting a second preset quantity of classification results from the plurality of classification results, and taking the classification result with the highest grade in the second preset quantity of classification results as a corrected target classification result; the second preset number of classification results is that the classification results of the previous second preset number are arranged in the plurality of classification results according to the sequence of the confidence degrees from high to low;
second determination subunit 2523: if the first quantity is not greater than the second quantity, selecting a second preset quantity of classification results from the multiple classification results, and taking the classification result with the lowest grade in the second preset quantity of classification results as a corrected target classification result;
the second preset number is larger than the first preset number; the levels in the first range of levels are each greater than the levels in the second range of levels.
In some embodiments, the first predetermined number is 2 and the second predetermined number is 3.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the foregoing division of each functional unit and module is merely used for illustration, and in practical applications, the foregoing function distribution may be performed by different functional units and modules as needed, that is, the internal structure of the terminal device is divided into different functional units or modules to perform all or part of the above-described functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned apparatus, reference may be made to the corresponding processes in the foregoing method embodiments, which are not described herein again.
Fig. 4 is a schematic block diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 4, the terminal device 4 of this embodiment includes: one or more processors 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processors 40. The processor 40, when executing the computer program 42, implements the steps in the above-described embodiments of the bone development level detection method, such as the steps S101 to S105 shown in fig. 1. Alternatively, the processor 40, when executing the computer program 42, implements the functions of the modules/units in the above-described embodiment of the bone development level detection apparatus, such as the functions of the modules 21 to 25 shown in fig. 3.
Illustratively, the computer program 42 may be divided into one or more modules/units, which are stored in the memory 41 and executed by the processor 40 to accomplish the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 42 in the terminal device 4. For example, the computer program 42 may be divided into the identification module 21, the parameter determination module 22, the reliability determination module 23, the first detection result determination module 24, and the second detection result determination module 25.
The identification module 21 is configured to obtain a target bone image, input the target bone image into a bone development level classification model, and identify the target bone image to obtain a plurality of classification results and confidence levels corresponding to the plurality of classification results;
the parameter determining module 22 is used for selecting a first preset number of classification results and target classification results from the multiple classification results; the first preset number of classification results is that the classification results of the previous first preset number are arranged in the plurality of classification results according to the sequence of the confidence degrees from large to small, and the target classification result is the classification result with the highest confidence degree in the plurality of classification results
The reliability judging module 23 is configured to determine the reliability of the target classification result according to the first preset number of classification results and the confidence of the target classification result;
the first detection result determining module 24 is configured to determine, if the target classification result is reliable, a bone development level corresponding to the target bone image according to the target classification result;
and the second detection result determining module 25 is configured to correct the target classification result if the target classification result is unreliable, and determine a bone development level corresponding to the target bone image according to the corrected target classification result.
Other modules or units are not described in detail herein.
The Processor 40 may be a Central Processing Unit (CPU), other 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, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 41 may be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The memory 41 may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal device. Further, the memory 41 may also include both an internal storage unit of the terminal device and an external storage device. The memory 41 is used for storing the computer program 42 and other programs and data required by the terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed terminal device and method may be implemented in other ways. For example, the above-described terminal device embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the embodiments described above may be implemented by a computer program, which is stored in a computer readable storage medium and used by a processor to implement the steps of the embodiments of the methods described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, software distribution medium, etc. It should be noted that the computer readable medium may include any suitable increase or decrease as required by legislation and patent practice in the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (8)
1. A bone development grade detection method is characterized by comprising the following steps:
acquiring a target bone image, inputting the target bone image into a bone development grade classification model for identification, and obtaining a plurality of classification results and confidence degrees corresponding to the classification results respectively;
selecting a first preset number of classification results and target classification results from the classification results; the first preset number of classification results is that the previous first preset number of classification results are arranged in the plurality of classification results according to the sequence of confidence degrees from large to small, and the target classification result is the classification result with the highest confidence degree in the plurality of classification results;
determining the reliability of the target classification result according to the classification results of the first preset number and the confidence coefficient of the target classification result;
if the target classification result is reliable, determining a bone development grade corresponding to the target bone image according to the target classification result;
if the target classification result is unreliable, correcting the target classification result, and determining a bone development grade corresponding to the target bone image according to the corrected target classification result;
the target skeleton is any one of thirteen metacarpophalangeal bones of a human hand, and the target classification result is corrected, wherein the target classification result comprises the following steps:
determining target classification results corresponding to twelve metacarpophalangeal bones except the target bone in the thirteen metacarpophalangeal bones;
correcting the target classification result corresponding to the target skeleton image according to the target classification results corresponding to the twelve metacarpophalangeal bones;
the correcting the target classification result corresponding to the target bone image according to the target classification results corresponding to the twelve metacarpophalangeal bones comprises the following steps:
determining a first quantity of target classification results of the twelve metacarpophalangeal bones in a first grade range and a second quantity of target classification results in a second grade range;
if the first quantity is larger than the second quantity, selecting a second preset quantity of classification results from the plurality of classification results, and taking a classification result with the highest grade in the second preset quantity of classification results as the corrected target classification result; the second preset number of classification results is that the classification results of the previous second preset number are arranged in the plurality of classification results according to the sequence of confidence degrees from high to low;
if the first quantity is not greater than the second quantity, selecting a second preset quantity of classification results from the plurality of classification results, and taking a classification result with the lowest grade in the second preset quantity of classification results as the corrected target classification result;
wherein the second preset number is greater than the first preset number; the levels in the first range of levels are each greater than the levels in the second range of levels.
2. The method as claimed in claim 1, wherein the step of determining the reliability of the target classification result according to the first predetermined number of classification results and the confidence of the target classification result comprises:
determining whether the target classification result has a suffix;
if the target classification result has no suffix, executing a first operation based on the first preset number of classification results and the confidence of the target classification result to obtain the reliability of the target classification result;
if the target classification result has a suffix, determining a target bone age standard;
if the target bone age standard is the RUS-CHN bone age standard, executing a first operation based on the classification results of the first preset number and the confidence coefficient of the target classification results to obtain the reliability of the target classification results;
and if the target bone age standard is the TW3 bone age standard, executing a second operation based on the first preset number of classification results to obtain the reliability of the target classification result.
3. The method as claimed in claim 2, wherein the performing a first operation based on the first predetermined number of classification results and the confidence level of the target classification result to obtain the reliability of the target classification result comprises:
determining whether a confidence of the target classification result is greater than a confidence threshold;
if the confidence coefficient of the target classification result is greater than the confidence coefficient threshold value, the target classification result is reliable;
if the confidence of the target classification result is not greater than the confidence threshold, determining whether the grades of the first preset number of classification results are continuous;
if the grades of the first preset number of classification results are continuous, the target classification result is reliable;
and if the grades of the first preset number of classification results are not continuous, the target classification result is unreliable.
4. The method as claimed in claim 2, wherein the performing a second operation based on the first predetermined number of classification results to obtain the reliability of the target classification result comprises:
determining whether the levels of the first preset number of classification results are continuous;
if the grades of the first preset number of classification results are continuous, the target classification result is reliable;
and if the grades of the first preset number of classification results are not continuous, the target classification result is unreliable.
5. The bone development level detection method according to claim 2, wherein the determining the bone development level corresponding to the target bone image according to the target classification result comprises:
if the target bone age standard is the RUS-CHN bone age standard, taking the target classification result as a bone development grade corresponding to the target bone image;
if the target bone age standard is the TW3 bone age standard, determining whether the target classification result has a suffix;
if the target classification result has a suffix, removing the suffix of the target classification result to be used as a bone development grade corresponding to the target bone image;
and if the target classification result has no suffix, taking the target classification result as the bone development grade corresponding to the target bone image.
6. The method of claim 1, wherein the first predetermined number is 2 and the second predetermined number is 3.
7. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the bone development level detection method according to any one of claims 1 to 6.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the bone development level detection method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010498270.5A CN111833298B (en) | 2020-06-04 | 2020-06-04 | Skeletal development grade detection method and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010498270.5A CN111833298B (en) | 2020-06-04 | 2020-06-04 | Skeletal development grade detection method and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111833298A CN111833298A (en) | 2020-10-27 |
| CN111833298B true CN111833298B (en) | 2022-08-19 |
Family
ID=72898375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010498270.5A Active CN111833298B (en) | 2020-06-04 | 2020-06-04 | Skeletal development grade detection method and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111833298B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115274098B (en) * | 2022-08-19 | 2023-04-07 | 北京咯咯网络科技有限公司 | Intelligent system for predicting height based on bone age and height |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463199A (en) * | 2014-11-28 | 2015-03-25 | 福州大学 | Rock fragment size classification method based on multiple features and segmentation recorrection |
| CN107766373A (en) * | 2016-08-19 | 2018-03-06 | 阿里巴巴集团控股有限公司 | The determination method and its system of the affiliated classification of picture |
| CN108921040A (en) * | 2018-06-08 | 2018-11-30 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium, electronic equipment |
| WO2019051814A1 (en) * | 2017-09-15 | 2019-03-21 | 达闼科技（北京）有限公司 | Target recognition method and apparatus, and intelligent terminal |
| CN110009605A (en) * | 2019-03-21 | 2019-07-12 | 浙江工业大学 | A kind of stone age prediction technique and system based on deep learning |
| CN110110600A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | The recognition methods of eye OCT image lesion, device and storage medium |
| CN110458107A (en) * | 2019-08-13 | 2019-11-15 | 北京百度网讯科技有限公司 | Method and apparatus for image recognition |
| CN110503624A (en) * | 2019-07-02 | 2019-11-26 | 平安科技（深圳）有限公司 | Stone age detection method, system, equipment and readable storage medium storing program for executing |
| CN110782450A (en) * | 2019-10-31 | 2020-02-11 | 北京推想科技有限公司 | Hand carpal development grade determining method and related equipment |
| CN111178428A (en) * | 2019-12-27 | 2020-05-19 | 上海联影智能医疗科技有限公司 | Cartilage damage classification method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147851B (en) * | 2010-02-08 | 2014-06-04 | 株式会社理光 | Device and method for judging specific object in multi-angles |
-
2020
- 2020-06-04 CN CN202010498270.5A patent/CN111833298B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463199A (en) * | 2014-11-28 | 2015-03-25 | 福州大学 | Rock fragment size classification method based on multiple features and segmentation recorrection |
| CN107766373A (en) * | 2016-08-19 | 2018-03-06 | 阿里巴巴集团控股有限公司 | The determination method and its system of the affiliated classification of picture |
| WO2019051814A1 (en) * | 2017-09-15 | 2019-03-21 | 达闼科技（北京）有限公司 | Target recognition method and apparatus, and intelligent terminal |
| CN108921040A (en) * | 2018-06-08 | 2018-11-30 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium, electronic equipment |
| CN110009605A (en) * | 2019-03-21 | 2019-07-12 | 浙江工业大学 | A kind of stone age prediction technique and system based on deep learning |
| CN110110600A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | The recognition methods of eye OCT image lesion, device and storage medium |
| CN110503624A (en) * | 2019-07-02 | 2019-11-26 | 平安科技（深圳）有限公司 | Stone age detection method, system, equipment and readable storage medium storing program for executing |
| CN110458107A (en) * | 2019-08-13 | 2019-11-15 | 北京百度网讯科技有限公司 | Method and apparatus for image recognition |
| CN110782450A (en) * | 2019-10-31 | 2020-02-11 | 北京推想科技有限公司 | Hand carpal development grade determining method and related equipment |
| CN111178428A (en) * | 2019-12-27 | 2020-05-19 | 上海联影智能医疗科技有限公司 | Cartilage damage classification method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| "无人车基于三维点云场景理解的语义地图构建";常欢;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170315;论文第3-4章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111833298A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741309B (en) | Bone age prediction method and device based on deep regression network | |
| CN108056786B (en) | Bone age detection method and device based on deep learning | |
| CN103440421B (en) | medical data processing method and system | |
| CN109146891B (en) | Hippocampus segmentation method and device applied to MRI and electronic equipment | |
| CN109993227B (en) | Method, system, apparatus and medium for automatically adding international disease classification code | |
| CN110619332B (en) | Data processing method, device and equipment based on visual field inspection report | |
| CN111738302A (en) | System for classifying and diagnosing Alzheimer disease based on multi-modal data | |
| CN110111905B (en) | Construction system and construction method of medical knowledge map | |
| CN111833298B (en) | Skeletal development grade detection method and terminal equipment | |
| CN111460991A (en) | Anomaly detection method, related device and readable storage medium | |
| CN110706200B (en) | Data prediction method and device | |
| CN109545370B (en) | Disease type determining method and device based on sample processing and terminal | |
| CN111883222A (en) | Text data error detection method and device, terminal equipment and storage medium | |
| CN114343577A (en) | Cognitive function evaluation method, terminal device, and computer-readable storage medium | |
| CN114117053A (en) | Disease classification model training method and device, storage medium and electronic device | |
| CN111582366B (en) | Image processing method, device and equipment | |
| CN111481208B (en) | Auxiliary system, method and storage medium applied to joint rehabilitation | |
| WO2021030868A1 (en) | A method and a system for determining a likelihood of presence of arthritis in a hand of a patient | |
| CN116704591A (en) | Eye axis prediction model training method, eye axis prediction method and device | |
| CN112447302B (en) | Height growth speed evaluation method and terminal equipment | |
| CN112545493B (en) | Height evaluation method and terminal equipment | |
| CN115631823A (en) | Similar case recommendation method and system | |
| CN115205954A (en) | Eye disease identification method, device and equipment | |
| CN112465104A (en) | Height development evaluation method and terminal equipment | |
| CN112734701A (en) | Fundus focus detection method, fundus focus detection device and terminal equipment |
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 |