CN112767315B

CN112767315B - Target area sketching quality determining method, target area sketching quality displaying method and electronic equipment

Info

Publication number: CN112767315B
Application number: CN202011635011.9A
Authority: CN
Inventors: 贾乐成
Original assignee: Shenzhen United Imaging Research Institute of Innovative Medical Equipment
Current assignee: Shenzhen United Imaging Research Institute of Innovative Medical Equipment
Priority date: 2020-12-31
Filing date: 2020-12-31
Publication date: 2024-04-19
Anticipated expiration: 2040-12-31
Also published as: CN112767315A

Abstract

The embodiment of the invention discloses a target area sketching quality determining method, a target area sketching quality displaying method and electronic equipment. The determination method may include: acquiring a target region delineation and a quality determination object of the delineated target region in the medical image, wherein the quality determination object comprises a compromised site and/or an a priori morphology of the delineated target region; determining delineating information of the target region delineation and object information of a quality determination object, wherein the object information comprises a endangered image of a endangered part and/or a priori morphology feature of a priori morphology; and determining punishment relation between the target region sketching and the quality determining object according to the sketching information and the object information, and determining the target region sketching quality of the target region sketching according to the punishment relation. According to the technical scheme, objective representation can be performed on the target area sketching quality manually determined by the user, so that the effect of automatically determining and determining the target area sketching quality consistent with the target area sketching quality manually determined by the user is achieved, and the target area sketching quality determination method has good clinical application value.

Description

Target area sketching quality determining method, target area sketching quality displaying method and electronic equipment

Technical Field

The embodiment of the invention relates to the field of image processing, in particular to a target area sketching quality determining method, a target area sketching quality displaying method and electronic equipment.

Background

Target delineation of a cancer radiotherapy target region (hereinafter may be simply referred to as a target region) is an important part of a radiotherapy process, and accuracy thereof directly affects an execution effect of a subsequent radiotherapy plan, so that determination of target delineation quality is indispensable in the radiotherapy process.

Currently, the determination of the sketching quality of a target area is mainly finished by a doctor manually, and the determination is very dependent on the clinical experience and subjective judgment of the doctor. It should be noted that, although the target area sketches have a uniform sketching consensus, different doctors have different understandings of the consensus, which may cause different doctors and even the same doctor to sketch the same target area in different time periods, which may give different quality evaluations, i.e. poor consistency and repeatability. In addition, the above-mentioned scheme requires a doctor to perform it manually, which consumes a lot of manpower resources and cannot process large-scale data.

Disclosure of Invention

The embodiment of the invention provides a method for determining the sketching quality of a target area, a display method and electronic equipment, so as to realize the effect of automatically determining the sketching quality of the target area.

In a first aspect, an embodiment of the present invention provides a method for determining a quality of a target area sketching, which may include:

Acquiring a target region delineation and a quality determination object of the delineated target region in the medical image, wherein the quality determination object comprises a compromised site and/or an a priori morphology of the delineated target region;

determining delineating information of the target region delineation and object information of a quality determination object, wherein the object information comprises a endangered image of a endangered part and/or a priori morphology feature of a priori morphology;

And determining punishment relation between the target region sketching and the quality determining object according to the sketching information and the object information, and determining the target region sketching quality of the target region sketching according to the punishment relation.

In a second aspect, an embodiment of the present invention further provides a method for displaying a target area sketching quality, which may include:

receiving a medical image and a target zone delineation of the delineated target zone in the medical image;

Outputting the processed medical image, and displaying quality information related to the target region sketching quality of the target region sketching on the processed medical image, wherein the quality information comprises at least one of a score of the target region sketching quality, a to-be-modified sub-sketch in the target region sketching and a modification reason of the to-be-modified sub-sketch;

Wherein the quality information is determined from a penalty relation between the target volume delineation and a quality determination object in the medical image, the penalty relation being determined from the delineation information of the target volume delineation and object information of the quality determination object, the quality determination object comprising a priori topography of the compromised region and/or the delineated target volume, and the object information comprising a priori topography features of the compromised image and/or the a priori topography of the compromised region.

In a third aspect, an embodiment of the present invention further provides an electronic device, which may include:

one or more processors;

A memory for storing one or more programs;

The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for determining or the method for displaying the quality of target delineation provided by any embodiment of the present invention.

According to the technical scheme, the target region sketching and quality determining object of the sketched target region in the acquired medical image can be used for determining sketching information of the target region sketching and object information of the quality determining object, and the quality determining object is an object which is arranged for simulating how a user manually determines the sketching quality of the target region, such as a compromised part and/or a priori morphology of the sketched target region, so that a punishment relation between the sketching and quality determining object determined according to the sketching information and the object information can indicate whether the target region sketching violates a compromised part which should not violate and/or whether a part which does not accord with the priori morphology exists, and then the target region sketching quality which corresponds to the target region sketching quality manually determined by the user can be automatically determined according to the punishment relation, so that the target region sketching quality determining method has good clinical application value. According to the technical scheme, the quality determination object is set from the aspect of manually determining the target area sketching quality by a user, and then when the target area sketching quality is determined based on the punishment relation between the target area sketching and the quality determination object, objective representation can be carried out on the manually determined target area sketching quality by the user, so that the effect of automatically determining and determining the target area sketching quality consistent with the manually determined target area sketching quality by the user is achieved.

Drawings

FIG. 1 is a flow chart of a method for determining target delineating quality in accordance with a first embodiment of the present invention;

FIG. 2 is a flow chart of a method for determining target delineating quality in accordance with a second embodiment of the present invention;

FIG. 3 is a flow chart of a method for determining target delineating quality in accordance with a third embodiment of the present invention;

FIG. 4 is a flow chart of a method for determining target delineating quality in accordance with a fourth embodiment of the present invention;

FIG. 5 is a flowchart of an alternative example of a method for determining the quality of a target delineation in accordance with a fourth embodiment of the present invention;

FIG. 6 is a flow chart of a method for displaying target delineating quality in a fifth embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to an eighth embodiment of the present invention.

Detailed Description

The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.

Before describing the embodiment of the present invention, an application scenario of the embodiment of the present invention is described in an exemplary manner: in order to solve the problems of poor consistency and repeatability and high manpower resource consumption caused by manual determination of the target area sketching quality by doctors, researchers have proposed an automatic determination scheme of the target area sketching quality. Specifically, the target region sketch is compared with a gold standard (namely, gold standard sketch), a comparison result is quantized based on a preset quality determination index, and the quantized result is used as the target region sketch quality. The quality determination index can be an intersection ratio (Intersection over Union, IOU), an accuracy, a recall, a Dice coefficient, a Hausdorff distance and the like, and has the advantages of high calculation speed, high repeatability, strong consistency and less human resource consumption.

However, such automatic determination schemes rely on the accuracy of "gold standards," are susceptible to tag noise, and are difficult to embody by various factors that a physician considers in manually determining the quality of a target delineation. For example, the target delineation is a multi-layer delineation result, and if each layer is more or less than the "gold standard", the automatically determined target delineation quality is still good, but it is poor for the physician. Again by way of example, a pixel is typically present or absent, and once the target is delineated by 1 layer, the quality of the target delineated by this determination remains very poor, but is still good for the physician. In addition, the automatic determination scheme determines the target region sketching quality from the pixel level, which cannot intuitively give specific situations of where the target region sketching is good, bad, and the like as if a doctor manually determines the target region sketching quality, and cannot give a feasible modification scheme.

On the basis, the method and the device have the greatest characteristics that the position size is not fixed and no clear boundary exists in medical images on the basis that the target area can comprise a primary tumor range, a metastasis range, a subclinical range and a tumor possibly infringed part, and if various factors considered by a doctor in the process of manually determining the target area sketching quality are fused into an automatic determination process, an automatic determination result consistent with the target area sketching quality manually determined by the doctor can be obtained, namely, the manual determination process of the doctor is objectively represented. Accordingly, the following method for determining the quality of target region delineation is provided, and the specific implementation process is as follows.

Example 1

Fig. 1 is a flowchart of a method for determining a target delineating quality according to a first embodiment of the present invention. The embodiment is applicable to the case of automatically determining the target volume sketching quality, and is particularly applicable to the case of automatically determining the target volume sketching quality from the perspective of how a user manually determines the target volume sketching quality. The method can be performed by a target volume delineation quality determination device provided by an embodiment of the invention, which can be implemented in software and/or hardware, and which can be integrated on an electronic device.

Referring to fig. 1, the method of the embodiment of the present invention specifically includes the following steps:

s110, target region delineation of the delineated target region in the medical image and a quality determination object are acquired, wherein the quality determination object comprises a endangered part and/or an a priori morphology of the delineated target region.

The target area sketched can be a target area where a tumor is located in a medical image, the target area sketching can be a sketching result of the sketched target area, the sketching result can be a sketching result obtained by manually sketching the sketched target area by a user, the sketching result can also be a sketching result obtained after the medical image is input into a target area sketching model, and the target area sketching model can be a neural network model or a mathematical model. On the basis, an optional target region sketching determination scheme is provided, segmented images of all parts in the medical image are determined, and the target region sketching is determined according to all the segmented images and priori sketching knowledge of the sketched target region, wherein the priori sketching knowledge can comprise the target region sketching and sketching position relations among all the parts. Specifically, the sketched positional relationship may indicate where the boundaries of the target region need to reach, for example, where the upper boundary of the target region needs to reach the lower side of the collarbone, where the target region cannot invade the pectoral muscle, etc., and then it is necessary to determine where the collarbone and pectoral muscle are in the medical image, respectively, and then determine the sketched target region according to the specific position. Therefore, a segmented image of each part in the medical image, which may be an organ, a tissue, or the like, may be determined first, the segmented image may be an image obtained after each part is segmented from the medical image, then the position of each part on the medical image is determined according to each segmented image, and then a target region sketch of the sketched target region is obtained by combining a priori sketch knowledge. On this basis, the segmented image of each part may be obtained based on different image segmentation models, or may be obtained based on the same image segmentation model, and at this time, different parts may be represented in the image segmentation model based on different labels, which is not specifically limited herein.

The quality determination object may be an object associated with determining a target volume delineating quality, i.e., the quality of a target volume delineation, such as a compromised region, an a priori topography of a delineated target volume, or the like. The endangered site may be a site of the individual site which cannot be delineated by the target area or which is affected by radiation to be protected, such as endangering tissue, organs, etc.; the a priori topography may be a shape-like appearance that the delineated target region should have, such as a triangle, butterfly, oval, etc.

S120, determining sketching information of sketching of a target area and object information of a quality determination object, wherein the object information comprises a endangered image of a endangered part and/or an a priori morphology feature of the a priori morphology.

The sketching information is information related to the sketching of the target area, and may be, for example, a sketching position of the sketching of the target area on a medical image, a sketching feature of the sketching of the target area, and the like. The object information may be information of a quality-determining object, for example, when the quality-determining object is a compromised site, the object information may be a compromised image of the compromised site, which may be a segmented image of the compromised site on the medical image, i.e. the compromised image may represent localization information of the compromised site on the medical image and/or descriptive information of the compromised site; further exemplary, when the quality determination object is a priori morphology, the object information may be a priori morphology feature of the a priori morphology, which may be a feature obtained by feature extraction of the a priori morphology, optionally represented by a number (e.g. 0 1). The object information may be obtained by inputting a medical image into a corresponding neural network model, but may be obtained in other manners, which are not particularly limited herein.

And S130, determining punishment relation between the target region sketching and the quality determination object according to the sketching information and the object information, and determining target region sketching quality of the target region sketching according to the punishment relation.

The punishment relation can be a relative relation between target region sketching and quality determination objects, and can have different meanings in different application scenes. For example, when the quality determination object is a compromised site, the punishment relationship may be that the target delineates whether the target is infringing on a compromised site that should not be infringing, in particular, may be that the compromised site is not infringing, the compromised site is infringing, and what the extent and/or location of infringing is, etc.; as yet another example, when the quality determination object is a priori topography, the penalty relationship may be whether the delineated topography of the target delineation is consistent with the a priori topography, in particular, may be fully consistent, partially non-consistent and non-conforming, and/or what the non-conforming location is, etc., i.e., it may indicate whether a target delineation that does not conform to the a priori topography is included in the target delineation, etc. The penalty relation can be determined in various ways, for example, the sketching information and the object information are input into a pre-trained neural network model or a pre-set mathematical model; for example, the sketching information is compared with the object information, and exemplary, the sketching position is compared with the endangered position of the endangered image in the medical image, the sketching morphological characteristics are compared with the priori morphological characteristics, and the like; of course, the penalty relationship may also be determined in the remaining ways, which are not specifically limited herein.

Further, since the punishment relationship can indicate whether information which can negatively affect the quality of the target region delineation exists in the target region delineation, the quality of the target region delineation can be determined according to the punishment relationship. Illustratively, continuing with the above example, if it is determined from the positional relationship that the target delineating violates a jeopardy that should not violate, then the target delineating is of lower quality; if the target zone sketch which does not accord with the prior morphology exists in the target zone sketch according to the punishment relation, the target zone sketch quality is lower; etc., and are not particularly limited herein. Of course, at least two of these may also be combined together to determine the target delineation quality, which is determined jointly from different angles, thereby improving the accuracy of the determination of the target delineation quality.

On the basis, optionally, besides determining the target zone sketch quality according to the punishment relation, the target zone sketch to be modified and the modification reason of the target zone sketch to be modified can be determined, and then the target zone sketch to be modified and the modification reason are displayed. The to-be-modified sub-sketch can be a part of the target area sketch which does not meet the related sketch requirement, and the modification reason is that the to-be-modified sub-sketch does not meet the related sketch requirement. Illustratively, continuing with the above example, if it is determined from the penalty relationship that a portion of the target delineation violates the compromised site, then the portion may be treated as a sub-delineation to be modified, and the modification cause may be violation of the compromised site; further exemplary, if it is determined from the penalty relationship that there is a portion of the target volume delineation that does not conform to the prior topography, then this portion may be treated as a sub-delineation to be modified, and the modification cause may be that it does not conform to the prior topography. Furthermore, as the to-be-modified sub-sketch and the modification reasons are the contents which can be directly understood by the user, the to-be-modified sub-sketch and the modification reasons can be displayed, so that the user can intuitively know whether problems exist in the target area sketch, what problems exist, what part the problems exist in, and the like according to the display result, and can intuitively know the feasible modification scheme, and the practical application value of the target area sketch quality determination is improved. The user may be a doctor or the like who is involved in the target drawing.

In practical application, optionally, in order to realize the digitization of the target area sketching quality, a preset quality determination index is obtained first, then an index score of the quality determination index is calculated according to a punishment relation, and the index score is used as the target area sketching quality of the target area sketching. The quality determination index may be an index for determining the quality of the target delineation, such as an IOU, an accuracy, a precision, a recall, a Dice coefficient, a Hausdorff distance, and the like. The specific implementation process of calculating the index score of the quality determination index according to the punishment relation can be related to the type of the quality determination index, and by way of example, assuming that the quality determination index is an IOU, the intersection area of the intersection region and the union area of the union region between the target region delineation and the quality determination object can be determined according to the punishment relation, and then the numerical value of the IOU is determined according to the intersection area and the union area; further exemplary, assuming that the quality determination index is a Dice coefficient, a similarity between a character string corresponding to the target region sketch and a character string corresponding to the quality determination object may be determined according to the penalty relation, and the similarity may be used as a numerical value of the Dice coefficient; and the like, are not particularly limited herein. The specific form of the index score may relate to the type of the quality determination index, or may be set in advance, and the index score may be represented by "excellent", "good", "middle", "poor", assuming that the calculation result of the quality determination index is a numerical value, but each numerical value and "excellent", "good", "middle", "poor" have been mapped in advance.

Example two

Fig. 2 is a flowchart of a method for determining a target delineating quality according to a second embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, the quality determining object comprises a region of compromise and the object information comprises a image of compromise, the delineating information comprising a delineating location of the target region delineated in the medical image; correspondingly, determining a punishment relation between the target region sketching and the quality determining object according to the sketching information and the object information, and determining the target region sketching quality of the target region sketching according to the punishment relation, wherein the method comprises the following steps: determining a punishment relation between the target region delineation and the endangered site according to the delineation position and the endangered position of the endangered image in the medical image; judging whether the target area sketch violates the endangered part according to the punishment relation, if so, determining the target area sketch quality of the target area sketch according to the degree of violation. Wherein, the explanation of the same or corresponding terms as the above embodiments is not repeated herein.

Referring to fig. 2, the method of this embodiment may specifically include the following steps:

S210, target region delineation of the delineated target region in the medical image and a endangered part in the medical image are acquired.

S220, determining a sketching position of the target area sketching in the medical image and a endangered image of the endangered part.

S230, determining punishment relation between target region delineation and endangered parts according to the delineation position and the endangered position of the endangered image in the medical image.

Wherein the delineated location may be a location of the target volume delineated on the medical image, which may indicate which locations on the medical image the target volume delineated is present on; while the compromised location may be the location of the compromised image on the medical image, which may indicate which locations on the medical image have compromised sites. The method comprises the steps of taking the position in the medical image as an intermediary, determining a punishment relation according to the endangered position and the sketched position, wherein various implementation modes exist, such as determining whether the punishment relation is infringed or not infringed to the endangered position according to whether the position coincident with the sketched position exists between the endangered position and the sketched position; further, the degree of invasion can be determined according to the number of the coincident positions, namely the invasion to the endangered position can be taken as a punishment relation; etc.

And S240, judging whether the target region sketch violates the endangered part according to the punishment relation, and if so, determining the target region sketch quality of the target region sketch according to the degree of violation.

In principle, the target region delineation should not violate the endangered site, so when the target region delineation is determined to violate the endangered site according to the punishment relation, the degree of violation of the target region delineation for the endangered site can be further determined, and the degree of violation can be expressed in various forms, such as an area, a distance, an area ratio, a distance ratio and the like, and is not particularly limited herein. And then according to the degree of invasion, the target zone sketching quality of the target zone sketching can be determined, if the degree of invasion is higher, the target zone sketching quality is very poor, and at the moment, information such as warning, modification advice and the like can be given, for example, the target zone sketching is infringed to the inner boundary of the bladder by 5mm; for example, when the invasion degree is low, the target area sketching quality can be also achieved; etc. Of course, if the target delineation does not violate the compromised site, then there is no serious problem in the target delineation from this point of view. In practical application, optionally, the target region sketching quality may be represented by a score, where the score may be at least one of a score, a pass-fail, a good-medium difference, an a+a-and the like, and then after determining the degree of invasion, the score of the target region sketching quality may be determined according to the degree of invasion and a preset degree score mapping relationship.

According to the technical scheme, when the quality determination object comprises a compromised part, the object information comprises a compromised image and the sketching information comprises the sketching position of the target area sketching on the medical image, whether the target area sketching infringes the compromised part or not can be judged according to the compromised position and the sketching position of the compromised image on the medical image, and if so, the target area sketching quality of the target area sketching can be determined according to the infringement degree of the target area sketching relative to the compromised part, so that the effect of automatically determining and determining the target area sketching quality consistent with the target area sketching quality manually determined by a user from the aspect of manually determining the infringement degree of the target area sketching relative to the compromised part, which is frequently involved in the target area sketching quality process by the user, is achieved.

Example III

Fig. 3 is a flowchart of a method for determining the quality of a target delineation provided in a third embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, the quality determination object includes a priori morphology and the object information includes a priori morphology features, and the delineating information includes delineated morphology features of the delineated morphology of the target region; correspondingly, determining a punishment relation between the target region sketching and the quality determining object according to the sketching information and the object information, and determining the target region sketching quality of the target region sketching according to the punishment relation, wherein the method comprises the following steps: determining a punishment relation between the sketched morphology and the priori morphology according to the sketched morphology features and the priori morphology features; and if the target zone sketch which does not accord with the prior morphology exists in the target zone sketch according to the punishment relation, determining the target zone sketch quality of the target zone sketch according to the target zone sketch and the target zone sketch. Wherein, the explanation of the same or corresponding terms as the above embodiments is not repeated herein.

Referring to fig. 3, the method of this embodiment may specifically include the following steps:

s310, target region delineation of the delineated target region in the medical image and prior morphology of the delineated target region are acquired.

It is considered that although there may be differences in the location and size of different tumors, the target region where they are located is likely to have a similar a priori morphology because of the distribution constraints of surrounding sites, and is generally three-dimensionally continuous in space, where the a priori morphology may be a shape pattern that the delineated target region should have. Accordingly, in determining the quality of the target delineation, the a priori morphology of the corresponding delineated target may be used as a determining factor, which is also one of the factors frequently referenced in manually determining the quality of the target delineation by the user.

S320, determining the delineated morphology feature of the delineated morphology of the target area and the prior morphology feature of the prior morphology.

Wherein the delineated topography is the topographical features that the target delineation actually has, and the prior topography is the topographical features that the target delineation should have, in other words, when the delineated topography is closer to the prior topography, the higher the quality of the target delineation is, i.e. when the delineated topography and the prior topography do not coincide, the problem exists in the target delineation. On this basis, it should be noted that, in order to ensure the engineering feasibility, the sketched morphology and the prior morphology may be digitally represented, for example, the sketched morphology may be represented by sketching morphology features, and the prior morphology may be represented by prior morphology features.

On this basis, the sketched morphology features may be obtained in various manners, for example, obtained after feature extraction of the sketched morphology, obtained by inputting the target region sketch into a pre-trained morphology feature generation model, and the like, which are not particularly limited herein. Accordingly, the prior topographical features may also be obtained in a variety of ways, for example, considering that the gold standard delineation may be used as the most accurate target region delineation, then the feature on the shape and appearance of the gold standard delineation may be used as the prior topographical feature; further exemplary, since the three-dimensional continuous prior morphology in space can be well fitted based on the neural network, the medical image can be input into the morphology feature generation model which is already trained, and the prior morphology feature can be determined according to the output result of the morphology feature generation model, wherein the morphology feature generation model can be pre-trained by the following steps: acquiring a history image and the marked morphology features of the history target area in the history image, inputting the history image into a generator, and obtaining the history morphology features of the history target area according to the output result of the generator; and (3) inputting the historical morphology features and the labeling morphology features into a discriminator, and adjusting network parameters in the generator according to the output result of the discriminator to obtain a morphology feature generation model, namely taking the generator after the network parameters are adjusted as the morphology feature generation model.

S330, determining punishment relation between the sketched morphology and the priori morphology according to the sketched morphology feature and the priori morphology feature.

And comparing the sketched morphology features with the priori morphology features, and determining a punishment relation between the sketched morphology and the priori morphology according to a comparison result. For example, if the delineated topography features are exactly identical to the prior topography features, the corresponding penalty relationship may be that the delineated topography and the prior topography are exactly identical; otherwise, the penalty relationship may be that the two do not agree fully, and it may further be determined which part of the delineated morphology does not agree with the prior morphology.

And S340, if the target zone sketch which does not accord with the prior morphology exists in the target zone sketch according to the punishment relation, determining the target zone sketch quality of the target zone sketch according to the target zone sketch and the target zone sketch.

If a certain part in the sketched morphology is not coincident with the priori morphology according to the punishment relation, the corresponding part of the part in the target zone sketch can be used as the target zone sketch, namely the target zone sketch is the part which is not coincident with the priori morphology in the target zone sketch. For example, assuming that the target delineation is a sphere and the prior delineation corresponding to the prior topography is a triangle, the non-overlapping portions of the two may be referred to as the target delineation. Further, the target region sketching quality can be determined according to the target region sketching and the target region sketching, for example, the ratio of the area of the sub-sketching area formed by the target region sketching to the area of the sketching area formed by the target region sketching is used as the target region sketching quality. And then, taking the ratio of the number of the pixel points contained in the target area sketch to the number of the pixel points contained in the target area sketch as the target area sketch quality; etc.

According to the technical scheme, when the quality determination object comprises the priori morphology, the object information comprises the priori morphology features, and the sketching information comprises the sketching morphology features of the sketching morphology of the target area, whether the target area sketch which is not in accordance with the priori morphology exists in the target area sketch or not can be determined according to the comparison result between the sketching morphology features and the priori morphology features, and if the target area sketch quality of the target area sketch can be determined according to the target area sketch and the target area sketch, the effect that whether the sketch morphology of the target area sketch which is often involved in the process of manually determining the target area sketch quality of the target area sketch accords with the priori morphology is achieved, and the effect of automatically determining and determining the target area sketch quality which is in accordance with the target area sketch quality which is manually determined by a user is achieved.

Example IV

Fig. 4 is a flowchart of a method for determining the quality of a target delineation provided in a fourth embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, the method for determining the quality of the target area sketching may further include: acquiring gold standard sketches of the sketched target area and a target area image of the target area part in the medical image; determining an overlapping area between the target area sketch and the gold standard sketch, and determining target area weights of all target area pixel points in the target area image based on a preset weight determining function; determining the overlapping weight of each overlapping pixel point in the overlapping region according to the overlapping position of the overlapping region in the medical image and the target region position of the target region image in the medical image; determining the basic quality of the target area sketching according to the overlapping area and each overlapping weight; correspondingly, determining the target region delineation quality of the target region delineation according to the punishment relation may include: and determining punishment quality of the target region sketch according to the punishment relation, and determining the target region sketch quality of the target region sketch according to the basic quality and the punishment quality. Wherein, the explanation of the same or corresponding terms as the above embodiments is not repeated herein.

Referring to fig. 4, the method of this embodiment may specifically include the following steps:

S410, acquiring a quality determination object, a target region image of a target region part, and a target region sketch and a gold standard sketch of a sketched target region in a medical image, wherein the quality determination object comprises a endangered part and/or an a priori morphology of the sketched target region.

The target area part in the medical image is the part where the tumor is located, the target area image is a segmented image of the target area part in the medical image, and the acquisition mode can be referred to as a endangered image, which is not described herein. Of course, the target image and the endangered image may be acquired in the same or different manners, and are not specifically limited herein. The gold standard delineation of the delineated target region may be the most standard delineation result of the delineated target region, which may be obtained by manually delineating the delineated target region by a user, or may be obtained by inputting a medical image into a target region delineation model and evaluating the target region delineation model by the user, etc., which is not particularly limited herein.

S420, determining an overlapping area between the target area sketch and the gold standard sketch, and determining target area weights of all target area pixel points in the target area image based on a preset weight determining function.

In the method, when determining the target volume sketch quality, in addition to whether a part which does not meet the related sketch requirement exists in the target volume sketch or not, whether a part which is consistent with the gold standard sketch exists in the target volume sketch or not can be considered, so that the target volume sketch quality can be determined jointly from the two angles of the front surface and the back surface, and therefore, the overlapping area between the target volume sketch and the gold standard sketch, in particular, the overlapping area between the gold standard areas of the target volume sketch formed by the target volume sketch can be determined.

Further, in a clinical practice scenario, there is a high possibility that there is a difference in effect of radiotherapy on different positions of a target region, and the reason for this is that each tumor includes at least a primary focus and a subclinical focus, the subclinical focus is a portion that expands out with respect to the primary focus, for example, a rectal tumor, the primary focus is in the rectum and the subclinical focus is around the primary focus, and since the subclinical focus cannot detect a tumor on a medical image, the tumor does exist on the subclinical focus, but there is only a problem of more or less, so that the effect of radiotherapy on the position of the primary focus in the target region is stronger than that of radiotherapy on the position of the subclinical focus. Since primary and subclinical foci are located at different locations of the target site, respectively, this means that there is a difference in the impact of the target delineation on the quality of the target delineation delineated on different locations of the target site. In other words, if the overlapping region is located on a primary focus, its impact on the quality of the target delineation may be greater; accordingly, if the overlapping region is located on a subclinical focus, its impact on the quality of the target delineation may be less.

Accordingly, in order to show that the importance degrees of the target region parts at different positions are different, the target region weights of the target region pixel points in the target region image of the target region part can be determined based on a preset weight determination function, wherein the weight determination function can be a function set based on linear weights, gaussian weights and the like, and exemplified by rectal tumors, the target region weights of the target region pixel points in the target region image where the rectum is located are the highest, and the target region weights of the target region pixel points other than the target region pixel points where the rectum is located can be gradually reduced along with the increase of the distance between the target region pixel points and the rectum. In other words, in principle, the target delineation should wrap more rectum and less rectum than rectum, then the target weight of the target pixel point where the rectum should wrap more rectum in the target image may be higher, and the target weight of the target where the rectum should wrap less may be lower. The weight determination function may be set by what the target weight of the target pixel point is located at what position, and thus the position of each position on the medical image may be determined from the segmented image of each position.

S430, determining the overlapping weight of each overlapping pixel point in the overlapping region according to the overlapping position of the overlapping region in the medical image and the target region position of the target region image in the medical image; and determining the basic quality of the target region sketching according to the overlapping region and each overlapping weight.

Wherein, for the overlapping position overlapped with the target position, the target weight of the target pixel point at the target position can be used as the overlapping weight of the overlapping pixel point at the overlapping position. Thus, the basis quality of the target volume delineation may be determined from the overlapping region and the overlapping weights, e.g., from the overlapping area of the overlapping region and the overlapping weights of the overlapping pixels within the overlapping region, and the delineation area of the target volume delineation, which may be a quality that has a positive impact on the target volume delineation quality.

S440, determining sketching information of the target area sketching and object information of quality determination objects, determining punishment relation between the target area sketching and quality determination objects according to the sketching information and the object information, and determining punishment quality of the target area sketching according to the punishment relation.

Wherein the object information may comprise a compromised image of the compromised region and/or a priori topographical features of the a priori topography, and the penalty quality may be a quality that negatively affects the quality of the target delineation.

S450, determining the target region sketching quality of the target region sketching according to the basic quality and the punishment quality.

Wherein, the punishment quality which has negative influence on the target zone sketching quality and the basic quality which has positive influence on the target zone sketching quality are comprehensively considered, and the accuracy of the obtained target zone sketching quality is higher. For example, taking the example of representing the mass by score, when the penalty mass includes a first penalty mass for the compromised region and a second penalty mass for the delineated topography, assuming the specific score of the base mass is 90, the specific score of the first penalty mass is 10, and the specific score of the second penalty mass is 13, the specific score of the final target delineated mass is 90-10-13 = 67.

According to the technical scheme, as the importance degree of different positions on the target area relative to radiotherapy is different, in order to show the difference, the target area weight of each target area pixel point in the target area image of the target area can be determined based on a preset weight determination function, and the overlapping position of an overlapping area between the target area sketch and the gold standard sketch in the medical image and the target area position of the target area image in the medical image are combined, so that the overlapping weight of each overlapping pixel point in the overlapping area can be obtained; therefore, the target region sketching quality can be determined from a plurality of angles in the front and back directions according to the basic quality of the target region sketching determined based on the overlapping region and each overlapping weight and the punishment quality of the target region sketching determined based on the punishment relation, and the determination accuracy of the target region sketching quality is improved.

In order to better understand the specific implementation procedure of the above steps, an exemplary method for determining the target delineation quality of the present embodiment is described below with reference to specific examples. Illustratively, given the complexity of the target, the present example integrates target distribution, organ-at-risk protection, and other constraint information to automatically and objectively determine the target delineation quality of the target delineation. The method and the device can be applied to various application scenes such as control of target volume sketching quality, doctor target volume sketching training, target volume segmentation model performance evaluation and the like. The system can comprise a plurality of mutually independent modules, such as a medical image digital expression module, a target area weight determining module, an organ protection determining module, a target area morphology priori module, a comprehensive determining module, a visualization module and the like, and can be flexibly invoked according to different application scenes.

Specifically, as shown in fig. 5, a medical image is input to a digital representation module of the medical image, so that the digital representation module of the medical image inputs the medical image to a pre-trained image segmentation model, segmented images of organs and tissues in the medical image are obtained according to an output result of the image segmentation model, and each segmented image is output, wherein the segmented image belonging to the organ at risk may be referred to as a jeopardy image, and the segmented image belonging to the organ at target and the tissue at target may be referred to as a target image. And acquiring target zone sketches and gold standard sketches of the sketched target zone in the medical image, inputting each segmented image, the target zone sketches and the gold standard sketches into a target zone weight determining module, so that the target zone weight determining module determines the basic quality of the sketched target zone by combining input data and a preset weight determining function, and outputting the basic quality. The image of the hazard and the target volume delineation are input into an organ protection determination module such that the organ protection determination module determines a first penalty quality based on the input data. And inputting the medical image and the sketched morphology into a target morphology priori module, so that the target morphology priori module inputs the medical image into a morphology generating model which is trained in advance, obtaining priori morphology features according to the output result of the morphology generating model, comparing the priori morphology features with the priori morphology features obtained after feature extraction of the sketched morphology, and obtaining second punishment quality according to the comparison result. The basic quality, the first punishment quality and the second punishment quality are input to the comprehensive determination module, so that the comprehensive determination module obtains the target zone sketch quality of the target zone sketch and the to-be-modified sub-sketch and the modification reason of the to-be-modified sub-sketch in the target zone sketch according to input data, and outputs the target zone sketch quality, the to-be-modified sub-sketch and the modification reason. Inputting the target region sketching quality, the sub sketching to be modified and the modification reasons into a visualization module so that the visualization module displays the input data, for example, highlighting the sub sketching to be modified in a medical image and marking the modification reasons.

Example five

Fig. 6 is a flowchart of a method for displaying the quality of target delineation provided in embodiment five of the present invention. The embodiment can be applied to the situation that the quality of the target area sketching is displayed on the medical image. The method can be performed by the target area sketching quality display device provided by the embodiment of the invention, the device can be realized by software and/or hardware, and the device can be integrated on electronic equipment. Wherein, the explanation of the same or corresponding terms as the above embodiments is not repeated herein.

Referring to fig. 6, the method of the embodiment of the present invention specifically includes the following steps:

s510, receiving the medical image and a target region delineation of the delineated target region in the medical image.

The user may input the medical image and the target area sketch of the sketched target area in the medical image through the electronic device, at this time, the electronic device may receive the corresponding medical image and the target area sketch, and may perform corresponding processing according to the medical image and the target area sketch to obtain quality information related to the quality of the target area sketch, such as a score of the quality of the target area sketch, a sketch to be modified in the target area sketch, a modification reason of the sketch to be modified, and so on, which are not specifically limited herein.

And S520, outputting the processed medical image, and displaying quality information related to the target region sketching quality of the target region sketching on the processed medical image, wherein the quality information comprises at least one of a score of the target region sketching quality, a to-be-modified sub-sketching in the target region sketching and a modification reason of the to-be-modified sub-sketching, the quality information is determined according to a punishment relation between the target region sketching and a quality determination object in the medical image, the punishment relation is determined according to the sketching information of the target region sketching and object information of the quality determination object, the quality determination object comprises a priori morphology of a compromised part and/or the sketched target region, and the object information comprises a priori morphology feature of the compromised image and/or the priori morphology of the compromised part.

After the electronic device obtains the corresponding quality information through processing, the electronic device can process the quality information on the medical image, so that the electronic device can output the processed medical image and display the quality information on the processed medical image, for example, display the score on a preset score position on the medical image, display the sub-sketch to be modified (such as highlighting display, color changing display and the like) on the medical image based on a preset display mode, display the modification reason of the sub-sketch to be modified nearby the sub-sketch to be modified and the like.

On the basis, optionally, if the quality information is the sub-sketch to be modified, the sub-sketch to be modified can be displayed on the processed medical image based on the first display mode, and the target modification sub-sketch corresponding to the sub-sketch to be modified can be displayed on the processed medical image based on the second display mode, wherein the target modification sub-sketch can be a modification target of the sub-sketch to be modified determined according to the modification reason, which can help a user to directly determine which part of the target area sketch needs modification and a feasible modification scheme, and therefore convenience of user operation is improved.

On this basis, further optionally, the first display mode may include a highlight display mode based on the first color, and the second display mode may include a highlight display mode based on the second color, so that in addition to displaying the quality information, the description information of the highlight display mode of the first color and the description information of the highlight display mode of the second color may be displayed on the processed medical image, which may help the user intuitively know which highlight part of the first color is a part to be modified and which highlight part of the second color is a modification target, thereby improving the friendliness of the user interface interaction.

According to the technical scheme, the effect of displaying the target area sketching quality on the medical image is achieved through the user interface interaction mode, so that a user can quickly and intuitively determine the quality information related to the target area sketching quality, such as the score of the target area sketching quality, whether problems exist in the target area sketching, what problems exist, which part the problems exist in, and the like, and the method has good practical application value.

Example six

The target volume sketching quality determining device provided in the sixth embodiment of the present invention is configured to execute the target volume sketching quality determining method provided in any of the above embodiments. The device and the method for determining the target area sketching quality in the above embodiments belong to the same invention conception, and details which are not described in detail in the embodiment of the device for determining the target area sketching quality can refer to the embodiment of the method for determining the target area sketching quality. The device specifically can include: the target region delineation system comprises a quality determination object acquisition module, an object information determination module and a target region delineation quality determination module.

The quality determination object acquisition module is used for acquiring target region delineation of the delineated target region and a quality determination object in the medical image, wherein the quality determination object comprises a compromised part and/or a priori morphology of the delineated target region;

The object information determining module is used for determining sketching information of sketching of a target area and object information of a quality determination object, wherein the object information comprises a endangered image of a endangered part and/or an priori morphology feature of an priori morphology;

and the target region sketching quality determining module is used for determining a punishment relation between the target region sketching and the quality determining object according to the sketching information and the object information and determining the target region sketching quality of the target region sketching according to the punishment relation.

Optionally, the quality determination object comprises a threat location and the object information comprises a threat image, the delineating information comprising a delineating location of the target region in the medical image;

The target region delineating quality determining module may specifically include:

the first punishment relation determining unit is used for determining punishment relations between target region sketching and the endangered parts according to the sketched positions and endangered positions of endangered images in the medical images;

And the first target region sketching quality determining unit is used for judging whether the target region sketching violates the endangered part according to the punishment relation, and if so, determining the target region sketching quality of the target region sketching according to the degree of violation.

Optionally, the quality determination object comprises a priori morphology and the object information comprises a priori morphology features, and the delineating information comprises delineating morphology features of the delineation of the target region;

the second punishment relation determining unit is used for determining punishment relation between the sketched morphology and the priori morphology according to the sketched morphology features and the priori morphology features;

And the second target area sketch quality determining unit is used for determining the target area sketch quality of the target area sketch according to the target area sketch and the target area sketch if the target area sketch which is not in accordance with the prior morphology exists in the target area sketch according to the punishment relation.

Optionally, the target region delineating quality determining module may specifically include:

And the third target region sketching quality determining unit is used for acquiring a preset quality determining index, calculating an index score of the quality determining index according to the punishment relation, and taking the index score as the target region sketching quality of the target region sketching.

Optionally, the target area sketching quality determining device may further include:

the target area image acquisition module is used for acquiring gold standard sketching of the sketched target area and a target area image of a target area part in the medical image; the target area weight determining module is used for determining an overlapping area between the target area sketch and the gold standard sketch and determining target area weights of all target area pixel points in the target area image based on a preset weight determining function; the overlapping weight determining module is used for determining the overlapping weight of each overlapping pixel point in the overlapping region according to the overlapping position of the overlapping region in the medical image and the target region position of the target region image in the medical image; the basic quality determining module is used for determining the basic quality of the target area sketching according to the overlapping area and each overlapping weight;

Correspondingly, the target region sketching quality determining module specifically may include:

And the fourth target region sketching quality determining unit is used for determining punishment quality of target region sketching according to punishment relation and determining target region sketching quality of target region sketching according to the basic quality and punishment quality.

And the target region sketching determining module is used for determining segmented images of all parts in the medical image and determining target region sketching according to all the segmented images and priori sketching knowledge of the sketched target region, wherein the priori sketching knowledge comprises target region sketching and sketching position relations among all the parts.

According to the target region sketching quality determining device provided by the sixth embodiment of the invention, the effect of automatically determining and determining the target region sketching quality consistent with the target region sketching quality manually determined by a user is realized by the mutual cooperation of the quality determining object acquisition module, the object information determining module and the target region sketching quality determining module.

The target region sketching quality determining device provided by the embodiment of the invention can execute the target region sketching quality determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

It should be noted that, in the embodiment of the target area sketching quality determining device, each unit and module included are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for convenience of distinguishing from each other, and are not used to limit the protection scope of the present invention.

Example seven

The display device for the target area sketching quality provided by the seventh embodiment of the invention is used for executing the display method for the target area sketching quality provided by any embodiment. The device and the method for displaying the target area sketching quality in the above embodiments belong to the same invention conception, and the details of the device for displaying the target area sketching quality, which are not described in detail in the embodiments of the device for displaying the target area sketching quality, can refer to the embodiments of the method for displaying the target area sketching quality. The device specifically can include: the target area sketching receiving module and the target area sketching quality display module.

The target region sketching receiving module is used for receiving the medical image and the target region sketching of the sketched target region in the medical image;

The target region sketching quality display module is used for outputting the processed medical image and displaying quality information related to the target region sketching quality of the target region sketching on the processed medical image, wherein the quality information comprises at least one of a score of the target region sketching quality, a to-be-modified sketch in the target region sketching and a modification reason of the to-be-modified sketch;

Optionally, the quality information includes a to-be-modified sub-sketch, and the target area sketch quality display module includes:

The target area sketching quality display unit is used for displaying the to-be-modified sub-sketch on the processed medical image based on the first display mode and displaying the target modification sub-sketch corresponding to the to-be-modified sub-sketch on the processed medical image based on the second display mode, wherein the target modification sub-sketch is a modification target of the to-be-modified sub-sketch determined according to modification reasons.

On this basis, optionally, the first display mode includes the highlight display mode based on first colour, and the second display mode includes the highlight display mode based on the second colour, and above-mentioned target area sketches the display device of quality, can also include: the explanation information display module is used for displaying the explanation information of the highlighting display mode of the first color and the highlighting display mode of the second color on the processed medical image respectively.

According to the target area sketching quality display device provided by the seventh embodiment of the invention, the target area sketching quality display module and the target area sketching receiving module are matched with each other, and the effect of displaying the target area sketching quality on a medical image is realized through a user interface interaction mode, so that a user can quickly and intuitively determine the score of the target area sketching quality, whether problems exist in the target area sketching, what problems exist, what parts of the problems exist, and the like, which are related to the target area sketching quality, and the display device has good practical application value.

The display device for the target region sketching quality provided by the embodiment of the invention can execute the display method for the target region sketching quality provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

It should be noted that, in the embodiment of the target area quality sketching display device, each unit and module included are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.

Example eight

Fig. 7 is a schematic structural diagram of an electronic device according to an eighth embodiment of the present invention, and as shown in fig. 7, the device includes a memory 610, a processor 620, an input device 630, and an output device 640. The number of processors 620 in the device may be one or more, one processor 620 being taken as an example in fig. 7; the memory 610, processor 620, input 630, and output 640 in the device may be connected by a bus or other means, for example, in fig. 7 by a bus 650.

The memory 610 may be used as a computer readable storage medium for storing a software program, a computer executable program, and a module, such as program instructions/modules corresponding to a method for determining a target delineating quality in an embodiment of the present invention (e.g., a quality determination object acquisition module, an object information determination module, and a target delineating quality determination module in a target delineating quality determination device), or program instructions/modules corresponding to a method for displaying a target delineating quality in an embodiment of the present invention (e.g., a target delineating receiving module and a target delineating quality display module in a target delineating quality display device). The processor 620 executes the software programs, instructions and modules stored in the memory 610 to perform various functional applications of the apparatus and data processing, i.e., to implement the above-described target delineation quality determination method or target delineation quality display method.

The memory 610 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the device, etc. In addition, memory 610 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 610 may further include memory remotely located relative to processor 620, which may be connected to the device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 630 may be used to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output device 640 may include a display device such as a display screen.

From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. In light of such understanding, the technical solution of the present invention may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random-access memory (Random Access Memory, RAM), FLASH memory (FLASH), hard disk, optical disk, or the like, of a computer, which may be a personal computer, a server, a network device, or the like, including instructions for causing a computer device (which may be a personal computer, a server, or the like) to perform the methods described in the various embodiments of the present invention.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. A method of determining the quality of a target delineation, comprising:

acquiring a target region delineation of a delineated target region in a medical image and a quality determination object, wherein the quality determination object comprises a compromised site and/or an a priori morphology of the delineated target region;

Determining delineation information of the target volume delineation and object information of the quality determination object, wherein the object information comprises a compromised image of the compromised site and/or a priori topographical features of the a priori topography;

And determining punishment relation between the target zone sketch and the quality determination object according to the sketch information and the object information, and determining target zone sketch quality of the target zone sketch according to the punishment relation, wherein the punishment relation is whether the target zone sketch is infringed to the endangered part which is not infringed or whether the sketch appearance of the target zone sketch accords with the prior appearance.

2. The method of claim 1, wherein the quality determination object comprises the compromised site and the object information comprises the compromised image, the delineating information comprising a delineating location of the target region delineation in the medical image;

Correspondingly, the determining the punishment relation between the target region sketch and the quality determination object according to the sketch information and the object information, and determining the target region sketch quality of the target region sketch according to the punishment relation includes:

determining a punishment relationship between the target volume delineation and the compromised site according to the delineation location and a compromised location of the compromised image in the medical image;

Judging whether the target zone sketch violates the endangered part or not according to the punishment relation, and if so, determining the target zone sketch quality of the target zone sketch according to the degree of violation.

3. The method of claim 1, wherein the quality determination object comprises the a priori topography and the object information comprises the a priori topography features, the delineation information comprising delineated topography features of the target volume delineated topography;

determining a punishment relation between the sketched morphology and the priori morphology according to the sketched morphology features and the priori morphology features;

And if the target zone sketch which is not consistent with the prior morphology exists in the target zone sketch according to the punishment relation, determining the target zone sketch quality of the target zone sketch according to the target zone sketch and the target zone sketch.

4. The method of claim 1, wherein the determining the target delineation quality of the target delineation based on the penalty relationship comprises:

And acquiring a preset quality determination index, calculating an index score of the quality determination index according to the punishment relation, and taking the index score as the target zone delineating quality of the target zone delineation.

5. The method as recited in claim 1, further comprising:

Acquiring gold standard sketches of the sketched target area and target area images of target area positions in the medical image;

Determining an overlapping area between the target area sketch and the gold standard sketch, and determining target area weights of all target area pixel points in the target area image based on a preset weight determining function;

Determining the overlapping weight of each overlapping pixel point in the overlapping region according to the overlapping position of the overlapping region in the medical image and the target region position of the target region image in the medical image;

determining the basic quality of the target region sketch according to the overlapping region and each overlapping weight;

Correspondingly, the determining the target region sketching quality of the target region sketching according to the punishment relation comprises the following steps:

and determining punishment quality of the target zone sketch according to the punishment relation, and determining the target zone sketch quality of the target zone sketch according to the basic quality and the punishment quality.

6. The method as recited in claim 1, further comprising:

Determining segmented images of all parts in the medical image, and determining the target region sketch according to the segmented images and priori sketch knowledge of the sketched target region, wherein the priori sketch knowledge comprises the target region sketch and sketch position relations among all the parts.

7. A method of displaying a target delineating quality, comprising:

Outputting the processed medical image, and displaying quality information related to target volume sketching quality of the target volume sketching on the processed medical image, wherein the quality information comprises at least one of a score of the target volume sketching quality, a to-be-modified sketch in the target volume sketch and a modification reason of the to-be-modified sketch;

Wherein the quality information is determined from a penalty relation between the target volume delineation and a quality determination object in the medical image, the penalty relation being determined from delineating information of the target volume delineation and object information of the quality determination object, the quality determination object comprising a priori topography of a compromised site and/or the delineated target volume, and the object information comprising a priori topographical feature of a compromised image of the compromised site and/or the a priori topography, wherein the penalty relation is whether the target volume delineation violates the compromised site that should not violate or whether the delineated topography of the target volume delineation coincides with the a priori topography.

8. The method of claim 7, wherein the quality information includes the sub-delineation to be modified, the displaying quality information relating to a quality of a target delineation of the target delineation on the processed medical image, comprising:

Displaying the to-be-modified sub-sketch on the processed medical image based on a first display mode, and displaying a target modification sub-sketch corresponding to the to-be-modified sub-sketch on the processed medical image based on a second display mode, wherein the target modification sub-sketch is a modification target of the to-be-modified sub-sketch determined according to the modification reason.

9. The method of claim 8, wherein the first display comprises a first color-based highlighting display and the second display comprises a second color-based highlighting display, the method further comprising: and respectively displaying the description information of the highlighting display mode of the first color and the highlighting display mode of the second color on the processed medical image.

10. An electronic device, comprising:

one or more processors;

A memory for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of determining target delineating quality as set forth in any one of claims 1-6 or the method of exhibiting target delineating quality as set forth in claims 7-9.