CN117609748A - System and method for evaluating reasoning effect of medical image key point detection model - Google Patents
System and method for evaluating reasoning effect of medical image key point detection model Download PDFInfo
- Publication number
- CN117609748A CN117609748A CN202410063618.6A CN202410063618A CN117609748A CN 117609748 A CN117609748 A CN 117609748A CN 202410063618 A CN202410063618 A CN 202410063618A CN 117609748 A CN117609748 A CN 117609748A
- Authority
- CN
- China
- Prior art keywords
- value
- medical image
- data
- coordinate
- key point
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 230000000694 effects Effects 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 65
- 238000011156 evaluation Methods 0.000 claims abstract description 21
- 238000012423 maintenance Methods 0.000 claims description 21
- 230000007423 decrease Effects 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 210000002411 hand bone Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000010972 statistical evaluation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Abstract
The invention discloses a system and a method for evaluating the reasoning effect of a medical image key point detection model, relates to the technical field of the evaluation of the reasoning effect of the medical image key point detection model, and solves the problems that the calculation of the maximum value, the minimum value, the mean value and the standard deviation SD of the distance error between the coordinate reasoning value and the coordinate standard value of the medical image sample key point detection model is not supported in the prior art, and the calculation of the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value of a certain point key model in the medical image sample is not supported, and the correlation between the coordinate reasoning value and the coordinate standard value of the model is obtained through calculation, so that whether the model has good performance is judged.
Description
Technical Field
The invention relates to the technical field of medical image key point detection model reasoning effect evaluation, in particular to a system and a method for evaluating a medical image key point detection model reasoning effect.
Background
The medical image key point detection has important significance in medical auxiliary diagnosis and operation navigation, the key points in the medical image are accurately detected, the diagnosis accuracy and the operation accuracy are improved, the traditional medical image key point detection model cannot carry out statistical evaluation on the reasoning effect while reasoning, and therefore the development of a system capable of accurately carrying out the reasoning effect evaluation of the medical image key point detection model is urgent.
The existing medical image key point detection technology only predicts key points in medical images, such as a medical image key point detection method and a medical image key point detection system based on an improved neural network, the invention of which is disclosed as CN113450328A, provides a medical image key point detection method, the invention of which is disclosed as a hand bone X-ray film medical image key point positioning method and a hand bone X-ray film medical image key point positioning system, and the invention of which is disclosed as CN 115631185A. The inference effect of the model is not evaluated in the aspect of statistics, and the problems of calculating the maximum value, the minimum value, the mean value and the standard deviation SD of the distance error between the coordinate inference value and the coordinate standard value of the detection model of the key point of the medical image sample and calculating the intra-group correlation coefficient ICC between the coordinate inference value and the coordinate standard value of the detection model of a certain key point in the medical image sample are solved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a system and a method for evaluating the reasoning effect of a medical image key point detection model, which solve the problems of calculating the maximum value, the minimum value, the mean value and the standard deviation SD of the distance error between the coordinate reasoning value and the coordinate standard value of the key point detection model of a medical image sample and calculating the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample in the prior art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the system for evaluating the reasoning effect of the medical image key point detection model is composed of a general background end, and is characterized in that the general background end is composed of a data acquisition template maintenance module, a data acquisition module, a calculation method maintenance module, a calculation evaluation result module, a user management module and a role management module, wherein the data acquisition template maintenance module is used for determining the format of data to be verified represented by the data acquisition template by a user, the data acquisition module is used for importing the data to be verified into the system after the user prepares the data to be verified according to the format of the data acquisition template, the calculation method maintenance module is used for maintaining a calculation method of the system by the administrator, the calculation evaluation result module is used for calculating the data to be verified by the user, the user management module is used for increasing and decreasing the user by the administrator, setting the user name, resetting the user password and the role management module is used for giving the role to the user by the administrator, and the user obtains the use authority of the system through the obtained role.
Preferably, the data acquisition template maintenance module is composed of a data acquisition template management unit, the data acquisition template management unit is a format used for determining data to be verified represented by a data acquisition template by a user, the format comprises the number n of key points of each sample in medical image samples, the total number s of the medical image samples and the name of the data acquisition template, columns in the format are represented by CM1x, CM1y, CT1x, CT1y, S.A. CMnx, CMny, CTnx, CTny, n E {1,2,3.. N } and represent inferred x coordinate values inferred by an nth key point model in the medical image samples, inferred y coordinate values and standard x coordinate values marked by an nth key point doctor, the standard y coordinate values, the number of rows in the format are equal to the total number of the medical image samples, namely, each medical image is one sample.
Preferably, the data acquisition module consists of a data acquisition and importing unit and an imported data query unit;
the data acquisition and importing unit is used for importing the data to be verified into the system after a user prepares the data to be verified according to the format of the data acquisition template;
the imported data query unit is used for querying the data to be verified which is imported into the system by a user, and confirming that the data to be verified meets the requirements.
Preferably, the computing method maintenance module is composed of a computing method management unit, wherein the computing method management unit is a computing method used by an administrator for maintaining a system, and is internally provided with a computing method of a maximum value, a minimum value, a mean value and a standard deviation SD of a distance error between a coordinate reasoning value and a coordinate standard value of a key point detection model of a medical image sample and an ICC computing method of a group correlation coefficient between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample;
the distance error calculating method comprises the following steps:
psn is the error value of the nth key point of the s-th medical image sample, CTnx is the standard X-coordinate value of the nth key point, CMnx is the standard Y-coordinate value of the nth key point, CTny is the standard Y-coordinate value of the nth key point, and CMny is the standard Y-coordinate value of the nth key point;
the error maximum value calculating method comprises the following steps: p (P) MAXS =MAX(P s1 ，P s2 ，P s3 .. Psn), psn is the error value of the nth key point of the s-th medical image sample;
the error minimum value calculating method comprises the following steps: p (P) MINS =MIN(P s1 ，P s2 ，P s3 .. Psn), psn is the error value of the nth key point of the s-th medical image sample;
the error average value calculating method comprises the following steps:
psn is the error value of the nth key point of the s-th medical image sample, s is the total number of medical image samples;
error standard deviation SD calculation method:
wherein P is SDn The standard deviation of the error value of the nth key point of the s-th medical image sample is the error value of the nth key point of the s-th medical image sample,the error mean value of the nth key point is used, and s is the total number of medical image samples;
the method for calculating the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value comprises the following steps:
MS R mean square of line variable in data to be verified, MS C Mean square of column variables in data to be verified, MS E And the error in the data to be verified is mean square, and s is the total number of medical image samples.
Preferably, the calculation evaluation result module is composed of a calculation evaluation result unit, and the calculation evaluation result unit is used for calculating the data to be verified by a user to obtain an error standard deviation SD of the data to be verified; and obtaining the intra-group correlation coefficient ICC of the data to be verified, determining the correlation between the coordinate reasoning value and the coordinate standard value, and when ICC is more than 0.75, having statistical significance, highly correlating the data, having better repeatability and effectively modeling.
Preferably, the user management module is composed of a user management unit, and the user management unit is used by an administrator for increasing and decreasing users, setting user names and resetting user passwords.
Preferably, the role management module is composed of a role management unit, wherein the role management unit is used for giving roles to users by an administrator, and the users acquire the system use rights through the obtained roles; and maintaining the system use authority of the role.
Firstly, an administrator increases and decreases users, sets user names and resets user passwords;
the administrator gives the user a role, and the user obtains the system use authority through the obtained role; maintaining the system use authority of the role;
a user logs in the system to determine the format of data to be verified, which is represented by the data acquisition template;
importing data to be verified, and importing the data to be verified into a system after preparing the data to be verified according to the format of a data acquisition template;
confirming a calculation method, checking a distance error maximum value, a minimum value, a mean value and a standard deviation SD calculation method between a coordinate reasoning value and a coordinate standard value of a built-in medical image sample key point detection model, and checking an intra-group correlation coefficient ICC calculation method between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample;
calculating an evaluation result, verifying the data to be verified by using a calculation method in a calculation method maintenance module to obtain an error standard deviation SD of the data to be verified, and determining the discrete degree of an inference result; and obtaining the intra-group correlation coefficient ICC of the data to be verified, determining the correlation between the coordinate reasoning value and the coordinate standard value, and when ICC is more than 0.75, having statistical significance, highly correlating the data, having better repeatability and effectively modeling.
Advantageous effects
The invention provides a system and a method for evaluating the reasoning effect of a medical image key point detection model, which solve the problems of calculating the maximum value, the minimum value, the mean value and the standard deviation SD of the distance error between the coordinate reasoning value and the coordinate standard value of the medical image sample key point detection model and calculating the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample by adopting a statistical method.
Drawings
Fig. 1 is a schematic diagram of a system and a method for evaluating the reasoning effect of a medical image key point detection model.
Detailed Description
In order to further illustrate the technical means and effects adopted for the purposes of the present invention, the technical solutions of the inventive embodiments will be clearly and completely described below with reference to the drawings in the inventive embodiments, and it is apparent that the described embodiments are only some embodiments, but not all embodiments of the inventive embodiments, and the detailed description will follow.
Referring to fig. 1, the present invention provides a technical solution: aiming at the defects of the prior art, the invention provides a system and a method for evaluating the reasoning effect of a medical image key point detection model, which solve the problems of calculating the maximum value, the minimum value, the mean value and the standard deviation SD of the distance error between the coordinate reasoning value and the coordinate standard value of the medical image sample key point detection model and calculating the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
the system for evaluating the reasoning effect of the medical image key point detection model is composed of a general background end, and is characterized in that the general background end is composed of a data acquisition template maintenance module, a data acquisition module, a calculation method maintenance module, a calculation evaluation result module, a user management module and a role management module, wherein the data acquisition template maintenance module is used for determining the format of data to be verified represented by the data acquisition template by a user, the data acquisition module is used for importing the data to be verified into the system after the user prepares the data to be verified according to the format of the data acquisition template, the calculation method maintenance module is used for maintaining a calculation method of the system by the administrator, the calculation evaluation result module is used for calculating the data to be verified by the user, the user management module is used for increasing and decreasing the user by the administrator, setting the user name, resetting the user password and the role management module is used for giving the role to the user by the administrator, and the user obtains the use authority of the system through the obtained role.
The data acquisition template maintenance module is further configured to be composed of a data acquisition template management unit, wherein the data acquisition template management unit is a format for determining data to be verified represented by a data acquisition template by a user, the format comprises the number n of key points of each sample in medical image samples, the total number s of the medical image samples and the name of the data acquisition template, columns in the format are represented by CM1x, CM1y, CT1x, CT1y, n epsilon {1,2,3.
The embodiment is further configured that the data acquisition module is composed of a data acquisition and import unit and an imported data query unit;
the data acquisition and importing unit is used for importing the data to be verified into the system after a user prepares the data to be verified according to the format of the data acquisition template;
the imported data query unit is used for querying the data to be verified which is imported into the system by a user, and confirming that the data to be verified meets the requirements.
The embodiment is further configured that the calculation method maintenance module is composed of a calculation method management unit, wherein the calculation method management unit is a calculation method used by an administrator for maintaining a system, and is internally provided with a maximum value, a minimum value, a mean value and a standard deviation SD calculation method of a distance error between a coordinate reasoning value and a coordinate standard value of a key point detection model of a medical image sample and an intra-group correlation coefficient ICC calculation method between the coordinate reasoning value and the coordinate standard value of a certain key point detection model of the medical image sample;
the distance error calculating method comprises the following steps:
psn is the error value of the nth key point of the s-th medical image sample, CTnx is the standard X-coordinate value of the nth key point, CMnx is the standard Y-coordinate value of the nth key point, CTny is the standard Y-coordinate value of the nth key point, and CMny is the standard Y-coordinate value of the nth key point;
the error maximum value calculating method comprises the following steps: p (P) MAXS =MAX(P s1 ，P s2 ，P s3 .. Psn), psn is the error value of the nth key point of the s-th medical image sample;
the error minimum value calculating method comprises the following steps: p (P) MINS =MIN(P s1 ，P s2 ，P s3 .. Psn), psn is the error value of the nth key point of the s-th medical image sample;
the error average value calculating method comprises the following steps:
psn is the error value of the nth key point of the s-th medical image sample, s is the total number of medical image samples;
error standard deviation SD calculation method:
wherein P is SDn The standard deviation of the error value of the nth key point of the s-th medical image sample is the error value of the nth key point of the s-th medical image sample,the error mean value of the nth key point is used, and s is the total number of medical image samples;
the method for calculating the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value comprises the following steps:
MS R mean square of line variable in data to be verified, MS C Mean square of column variables in data to be verified, MS E And the error in the data to be verified is mean square, and s is the total number of medical image samples.
The embodiment is further configured that the calculation evaluation result module is composed of a calculation evaluation result unit, and the calculation evaluation result unit is used for calculating data to be verified by a user to obtain an error standard deviation SD of the data to be verified; and obtaining the intra-group correlation coefficient ICC of the data to be verified, determining the correlation between the coordinate reasoning value and the coordinate standard value, and when ICC is more than 0.75, having statistical significance, highly correlating the data, having better repeatability and effectively modeling.
The embodiment is further configured that the user management module is composed of a user management unit, and the user management unit is used by an administrator to increase and decrease users, set user names, and reset user passwords.
The embodiment is further configured that the role management module is composed of a role management unit, wherein the role management unit is used by an administrator to give a role to a user, and the user obtains the system use authority through the obtained role; and maintaining the system use authority of the role.
Firstly, an administrator increases and decreases users, sets user names and resets user passwords;
the administrator gives the user a role, and the user obtains the system use authority through the obtained role; maintaining the system use authority of the role;
a user logs in the system to determine the format of data to be verified, which is represented by the data acquisition template;
importing data to be verified, and importing the data to be verified into a system after preparing the data to be verified according to the format of a data acquisition template;
confirming a calculation method, checking a distance error maximum value, a minimum value, a mean value and a standard deviation SD calculation method between a coordinate reasoning value and a coordinate standard value of a built-in medical image sample key point detection model, and checking an intra-group correlation coefficient ICC calculation method between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample;
calculating an evaluation result, verifying the data to be verified by using a calculation method in a calculation method maintenance module to obtain an error standard deviation SD of the data to be verified, and determining the discrete degree of an inference result; and obtaining the intra-group correlation coefficient ICC of the data to be verified, determining the correlation between the coordinate reasoning value and the coordinate standard value, and when ICC is more than 0.75, having statistical significance, highly correlating the data, having better repeatability and effectively modeling.
A system for medical image keypoint detection model inference effect assessment provides significant improvements and advantages over the prior art in a number of respects. The following are specific improvements to the shortcomings of conventional systems:
the method realizes the calculation of the maximum value, the minimum value, the mean value and the standard deviation SD of the distance error between the coordinate reasoning value and the coordinate standard value of the key point detection model of the medical image sample, and the calculation of the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value of the key point detection model of a certain key point in the medical image sample.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (8)
1. The system for evaluating the reasoning effect of the medical image key point detection model is composed of a general background end, and is characterized in that the general background end comprises a data acquisition template maintenance module, a data acquisition module, a calculation method maintenance module, a calculation evaluation result module, a user management module and a role management module:
the data acquisition template maintenance module is used for determining the format of data to be verified, which is represented by the data acquisition template, by a user;
the data acquisition module is used for leading the data to be verified into the system after the user prepares the data to be verified according to the format of the data acquisition template, and confirming that the data to be verified meets the requirements;
the computing method maintenance module is a computing method for an administrator to maintain the system;
the calculation evaluation result module is used for calculating the data to be tested by a user;
the user management module is used for an administrator to increase and decrease users, set user names and reset user passwords;
the role management module is used for giving roles to users by the administrator, and the users acquire the system use rights through the obtained roles.
2. The system for evaluating the reasoning effect of the medical image keypoint detection model according to claim 1, wherein the data acquisition template maintenance module is composed of a data acquisition template management unit, the data acquisition template management unit is used for determining a format of data to be verified represented by the data acquisition template, the format comprises the number n of keypoints of each sample in the medical image sample, the total number s of the medical image samples and the name of the data acquisition template, columns in the format are represented by CM1x, CM1y, CT1x, CT1y, CMnx, CMny, CTnx, CTny, n E {1,2,3.. N } and represent the reasoning x coordinate value deduced by the nth keypoint model in the medical image sample, the reasoning y coordinate value and the standard x coordinate value marked by the nth keypoint doctor, the standard y coordinate value, and the number of rows in the format are equal to the total number of the medical image samples, namely each medical image is a sample.
3. The system for evaluating the reasoning effect of the medical image key point detection model according to claim 1, wherein the data acquisition module consists of a data acquisition and importing unit and an imported data query unit;
the data acquisition and importing unit is used for importing the data to be verified into the system after a user prepares the data to be verified according to the format of the data acquisition template;
the imported data query unit is used for querying the data to be verified which is imported into the system by a user, and confirming that the data to be verified meets the requirements.
4. The system for evaluating the reasoning effect of the medical image key point detection model according to claim 1, wherein the calculation method maintenance module is composed of a calculation method management unit, wherein the calculation method management unit is a calculation method used by an administrator for maintaining the system, and is internally provided with a maximum value, a minimum value, a mean value and a standard deviation SD calculation method of a distance error between a coordinate reasoning value and a coordinate standard value of the medical image sample key point detection model and an intra-group correlation coefficient ICC calculation method between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample;
the distance error value calculating method comprises the following steps:
，
wherein Psn is the error value of the nth key point of the s-th medical image sample, CTnx is the standard X coordinate value of the nth key point, CMnx is the standard Y coordinate value of the nth key point, CTny is the standard Y coordinate value of the nth key point, and CMny is the standard Y coordinate value of the nth key point;
the error maximum value calculating method comprises the following steps: p (P) MAXS =MAX(P s1 ，P s2 ，P s3 .. Psn), psn is the error value of the nth key point of the s-th medical image sample;
the error minimum value calculating method comprises the following steps: p (P) MINS =MIN(P s1 ，P s2 ，P s3 .. Psn), psn is the error value of the nth key point of the s-th medical image sample;
the error average value calculating method comprises the following steps:
，
wherein Psn is the error value of the nth key point of the s-th medical image sample, and s is the total number of medical image samples;
error standard deviation SD calculation method:
，
wherein P is SDn The standard deviation of the error value of the nth key point of the s-th medical image sample is the error value of the nth key point of the s-th medical image sample,an error mean value of the nth key point, s is the total number of medical image samples,
the method for calculating the intra-group correlation coefficient ICC between the coordinate reasoning value and the coordinate standard value comprises the following steps:
，
MS R mean square of line variable in data to be verified, MS C Mean square of column variables in data to be verified, MS E And the error in the data to be verified is mean square, and s is the total number of medical image samples.
5. The system for evaluating the reasoning effect of the medical image key point detection model according to claim 1, wherein the calculation evaluation result module consists of a calculation evaluation result unit, and the calculation evaluation result unit is used for calculating data to be tested by a user to obtain an error standard deviation SD of the data to be verified; and obtaining the intra-group correlation coefficient ICC of the data to be verified, determining the correlation between the coordinate reasoning value and the coordinate standard value, and when ICC is more than 0.75, having statistical significance, highly correlating the data, having better repeatability and effectively modeling.
6. The system for evaluating the reasoning effect of the medical image keypoint detection model according to claim 1, wherein the user management module is composed of a user management unit, and the user management unit is used by an administrator to increase and decrease users, set user names and reset user passwords.
7. The system for evaluating the reasoning effect of the medical image keypoint detection model according to claim 1, wherein the role management module is composed of a role management unit for giving a role to a user by an administrator, and the user obtains the system use authority through the obtained role; and maintaining the system use authority of the role.
8. A method for evaluating the reasoning effect of a medical image keypoint detection model, using a system according to any one of claims 1 to 7, characterized by the following steps:
firstly, an administrator increases and decreases users, sets user names and resets user passwords;
the administrator gives the user a role, and the user obtains the system use authority through the obtained role; maintaining the system use authority of the role;
a user logs in the system to determine the format of data to be verified, which is represented by the data acquisition template;
importing data to be verified, and importing the data to be verified into a system after preparing the data to be verified according to the format of a data acquisition template;
confirming a calculation method, checking a distance error maximum value, a minimum value, a mean value and a standard deviation SD calculation method between a coordinate reasoning value and a coordinate standard value of a built-in medical image sample key point detection model, and checking an intra-group correlation coefficient ICC calculation method between the coordinate reasoning value and the coordinate standard value of a certain key point detection model in the medical image sample;
calculating an evaluation result, verifying the data to be verified by using a calculation method in a calculation method maintenance module to obtain an error standard deviation SD of the data to be verified, and determining the discrete degree of an inference result; and obtaining the intra-group correlation coefficient ICC of the data to be verified, determining the correlation between the coordinate reasoning value and the coordinate standard value, and when ICC is more than 0.75, having statistical significance, highly correlating the data, having better repeatability and effectively modeling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410063618.6A CN117609748A (en) | 2024-01-17 | 2024-01-17 | System and method for evaluating reasoning effect of medical image key point detection model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410063618.6A CN117609748A (en) | 2024-01-17 | 2024-01-17 | System and method for evaluating reasoning effect of medical image key point detection model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117609748A true CN117609748A (en) | 2024-02-27 |
Family
ID=89960105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410063618.6A Pending CN117609748A (en) | 2024-01-17 | 2024-01-17 | System and method for evaluating reasoning effect of medical image key point detection model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117609748A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070031007A1 (en) * | 2003-09-26 | 2007-02-08 | Elias Bitar | Distance-estimation method for a travelling object subjected to dynamic path constraints |
| CN1916949A (en) * | 2006-09-06 | 2007-02-21 | 曾德华 | Support system for evaluating status of electric power equipments, and maintaining strategy |
| CN110188769A (en) * | 2019-05-14 | 2019-08-30 | 广州虎牙信息科技有限公司 | Checking method, device, equipment and the storage medium of key point mark |
| CN110210526A (en) * | 2019-05-14 | 2019-09-06 | 广州虎牙信息科技有限公司 | Predict method, apparatus, equipment and the storage medium of the key point of measurand |
| CN113642551A (en) * | 2020-04-27 | 2021-11-12 | 北京达佳互联信息技术有限公司 | Nail key point detection method and device, electronic equipment and storage medium |
| US20220051004A1 (en) * | 2020-11-27 | 2022-02-17 | Beijing Baidu Netcom Science Technology Co., Ltd. | Image processing method, apparatus, device and storage medium |
| CN114267065A (en) * | 2021-12-23 | 2022-04-01 | 广州津虹网络传媒有限公司 | Face key point correction method and device, equipment and medium thereof |
-
2024
- 2024-01-17 CN CN202410063618.6A patent/CN117609748A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070031007A1 (en) * | 2003-09-26 | 2007-02-08 | Elias Bitar | Distance-estimation method for a travelling object subjected to dynamic path constraints |
| CN1916949A (en) * | 2006-09-06 | 2007-02-21 | 曾德华 | Support system for evaluating status of electric power equipments, and maintaining strategy |
| CN110188769A (en) * | 2019-05-14 | 2019-08-30 | 广州虎牙信息科技有限公司 | Checking method, device, equipment and the storage medium of key point mark |
| CN110210526A (en) * | 2019-05-14 | 2019-09-06 | 广州虎牙信息科技有限公司 | Predict method, apparatus, equipment and the storage medium of the key point of measurand |
| CN113642551A (en) * | 2020-04-27 | 2021-11-12 | 北京达佳互联信息技术有限公司 | Nail key point detection method and device, electronic equipment and storage medium |
| US20220051004A1 (en) * | 2020-11-27 | 2022-02-17 | Beijing Baidu Netcom Science Technology Co., Ltd. | Image processing method, apparatus, device and storage medium |
| CN114267065A (en) * | 2021-12-23 | 2022-04-01 | 广州津虹网络传媒有限公司 | Face key point correction method and device, equipment and medium thereof |
Non-Patent Citations (2)
| Title |
|---|
| 李云飞;马建锋;陈晓婷;: "检测结果一致性评价方法的选择", 临床检验杂志, no. 08, 28 August 2015 (2015-08-28) * |
| 杨毅宇;: "基于WEB和微信公众平台开发模式的高校选课管理系统的设计研究", 环球市场信息导报, no. 34, 27 September 2017 (2017-09-27) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111625413A (en) | Index abnormality analysis method, index abnormality analysis device and storage medium | |
| CN109840671A (en) | Operational development effect calculates equipment, operational development effect calculation method and recording medium | |
| CN109004997A (en) | A kind of frequency spectrum sensing method, device and computer readable storage medium | |
| KR101953558B1 (en) | Apparatus and Method for Fault Management of Smart Devices | |
| CN108491875A (en) | A kind of data exception detection method, device, equipment and medium | |
| CN116506200A (en) | Cloud security service implementation system and method | |
| CN116187621A (en) | Carbon emission monitoring method and device | |
| CN107014561A (en) | A kind of semi-automatic calibration method of pointer pressure | |
| CN117609748A (en) | System and method for evaluating reasoning effect of medical image key point detection model | |
| CN111680083B (en) | Intelligent multi-level government financial data acquisition system and data acquisition method | |
| CN102480381B (en) | Method and device for checking network service operational data | |
| CN110222098A (en) | Electric power high amount of traffic abnormality detection based on flow data clustering algorithm | |
| CN108924120A (en) | A kind of dynamic accesses control method of multi-dimensional state perception | |
| CN116644825B (en) | Big data-based outpatient information inquiry reservation management system | |
| CN102523286A (en) | Method and device for obtaining credit degree of service | |
| US11265232B2 (en) | IoT stream data quality measurement indicator and profiling method and system therefor | |
| CN109341650B (en) | Unmanned aerial vehicle elevation error double-threshold correction method based on minimum detection cost | |
| CN115802376A (en) | Method and device for calibrating work parameter data, electronic equipment and storage medium | |
| CN115841108A (en) | Metering detection calibration method | |
| CN110796761B (en) | Data acquisition system for vehicle-mounted equipment based on embedded system | |
| CN109889292B (en) | Time deviation calibration method in three-layer correlation audit | |
| CN113032822A (en) | AI safety management data system | |
| CN115019136B (en) | Training method and detection method of target key point detection model for resisting boundary point drift | |
| CN117390008B (en) | Method and device for processing measurement data of multi-type observation instrument | |
| CN117607373B (en) | Method, system, equipment and medium for calibrating greenhouse gas monitoring data |
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 |