CN212037803U - Automatic change head shadow measurement system - Google Patents
Automatic change head shadow measurement system Download PDFInfo
- Publication number
- CN212037803U CN212037803U CN202020299141.9U CN202020299141U CN212037803U CN 212037803 U CN212037803 U CN 212037803U CN 202020299141 U CN202020299141 U CN 202020299141U CN 212037803 U CN212037803 U CN 212037803U
- Authority
- CN
- China
- Prior art keywords
- module
- network module
- neural network
- input module
- measurement system
- 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
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The utility model discloses an automatic head shadow measuring system, which comprises a system assembly, wherein the system assembly comprises a neural network module and a positioning network module; the neural network module comprises a first input module, the first input module is arranged in the neural network module, and the first input module is connected with a first output module; the neural network module is connected with the positioning network module, the positioning network module comprises a second input module, and the second input module is connected with a second output module. Compared with the prior art, the utility model the advantage lie in: the algorithm is high in speed and precision; the side film can be widely used for side films of various different types; the design mode adopts the form of SAAS service; besides orthodontic treatment, the lateral plate cervical vertebra age measuring instrument can also be used for lateral plate fixed-point teaching of dentists, orthodontic correction knowledge popularization and lateral plate cervical vertebra age measurement.
Description
Technical Field
The utility model relates to an oral medicine field specifically indicates an automatic change head shadow measurement system.
Background
The lateral slice is an important reference for judging the causes of malformation of teeth, bones and soft tissues and determining the correction scheme in the field of orthodontic treatment. In practical application, specific anatomical marks on the lateral side pieces need to be positioned, and angles or distances between mark points need to be measured so as to judge the cause and severity of deformity and provide reference for formulating a tooth correction scheme. At present, the number of the anatomical landmark points is more than 50, the physician is mainly relied on to manually mark the anatomical landmark points through digital measurement software, the time and the labor are wasted, the positioning of the anatomical landmark points is related to the experience of the physician due to the overlapping and the variation of the anatomical landmarks, and the positioning of the physician is often inaccurate in low-cost.
The existing measurement index normal value reference range is inaccurate, and the judgment of a doctor is often mistaken, so that the design of an automatic head shadow measurement system is imperative.
SUMMERY OF THE UTILITY MODEL
The to-be-solved technical problem of the utility model is that current measurement index normal value reference range is inaccurate, often misleads doctor's judgement, and dissects the location of mark point and is relevant with doctor's experience, and the old-age medical doctor often fixes a position inaccurately, has not only increased medical staff's work load, still can appear patient's tooth state and judge unsafe problem, delays best treatment opportunity.
In order to solve the technical problem, the utility model provides a technical scheme does: an automatic head shadow measuring system comprises a system assembly, a positioning module and a control module, wherein the system assembly comprises a neural network module and a positioning network module;
the neural network module comprises a first input module, the first input module is arranged in the neural network module, and the first input module is connected with a first output module;
the neural network module is connected with the positioning network module, the positioning network module comprises a second input module, and the second input module is connected with a second output module.
Compared with the prior art, the utility model the advantage lie in: (1) the algorithm is high in speed and precision;
(2) the side film can be widely used for side films of various different types;
(3) the design mode adopts the form of SAAS service;
(4) besides orthodontic treatment, the lateral plate cervical vertebra age measuring instrument can also be used for lateral plate fixed-point teaching of dentists, orthodontic correction knowledge popularization and lateral plate cervical vertebra age measurement.
As an improvement, the neural network module obtains lateral slice global information and local information in a multi-layer cascade mode and reflects the lateral slice global information and the local information on the accurate positioning of the anatomical landmark points.
As an improvement, the neural network module incorporates a priori manner by accurately labeling anatomical landmark point data by the same senior physician.
As an improvement, classification is added into the neural network module, and separate intensive training is carried out on samples with overlapped structures and fuzzy variation.
And as an improvement, the second input module receives the local anatomical feature data output by the first output module, and outputs the coordinate data of the mark point through the second output module after the data are calculated and analyzed.
Drawings
Fig. 1 is a schematic diagram of an automated overhead radiography measuring system.
Fig. 2 is a schematic workflow diagram of an automated overhead radiography measurement system.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The utility model discloses when the concrete implementation, an automatic head shadow measurement system, including the system assembly, the system assembly include neural network module and positioning network module;
the neural network module comprises a first input module, the first input module is arranged in the neural network module, and the first input module is connected with a first output module;
the neural network module is connected with the positioning network module, the positioning network module comprises a second input module, and the second input module is connected with a second output module.
The neural network module obtains lateral slice global information and local information in a multilayer cascade mode and is reflected in accurate positioning of anatomical landmark points.
The neural network module incorporates a priori mode by the same senior physician accurately labeling anatomical landmark point data.
The neural network module adds classification, and performs independent strengthening training on samples of overlapping structures and fuzzy variation.
The second input module receives the local anatomical feature data output by the first output module, and outputs the coordinate data of the mark point through the second output module after the data are calculated and analyzed.
The utility model discloses a theory of operation: the original image of the side picture is input to the input module I of the neural network module, local anatomical feature data needing attention is output by the output module I after calculation of a built-in algorithm of the neural network module, the local anatomical feature data are input to the input module II of the positioning network module, and mark point coordinate data are generated by the output module II after calculation of the built-in algorithm of the positioning network module, so that accurate positioning of mark point coordinates is achieved.
The neural network module obtains side slice global information and local information in a multilayer cascade mode and is embodied on the accurate positioning of the anatomical landmark points, the neural network module adds prior, and the mode of adding the prior adopts a mode of accurately marking the anatomical landmark point data by the same senior capital physician, namely adding the prior in the process of marking samples.
The neural network module adds classification and performs independent strengthening training on samples of overlapping structures and fuzzy variation.
The neural network module can process samples shot by different models, including but not limited to samples of models used for training, can be popularized to clinic in a large quantity, and can also identify samples with low shot treatment.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the invention, "plurality" means two or more unless a limitation is explicitly stated.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "fixed" are to be construed broadly and may include, for example, fixed connections, detachable connections, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood according to specific situations by those skilled in the art.
In the present disclosure, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may comprise direct contact between the first and second features, or may comprise contact between the first and second features not directly. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly above and obliquely above the second feature, or simply meaning that the first feature is at a lesser level than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art without departing from the principles and spirit of the present invention.
Claims (5)
1. An automatic head shadow measurement system, includes system assembly, its characterized in that: the system assembly comprises a neural network module and a positioning network module;
the neural network module comprises a first input module, the first input module is arranged in the neural network module, and the first input module is connected with a first output module;
the neural network module is connected with the positioning network module, the positioning network module comprises a second input module, and the second input module is connected with a second output module.
2. An automated cephalometric measurement system according to claim 1, characterized in that: the neural network module obtains lateral slice global information and local information in a multilayer cascade mode and is reflected in accurate positioning of anatomical landmark points.
3. An automated cephalometric measurement system according to claim 1, characterized in that: the neural network module incorporates a priori mode by the same senior physician accurately labeling anatomical landmark point data.
4. An automated cephalometric measurement system according to claim 1, characterized in that: the neural network module adds classification, and performs independent strengthening training on samples of overlapping structures and fuzzy variation.
5. An automated cephalometric measurement system according to claim 1, characterized in that: the second input module receives the local anatomical feature data output by the first output module, and outputs the coordinate data of the mark point through the second output module after the data are calculated and analyzed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020299141.9U CN212037803U (en) | 2020-03-12 | 2020-03-12 | Automatic change head shadow measurement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020299141.9U CN212037803U (en) | 2020-03-12 | 2020-03-12 | Automatic change head shadow measurement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212037803U true CN212037803U (en) | 2020-12-01 |
Family
ID=73532040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020299141.9U Active CN212037803U (en) | 2020-03-12 | 2020-03-12 | Automatic change head shadow measurement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212037803U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822921A (en) * | 2021-11-22 | 2021-12-21 | 四川大学 | Side film intelligent head shadow measuring method based on deep neural network |
| CN114947902A (en) * | 2022-05-16 | 2022-08-30 | 天津大学 | X-ray head shadow measurement mark point automatic positioning method based on reinforcement learning |
-
2020
- 2020-03-12 CN CN202020299141.9U patent/CN212037803U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822921A (en) * | 2021-11-22 | 2021-12-21 | 四川大学 | Side film intelligent head shadow measuring method based on deep neural network |
| CN114947902A (en) * | 2022-05-16 | 2022-08-30 | 天津大学 | X-ray head shadow measurement mark point automatic positioning method based on reinforcement learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meriç et al. | Web-based fully automated cephalometric analysis: comparisons between app-aided, computerized, and manual tracings | |
| Durão et al. | Cephalometric landmark variability among orthodontists and dentomaxillofacial radiologists: a comparative study | |
| Sandler | Reproducibility of cephalometric measurements | |
| Trpkova et al. | Assessment of facial asymmetries from posteroanterior cephalograms: validity of reference lines | |
| Chien et al. | Comparison of reliability in anatomical landmark identification using two-dimensional digital cephalometrics and three-dimensional cone beam computed tomography in vivo | |
| CN212037803U (en) | Automatic change head shadow measurement system | |
| Demétrio et al. | Accuracy between virtual surgical planning and actual outcomes in orthognathic surgery by iterative closest point algorithm and color maps: A retrospective cohort study | |
| US9144472B2 (en) | System and method for evaluating orthodontic treatment | |
| Miloro et al. | Is there consistency in cephalometric landmark identification amongst oral and maxillofacial surgeons? | |
| Simon et al. | Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study | |
| Liberton et al. | Development and validation of novel three-dimensional craniofacial landmarks on cone-beam computed tomography scans | |
| CN108038877B (en) | Visual head shadow measuring method and system and computer processing equipment | |
| Kurt et al. | Mandibular asymmetry in cleft lip and palate patients | |
| WO2022214105A1 (en) | Orthopedic surgery registration apparatus, terminal device, and storage medium | |
| WO2022188547A1 (en) | Method for detecting key point of x-ray cephalogram image | |
| Mummolo et al. | The 3D tele motion tracking for the orthodontic facial analysis | |
| Cheung et al. | The validity of transverse intermaxillary analysis by traditional PA cephalometry compared with cone-beam computed tomography | |
| Woodsend et al. | Development of intra-oral automated landmark recognition (ALR) for dental and occlusal outcome measurements | |
| Kılınç et al. | Evaluation and comparison of smartphone application tracing, web based artificial intelligence tracing and conventional hand tracing methods | |
| Tan et al. | Picture archiving and communications systems: a study of reliability of orthodontic cephalometric analysis | |
| JP2013226384A (en) | Method for calculating indicator for determining necessity of jaw surgery in orthodontic treatment, method for determining necessity of jaw surgery in orthodontic treatment, method for calculating indicator for determining disharmony of maxilla and mandible, method for determining disharmony of maxilla and mandible, method for calculating indicators for determining jaw deformity, method for determining jaw deformity, program and computer | |
| CN111227977A (en) | Automatic change head shadow measurement system | |
| Bonanni | Contour and angle-function based scoliosis monitoring: relaxing the requirement on image quality in the measurement of spinal curvature | |
| Kamaluddin et al. | Does the Eastman correction over-or under-adjust ANB for positional changes of N? | |
| Grogger et al. | Identification of ‘Point A’as the prevalent source of error in cephalometric analysis of lateral radiographs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |