CN117690551A - Isodose line-based complication occurrence probability determining device and electronic equipment - Google Patents
Isodose line-based complication occurrence probability determining device and electronic equipment Download PDFInfo
- Publication number
- CN117690551A CN117690551A CN202410158045.5A CN202410158045A CN117690551A CN 117690551 A CN117690551 A CN 117690551A CN 202410158045 A CN202410158045 A CN 202410158045A CN 117690551 A CN117690551 A CN 117690551A
- Authority
- CN
- China
- Prior art keywords
- isodose
- target
- image
- isodose line
- distribution
- 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
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000001959 radiotherapy Methods 0.000 claims abstract description 16
- 210000000056 organ Anatomy 0.000 claims description 61
- 230000005855 radiation Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000005305 organ development Effects 0.000 claims description 4
- 230000000888 organogenic effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 210000000920 organ at risk Anatomy 0.000 description 4
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007408 cone-beam computed tomography Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The application discloses an isodose line-based complication occurrence probability determining device and electronic equipment. Wherein the device includes: an acquisition unit configured to acquire N isodose line distribution images corresponding to the first object based on the N isodose lines and N isodose line distribution images corresponding to the second object based on the N isodose lines; a similarity comparing unit for comparing the similarity of each two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images of the first object and the N isodose line distribution images of the second object; the processing unit is used for combining every two isodose line distribution images with the similarity smaller than a preset threshold value as target images; and the determining unit is used for determining the probability of the complication of the target object according to the target image combination. The method and the device solve the technical problem that whether complications occur after the patient receives radiotherapy can not be predicted through difference information among isodose lines of different patients in the prior art.
Description
Technical Field
The present application relates to the field of medical science and technology, and more particularly, to an isodose line-based complication occurrence probability determining device and an electronic device.
Background
The dose of the patient is usually estimated by using DVH (Dose and Volume Histogram, dose volume histogram) information, however, for different patients, the dose distribution information in DVH loses shape information, and meanwhile, although isodose lines can reflect shape information, the isodose line distribution image in 3D form cannot be directly estimated manually, so that in the prior art, whether complications occur after the patient receives radiation treatment or not cannot be predicted by using difference information between isodose lines of different patients.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The application provides a complication probability determining device and electronic equipment based on isodose lines, which at least solve the technical problem that whether complications can occur after patients receive radiotherapy or not cannot be predicted through difference information among isodose lines of different patients in the prior art.
According to an aspect of the present application, there is provided an isodose line-based complication occurrence probability determining apparatus including: an acquisition unit configured to acquire N isodose line distribution images corresponding to N isodose lines for a first object and N isodose line distribution images corresponding to N isodose lines for a second object, where N is an integer greater than 1, the first object being an object of a target organ in which complications have occurred after receiving radiation treatment, and the second object being an object of a target organ in which complications have not occurred after receiving radiation treatment; a similarity comparing unit, configured to compare the similarity of each two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object, where the isodose value is a dose value corresponding to the isodose line; the processing unit is used for combining every two isodose line distribution images with the similarity smaller than a preset threshold value as a target image; and the determining unit is used for determining the probability of complications of a target organ of a target object after receiving the radiotherapy according to the target image combination, wherein the target object is an object different from the first object and the second object.
Optionally, the acquiring unit includes: a first acquisition subunit, configured to acquire a target dose distribution image corresponding to a target organ of a first object; the setting subunit is used for setting N isodose lines corresponding to a target organ of the first object in the target dose distribution image, wherein the interval between every two adjacent isodose lines in the N isodose lines is a preset interval; a first generating subunit, configured to generate N isodose line mask images based on N isodose lines corresponding to a target organ of the first object in the target dose distribution image, where the N isodose lines and the N isodose line mask images are in a one-to-one correspondence, and each isodose line mask image corresponding to an isodose line includes at least a target image area surrounded by the isodose line; and the second generation subunit is used for generating N isodose line distribution images corresponding to the first object according to the N isodose line mask images.
Optionally, the second generating subunit includes: the first processing module is used for multiplying the N isodose line mask images with the target dose distribution image respectively, and taking the multiplied result as N isodose line distribution images corresponding to the first object, wherein the N isodose line distribution images corresponding to the first object have a one-to-one correspondence with the N isodose line mask images, and the isodose line distribution image corresponding to each isodose line mask image in the N isodose line mask images is used for representing dose distribution information corresponding to a target image area of the isodose line mask image.
Optionally, the first acquisition subunit includes: the first acquisition module is used for acquiring medical images corresponding to target organs of the first object; the sketching module is used for sketching the medical image to obtain a sketched image corresponding to the target organ of the first object, wherein the sketched image is used for representing outline information of the target organ of the first object in the medical image; the second acquisition module is used for acquiring a dose distribution image adopted by the first object in the radiotherapy process, wherein the dose distribution information contained in the dose distribution image at least comprises the dose distribution information contained in the target dose distribution image; and the second processing module is used for multiplying the sketched image and the dose distribution image and taking the multiplied result as a target dose distribution image corresponding to the target organ of the first object.
Optionally, the similarity comparing unit includes: a first extraction subunit, configured to extract an image feature of each of N isodose line distribution images corresponding to the first object; the second extraction subunit is used for extracting the image characteristics of each isodose line distribution image in the N isodose line distribution images corresponding to the second object; a first processing subunit, configured to combine each two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object into an image set; and the second processing subunit is used for taking the image characteristic similarity between two isodose line distribution images in the image set as the similarity of the two isodose line distribution images.
Optionally, the determining unit includes: a third processing subunit, configured to take the same isodose values corresponding to the two isodose distribution images in the target image combination as target isodose values; the second acquisition subunit is used for acquiring a target equivalent dose distribution image corresponding to a target organ of the target object under an equivalent dose line corresponding to a target equivalent dose value; a first determination subunit for determining a probability of a target organogenesis complication of the target subject from the target isodose distribution image and the target image combination.
Optionally, the first determining subunit includes: the third processing module is used for taking an equal dose distribution image corresponding to the first object in the target image combination as a first equal dose distribution image; a fourth processing module, configured to take an isodose distribution image corresponding to the second object in the target image combination as a second isodose distribution image; the first calculation module is used for calculating a first similarity between the target equal-dose distribution image and the first equal-dose distribution image; the second calculation module is used for calculating a second similarity between the target equal-dose distribution image and the first equal-dose distribution image; and the first determining module is used for determining the probability of the target organ occurrence complication of the target object according to the first similarity and the second similarity.
Optionally, the first determining module includes: the calculating sub-module is used for calculating the ratio of the first similarity to the second similarity; a determination submodule for determining the probability of the target organ occurrence complication of the target object according to the ratio.
According to another aspect of the present application, there is also provided a computer readable storage medium, where a computer program is stored in the computer readable storage medium, where the isodose line based complication occurrence probability determining apparatus of any one of the above is run by a device where the computer readable storage medium is located when the computer program is run.
According to another aspect of the present application, there is also provided an electronic device, wherein the electronic device includes one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to control the operation of the isodose line-based complication occurrence probability determination apparatus of any of the above.
In the present application, a method for determining a probability of occurrence of complications in a target organ of a target object after receiving radiation treatment based on isodose line distribution images of a history patient (i.e., a first object and a second object) is adopted, and an acquisition unit is used to acquire N isodose line distribution images corresponding to the first object based on N isodose lines and N isodose line distribution images corresponding to the second object based on N isodose lines, wherein the first object is an object in which complications occur in the target organ after receiving radiation treatment, and the second object is an object in which complications do not occur in the target organ after receiving radiation treatment. And comparing the similarity of every two isodose line distribution images with corresponding equivalent dose values in N isodose line distribution images corresponding to the first object and N isodose line distribution images corresponding to the second object through a similarity comparison unit, wherein the equivalent dose values are the equivalent dose values corresponding to the isodose lines. And then taking each two isodose line distribution images with the similarity smaller than a preset threshold value as a target image combination through a processing unit, and finally determining the probability of complications of a target organ of a target object after receiving radiation treatment according to the target image combination through a determining unit, wherein the target object is an object different from the first object and the second object.
As can be seen from the above, the present application achieves obtaining difference information between the isodose line distribution images of the first object and the second object based on the same isodose value by comparing the similarity of each two isodose line distribution images of the corresponding same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object. In addition, each two isodose line distribution images with the similarity smaller than a preset threshold value are used as a target image combination, and the probability of complications of a target organ of a target object after receiving radiation treatment is determined according to the target image combination, so that whether the complications occur to a patient after receiving radiation treatment can be predicted according to the isodose line distribution images of the patient with the complications and the isodose line distribution images of the patient without the complications, and the problem that whether the complications occur to the patient after receiving radiation treatment cannot be predicted according to difference information among isodose lines of different patients in the prior art is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic diagram of an alternative isodose line-based complication occurrence probability determination apparatus according to embodiments of the present application;
FIG. 2 is a schematic diagram of an alternative N isodose lines according to an embodiment of the present application;
fig. 3 is a schematic diagram of an alternative isodose line mask image according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be further noted that, related information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.
According to an embodiment of the present application, there is provided an embodiment of an isodose line-based complication occurrence probability determining apparatus, wherein fig. 1 is a schematic diagram of an optional isodose line-based complication occurrence probability determining apparatus according to an embodiment of the present application, and as shown in fig. 1, the schematic diagram of the isodose line-based complication occurrence probability determining apparatus includes the following units: an acquisition unit 101, a similarity comparison unit 102, a processing unit 103, and a determination unit 104.
Optionally, the acquiring unit 101 is configured to acquire N isodose line distribution images corresponding to N isodose lines for a first object and N isodose line distribution images corresponding to N isodose lines for a second object, where N is an integer greater than 1, where the first object is an object having complications after receiving radiation treatment for a target organ, and the second object is an object having no complications after receiving radiation treatment for the target organ.
Alternatively, the number of the first objects and the number of the second objects may be plural, wherein the isodose lines represent lines connecting points corresponding to the same dose values in the dose distribution image, and the N isodose lines are in one-to-one correspondence with the N dose values.
Optionally, the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object may be classified in a statistical manner, or the image features of each isodose line distribution image may be fitted based on a neural network or a machine learning algorithm with whether complications occur as an endpoint, and by adding a regularization term, the classification of the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object is finally achieved.
In an alternative embodiment, the similarity comparing unit 102 in the isodose line-based complication occurrence probability determining device is configured to compare the similarity of every two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object, where the isodose value is the isodose value corresponding to the isodose line.
Alternatively, it is assumed that N isodose lines corresponding to the first object are respectively an isodose line A1 (corresponding dose value is a-11), an isodose line A2 (corresponding dose value is a-12), and an isodose line A3 (corresponding dose value is a-13), wherein the isodose line distribution image corresponding to the first object based on the isodose line A1 is an isodose line distribution image B1, the isodose line distribution image corresponding to the first object based on the isodose line A2 is an isodose line distribution image B2, and the isodose line distribution image corresponding to the first object based on the isodose line A3 is an isodose line distribution image B3. The isodose line distribution image corresponding to the isodose line with the dose value of A-11 is an isodose line distribution image C1, the isodose line distribution image corresponding to the isodose line with the dose value of A-11 is an isodose line distribution image C2, and the isodose line distribution image corresponding to the isodose line with the dose value of A-11 is an isodose line distribution image C3.
The isodose line corresponding to the first object and the isodose line corresponding to the second object based on the same isodose value may be different or the same.
Alternatively, the similarity comparing unit 102 is configured to compare the similarity (may be denoted as F1) of the isodose line distribution image B1 and the isodose line distribution image C1, the similarity (may be denoted as F2) of the isodose line distribution image B2 and the isodose line distribution image C2, and the similarity (may be denoted as F3) of the isodose line distribution image B3 and the isodose line distribution image C3.
It should be noted that, the similarity of the two isodose line distribution images includes, but is not limited to, the similarity of image shapes and the similarity of data included in the images.
In an alternative embodiment, the processing unit 103 in the isodose line based complication occurrence probability determining device is configured to combine each two isodose line distribution images with a similarity smaller than a preset threshold as one target image.
Alternatively, the preset threshold may be set by user, and if the above F1 is smaller than the preset threshold and both F2 and F3 are greater than or equal to the preset threshold, the processing unit 103 combines the isodose line distribution image B1 and the isodose line distribution image C1 as one target image.
In an alternative embodiment, the determining unit 104 in the isodose line based complication occurrence probability determining device is configured to determine, based on the target image combination, a probability that a target organ of the target object is complication after receiving the radiotherapy, wherein the target object is an object different from the first object and the second object.
Alternatively, the target object may be a patient who is ready to receive radiation therapy, or a patient who has already received radiation therapy but has not yet developed complications.
As can be seen from the above, the present application achieves obtaining difference information between the isodose line distribution images of the first object and the second object based on the same isodose value by comparing the similarity of each two isodose line distribution images of the corresponding same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object. In addition, each two isodose line distribution images with the similarity smaller than a preset threshold value are used as a target image combination, and the probability of complications of a target organ of a target object after receiving radiation treatment is determined according to the target image combination, so that whether the complications occur to a patient after receiving radiation treatment can be predicted according to the isodose line distribution images of the patient with the complications and the isodose line distribution images of the patient without the complications, and the problem that whether the complications occur to the patient after receiving radiation treatment cannot be predicted according to difference information among isodose lines of different patients in the prior art is solved.
In an alternative embodiment, the acquisition unit 101 comprises: the device comprises a first acquisition subunit, a setting subunit, a first generation subunit and a second generation subunit.
Optionally, the first acquisition subunit is configured to acquire a target dose distribution image corresponding to a target organ of the first object.
The target organ may also be referred to as a region of interest (ROI Region of Interest), including a target region of radiotherapy and/or an organ at risk.
Optionally, the setting subunit is configured to set N isodose lines corresponding to the target organ of the first object in the target dose distribution image, where a distance between every two adjacent isodose lines in the N isodose lines is a preset distance.
Alternatively, the preset interval between every two adjacent isodose lines of the N isodose lines may be set in a custom manner, for example, as shown in fig. 2, the preset interval may be set to 100cgy, and when N is 5, the N isodose lines may be five isodose lines corresponding to five dose values of 1cgy, 101cgy, 201cgy, 301cgy, 401cgy, respectively.
In an alternative embodiment, the first generating subunit is configured to generate N isodose line mask images based on N isodose lines corresponding to the target organ of the first object in the target dose distribution image, where the N isodose lines and the N isodose line mask images are in a one-to-one correspondence, and each isodose line corresponding to the isodose line mask image includes at least a target image area surrounded by the isodose line.
Optionally, fig. 3 is a schematic diagram of an optional isodose line mask image according to an embodiment of the present application, specifically, fig. 3 is an isodose line mask image generated based on an isodose line (corresponding to 101 cgy), where a target image area surrounded by the isodose line may be filled with a first filling value (e.g. 1) (i.e. a hatched area in fig. 3), and an image area not surrounded by the isodose line may be filled with a second filling value (e.g. 0).
In an alternative embodiment, the second generating subunit is configured to generate N isodose line distribution images corresponding to the first object according to the N isodose line mask images.
Optionally, the second generating subunit includes a first processing module, where the first processing module is configured to multiply the N isodose line mask images with the target dose distribution image, and use a result of the multiplication as N isodose line distribution images corresponding to the first object, where the N isodose line distribution images corresponding to the first object have a one-to-one correspondence with the N isodose line mask images, and the isodose line distribution image corresponding to each of the N isodose line mask images is used to characterize dose distribution information corresponding to a target image area of the isodose line mask image.
Alternatively, after obtaining the N isodose line mask images corresponding to the first object, the first processing module may multiply one isodose line mask image (for example, the image Y1) corresponding to the first object with the target dose distribution image corresponding to the first object, thereby obtaining one isodose line distribution image (isodose line distribution image corresponding to the image Y1) corresponding to the first object, and since the first object has N isodose line mask images, N isodose line distribution images corresponding to the first object may be finally obtained.
In an alternative embodiment, the N isodose line distribution images of the second object are generated in a similar manner to the N isodose line distribution images of the first object, so that the first acquisition subunit is further configured to acquire a first dose distribution image corresponding to the target organ of the second object; the setting subunit is further configured to set N isodose lines corresponding to the target organ of the second object in the first dose distribution image, where a distance between every two adjacent isodose lines in the N isodose lines is a preset distance; the first generation subunit is further used for generating N isodose line mask images corresponding to the second object based on N isodose lines corresponding to the target organ of the second object in the first dose distribution image; the second generation subunit is further configured to generate N isodose line distribution images corresponding to the second object according to the N isodose line mask images corresponding to the second object.
Optionally, the first processing module is further configured to multiply the N isodose line mask images corresponding to the second object with the first dose distribution image, and use a result of the multiplication as N isodose line distribution images corresponding to the second object, where the N isodose line distribution images corresponding to the second object and the N isodose line mask images corresponding to the second object have a one-to-one correspondence.
In an alternative embodiment, the first acquisition subunit comprises: the system comprises a first acquisition module, a sketching module, a second acquisition module and a second processing module.
The first acquisition module is used for acquiring medical images corresponding to target organs of a first object; the sketching module is used for sketching the medical image to obtain a sketched image corresponding to the target organ of the first object, wherein the sketched image is used for representing outline information of the target organ of the first object in the medical image; the second acquisition module is used for acquiring a dose distribution image adopted by the first object in the radiotherapy process, wherein the dose distribution information contained in the dose distribution image at least comprises the dose distribution information contained in the target dose distribution image; and the second processing module is used for multiplying the sketched image and the dose distribution image and taking the multiplied result as a target dose distribution image corresponding to the target organ of the first object.
Optionally, the medical images include, but are not limited to, CT images, MR images, and CBCT images. The delineating operation can be to delineate the ROI in the medical image manually or by pre-training a neural network model.
Optionally, the first obtaining module may obtain a radiation treatment plan and a dose distribution image of the first object used in a radiation treatment process, where it is to be noted that the dose distribution image of the first object used in the radiation treatment process must include dose distribution information corresponding to each target region of the radiation treatment and dose distribution information corresponding to each organ at risk, but the target dose distribution image may only relate to a portion of the dose distribution information corresponding to the target region of the radiation treatment and/or the organ at risk, and therefore, the dose distribution information included in the dose distribution image of the first object used in the radiation treatment process includes at least the dose distribution information included in the target dose distribution image.
Optionally, the radiotherapy target region and/or the organs at risk related to the target dose distribution image are characterized by sketching images, so that the sketching images are multiplied by the dose distribution image adopted by the first object in the radiotherapy process, and the target dose distribution image corresponding to the target organs of the first object can be obtained.
In an alternative embodiment, the first obtaining module may be further configured to obtain a medical image corresponding to a target organ of the second object; the sketching module is further used for sketching the medical image corresponding to the target organ of the second object to obtain a sketched image corresponding to the target organ of the second object; the second acquisition module is also used for acquiring a dose distribution image adopted by the second object in the radiotherapy process; and the second processing module is used for multiplying the sketched image corresponding to the target organ of the second object by the dose distribution image adopted by the second object in the radiotherapy process, and taking the multiplied result as a first dose distribution image corresponding to the target organ of the second object.
In an alternative embodiment, the similarity comparison unit 102 includes: the device comprises a first extraction subunit, a second extraction subunit, a first processing subunit and a second processing subunit.
Optionally, the first extraction subunit is configured to extract an image feature of each isodose line distribution image in the N isodose line distribution images corresponding to the first object; the second extraction subunit is used for extracting the image characteristics of each isodose line distribution image in the N isodose line distribution images corresponding to the second object; a first processing subunit, configured to combine each two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object into an image set; and the second processing subunit is used for taking the image characteristic similarity between two isodose line distribution images in the image set as the similarity of the two isodose line distribution images.
Optionally, the image feature extraction method may be to manually identify and label the image feature, or extract the image feature through a pre-trained neural network model.
Alternatively, it is assumed that N isodose lines corresponding to the first object are respectively an isodose line A1 (corresponding dose value is a-11), an isodose line A2 (corresponding dose value is a-12), and an isodose line A3 (corresponding dose value is a-13), wherein the isodose line distribution image corresponding to the first object based on the isodose line A1 is an isodose line distribution image B1, the isodose line distribution image corresponding to the first object based on the isodose line A2 is an isodose line distribution image B2, and the isodose line distribution image corresponding to the first object based on the isodose line A3 is an isodose line distribution image B3. The isodose line distribution image corresponding to the isodose line with the dose value of A-11 is an isodose line distribution image C1, the isodose line distribution image corresponding to the isodose line with the dose value of A-11 is an isodose line distribution image C2, and the isodose line distribution image corresponding to the isodose line with the dose value of A-11 is an isodose line distribution image C3. On this basis, the similarity of the isodose line distribution image B1 and the isodose line distribution image C1 can be represented by the image feature similarity of the isodose line distribution image B1 and the isodose line distribution image C1; the similarity between the isodose line distribution image B2 and the isodose line distribution image C2 can be represented by the image feature similarity between the isodose line distribution image B2 and the isodose line distribution image C2; the similarity between the isodose line distribution image B3 and the isodose line distribution image C3 can be represented by the image feature similarity between the isodose line distribution image B3 and the isodose line distribution image C3.
In an alternative embodiment, the determining unit 104 comprises: the third processing subunit, the second acquisition subunit and the first determination subunit.
Optionally, the third processing subunit is configured to take the same isodose values corresponding to the two isodose distribution images in the target image combination as target isodose values; the second acquisition subunit is used for acquiring a target equivalent dose distribution image corresponding to a target organ of the target object under an equivalent dose line corresponding to a target equivalent dose value; a first determination subunit for determining a probability of a target organogenesis complication of the target subject from the target isodose distribution image and the target image combination.
Alternatively, taking the isodose line distribution image B1 and the isodose line distribution image C1 as one target image combination as an example, the isodose value corresponding to the isodose line distribution image B1 and the isodose line distribution image C1 together is a-11, and thus the third processing subunit takes the dose value a-11 as the target isodose value. After a dose distribution map corresponding to a target organ of a target object is acquired, an isodose line of a dose value A-11 is determined in the dose distribution image, and a target isodose distribution image based on the isodose line is acquired. Finally, the first determination subunit is configured to determine a probability of a target organogenesis complication of the target subject from the target isodose distribution image and the target image combination.
In an alternative embodiment, the first determining subunit comprises: the system comprises a third processing module, a fourth processing module, a first calculating module, a second calculating module and a first determining module.
Optionally, the third processing module is configured to take an isodose distribution image corresponding to the first object in the target image combination as a first isodose distribution image; a fourth processing module, configured to take an isodose distribution image corresponding to the second object in the target image combination as a second isodose distribution image; the first calculation module is used for calculating a first similarity between the target equal-dose distribution image and the first equal-dose distribution image; the second calculation module is used for calculating a second similarity between the target equal-dose distribution image and the first equal-dose distribution image; and the first determining module is used for determining the probability of the target organ occurrence complication of the target object according to the first similarity and the second similarity.
Alternatively, taking the isodose line distribution image B1 and the isodose line distribution image C1 as one target image combination as an example, the isodose line distribution image B1 is a first isodose distribution image, the isodose line distribution image C1 is a second isodose distribution image, and assuming that a target isodose distribution image corresponding to a target organ of the target object under an isodose line corresponding to a target isodose value is an isodose line distribution image D1, the similarity (corresponding to a first similarity, R1) between the isodose line distribution image B1 and the isodose line distribution image D1 is calculated by the first calculation module, and the similarity (corresponding to a second similarity, R2) between the isodose line distribution image C1 and the isodose line distribution image D1 is calculated by the second calculation module.
In the above example, if R1 is larger than R2, the isodose line distribution image B1 and the isodose line distribution image D1 are more similar, and since the isodose line distribution image B1 corresponds to the first subject whose target organ is complicated after receiving radiation treatment, the probability of the target organ of the target subject being complicated after receiving radiation treatment may be high. If R1 is smaller than R2, it is indicated that the isodose line distribution image C1 and the isodose line distribution image D1 have higher similarity, and since the isodose line distribution image C1 corresponds to the second object for which the target organ does not have complications after receiving radiation treatment, the probability of complications occurring in the target organ of the target object after receiving radiation treatment may be smaller.
In an alternative embodiment, the first determining module includes: a calculation sub-module and a determination sub-module.
Optionally, a calculating submodule is used for calculating the ratio of the first similarity to the second similarity; a determination submodule for determining the probability of the target organ occurrence complication of the target object according to the ratio.
Alternatively, assuming that r1=90% and r2=10% in the above example, the probability that the target subject may develop complications may be 90%/10% multiplied by a preset coefficient, thereby obtaining the probability that the target subject may develop complications, for example, 72% when the preset coefficient is 0.8.
It should be noted that, if the ratio of the first similarity to the second similarity is 1, that is, the first similarity and the second similarity are the same, the probability of occurrence of complications in the target organ of the target subject is 50%.
According to another aspect of the embodiments of the present application, there is further provided a computer readable storage medium, where the computer readable storage medium includes a stored computer program, and when the computer program runs, the isodose line-based complication occurrence probability determining apparatus of any one of the above is run by a device in which the computer readable storage medium is located.
According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the isodose line based complication occurrence probability determination apparatus of any of the above via execution of the executable instructions.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (10)
1. An isodose line-based complication occurrence probability determination device comprising:
an acquisition unit, configured to acquire N isodose line distribution images corresponding to N isodose lines for a first object and N isodose line distribution images corresponding to N isodose lines for a second object, where N is an integer greater than 1, the first object is an object of a target organ that has undergone complications after receiving radiotherapy, and the second object is an object of the target organ that has not undergone complications after receiving radiotherapy;
a similarity comparing unit, configured to compare the similarity of each two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object, where the isodose value is a dose value corresponding to an isodose line;
the processing unit is used for combining every two isodose line distribution images with the similarity smaller than a preset threshold value as a target image;
and the determining unit is used for determining the probability of complications of a target organ of a target object after receiving radiation treatment according to the target image combination, wherein the target object is an object different from the first object and the second object.
2. The isodose line-based complication occurrence probability determination apparatus according to claim 1, wherein the acquisition unit comprises:
a first acquisition subunit, configured to acquire a target dose distribution image corresponding to a target organ of the first object;
the setting subunit is used for setting N isodose lines corresponding to a target organ of the first object in the target dose distribution image, wherein the interval between every two adjacent isodose lines in the N isodose lines is a preset interval;
a first generating subunit, configured to generate N isodose line mask images based on N isodose lines corresponding to a target organ of the first object in the target dose distribution image, where the N isodose lines and the N isodose line mask images are in a one-to-one correspondence, and each isodose line mask image corresponding to an isodose line includes at least a target image area surrounded by the isodose line;
and the second generation subunit is used for generating N isodose line distribution images corresponding to the first object according to the N isodose line mask images.
3. The isodose line-based complication occurrence probability determination apparatus of claim 2, wherein the second generation subunit comprises:
The first processing module is configured to multiply the N isodose line mask images with the target dose distribution image respectively, and use a result of the multiplication as N isodose line distribution images corresponding to the first object, where the N isodose line distribution images corresponding to the first object have a one-to-one correspondence with the N isodose line mask images, and the isodose line distribution image corresponding to each of the N isodose line mask images is used to characterize dose distribution information corresponding to a target image area of the isodose line mask image.
4. The isodose line-based complication occurrence probability determination apparatus of claim 2, wherein the first acquisition subunit comprises:
the first acquisition module is used for acquiring medical images corresponding to target organs of the first object;
the sketching module is used for sketching the medical image to obtain a sketched image corresponding to the target organ of the first object, wherein the sketched image is used for representing outline information of the target organ of the first object in the medical image;
the second acquisition module is used for acquiring a dose distribution image adopted by the first object in the radiotherapy process, wherein the dose distribution information contained in the dose distribution image at least comprises the dose distribution information contained in the target dose distribution image;
And the second processing module is used for multiplying the sketched image and the dose distribution image and taking the multiplied result as a target dose distribution image corresponding to a target organ of the first object.
5. The isodose line-based complication occurrence probability determination apparatus according to claim 1, wherein the similarity comparison unit comprises:
a first extraction subunit, configured to extract an image feature of each isodose line distribution image in N isodose line distribution images corresponding to the first object;
a second extraction subunit, configured to extract an image feature of each isodose line distribution image in the N isodose line distribution images corresponding to the second object;
a first processing subunit, configured to combine each two isodose line distribution images corresponding to the same isodose value in the N isodose line distribution images corresponding to the first object and the N isodose line distribution images corresponding to the second object into an image set;
and the second processing subunit is used for taking the image characteristic similarity between the two isodose line distribution images in the image set as the similarity of the two isodose line distribution images.
6. The isodose line-based complication occurrence probability determination apparatus according to claim 1, wherein the determination unit comprises:
a third processing subunit, configured to take the same isodose values corresponding to the two isodose distribution images in the target image combination as target isodose values;
a second obtaining subunit, configured to obtain a target isodose distribution image corresponding to a target organ of the target object under an isodose line corresponding to the target isodose value;
a first determination subunit configured to determine a probability of a target organogenesis complication of the target object from the target isodose distribution image and the target image combination.
7. The isodose line-based complication occurrence probability determination apparatus of claim 6, wherein the first determination subunit comprises:
a third processing module, configured to take an isodose distribution image corresponding to the first object in the target image combination as a first isodose distribution image;
a fourth processing module, configured to take an isodose distribution image corresponding to the second object in the target image combination as a second isodose distribution image;
A first calculation module, configured to calculate a first similarity between the target isodose distribution image and the first isodose distribution image;
a second calculation module for calculating a second similarity between the target isodose distribution image and the first isodose distribution image;
a first determination module for determining a probability of a target organogenic complication of the target subject based on the first similarity and the second similarity.
8. The isodose line-based complication occurrence probability determination apparatus of claim 7, wherein the first determination module comprises:
a calculating sub-module for calculating a ratio of the first similarity to the second similarity;
a determination submodule for determining the probability of the target organ occurrence complication of the target object according to the ratio.
9. A computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and wherein the isodose line-based complication occurrence probability determining apparatus according to any one of claims 1 to 8 is operated by a device in which the computer readable storage medium is located when the computer program is operated.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to control the isodose line based complication occurrence probability determination apparatus of any of claims 1 to 8 to operate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410158045.5A CN117690551A (en) | 2024-02-04 | 2024-02-04 | Isodose line-based complication occurrence probability determining device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410158045.5A CN117690551A (en) | 2024-02-04 | 2024-02-04 | Isodose line-based complication occurrence probability determining device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117690551A true CN117690551A (en) | 2024-03-12 |
Family
ID=90137619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410158045.5A Pending CN117690551A (en) | 2024-02-04 | 2024-02-04 | Isodose line-based complication occurrence probability determining device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117690551A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992058A (en) * | 2015-06-25 | 2015-10-21 | 成都厚立信息技术有限公司 | Disease risk regulation model establishment method |
| US20170083682A1 (en) * | 2014-05-15 | 2017-03-23 | The Johns Hopkins University | Method, system and computer-readable media for treatment plan risk analysis |
| KR101831340B1 (en) * | 2016-09-07 | 2018-02-23 | 서울여자대학교 산학협력단 | Method and apparatus for automatic segmentation of renal parenchyma using graph-cuts with shape constraint based on multi-probabilistic atlas in abdominal ct images |
| US20180099001A1 (en) * | 2011-04-29 | 2018-04-12 | Volant Holdings Gmbh | Diagnostics and methods for treatment of non-alcoholic hepatic steatosis and hepatic steatohepatitis, and prevention of complications thereof |
| CN110604550A (en) * | 2019-09-24 | 2019-12-24 | 广州医科大学附属肿瘤医院 | Prediction method of normal tissue organ complications after tumor radiotherapy |
| WO2021151342A1 (en) * | 2020-09-07 | 2021-08-05 | 平安科技（深圳）有限公司 | Dose prediction method and apparatus in radiotherapy planning, and computer device and storage medium |
| US20220296924A1 (en) * | 2021-03-22 | 2022-09-22 | Varian Medical Systems, Inc. | Artificial intelligence modeling for radiation therapy dose distribution analysis |
| CN117198543A (en) * | 2023-09-18 | 2023-12-08 | 北京紫云智能科技有限公司 | Wound resuscitation unit complication prediction model training and prediction method and electronic equipment |
-
2024
- 2024-02-04 CN CN202410158045.5A patent/CN117690551A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180099001A1 (en) * | 2011-04-29 | 2018-04-12 | Volant Holdings Gmbh | Diagnostics and methods for treatment of non-alcoholic hepatic steatosis and hepatic steatohepatitis, and prevention of complications thereof |
| US20170083682A1 (en) * | 2014-05-15 | 2017-03-23 | The Johns Hopkins University | Method, system and computer-readable media for treatment plan risk analysis |
| CN104992058A (en) * | 2015-06-25 | 2015-10-21 | 成都厚立信息技术有限公司 | Disease risk regulation model establishment method |
| KR101831340B1 (en) * | 2016-09-07 | 2018-02-23 | 서울여자대학교 산학협력단 | Method and apparatus for automatic segmentation of renal parenchyma using graph-cuts with shape constraint based on multi-probabilistic atlas in abdominal ct images |
| CN110604550A (en) * | 2019-09-24 | 2019-12-24 | 广州医科大学附属肿瘤医院 | Prediction method of normal tissue organ complications after tumor radiotherapy |
| WO2021151342A1 (en) * | 2020-09-07 | 2021-08-05 | 平安科技（深圳）有限公司 | Dose prediction method and apparatus in radiotherapy planning, and computer device and storage medium |
| US20220296924A1 (en) * | 2021-03-22 | 2022-09-22 | Varian Medical Systems, Inc. | Artificial intelligence modeling for radiation therapy dose distribution analysis |
| CN117198543A (en) * | 2023-09-18 | 2023-12-08 | 北京紫云智能科技有限公司 | Wound resuscitation unit complication prediction model training and prediction method and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| DANDAN WANG ET AL.: "Dosimetric predictors and Lyman normal tissue complication probability model of hematological toxicity in cervical cancer patients with treated with pelvic irradiation", MEDICAL PHYSICS, 31 January 2022 (2022-01-31), pages 756 - 766 * |
| 陈嘉伟 等: "宫颈癌放疗中基于精确表面剂量累加的直肠并发症预测模型", 南方医科大学学报, no. 12, 20 December 2017 (2017-12-20), pages 1626 - 1631 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11727569B2 (en) | Training a CNN with pseudo ground truth for CT artifact reduction | |
| US9792703B2 (en) | Generating a synthetic two-dimensional mammogram | |
| CN110097611A (en) | Image rebuilding method, device, equipment and storage medium | |
| US9600856B2 (en) | Hybrid point-based registration | |
| KR101957811B1 (en) | Method for computing severity with respect to dementia of subject based on medical image and apparatus using the same | |
| CN117274235B (en) | Determination device for radiotherapy curative effect, electronic equipment and storage medium | |
| CN105556507A (en) | Method and system for statistical modeling of data using a quadratic likelihood functional | |
| CN112150376B (en) | Vascular medical image analysis method, vascular medical image analysis device, vascular medical image analysis computer equipment and vascular medical image storage medium | |
| CN111145160B (en) | Method, device, server and medium for determining coronary artery branches where calcified regions are located | |
| CN113159040B (en) | Method, device and system for generating medical image segmentation model | |
| CN116072263B (en) | Planning parameter prediction device based on radiotherapy | |
| CN116030938B (en) | Determination device for radiotherapy dosage distribution interval and electronic equipment | |
| US20210110520A1 (en) | Method and system for simulating and constructing original medical images from one modality to other modality | |
| Xie et al. | Contextual loss based artifact removal method on CBCT image | |
| CN116844734B (en) | Method and device for generating dose prediction model, electronic equipment and storage medium | |
| Flaus et al. | PET image enhancement using artificial intelligence for better characterization of epilepsy lesions | |
| CN113888566A (en) | Target contour curve determining method and device, electronic equipment and storage medium | |
| CN111723836A (en) | Image similarity calculation method and device, electronic equipment and storage medium | |
| US20200376295A1 (en) | Determining at least one final two-dimensional image for visualizing an object of interest in a three dimensional ultrasound volume | |
| CN117690551A (en) | Isodose line-based complication occurrence probability determining device and electronic equipment | |
| CN114463459B (en) | Partial volume correction method, device, equipment and medium for PET image | |
| Bergamasco et al. | A new local feature extraction approach for content-based 3D medical model retrieval using shape descriptor | |
| CN117717723A (en) | Portal information determining device, processor and electronic equipment | |
| US11823399B2 (en) | Multi-scan image processing | |
| US11430126B2 (en) | Method and image processing apparatus for the segmentation of image data and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |