CN104036109A - Image based system and method for case retrieving, sketching and treatment planning - Google Patents
Image based system and method for case retrieving, sketching and treatment planning Download PDFInfo
- Publication number
- CN104036109A CN104036109A CN201410093559.3A CN201410093559A CN104036109A CN 104036109 A CN104036109 A CN 104036109A CN 201410093559 A CN201410093559 A CN 201410093559A CN 104036109 A CN104036109 A CN 104036109A
- Authority
- CN
- China
- Prior art keywords
- case
- organ
- image
- target area
- new case
- 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
Abstract
The invention relates to image based system and method for case retrieving, sketching and treatment planning and belongs to the technical field of medical equipment and application method. The system comprises an organ notification module, a case database, a similar case selection module, an organ and target section positioning module and a plan mapping module which correspondingly realize functions of case database, similar case retrieving, organ sketching, plan designing and plan evaluating, so that historical similar cases can be retrieved on the basis of images of a new case, organ sketching and treatment planning of the new case can be confirmed according to the similar cases, the speeds for sketching and plan designing can be improved, dependency on experience of a user can be lowered for plan designing, and stability and precision of treatment schemes are improved.
Description
Technical field
The present invention relates to medical supply and application process technical field, particularly radiotherapy equipment and method and technology field.
Background technology
Radiation therapy and operation, chemotherapy are three large means of current oncotherapy, and radiotherapy treatment planning system is radiocurable important component part.The object of radiotherapy treatment planning is as much as possible high-dose irradiation to be implemented in target area to make the influenced minimum of normal surrounding tissue simultaneously.
Existing radiotherapy system, needs the therapeutic scheme that can be used for linear accelerator by inputting patient's CT image data, utilizing computing machine to design.What complete that a treatment plan generally includes target area and critical organ delineates, plans the committed steps such as cloth open country and optimization, Rapid Dose Calculation and plan checking.Wherein the technical merit that cloth open country, optimization etc. not only depend on doctor and physics teacher is delineated, planned in organ and target area, and often very consuming time, some plans need design verification repeatedly, repeat many times, therefore becoming the most consuming time in treatment plan design is also the committed step of the final therapeutic scheme quality of impact.Therefore, how to accelerate to delineate and design process, the quality of raising plan is simultaneously significant to whole tumour radiotherapy.
Patent " a kind of radiotherapy treatment planning system based on retrieval and search method (application number: 201110129576.4) " a kind of retrieval of carrying out similar case based on semantic feature proposed, thus the plan design for new case by the treatment plan of similar case.This search method based on semantic not only needs manually to input the text description of each case, workload is large, efficiency is low, the more important thing is, the similar case retrieving is mainly being similar to based on text description, and the image data possibility difference that plan design relies on is larger, thereby improved, in current case, uses the difficulty of similar case and reduced the result of use of similar case as reference.
Summary of the invention
The object of the invention is to have overcome above-mentioned shortcoming of the prior art, a kind of accuracy that can improve similar case retrieval is provided, thereby for new radiation therapy provides reference data, accelerate new case's organ and target area is delineated and radiocurable plan design, and then bulk velocity and the quality of the design of raising radiotherapy treatment planning, shortened formulation treatment plan required time, reduce working doctor intensity, increase work efficiency, and the retrieval of radiation therapy similar case, organ based on image with low cost and target area is delineated and planning system and method.
In order to realize above-mentioned object, the similar case searching system based on image of the present invention has following formation:
This similar case searching system comprises: load module, organ identification module, case database and similar case are selected module.Wherein, load module, in order to operate by user, obtains the image that need to carry out radiocurable new case; Organ identification module is identified in order to each organ in the image of the new case to described, obtains new case's organ fixation and recognition information; Case database is in order to store the image of a plurality of existing cases, and organ fixation and recognition information, organ and target area locating information and the treatment plan information of the existing case corresponding with described existing case image; Similar case selects module in order to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case.
Be somebody's turn to do in the similar case searching system based on image, described organ identification module comprises: contoured skin extraction unit, bone contours extraction unit and zone location unit.Wherein, in the image of contoured skin extraction unit in order to the new case described, by skin partitioning algorithm, obtain new case's contoured skin data; Bone contours extraction unit is in order to according to described new case's contoured skin data, in skin area, and automatic acquisition new case's bone contours data; Zone location unit is in order to contrast described contoured skin data and bone contours data and the skin of standard manikin and the geometric properties of skeleton data, obtains the new case's organ fixation and recognition information in described new case's image.
Be somebody's turn to do in the similar case searching system based on image, described similar case selects module to comprise: screening control module, similarity measurement unit, selection control module and transformation matrix computing unit.Wherein screen control module in order to according to described new case's organ fixation and recognition information, in described case database, filter out and have with at least one existing case of homolog fixation and recognition information as candidate's case; Similarity measurement unit is in order to the image of the candidate's case described in each is mapped in described new case's image by the deformable registration based on pixel, and calculates the similarity between existing case and new case based on pixel; Select control module in order to according to described existing case and the similarity between new case, determine that at least one candidate's case is as described similar case; Transformation matrix computing unit calculates and obtains the transformation matrix that the pixel in similar case image is mapped to the respective pixel in new case's image according to deformable registration mapping relations between similar case and new case.
The present invention also provides a kind of and utilizes described system to realize the similar case search method based on image, and the method comprises the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case.
Be somebody's turn to do in the similar case search method based on image, described organ identification module comprises contoured skin extraction unit, bone contours extraction unit and zone location unit, and described step (2) specifically comprises the following steps:
(21) described contoured skin extraction unit by automatic skin partitioning algorithm, obtains new case's contoured skin data in described new case's image;
(22) described bone contours extraction unit, and according to described new case's contoured skin data, in skin area, obtain new case's bone contours data;
(23) described zone location unit contrasts described contoured skin data and bone contours data with the skin of standard manikin and the geometric properties of skeleton data, the new case's organ fixation and recognition information in the image of the new case described in obtaining.
Be somebody's turn to do in the similar case search method based on image, described similar case selects module to comprise screening control module, similarity measurement unit, select control module and transformation matrix computing unit, and described step (3) specifically comprises the following steps:
(31) described screening control module in described case database, filter out there is the organ fixation and recognition information identical with described new case's organ fixation and recognition information at least one existing case as candidate's case;
(32) described similarity measurement unit is mapped to the image of the candidate's case described in each in image of described new case by the deformable registration based on pixel, and calculates the similarity between existing case and new case based on pixel;
(33) described selection control module, according to described existing case and the similarity between new case, determines that at least one candidate's case is as described similar case;
(34) described transformation matrix computing unit calculates and obtains the transformation matrix that the pixel in similar case image is mapped to the respective pixel in new case's image according to the deformable registration mapping relations between similar case and new case.
The present invention also provides a kind of organ and target area based on image to delineate system, and this organ and the target area system of delineating comprise: described similar case searching system and organ and target area locating module.Wherein, organ and the target area locating module organ of similar case and the definite described new case's of target area locating information organ and the target area locating information in order to obtain according to similar case searching system.
Should delineate in system in organ and target area based on image, described organ and target area locating module comprise: organ and target area profile map unit and organ and target area positioning unit.Wherein, organ and target area profile map unit are in order to be mapped to the organ of at least one similar case and target area locating information in new case's image according to described transformation matrix; Organ and target area positioning unit are in order to organ and the target area locating information of the definite described new case of the mapping result in new case's image according to the organ of at least one described similar case and target area locating information.
The present invention also provides a kind of described organ and target area system of delineating of utilizing to realize organ and the target area delineation method based on image, and the method comprises the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case;
(4) described organ and target area locating module are determined described new case's target area locating information according to the organ of described similar case and target area locating information and described transformation matrix.
Be somebody's turn to do in the organ and target area delineation method based on image, described organ and target area locating module comprise organ and target area profile map unit and organ and target area positioning unit, and described step (4) specifically comprises the following steps:
(41) described organ and target area profile map unit is mapped to the target area locating information of at least one similar case in new case's image according to described transformation matrix;
(42) described organ and the target area positioning unit definite described new case's of the mapping result in new case's image according to the organ of at least one described similar case and target area locating information organ and target area locating information.
The present invention also provides a kind of radiotherapy treatment planning system based on image, and this radiotherapy treatment planning system comprises:
Foregoing target volume positioning system and plan mapping block based on image.This plan mapping block is in order to determine described new case's treatment plan information according to the treatment plan information of described similar case and transformation matrix.
The present invention also provides a kind of and utilizes described radiotherapy treatment planning system to realize the radiotherapy treatment planning method based on image, should the radiotherapy treatment planning method based on image comprise the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case;
(4 ') described plan mapping block is determined described new case's treatment plan information according to the treatment plan information of described similar case and transformation matrix.
Adopted retrieving based on image radiation therapy similar case of this invention, organ and target area are delineated and planning system and method, because similar case searching system comprises organ identification module, case database and similar case are selected module, thereby can determine similar case based on new case's organ fixation and recognition information and existing case organ fixation and recognition information, for new radiation therapy provides reference data, and then according to the organ of similar case and the definite described new case's of target area locating information organ and target area locating information, thereby without new case's image is carried out to semantic description, avoided adopting semantic close but image difference apart from larger existing case, improved the similarity of the existing case retrieving, and then significantly accelerated new case's organ and target area is delineated and radiocurable plan, bulk velocity and the quality of radiotherapy treatment planning design have been improved, effectively shortened formulation treatment plan required time, further reduce working doctor intensity, increase work efficiency, and the radiation therapy similar case retrieval based on image of the present invention, organ and target area are delineated and planning system and method, its cost is also quite cheap.
Accompanying drawing explanation
Fig. 1 is the structural representation of the similar case searching system based on image of the present invention.
Fig. 2 is the flow chart of steps of the similar case search method based on image of the present invention.
Fig. 3 is that the retrieval of radiation therapy similar case, organ and location, target area and the method for planning based on image of the present invention is applied to the schematic flow sheet in actual radiotherapy treatment planning formulation process.
Embodiment
In order more clearly to understand technology contents of the present invention, especially exemplified by following examples, describe in detail.
Referring to shown in Fig. 1, is the structural representation of the similar case searching system based on image of the present invention.
In one embodiment, should the similar case searching system based on image comprise load module, organ identification module, case database and similar case selection module.Wherein, load module, in order to operate by user, obtains the image that need to carry out radiocurable new case; Organ identification module is identified in order to each organ in the image of the new case to described, obtains new case's organ fixation and recognition information; Case database is in order to store the image of a plurality of existing cases, and organ fixation and recognition information, organ and target area locating information and the treatment plan information of the existing case corresponding with described existing case image; Similar case selects module in order to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case.
Utilize the system described in this embodiment to realize the similar case search method based on image, as shown in Figure 2, comprise the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case.
A kind of preferred embodiment in, described organ identification module comprises: contoured skin extraction unit, bone contours extraction unit and zone location unit.Wherein, in the image of contoured skin extraction unit in order to the new case described, by skin partitioning algorithm, obtain new case's contoured skin data; Bone contours extraction unit, in order to according to described new case's contoured skin data, in skin area, by auto-thresholding algorithm, obtains new case's bone contours data; Zone location unit is in order to contrast described contoured skin data and bone contours data and the skin of standard manikin and the geometric properties of skeleton data, obtains the new case's organ fixation and recognition information in described new case's image.
Utilize the system described in this preferred implementation to realize in the similar case search method based on image, described step (2) specifically comprises the following steps:
(21) described contoured skin extraction unit by skin partitioning algorithm, obtains new case's contoured skin data in described new case's image;
(22) described bone contours extraction unit by auto-thresholding algorithm, and according to described new case's contoured skin data, obtains new case's bone contours data in skin area;
(23) described zone location unit contrasts described contoured skin data and bone contours data with the skin of standard manikin and the geometric properties of skeleton data, the new case's organ fixation and recognition information in the image of the new case described in obtaining.
In preferred embodiment, described similar case selects module to comprise: screening control module, similarity measurement unit, selection control module and transformation matrix computing unit.Wherein screen control module in order to according to described new case's organ fixation and recognition information, in described case database, filter out and have with at least one existing case of homolog fixation and recognition information as candidate's case; Similarity measurement unit is in order to the image of the candidate's case described in each is mapped in described new case's image by the deformable registration based on pixel, and calculates the similarity between existing case and new case based on pixel; Select control module in order to according to described existing case and the similarity between new case, determine that at least one candidate's case is as described similar case; Transformation matrix computing unit calculates and obtains the transformation matrix that the pixel in similar case image is mapped to the respective pixel in new case's image according to deformable registration mapping relations between similar case and new case.
Utilize this more preferably the system described in embodiment realize in the similar case search method based on image, described step (3) specifically comprises the following steps:
(31) described screening control module in described case database, filter out there is the organ fixation and recognition information identical with described new case's organ fixation and recognition information at least one existing case as candidate's case;
(32) described similarity measurement unit is mapped to the image of the candidate's case described in each in image of described new case by deformable registration, and calculates the similarity between existing case and new case based on pixel;
(33) described selection control module, according to described existing case and the similarity between new case, determines that at least one candidate's case is as described similar case;
(34) described transformation matrix computing unit calculates and obtains the transformation matrix that the pixel in similar case image is mapped to the respective pixel in new case's image according to the deformable registration mapping relations between similar case and new case.
The present invention also provides a kind of organ and target area based on image to delineate system, and in one embodiment, this organ and the target area system of delineating comprise described similar case searching system and organ and target area locating module.Wherein, organ and the target area locating module organ of similar case and the definite described new case's of target area locating information organ and the target area locating information in order to obtain according to similar case searching system.
Organ and the target area delineation method of utilizing organ described in this embodiment and the target area system of delineating to realize based on image comprise the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case;
(4) described organ and target area locating module are determined described new case's target area locating information according to the organ of described similar case and target area locating information and described transformation matrix.
In a preferred embodiment, described organ and target area locating module comprise: organ and target area profile map unit and organ and target area positioning unit.Wherein, organ and target area profile map unit are in order to be mapped to the organ of at least one similar case and target area locating information in new case's image according to described transformation matrix; Organ and target area positioning unit are in order to organ and the target area locating information of the definite described new case of the mapping result in new case's image according to the organ of at least one described similar case and target area locating information.
Utilize this preferred embodiment described organ and the target area system of delineating realize in the organ and target area delineation method based on image, described step (4) specifically comprises the following steps:
(41) described organ and target area profile map unit is mapped to the target area locating information of at least one similar case in new case's image according to described transformation matrix;
(42) described organ and the target area positioning unit definite described new case's of the mapping result in new case's image according to the organ of at least one described similar case and target area locating information organ and target area locating information.
The present invention also provides a kind of radiotherapy treatment planning system based on image, and in one embodiment, this radiotherapy treatment planning system comprises: foregoing target volume positioning system and plan mapping block based on image.Described plan mapping block is in order to determine described new case's treatment plan information according to the treatment plan information of described similar case and transformation matrix.
The radiotherapy treatment planning method of utilizing the radiotherapy treatment planning system described in this embodiment to realize based on image comprises the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case;
(4 ') described plan mapping block is determined described new case's treatment plan information according to the treatment plan information of described similar case and transformation matrix.
In actual applications, the thought that has proposed the radiotherapy treatment planning design based on image retrieval of the present invention, as the gordian technique that solves similar case retrieval.Can comprise and utilize X ray, gamma ray, electric wire, proton etc. to carry out radiocurable various radiotherapy treatment planning system.Its major technique thinking is, along with the particularly development of cloud computing technology of computer technology, by setting up the clinical database of tumour patient, utilize the technology such as cloud computing to realize the intelligent radiotherapy treatment planning system based on image retrieval, to improving the design of current case radiotherapy treatment planning, not only can improve and design to obtain efficiency and quality, and there is important science and clinical value.Particularly, be by the search case data similar to current case in historical case data, by image processing techniques, the therapeutic scheme of historical case is mapped to current case, thereby realizes conceptual design fast.
In this system, according to data such as the delineating of the historical similar case of the image data acquisition of current case, treatment plan and dosage, for instruct current case radiotherapy treatment planning delineate and plan design, this will greatly reduce time and the complicacy of radiotherapy treatment planning design, excellent drawback is owed in poor efficiency and plan that reduction brings because user lacks experience etc., thereby improve the efficiency of radiotherapy treatment planning design and the quality of radiotherapy treatment planning, this is the important improvement to existing radiotherapy treatment planning design.
As shown in Figure 3, for the retrieval of radiation therapy similar case, organ and location, target area and the method for planning based on image of the present invention is applied to the schematic flow sheet in actual radiotherapy treatment planning formulation process.
The whole radiotherapy treatment planning design process based on image retrieval, comprises two large divisions: similar case image retrieval (shown in the rectangle frame of the left side) and utilize the design (the right rectangle frame comprises part) of hitting the target of the similar case retrieve.Specifically can be divided into:
1, similar case retrieval:
The input of similar case retrieving is new case's image and historical case database, and output is all similar case data that find.After given new case data, the process of searching for similar case from database comprises:
(1) contoured skin is extracted: in new case image, by skin full-automatic dividing algorithm, obtain patient's three-dimensional skin surface outline data.
(2) bone contours is extracted: in skin area, by full-automatic bone detection algorithm, obtain patient's bone contours surface data; Also can adopt auto-thresholding algorithm to obtain patient's bone contours surface data, those maximum pixels of CT value are exactly bone region, can complete the proposition of bone contours by auto-thresholding algorithm.
(3) zone location: its skin enclosing region of diverse location and bone have different geometric properties (such as head and chest or belly from top to bottom due to human body, the area of its skin area, the shape of bone etc. are all different), thereby by the comparison of the skin with standard manikin and bony areas geometric properties, can obtain new case's image position and inclusion region scope.
(4) candidate's similar case: by the area information of each case in the regional location obtaining and case database, acquisition has candidate's case data of identical or close regional location, by calculating the image similarity based on pixel of current case and candidate's case, the similarity that obtains a plurality of similar cases and correspondence thereof is selected for user.
(5) case database: the required essential informations of radiation therapy such as data, treatment plan, calculating dosage are delineated in the image, the organ target area that comprise patient; In addition to one of each case definition in human body zone position information---these data are automatically obtained when patient imports database, computing method are identical with new case's area positioning method.
(6) similarity measurement: the method by the image of candidate's case by the deformable registration based on pixel is mapped in new case's data, calculates the similarity based on pixel.
(7) similar case: by the result of similarity measurement, obtain the most similar several or all cases and design for follow-up plan as similar case.Each similar case not only comprises itself and new case's similarity, also comprises that this case is to new case's transformation matrix, and this matrix is mapped to its each pixel new case's respective pixel in the mode of deformation.
2, plan design:
(1) contour shape of organ and target area mapping: user can select the most similar case or its to think the most applicable certain similar case making reference, by corresponding transformation matrix, the result of delineating of organ and target area is mapped in new case, thereby the organ that has completed quickly and easily new case is delineated.
(2) mapping for the treatment of plan: the planning data of the similar case of selection is mapped in new case, and wherein the parameter relevant with patient location is converted to new case's parameter by transformation matrix.
(3) planning optimization: to delineating and planning data of mapping, user evaluates, and the data that do not meet the demands are carried out to manual amendment; To planning data, also can carry out further optimal planning parameter by reverse optimization, make the plan of setting can adapt to better new case's data.
(4) Rapid Dose Calculation: hit the target after optimization, the Rapid Dose Calculation engine of calling system completes Rapid Dose Calculation.
(5) Program Assessment: doctor assesses checking to the plan of design, guarantees the rationality of plan.
(6) planning data output: by exporting to treatment linear accelerator through the treatment plan of assessment checking, wait to be treated.
Adopted retrieving based on image radiation therapy similar case of this invention, organ and target area are delineated and planning system and method, because similar case searching system comprises organ identification module, case database and similar case are selected module, thereby can determine similar case based on new case's organ fixation and recognition information and existing case organ fixation and recognition information, for new radiation therapy provides reference data, and then according to the organ of similar case and the definite described new case's of target area locating information organ and target area locating information, thereby without new case's image is carried out to semantic description, avoided adopting semantic close but image difference apart from larger existing case, improved the similarity of the existing case retrieving, and then significantly accelerated new case's organ and target area is delineated and radiocurable plan, bulk velocity and the quality of radiotherapy treatment planning design have been improved, effectively shortened formulation treatment plan required time, further reduce working doctor intensity, increase work efficiency, and the radiation therapy similar case retrieval based on image of the present invention, organ and target area are delineated and planning system and method, its cost is also quite cheap.
In this instructions, the present invention is described with reference to its specific embodiment.But, still can make various modifications and conversion obviously and not deviate from the spirit and scope of the present invention.Therefore, instructions and accompanying drawing are regarded in an illustrative, rather than a restrictive.
Claims (10)
1. the similar case searching system based on image, is characterized in that, described similar case searching system comprises:
Load module, in order to operate by user, obtains the image that need to carry out radiocurable new case;
Organ identification module, identifies in order to each organ in the image of the new case to described, obtains new case's organ fixation and recognition information;
Case database, in order to store the image of a plurality of existing cases, and organ fixation and recognition information, organ and target area locating information and the treatment plan information of the existing case corresponding with described existing case image; And
Similar case is selected module, in order to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case.
2. the similar case searching system based on image according to claim 1, is characterized in that,
Described organ identification module comprises:
Contoured skin extraction unit, in the image in order to the new case described, by automatic skin partitioning algorithm, obtains new case's contoured skin data;
Bone contours extraction unit, in order to according to described new case's contoured skin data, automatic acquisition new case's bone contours data; And
Zone location unit, in order to described contoured skin data and bone contours data and the skin of standard manikin and the geometric properties of skeleton data are contrasted, obtain the new case's organ fixation and recognition frame similar case searching system in described new case's image;
Described similar case selects module to comprise:
Screening control module in order to according to described new case's organ fixation and recognition information, filters out and has with at least one existing case of homolog fixation and recognition information as candidate's case in described case database;
Similarity measurement unit, in order to the image of the candidate's case described in each is mapped in described new case's image by the deformable registration based on pixel, and calculates the similarity between existing case and new case based on pixel;
Select control module, in order to according to described existing case and the similarity between new case, determine that at least one candidate's case is as described similar case;
Transformation matrix computing unit, calculates and obtains the transformation matrix that the pixel in similar case image is mapped to the respective pixel in new case's image according to deformable registration mapping relations between similar case and new case.
3. utilize the system described in claim 1 to realize the similar case search method based on image, it is characterized in that, described method comprises the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case.
4. the similar case search method based on image according to claim 3, it is characterized in that, described organ identification module comprises contoured skin extraction unit, bone contours extraction unit and zone location unit, and described similar case selects module to comprise screening control module, similarity measurement unit, select control module and transformation matrix computing unit
Described step (2) specifically comprises the following steps:
(21) described contoured skin extraction unit by skin partitioning algorithm, obtains new case's contoured skin data in described new case's image;
(22) described bone contours extraction unit according to described new case's contoured skin data, obtains new case's bone contours data in skin area;
(23) described zone location unit contrasts described contoured skin data and bone contours data with the skin of standard manikin and the geometric properties of skeleton data, the new case's organ fixation and recognition information in the image of the new case described in obtaining;
Described step (3) specifically comprises the following steps:
(31) described screening control module in described case database, filter out there is the organ fixation and recognition information identical with described new case's organ fixation and recognition information at least one existing case as candidate's case;
(32) described similarity measurement unit is mapped to the image of the candidate's case described in each in image of described new case by the deformable registration based on pixel, and calculates the similarity between existing case and new case based on pixel;
(33) described selection control module, according to described existing case and the similarity between new case, determines that at least one candidate's case is as described similar case;
(34) described transformation matrix computing unit calculates and obtains the transformation matrix that the pixel in similar case image is mapped to the respective pixel in new case's image according to the deformable registration mapping relations between similar case and new case.
5. a system is delineated in the organ based on image and target area, it is characterized in that, described organ and the target area system of delineating comprise:
Similar case searching system as claimed in claim 1, and
Organ and target area locating module, in order to the organ of similar case and the definite described new case's of target area locating information organ and the target area locating information obtaining according to similar case searching system.
6. system is delineated in organ and the target area based on image according to claim 5, it is characterized in that, described organ and target area locating module comprise:
Organ and target area profile map unit, in order to be mapped to the organ of at least one similar case and target area locating information in new case's image according to described transformation matrix;
Organ and target area positioning unit, in order to organ and the target area locating information of the definite described new case of the mapping result in new case's image according to the organ of at least one described similar case and target area locating information.
7. utilize organ and the target area system of delineating described in claim 5 to realize organ and the target area delineation method based on image, it is characterized in that, described method comprises the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case;
(4) described organ and target area locating module are determined described new case's target area locating information according to the organ of described similar case and target area locating information and described transformation matrix.
8. organ and the target area delineation method based on image according to claim 7, it is characterized in that, described organ and target area locating module comprise organ and target area profile map unit and organ and target area positioning unit, and described step (4) specifically comprises the following steps:
(41) described organ and target area profile map unit is mapped to the target area locating information of at least one similar case in new case's image according to described transformation matrix;
(42) described organ and the target area positioning unit definite described new case's of the mapping result in new case's image according to the organ of at least one described similar case and target area locating information organ and target area locating information.
9. the radiotherapy treatment planning system based on image, is characterized in that, described radiotherapy treatment planning system comprises:
Target volume positioning system based on image as claimed in claim 1;
Plan mapping block, in order to determine described new case's treatment plan information according to the treatment plan information of described similar case and transformation matrix.
10. utilize the radiotherapy treatment planning system described in claim 9 to realize the radiotherapy treatment planning method based on image, it is characterized in that, the described radiotherapy treatment planning method based on image comprises the following steps:
(1) described load module operates by user, obtains the image that need to carry out radiocurable new case;
(2) described organ identification module is identified each organ in described new case's image, obtains new case's organ fixation and recognition information;
(3) described similar case selects module to contrast according to described new case's organ fixation and recognition information and each existing case organ fixation and recognition information, select at least one existing case organ as similar case, and calculate the transformation matrix between similar case and new case;
(4 ') described plan mapping block is determined described new case's treatment plan information according to the treatment plan information of described similar case and transformation matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410093559.3A CN104036109A (en) | 2014-03-14 | 2014-03-14 | Image based system and method for case retrieving, sketching and treatment planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410093559.3A CN104036109A (en) | 2014-03-14 | 2014-03-14 | Image based system and method for case retrieving, sketching and treatment planning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104036109A true CN104036109A (en) | 2014-09-10 |
Family
ID=51466879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410093559.3A Pending CN104036109A (en) | 2014-03-14 | 2014-03-14 | Image based system and method for case retrieving, sketching and treatment planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104036109A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104815392A (en) * | 2015-04-10 | 2015-08-05 | 石峰 | Interactive radiotherapy plan system optimization method and system thereof |
| CN106846317A (en) * | 2017-02-27 | 2017-06-13 | 北京连心医疗科技有限公司 | A kind of feature based extracts the method for retrieving medicine image with Similarity matching |
| CN106823159A (en) * | 2015-11-20 | 2017-06-13 | 西门子保健有限责任公司 | Profile for configuring radiotherapy equipment determines |
| CN106920234A (en) * | 2017-02-27 | 2017-07-04 | 北京连心医疗科技有限公司 | A kind of method of the automatic radiotherapy planning of combined type |
| CN107392897A (en) * | 2017-07-17 | 2017-11-24 | 上海联影医疗科技有限公司 | Organ contours acquisition methods, image documentation equipment, radiotherapy planning system and storage medium |
| CN108073676A (en) * | 2016-11-07 | 2018-05-25 | 富士通株式会社 | Image retrieval apparatus and image search method |
| CN108778420A (en) * | 2016-03-31 | 2018-11-09 | 住友重机械工业株式会社 | Neutron capture cure treatment planning systems |
| CN109002442A (en) * | 2017-06-06 | 2018-12-14 | 株式会社日立制作所 | A kind of device and method based on doctor's association attributes retrieval diagnosed case |
| CN109615642A (en) * | 2018-11-05 | 2019-04-12 | 北京全域医疗技术有限公司 | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning |
| CN109716445A (en) * | 2017-03-10 | 2019-05-03 | 富士通株式会社 | Similar cases image retrieval program, similar cases image retrieving apparatus and similar cases image search method |
| CN110120052A (en) * | 2019-05-13 | 2019-08-13 | 上海联影医疗科技有限公司 | A kind of target area image segmenting system and device |
| CN111445463A (en) * | 2020-03-31 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Retrieval method and device for similar lung disease cases and computer equipment |
| CN111588995A (en) * | 2020-05-09 | 2020-08-28 | 广东普能生物科技有限公司 | Radiotherapy positioning assembly customization system and method |
| CN113077433A (en) * | 2021-03-30 | 2021-07-06 | 山东英信计算机技术有限公司 | Deep learning-based tumor target area cloud detection device, system, method and medium |
| WO2021143019A1 (en) * | 2020-01-14 | 2021-07-22 | 平安科技（深圳）有限公司 | Image search method and apparatus based on artificial intelligence, device, and medium |
| CN113192053A (en) * | 2021-05-18 | 2021-07-30 | 北京大学第三医院（北京大学第三临床医学院） | Cervical tumor target area intelligent delineation method, equipment and medium based on deep learning |
| WO2022134028A1 (en) * | 2020-12-25 | 2022-06-30 | 深圳迈瑞生物医疗电子股份有限公司 | Similar case retrieval method, similar case retrieval system and ultrasonic imaging system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1914641A (en) * | 2004-01-26 | 2007-02-14 | 皇家飞利浦电子股份有限公司 | Example-based diagnosis decision support |
| US7374077B2 (en) * | 2002-04-03 | 2008-05-20 | Fujifilm Corporation | Similar image search system |
| CN102033933A (en) * | 2010-12-17 | 2011-04-27 | 南方医科大学 | Distance metric optimization method for maximizing mean average precision (MAP) |
| CN102184334A (en) * | 2011-05-19 | 2011-09-14 | 南京航空航天大学 | Retrieval-based radiotherapy planning system and retrieval method |
| CN102985924A (en) * | 2011-02-14 | 2013-03-20 | 松下电器产业株式会社 | Similar case retrieval device and similar case retrieval method |
| CN103380441A (en) * | 2010-12-20 | 2013-10-30 | 皇家飞利浦电子股份有限公司 | System and method for automatic generation of initial radiation treatment plans |
-
2014
- 2014-03-14 CN CN201410093559.3A patent/CN104036109A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7374077B2 (en) * | 2002-04-03 | 2008-05-20 | Fujifilm Corporation | Similar image search system |
| CN1914641A (en) * | 2004-01-26 | 2007-02-14 | 皇家飞利浦电子股份有限公司 | Example-based diagnosis decision support |
| CN102033933A (en) * | 2010-12-17 | 2011-04-27 | 南方医科大学 | Distance metric optimization method for maximizing mean average precision (MAP) |
| CN103380441A (en) * | 2010-12-20 | 2013-10-30 | 皇家飞利浦电子股份有限公司 | System and method for automatic generation of initial radiation treatment plans |
| CN102985924A (en) * | 2011-02-14 | 2013-03-20 | 松下电器产业株式会社 | Similar case retrieval device and similar case retrieval method |
| CN102184334A (en) * | 2011-05-19 | 2011-09-14 | 南京航空航天大学 | Retrieval-based radiotherapy planning system and retrieval method |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104815392B (en) * | 2015-04-10 | 2018-01-26 | 石峰 | A kind of interactive radiotherapy treatment planning system optimization system |
| CN104815392A (en) * | 2015-04-10 | 2015-08-05 | 石峰 | Interactive radiotherapy plan system optimization method and system thereof |
| US10384079B2 (en) | 2015-11-20 | 2019-08-20 | Siemens Healthcare Gmbh | Method and computer using contour determination for configuring a radiotherapy apparatus |
| CN106823159A (en) * | 2015-11-20 | 2017-06-13 | 西门子保健有限责任公司 | Profile for configuring radiotherapy equipment determines |
| CN108778420A (en) * | 2016-03-31 | 2018-11-09 | 住友重机械工业株式会社 | Neutron capture cure treatment planning systems |
| CN108073676A (en) * | 2016-11-07 | 2018-05-25 | 富士通株式会社 | Image retrieval apparatus and image search method |
| CN108073676B (en) * | 2016-11-07 | 2022-10-11 | 富士通株式会社 | Image retrieval apparatus and image retrieval method |
| CN106846317A (en) * | 2017-02-27 | 2017-06-13 | 北京连心医疗科技有限公司 | A kind of feature based extracts the method for retrieving medicine image with Similarity matching |
| CN106920234A (en) * | 2017-02-27 | 2017-07-04 | 北京连心医疗科技有限公司 | A kind of method of the automatic radiotherapy planning of combined type |
| CN106846317B (en) * | 2017-02-27 | 2021-09-17 | 北京连心医疗科技有限公司 | Medical image retrieval method based on feature extraction and similarity matching |
| CN106920234B (en) * | 2017-02-27 | 2021-08-27 | 北京连心医疗科技有限公司 | Combined automatic radiotherapy planning method |
| CN109716445B (en) * | 2017-03-10 | 2023-03-24 | 富士通株式会社 | Similar case image search program, similar case image search device, and similar case image search method |
| CN109716445A (en) * | 2017-03-10 | 2019-05-03 | 富士通株式会社 | Similar cases image retrieval program, similar cases image retrieving apparatus and similar cases image search method |
| CN109002442B (en) * | 2017-06-06 | 2023-04-25 | 株式会社日立制作所 | Device and method for searching diagnosis cases based on doctor related attributes |
| CN109002442A (en) * | 2017-06-06 | 2018-12-14 | 株式会社日立制作所 | A kind of device and method based on doctor's association attributes retrieval diagnosed case |
| CN107392897A (en) * | 2017-07-17 | 2017-11-24 | 上海联影医疗科技有限公司 | Organ contours acquisition methods, image documentation equipment, radiotherapy planning system and storage medium |
| CN109615642A (en) * | 2018-11-05 | 2019-04-12 | 北京全域医疗技术有限公司 | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning |
| CN110120052A (en) * | 2019-05-13 | 2019-08-13 | 上海联影医疗科技有限公司 | A kind of target area image segmenting system and device |
| CN110120052B (en) * | 2019-05-13 | 2021-05-07 | 上海联影医疗科技股份有限公司 | Target area image segmentation system and device |
| WO2021143019A1 (en) * | 2020-01-14 | 2021-07-22 | 平安科技（深圳）有限公司 | Image search method and apparatus based on artificial intelligence, device, and medium |
| CN111445463A (en) * | 2020-03-31 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Retrieval method and device for similar lung disease cases and computer equipment |
| CN111588995A (en) * | 2020-05-09 | 2020-08-28 | 广东普能生物科技有限公司 | Radiotherapy positioning assembly customization system and method |
| WO2022134028A1 (en) * | 2020-12-25 | 2022-06-30 | 深圳迈瑞生物医疗电子股份有限公司 | Similar case retrieval method, similar case retrieval system and ultrasonic imaging system |
| CN113077433B (en) * | 2021-03-30 | 2023-04-07 | 山东英信计算机技术有限公司 | Deep learning-based tumor target area cloud detection device, system, method and medium |
| CN113077433A (en) * | 2021-03-30 | 2021-07-06 | 山东英信计算机技术有限公司 | Deep learning-based tumor target area cloud detection device, system, method and medium |
| CN113192053A (en) * | 2021-05-18 | 2021-07-30 | 北京大学第三医院（北京大学第三临床医学院） | Cervical tumor target area intelligent delineation method, equipment and medium based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104036109A (en) | Image based system and method for case retrieving, sketching and treatment planning | |
| US11386557B2 (en) | Systems and methods for segmentation of intra-patient medical images | |
| US11869202B2 (en) | Method and system for processing multi-modality image | |
| JP6514325B2 (en) | System and method for segmenting medical images based on anatomical landmark-based features | |
| EP2965285B1 (en) | Scan region determining apparatus | |
| CN103620646B (en) | For generating the system, method and computer-readable medium of image registration figure | |
| EP3559905B1 (en) | Online learning enhanced atlas-based auto-segmentation | |
| CN106902475A (en) | Radiation therapy method, computer program and computer system | |
| CN104636618B (en) | Radiotherapy planning system | |
| CN109754860B (en) | Method for automatically predicting planning difficulty level based on DVH prediction model | |
| CN113077433B (en) | Deep learning-based tumor target area cloud detection device, system, method and medium | |
| CN113975662A (en) | Accurate radiotherapy platform of nasopharyngeal darcinoma based on data mining technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140910 |
|
| RJ01 | Rejection of invention patent application after publication |