CN110833395B - Mammary fat level determination method and device - Google Patents
Mammary fat level determination method and device Download PDFInfo
- Publication number
- CN110833395B CN110833395B CN201911122300.6A CN201911122300A CN110833395B CN 110833395 B CN110833395 B CN 110833395B CN 201911122300 A CN201911122300 A CN 201911122300A CN 110833395 B CN110833395 B CN 110833395B
- Authority
- CN
- China
- Prior art keywords
- breast
- target
- sample
- fat level
- mammary gland
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4869—Determining body composition
- A61B5/4872—Body fat
Abstract
The disclosure relates to the technical field of biomedicine, in particular to a method and a device for determining mammary gland fat level. By acquiring the time sequence of the target mammary gland and acquiring the fat level of the target mammary gland according to the time sequence of the target mammary gland, the fat level of the target mammary gland can be acquired without exposure photography of the target mammary gland, and the radiation quantity borne by the target mammary gland can be reduced.
Description
Technical Field
The disclosure relates to the technical field of biomedicine, in particular to a method and a device for determining mammary gland fat level.
Background
At present, when a mammary gland X-ray machine is used for detecting mammary glands, corresponding exposure parameters are generally adopted for mammary glands with different thicknesses according to experience to ensure the penetrating capability of X-rays, but the composition difference inside the mammary glands is ignored, so that the finally obtained mammary gland image cannot reflect the real condition of the mammary glands. If the corresponding exposure parameters are selected according to the fat level of the mammary gland, a mammary gland image reflecting the real condition of the mammary gland can be obtained. However, there is a lack in the art of methods or devices that can obtain breast fat levels without exposing the breast to light.
Disclosure of Invention
In order to achieve the purpose of obtaining the fat level of the breast without performing exposure photography on the breast, the present disclosure provides a breast fat level determination method and apparatus.
In one aspect, the present disclosure provides a method of determining a breast fat level, the method comprising:
acquiring a time sequence of a target mammary gland, wherein the time sequence of the target mammary gland is a time sequence of the compression thickness of the target mammary gland and the supporting force of the target mammary gland on a compression device;
based on the first identification system, the fat level of the target breast is obtained according to the time sequence of the target breast, the time sequence of the target breast is input into the first identification system, the fat level of the target breast is output from the first identification system, and the first identification system is established according to the sample time sequence and the sample fat level.
Optionally, acquiring the time series of the target breast comprises:
acquiring the compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device at fixed intervals;
judging whether the difference value between the currently acquired supporting force of the target breast on the compression device and the supporting force of the target breast on the compression device acquired at the previous time is larger than a first threshold value or not;
if so, recording the currently acquired compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device in a binary form; if not, the currently acquired compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device are not recorded;
And if the difference value between the continuously obtained supporting force of the fixed number of target mammary glands on the compression device and the supporting force of the target mammary glands on the compression device obtained in the previous time is not larger than a first threshold value, forming a time sequence of the target mammary glands according to the recording time of the binary group.
Optionally, the first recognition system is obtained by training the long-short term memory network model by using a training sample consisting of a sample time sequence and a sample fat level.
Optionally, the sample fat level is obtained based on a second recognition system, an input of the second recognition system is an image of the sample breast, and an output of the second recognition system is a sample fat level corresponding to the sample breast.
Optionally, the second recognition system is obtained by training the convolutional neural network model by using a training sample composed of an image of the sample breast and a sample fat level corresponding to the sample breast.
In another aspect, the present disclosure provides a breast fat level determination apparatus, the apparatus comprising:
a first acquisition module configured to acquire a time series of a target breast, the time series of the target breast being a compression thickness of the target breast and a time series of a supporting force of the target breast to the compression device;
A second obtaining module configured to obtain the fat level of the target breast according to a time series of the target breast based on the first recognition system, the time series of the target breast being an input of the first recognition system, the fat level of the target breast being an output of the first recognition system, the first recognition system being established according to the sample time series and the sample fat level.
Optionally, the first obtaining module includes:
a first acquisition unit configured to acquire a compression thickness of the target breast and a supporting force of the target breast to the compression device at fixed time intervals;
the first judgment unit is configured to judge whether the difference value between the currently acquired supporting force of the target breast on the compression device and the supporting force of the target breast on the compression device acquired at the previous time is larger than a first threshold value;
the recording unit is configured to record the currently acquired compression thickness of the target breast and the supporting force of the target breast on the compression device in a binary group mode if the compression thickness is larger than the first threshold;
and the recording unit is also configured to form a time sequence of the target mammary gland according to the recording time of the binary group if the difference value between the continuously obtained supporting force of the fixed number of target mammary glands on the compression device and the supporting force of the target mammary gland on the compression device obtained at the previous time is not larger than a first threshold value.
Optionally, the first recognition system is obtained by training the long-short term memory network model by using a training sample consisting of a sample time sequence and a sample fat level.
Optionally, the sample fat level is obtained based on a second recognition system, the input of the second recognition system is an image of the sample breast, and the output of the second recognition system is the sample fat level corresponding to the sample breast.
In yet another aspect, the present disclosure provides a breast fat level determination apparatus, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to cause the breast fat level determination apparatus to perform the above-described breast fat level determination method when executing the executable instructions.
The beneficial effects brought by the technical scheme provided by the embodiment of the disclosure at least comprise:
by acquiring the time sequence of the target mammary gland and acquiring the fat level of the target mammary gland according to the time sequence of the target mammary gland, the fat level of the target mammary gland can be acquired without exposure photography of the target mammary gland, and the radiation quantity borne by the target mammary gland can be reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
Fig. 1 is a schematic diagram of a breast fat level determination method provided by an exemplary embodiment of the present disclosure;
fig. 2 is a schematic diagram of a breast fat level determination method provided by another exemplary embodiment of the present disclosure;
fig. 3 is a schematic diagram of a breast fat level determination apparatus provided in an exemplary embodiment of the present disclosure.
Detailed Description
The present disclosure will be described in further detail with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limitations of the present disclosure. It should be further noted that, for the convenience of description, only the portions relevant to the present disclosure are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In the prior art, when acquiring the fat level of the breast, it is usually necessary to first perform exposure photography on the breast and then acquire the fat level of the breast according to the obtained breast image. This causes the breast to be exposed more than once, which is likely to cause damage to the subject's body. Therefore, there is a need for a method or apparatus that can obtain the fat level of the breast without exposing the breast to light.
The first embodiment of the present disclosure provides a method for determining a mammary gland fat level, as shown in fig. 1, which is applied to a mammary gland X-ray machine, and the method includes:
step S101, acquiring a time sequence of a target mammary gland, wherein the time sequence of the target mammary gland is a time sequence of the compression thickness of the target mammary gland and the supporting force of the target mammary gland to a compression device;
step S102, based on the first identification system, obtaining the fat level of the target breast according to the time sequence of the target breast, wherein the time sequence of the target breast is input to the first identification system, the fat level of the target breast is output from the first identification system, and the first identification system is established according to the sample time sequence and the sample fat level.
Optionally, obtaining the time series of the target breast comprises:
acquiring the compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device at fixed intervals;
judging whether the difference value between the currently acquired supporting force of the target breast on the compression device and the supporting force of the target breast on the compression device acquired at the previous time is larger than a first threshold value or not;
if so, recording the currently acquired compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device in a binary form; if not, the currently acquired compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device are not recorded;
And if the difference value between the continuously obtained supporting force of the fixed number of target mammary glands on the compression device and the supporting force of the target mammary glands on the compression device obtained in the previous time is not larger than a first threshold value, forming a time sequence of the target mammary glands according to the recording time of the binary group.
Optionally, the first recognition system is obtained by training the long-short term memory network model by using a training sample consisting of a sample time sequence and a sample fat level.
Optionally, the sample fat level is obtained based on a second recognition system, an input of the second recognition system is an image of the sample breast, and an output of the second recognition system is a sample fat level corresponding to the sample breast.
Optionally, the second recognition system is obtained by training the convolutional neural network model by using a training sample composed of an image of the sample breast and a sample fat level corresponding to the sample breast.
In this embodiment, by acquiring the time sequence of the target breast and acquiring the fat level of the target breast according to the time sequence of the target breast, the fat level of the target breast can be acquired without performing exposure photography on the target breast, so that the radiation dose borne by the target breast can be reduced.
A second embodiment of the present disclosure provides a method for determining a mammary gland fat level, as shown in fig. 2, which is applied to a mammary gland X-ray machine, and the method includes:
step S201, a time series of the target breast is acquired.
The target mammary gland refers to a mammary gland to be detected, and the time sequence of the target mammary gland is the compression thickness of the target mammary gland and the time sequence of the supporting force of the target mammary gland on the compression device.
In one possible implementation, obtaining the time series of the target breast includes:
(1) and acquiring the compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device at fixed intervals.
When the mammary gland X-ray machine is used for detecting a target mammary gland, a pressing device arranged on the mammary gland X-ray machine can continuously apply acting force to the target mammary gland, and the acting force can be an increasing force. By applying acting force to the target mammary gland, the position of the target mammary gland can be fixed, the internal structure of the target mammary gland can be closer to a intensifying screen-film on the mammary gland X-ray machine, and the blurring degree of the finally output image can be reduced. In the process of applying force to the target breast by the compression device, the compression thickness of the target breast may change, and the supporting force of the target breast to the compression device may also change.
The compression device can obtain the compression thickness of the target mammary gland and the supporting force of the target mammary gland to the compression device at fixed time intervals. Wherein, the supporting force of the mammary gland on the pressing device is equal to the pressing force born by the target mammary gland. For example, the compression device may acquire the compression thickness of the target breast and the supporting force of the target breast to the compression device every 2s,3s or 4 s. The specific value of the fixed time can be set by a technician or a user of the mammary X-ray machine.
(2) And judging whether the difference value between the currently acquired supporting force of the target breast on the compression device and the supporting force of the target breast on the compression device acquired at the previous time is greater than a first threshold value.
After the compression device acquires the compression thickness of the target breast and the supporting force of the target breast to the compression device, the currently acquired supporting force F of the target breast to the compression device can be judgedi+1The supporting force F of the target mammary gland on the compression device acquired at the previous timeiIs equal to (Δ F) is greater than (Δ F ═ F)i+1-Fi|) is greater than the first threshold. Wherein i is a positive integer of 1 or more, FiAnd the support force of the obtained ith target mammary gland on the compression device is shown. By determining whether Δ F is greater than the first threshold, it can be determined whether the variation range of the supporting force of the target breast to the compression apparatus does not exceed the first threshold, or whether the supporting force of the target breast to the compression apparatus varies. The specific value of the first threshold may be set by a technician or the user of the mammography machine. For example, the specific value of the first threshold may be 2N or 3N, etc.
(3) If the delta F is larger than the first threshold value, recording the currently acquired compression thickness of the target mammary gland and the supporting force of the target mammary gland on the compression device in a binary form; otherwise, the currently acquired compression thickness of the target breast and the supporting force of the target breast to the compression device are not recorded.
If Δ F is greater than the first threshold, then it may be in binary (T)i+1,Fi+1) Recording the currently acquired compression thickness T of the target breasti+1And the supporting force F of the target breast to the compression devicei+1At the same time or later, the compression thickness T of the target mammary gland at the next time can be obtained continuouslyi+2And the supporting force F of the target breast to the compression devicei+2. If Δ F is not greater than the first threshold, the compression thickness T of the target breast at the next time can be directly obtainedi+2And the supporting force F of the target mammary gland to the compression devicei+2。
(4) If the difference value between the continuously obtained supporting force of the fixed number of target mammary glands on the compression device and the supporting force of the target mammary glands on the compression device obtained in the previous time is not larger than the first threshold value, forming a time sequence of the target mammary glands according to the recording time of the binary group, and taking the finally obtained compression thickness of the target mammary glands as the steady-state thickness. Wherein the specific numerical value of the fixed number can be set by a technician or a user of the mammary X-ray machine.
For example, if none of the continuously obtained 3 or 5 Δ F is greater than the first threshold value, it can be determined that the supporting force of the target breast to the compression apparatus has stabilized. At this point, all the tuples (T) of the record may be recordedi+1,Fi+1) Forming a time sequence according to the acquired time sequence (T)i+1,Fi+1)j}. Wherein (T)i+1,Fi+1)jAnd j is a positive integer which is greater than or equal to 1 and represents the jth binary group acquired successively according to the recording time. After the supporting force of the target breast to the compression device tends to be stable, the target breast can be determined to enter a stable state, and the compression thickness of the target breast and the supporting force of the target breast to the compression device are not acquired at the moment.
Step S202, based on the first identification system, obtaining the fat level of the target mammary gland according to the time sequence of the target mammary gland.
The first identification system is established based on the sample time series and the sample fat level, the time series of the target breast is an input of the first identification system, and the fat level of the target breast is an output of the first identification system. The first recognition system can be obtained by training the long-term and short-term memory network model by using a training sample consisting of a sample time sequence and a sample fat level.
In one possible implementation, the first recognition system may be established as follows:
(1) Obtaining a sample time series and a sample fat level;
(2) establishing a long-term and short-term memory network model for image recognition;
(3) training the model off-line by using a training sample consisting of a sample time sequence and a sample fat level;
(4) after the model is trained, a first recognition system is obtained.
The sample time series may be a time series of sample breasts obtained by detecting the sample breasts by a conventional exposure method before the first identification system is established. The time series of the sample mammary gland can be obtained as described above for obtaining the time series of the target mammary gland, or can be obtained according to other prior arts. The sample breast here is understood to be a breast which is detected by conventional exposure means. The sample fat level refers to the fat level of the sample mammary gland, i.e. each sample mammary gland corresponds to a sample time series and a sample fat level. The sample fat level corresponding to the sample breast can be determined by a technician according to the ratio of the gland and the fat in the sample breast image in combination with the working experience. However, considering that the number of sample breasts is relatively large, it takes a lot of time to completely and manually evaluate the fat level of the breast image of the sample, so the sample fat level corresponding to the sample breast can also be obtained by the following steps:
(a) An image of a portion of the sample breast is acquired.
From the above, the sample mammary gland is the mammary gland detected by the conventional exposure method. Thus, the breast image comprised in the set of images of the sample breast may be an image of the sample breast acquired under conventional exposure control. Since the number of sample breasts is very large, in order to save workload, images of a part of the sample breasts may be acquired to form a sample image set for subsequent use.
(b) The fat level of each breast image in the sample image set is determined.
Since the gray values of breast images with different fat levels are often different, the fat level of each breast image can be determined from the gray values of each breast image in the sample image set. For example, a preset number of different and continuous gray scale intervals may be set, and each gray scale interval corresponds to a level of a fat level. For example, when the same dose level is taken, the lower the fat level of the breast of a unit thickness is, the lower the average gray scale value of the breast region in the acquired image is, so 10 consecutive gray scale intervals may be set in the order of gray scale values from low to high, and the breast fat level may be divided into 10 levels from low to high, where each gray scale interval corresponds to the level of one fat level. For example, 10 consecutive gray levels of a first gray level section and a second gray level section … … tenth gray level section may be set in order of gray level from low to high, the fat level of the breast may be divided into ten levels of one level and two levels … … tenth levels from low to high, and each gray level section may be in one-to-one correspondence with each fat level (e.g., the first gray level section corresponds to a first fat level, and the second gray level section corresponds to a second fat level, etc.). Before determining the fat level of each breast image in the sample image set, the mean gray value of each breast image may be obtained. After the average gray value of each breast image is obtained, the gray level section corresponding to the average gray value of the breast image, that is, the gray level section in which the gray value of the breast image is located, can be determined. Then, the fat level corresponding to the breast image can be determined according to the level of the fat level corresponding to the gray scale interval.
After the fat level of each breast image in the sample image set is obtained, the fat level of each breast image can be used as a label of each breast image, that is, each breast image has a label representing its fat level.
It should be noted that the above method for acquiring the fat level of the breast image according to the gray scale values can also be used to acquire the fat levels of all the sample breasts, but this will definitely increase the workload and consume a lot of time.
(c) And establishing a convolutional neural network model for image recognition.
(d) Using a training sample composed of labels corresponding to each mammary gland image and each mammary gland image in a sample image set { (image)i,labeli) The model is trained. Wherein, the imageiFor the ith breast image, labeliIs a label of the ith mammary gland image, and i is a positive integer greater than or equal to 1. In addition, the model can be trained using a gradient back propagation algorithm.
After the training of the convolutional neural network model is completed, a second recognition system based on the convolutional neural network can be obtained. Through the second identification system, the single-frame breast image can be used as input, namely, the label corresponding to the fat level of the breast image can be output, namely, the breast image of the sample breast is used as input, and the sample fat level corresponding to the sample breast can be output.
After the sample time sequence and the sample fat level corresponding to the sample mammary gland are obtained, the sample time sequence and the sample fat level can be combined into a training sample to train the established long-short term memory network model. Wherein, the long-term and short-term memory network model can be trained by adopting a gradient back propagation algorithm.
After the long-short term memory network model is trained, a first recognition system based on the long-short term memory network can be obtained. By constructing the first recognition system, the fat level of the target breast can be acquired according to the first recognition system after acquiring the time series of the target breast without performing exposure photography on the target breast.
It should be noted that, establishing a convolutional neural network model and a long-short term memory network model, and training the convolutional neural network model and the long-short term memory network model are relatively mature prior art, and are not described herein again.
In a possible implementation manner, after the first recognition system and the second recognition system are obtained, the first recognition system and the second recognition system may be modified respectively. For example, a breast image with a known fat level may be used as an input of the second recognition system, and it is determined whether a difference between the fat level output by the second recognition system and the actual fat level of the breast image is smaller than a second threshold, if so, it is determined that a result of the second recognition system is accurate, that is, the second recognition system is not required to be modified, otherwise, it is determined that the second recognition system is required to be modified. The specific value of the second threshold may be set by a technician or a user of the mammography apparatus, for example, the second threshold may be 0.03 or 0.05. In the correction of the second recognition system, the output result of the second recognition system may be multiplied by the correction coefficient. Wherein, the specific value of the correction coefficient needs to be selected according to the actual situation. For example, if the fat level output by the second recognition system is much greater than the true fat level of the breast image, the correction factor may be set to 0.7 or 0.8, etc., which is less than 1; if the fat level output by the second recognition system is much less than the true fat level of the breast image, the correction factor may be set to 1.2 or 1.3, etc., which is greater than 1.
When the first recognition system is corrected, the time series corresponding to the mammary gland with known fat level can be used as the input of the first recognition system, whether the difference value between the fat level output by the first recognition system and the real fat level of the mammary gland image is smaller than a third threshold value or not is judged, if yes, the result of the first recognition system is determined to be accurate, namely, the first recognition system is not required to be corrected, and if not, the second recognition system is determined to be required to be corrected. The specific value of the third threshold may be set by a technician or a user of the mammography apparatus, for example, the third threshold may be 0.03 or 0.05. In the correction of the first recognition system, the output result of the first recognition system may be multiplied by a correction coefficient. Wherein, the specific value of the correction coefficient needs to be selected according to the actual situation. For example, if the fat level output by the first recognition system is much greater than the true fat level of the breast image, the correction coefficient may be set to 0.7 or 0.8, etc., which is less than 1; if the fat level output by the first recognition system is much smaller than the true fat level of the breast image, the correction factor may be set to 1.2 or 1.3, etc., which is larger than 1.
In this embodiment, by acquiring the time sequence of the target breast and acquiring the fat level of the target breast according to the time sequence of the target breast, the fat level of the target breast can be acquired without performing exposure photography on the target breast, so that the radiation dose borne by the target breast can be reduced.
A third embodiment of the present disclosure provides a mammary gland fat level determination apparatus 300, as shown in fig. 3, the apparatus 300 being applied to a mammary gland X-ray machine, the apparatus 300 including:
a first obtaining module 301, wherein the first obtaining module 301 is configured to obtain a time series of a target breast, and the time series of the target breast is a time series of a compression thickness of the target breast and a supporting force of the target breast to the compression device;
a second obtaining module 302, wherein the second obtaining module 302 is configured to obtain the fat level of the target breast according to a time series of the target breast based on the first identification system, the time series of the target breast is an input of the first identification system, the fat level of the target breast is an output of the first identification system, and the first identification system is established according to the sample time series and the sample fat level.
Optionally, the first obtaining module 301 includes:
A first acquisition unit configured to acquire a compression thickness of a target breast and a supporting force of the target breast to the compression device at fixed time intervals;
the first judgment unit is configured to judge whether the difference value between the currently acquired supporting force of the target breast on the compression device and the supporting force of the target breast on the compression device acquired at the previous time is larger than a first threshold value;
the recording unit is configured to record the currently acquired compression thickness of the target breast and the supporting force of the target breast on the compression device in a binary group mode if the compression thickness is larger than the first threshold;
and the recording unit is also configured to form a time sequence of the target mammary gland according to the recording time of the binary group if the difference value between the continuously obtained supporting force of the fixed number of target mammary glands on the compression device and the supporting force of the target mammary gland on the compression device obtained at the previous time is not larger than a first threshold value.
Optionally, the first recognition system is obtained by training the long-short term memory network model by using a training sample consisting of a sample time sequence and a sample fat level.
Optionally, the sample fat level is obtained based on a second recognition system, an input of the second recognition system is an image of the sample breast, and an output of the second recognition system is a sample fat level corresponding to the sample breast.
In this embodiment, by acquiring the time sequence of the target breast and acquiring the fat level of the target breast according to the time sequence of the target breast, the fat level of the target breast can be acquired without performing exposure photography on the target breast, so that the radiation amount borne by the target breast can be reduced.
It should be noted that, when the breast fat level determining apparatus provided in the foregoing embodiment is used to obtain the breast fat level, only the division of the above functional modules is illustrated, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure or program of the apparatus may be divided into different functional modules to complete all or part of the above described functions. In addition, the mammary gland fat level determining device provided by the above embodiment and the mammary gland fat level determining method embodiment belong to the same concept, and the specific implementation process thereof is described in the method embodiment, and is not described again.
A fourth embodiment of the present disclosure provides a mammary fat level determination apparatus, which may be a mammary X-ray machine. The mammary fat level determination apparatus includes:
a processor;
a memory for storing processor-executable instructions;
Wherein the processor is configured to cause the breast fat level determination apparatus to perform the breast fat level determination method described in the above embodiments when executing the executable instructions.
A fifth embodiment of the present disclosure provides a non-transitory computer-readable storage medium, which may be a computer-readable storage medium contained in the memory in the above-described embodiments; or it may be a separate computer-readable storage medium not incorporated in the terminal. The computer-readable storage medium has stored therein one or more computer-readable instructions (programs) that, when executed by a processor of an electronic device, cause the electronic device to perform the breast fat level determination method described in the above embodiments.
In the description herein, reference to the description of the terms "one embodiment/mode," "some embodiments/modes," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/mode or example is included in at least one embodiment/mode or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to be the same embodiment/mode or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/aspects or examples and features of the various embodiments/aspects or examples described in this specification can be combined and combined by one skilled in the art without conflicting therewith.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In the description of the present disclosure, "plurality" means at least two, e.g., two, three, etc., unless explicitly defined otherwise.
It will be understood by those skilled in the art that the foregoing embodiments are provided merely for clarity of explanation and are not intended to limit the scope of the disclosure. Other variations or modifications may be made to those skilled in the art, based on the above disclosure, and still be within the scope of the present disclosure.
Claims (8)
1. A method of determining breast fat levels, the method comprising:
acquiring a time sequence of a target mammary gland, wherein the time sequence is the time sequence of the compression thickness of the target mammary gland and the supporting force of the target mammary gland to a compression device;
based on a first identification system, acquiring the fat level of the target mammary gland according to the time sequence, wherein the time sequence is input into the first identification system, the fat level is output from the first identification system, and the first identification system is established according to the sample time sequence and the sample fat level;
The acquiring the time series of the target breast comprises:
acquiring the compression thickness of the target mammary gland and the supporting force of the target mammary gland to a compression device at fixed time intervals;
judging whether the difference value between the currently acquired supporting force of the target breast on the compression device and the supporting force of the target breast on the compression device acquired at the previous time is larger than a first threshold value or not;
if so, in binary (T)i+1,Fi+1) Recording the currently acquired compression thickness of the target breast and the supporting force of the target breast on a compression device; if not, not recording the currently obtained compression thickness of the target mammary gland and the supporting force of the target mammary gland to the compression device;
if the difference between the continuously obtained support force of the target breasts on the compression device in a fixed number and the support force of the target breasts on the compression device obtained at the previous time is not more than the first threshold value, forming the time sequence (T) according to the recording time of the binary groupi+1,Fi+1)j。
2. The method of claim 1, wherein the first recognition system is obtained by training a long-short term memory network model using training samples consisting of the time series of samples and the fat level of the samples.
3. The method of claim 2, wherein the sample fat level is obtained based on a second recognition system, wherein an input to the second recognition system is an image of a sample breast, and wherein an output from the second recognition system is a sample fat level corresponding to the sample breast.
4. The method according to claim 3, wherein the second recognition system is obtained by training a convolutional neural network model using a training sample consisting of the image of the sample breast and a sample fat level corresponding to the sample breast.
5. A breast fat level determining apparatus, the apparatus comprising:
a first acquisition module configured to acquire a time series of a target breast, the time series being a compression thickness of the target breast and a time series of a supporting force of the target breast to a compression device;
the first obtaining module comprises:
a first acquisition unit configured to acquire a compression thickness of the target breast and a supporting force of the target breast to a compression device at fixed time intervals;
a first judging unit configured to judge whether a difference value between a currently acquired supporting force of the target breast on a compression device and a supporting force of the target breast on the compression device acquired at a previous time is greater than a first threshold;
A recording unit configured to record a currently acquired compression thickness of the target breast and a supporting force of the target breast to a compression device in a binary form if the compression thickness is greater than the first threshold;
the recording unit is further configured to compose the time sequence according to the recording time of the binary group if the difference between the support force of the target breasts on the compression device obtained continuously in a fixed number and the support force of the target breasts on the compression device obtained in the previous time is not greater than the first threshold;
a second acquisition module configured to acquire the fat level of the target breast according to the time series based on a first identification system, the time series being an input of the first identification system, the fat level being an output of the first identification system, the first identification system being established according to a sample time series and a sample fat level.
6. The apparatus of claim 5, wherein the first recognition system is derived from training a long-short term memory network model using training samples consisting of the time series of samples and the fat levels of the samples.
7. The apparatus of claim 6, wherein the sample fat level is obtained based on a second recognition system, wherein an input to the second recognition system is an image of a sample breast, and wherein an output from the second recognition system is a corresponding sample fat level of the sample breast.
8. A breast fat level determining apparatus, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to cause the breast fat level determination apparatus to perform the breast fat level determination method of any one of claims 1 to 4 when executing the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911122300.6A CN110833395B (en) | 2019-11-15 | 2019-11-15 | Mammary fat level determination method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911122300.6A CN110833395B (en) | 2019-11-15 | 2019-11-15 | Mammary fat level determination method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110833395A CN110833395A (en) | 2020-02-25 |
| CN110833395B true CN110833395B (en) | 2022-06-28 |
Family
ID=69576643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911122300.6A Active CN110833395B (en) | 2019-11-15 | 2019-11-15 | Mammary fat level determination method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110833395B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002065653A (en) * | 2000-04-26 | 2002-03-05 | Ge Medical Systems Global Technology Co Llc | Radiography apparatus, method and program relating to control with respect to the same apparatus |
| US7315640B1 (en) * | 1999-03-01 | 2008-01-01 | Mirada Solutions Limited | X-ray image processing |
| CN103561640A (en) * | 2011-05-24 | 2014-02-05 | 欧姆龙健康医疗事业株式会社 | Blood pressure measurement device |
| CN103854028A (en) * | 2008-12-22 | 2014-06-11 | 赛利恩影像股份有限公司 | Method and system of automated detection of lesions in medical images |
| CN104367331A (en) * | 2013-08-15 | 2015-02-25 | 深圳市蓝韵实业有限公司 | Full-digital automatic exposure method for digital mammary gland X-ray machine |
| CN105147309A (en) * | 2015-09-28 | 2015-12-16 | 上海联影医疗科技有限公司 | Mammography system and method |
| CN108464840A (en) * | 2017-12-26 | 2018-08-31 | 安徽科大讯飞医疗信息技术有限公司 | A kind of breast lump automatic testing method and system |
| CN110200659A (en) * | 2018-11-14 | 2019-09-06 | 江苏集萃智能传感技术研究所有限公司 | A kind of clothes and detection method of the wearable detection human breast of intelligence |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2203198A1 (en) * | 1997-04-17 | 1998-10-17 | Barbara Barnes Pellew-Harvey | Subcutaneous adipose tissue measuring instrument |
| US6354996B1 (en) * | 1998-04-15 | 2002-03-12 | Braun Gmbh | Body composition analyzer with trend display |
| JP4837507B2 (en) * | 2005-10-06 | 2011-12-14 | 富士フイルム株式会社 | Breast imaging device |
| JP5456884B2 (en) * | 2010-03-31 | 2014-04-02 | 公立大学法人大阪府立大学 | Adipose tissue image display device |
| US9642593B2 (en) * | 2014-09-19 | 2017-05-09 | MuscleSound, LLC | System and method for non-invasive determination of human body fat |
| JP6682150B2 (en) * | 2017-03-29 | 2020-04-15 | 富士フイルム株式会社 | Breast volume acquisition device, method and program |
-
2019
- 2019-11-15 CN CN201911122300.6A patent/CN110833395B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7315640B1 (en) * | 1999-03-01 | 2008-01-01 | Mirada Solutions Limited | X-ray image processing |
| JP2002065653A (en) * | 2000-04-26 | 2002-03-05 | Ge Medical Systems Global Technology Co Llc | Radiography apparatus, method and program relating to control with respect to the same apparatus |
| CN103854028A (en) * | 2008-12-22 | 2014-06-11 | 赛利恩影像股份有限公司 | Method and system of automated detection of lesions in medical images |
| CN103561640A (en) * | 2011-05-24 | 2014-02-05 | 欧姆龙健康医疗事业株式会社 | Blood pressure measurement device |
| CN104367331A (en) * | 2013-08-15 | 2015-02-25 | 深圳市蓝韵实业有限公司 | Full-digital automatic exposure method for digital mammary gland X-ray machine |
| CN105147309A (en) * | 2015-09-28 | 2015-12-16 | 上海联影医疗科技有限公司 | Mammography system and method |
| CN108464840A (en) * | 2017-12-26 | 2018-08-31 | 安徽科大讯飞医疗信息技术有限公司 | A kind of breast lump automatic testing method and system |
| CN110200659A (en) * | 2018-11-14 | 2019-09-06 | 江苏集萃智能传感技术研究所有限公司 | A kind of clothes and detection method of the wearable detection human breast of intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110833395A (en) | 2020-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106413236B (en) | A kind of exposure parameter method of adjustment and device | |
| CN108737738B (en) | Panoramic camera and exposure method and device thereof | |
| US11106193B1 (en) | Neural network-based error compensation method, system and device for 3D printing | |
| KR20170125604A (en) | Electronic apparatus and controlling method thereof | |
| US10172584B2 (en) | Method for generating approximate function of total MTF of X-ray image, based on conditions for imaging with X-ray | |
| CN110833395B (en) | Mammary fat level determination method and device | |
| CN111183371A (en) | Handling detector pixel performance variation for digital positron emission tomography | |
| CN105054959B (en) | Air correction method, apparatus and equipment | |
| CN109814037A (en) | Acquisition methods, terminal device and the medium of the hot coefficient of lithium ion battery entropy | |
| CN116563085A (en) | Large-scale parallel processing method and system for offline rendering | |
| CN110840469B (en) | Mammary X-ray machine exposure control method and device and mammary X-ray machine | |
| CN108013887A (en) | A kind of automatic exposure control method and device and auto exposure system | |
| US7274770B2 (en) | X-ray examination apparatus and a method of controlling an output of an X-ray source of an X-ray examination apparatus | |
| CN107845070B (en) | Method for fully automatically tracking digital X-ray perspective dose | |
| CN116421207B (en) | Medical X-ray imaging method and medical X-ray imaging device | |
| CN113507886A (en) | System, method and computer program for acquiring phase imaging data of an object | |
| CN111949493A (en) | Inference application-based power consumption testing method and device for edge AI server | |
| CN114693830B (en) | Multi-organ segmentation and model training method, equipment and medium for medical image | |
| CN114202522A (en) | Red blood silk non-contact measuring method, storage medium and processor | |
| CN109587389A (en) | A kind of method and system of number grid system acquisition image | |
| CN110706161B (en) | Image brightness adjusting method, medium, device and apparatus | |
| CN112422841B (en) | Image compensation method, image compensation device, computer equipment and storage medium | |
| US20170020476A1 (en) | Method for generating approximate function of total mtf of x-ray image, based on conditions for imaging with x-ray | |
| CN104586416A (en) | Method and device for generating attenuation diagrams and positron emission cross-sectional images | |
| CN111754612A (en) | Moving picture generation method and device |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ye Sheng Inventor after: Li Shouxian Inventor after: Huang Huaping Inventor before: Liu Jianli Inventor before: Li Shouxian Inventor before: Huang Huaping |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |