CN110916703A - Scanning dose modulation method and device, scanning equipment and storage medium - Google Patents
Scanning dose modulation method and device, scanning equipment and storage medium Download PDFInfo
- Publication number
- CN110916703A CN110916703A CN201911060483.3A CN201911060483A CN110916703A CN 110916703 A CN110916703 A CN 110916703A CN 201911060483 A CN201911060483 A CN 201911060483A CN 110916703 A CN110916703 A CN 110916703A
- Authority
- CN
- China
- Prior art keywords
- data
- attenuation
- scanning
- obtaining
- scan
- 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.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/40—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment with arrangements for generating radiation specially adapted for radiation diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/02—Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computerised tomographs
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/54—Control of apparatus or devices for radiation diagnosis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
Abstract
The invention relates to the technical field of medical equipment, and particularly provides a scanning dose modulation method and device, scanning equipment and a storage medium. The scanning dose modulation method comprises the following steps: acquiring plain film data of a measured object; obtaining attenuation curve data of each slice position according to the plain film data; inputting attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network, and outputting corresponding scanning attenuation data; wherein, the scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slice position; and obtaining the corresponding scanning dose according to the scanning attenuation data. According to the scanning dose modulation method provided by the invention, the relation network of attenuation curve data and scanning attenuation data is trained in advance, and the scanning doses at different positions are modulated according to the scanning attenuation data at the corresponding output positions, so that the consistency of imaging noise is better, and the imaging quality is improved.
Description
Technical Field
The invention relates to the technical field of medical equipment, in particular to a scanning dose modulation method and device, scanning equipment and a storage medium.
Background
CT (computed tomography) equipment is a device that uses precisely collimated X-rays to scan a cross-section around a target of a measured object together with a detector with extremely high sensitivity, thereby obtaining medical images of internal tissues of the measured object. In the CT scanning process, the higher the scanning dose, the higher the quality of the produced image, but at the same time, the more the X-ray damages the human body, so the scanning dose needs to be modulated reasonably according to the different scanning objects, scanning parts, etc. Taking the example of scanning the human torso, a larger dose should be used for the parts with larger attenuation values (for example, the shoulders), and a smaller dose is needed for the parts with smaller attenuation values (for example, the lungs), so that the modulation of the scanning dose is an important research direction for X-ray imaging.
Disclosure of Invention
The invention provides a scanning dose modulation method, a scanning dose modulation device, scanning equipment and a storage medium, which are used for reasonably modulating a radiation scanning dose.
In a first aspect, the present invention provides a scan dose modulation method, including:
acquiring plain film data of a measured object;
obtaining attenuation curve data of each slice position according to the plain film data;
inputting the attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network, and outputting corresponding scanning attenuation data; wherein, the scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slice position;
and obtaining the corresponding scanning dose according to the scanning attenuation data.
In some embodiments, the training process of the attenuation curve data and scan attenuation data relation network comprises:
acquiring plain film data and scanning data of a measured object;
obtaining attenuation curve data of each slice position according to the plain film data;
obtaining scanning attenuation data corresponding to each unwrapping wire position of the measured object at each slice position according to the scanning data;
inputting the attenuation curve data into an untrained attenuation curve data and scanning attenuation data relation network to obtain predicted attenuation data output by the relation network;
obtaining a loss between the predicted attenuation data and the scan attenuation data;
and adjusting the network parameters of the relation network according to the loss to obtain the trained relation network of the attenuation curve data and the scanning attenuation data.
In some embodiments, said deriving attenuation curve data for each slice location from said slab data comprises:
correcting the plain film data to obtain first attenuation domain data corresponding to the plain film data;
and obtaining attenuation curve data of each slice position according to the first attenuation domain data.
In some embodiments, the obtaining the scan attenuation data of the object at each slice position according to the scan data includes:
correcting the scanning data to obtain second attenuation domain data corresponding to the scanning data;
and obtaining scanning attenuation data corresponding to each pay-off position of each slice position according to the second attenuation domain data.
In some embodiments, the scan attenuation data comprises:
a maximum attenuation value; or
Average attenuation values; or
Attenuation values of the location of interest.
In a second aspect, the present invention provides a scanning dose modulation device comprising:
the first acquisition module is used for acquiring plain film data of the object to be measured;
the first processing module is used for obtaining attenuation curve data of each slice according to the plain film data;
the second processing module is used for inputting the attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network and outputting corresponding scanning attenuation data; wherein, the scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slice position; and
and the third processing module is used for obtaining the corresponding scanning dose according to the scanning attenuation data.
In some embodiments, the scanning dose modulating device further comprises:
the second acquisition module is used for acquiring plain film data and scanning data of the object to be detected;
the fourth processing module is used for obtaining attenuation curve data of each slice position according to the plain film data;
the fifth processing module is used for obtaining scanning attenuation data corresponding to each unwrapping wire position of the measured object at each slice position according to the scanning data;
the sixth processing module is used for inputting the attenuation curve data into an untrained attenuation curve data and scanning attenuation data relation network to obtain predicted attenuation data output by the relation network;
a third acquisition module that acquires a loss between the predicted attenuation data and the scan attenuation data;
and the seventh processing module is used for adjusting the network parameters of the relational network according to the loss to obtain the trained relational network of the attenuation curve data and the scanning attenuation data.
In some embodiments, the scanning dose modulating device further comprises:
the first correction module is used for correcting the plain film data to obtain first attenuation domain data corresponding to the plain film data;
and the first obtaining module is used for obtaining attenuation curve data of each slice position according to the first attenuation domain data.
In some embodiments, the scanning dose modulating device further comprises:
the second correction module is used for correcting the scanning data to obtain second attenuation domain data corresponding to the scanning data;
and the second obtaining module is used for obtaining scanning attenuation data corresponding to each pay-off position of each slice position according to the second attenuation domain data.
In a third aspect, the present invention provides a scanning device comprising:
a processor; and
a memory communicatively coupled to the processor and storing computer readable instructions executable by the processor, the processor executing the scan dose modulation method according to any of the embodiments of the first aspect when the computer readable instructions are executed.
In a fourth aspect, the present invention provides a storage medium storing computer instructions for causing a computer to execute the scan dose modulation method according to any one of the embodiments of the first aspect.
The scanning dose modulation method provided by the invention comprises the steps of obtaining plain film data of a measured object, obtaining attenuation curve data of each slice according to the plain film data, inputting the attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network so as to output corresponding scanning attenuation data, and obtaining a scanning dose corresponding to each pay-off position according to the scanning attenuation data corresponding to each pay-off position on the slice position, so that the dose modulation of different scanning positions is realized, the dose modulation is more reasonable and accurate, the consistency of imaging noise is ensured, and the imaging quality is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of a scanning device suitable for implementing the method of the invention.
Fig. 2 is a flow chart of a method of scanning dose modulation according to some embodiments of the present invention.
FIG. 3 is a flow chart of training an attenuation curve data versus scan attenuation data network in accordance with some embodiments of the present invention.
FIG. 4 is a flow chart of obtaining attenuation curve data from flat sheet data according to some embodiments of the present invention.
FIG. 5 is a slice schematic of tile data according to some embodiments of the invention.
FIG. 6 is a schematic of an attenuation curve for a slice in accordance with some embodiments of the invention.
FIG. 7 is a flow chart of obtaining scan attenuation data from scan data according to some embodiments of the present invention.
Fig. 8 is a schematic view of a slice in accordance with some embodiments of the invention.
Fig. 9 is a block diagram of a scanning dose modulation device according to some embodiments of the present invention.
Fig. 10 is a schematic diagram of a computer system suitable for implementing a scan dose modulation method or processor in an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some examples of the present invention, but not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The scanning dose modulation method provided by the invention can be used for automatically adjusting the scanning dose in the process of ray scanning. Taking CT scanning (computed tomography) as an example, a structure of a commonly used CT apparatus can be referred to fig. 1. The bulb and the detector are relatively fixed on the circular ring-shaped frame, and the random frame rotates. The bulb is used to emit X-rays and the detector is typically made up of hundreds of channels for receiving the rays transmitted through the body. The main control system is connected with the bulb tube and the detector, controls the bulb tube to emit X rays on one hand, and receives signals of the detector on the other hand, so that imaging output is achieved. In general, the plane of the circular ring type gantry is defined as xy plane, and the direction perpendicular to the xy plane is the z-axis direction. In scanning, the object to be measured is moved along the z-axis by, for example, a scanning bed, and the gantry is rotated in the xy-plane, thereby performing a tomographic scan or a helical scan one after another around the object to be measured.
For ease of understanding, technical terms of the related art appearing hereinafter are explained.
Flattening: when the stand is static and does not rotate, only the scanning bed moves along the z axis, and meanwhile, the bulb tube is paid off for sampling, and the position of the bulb tube, which is static at 0 degree, 90 degrees, 180 degrees or 270 degrees, can be used for positioning a detection part before scanning, namely a positioning sheet. For example, as shown in FIG. 1, the bulb is at rest at the 0 position and the scanning bed is moved in the z-axis direction.
Slicing: several slices or helical sections of the measured object perpendicular to the z-axis.
Pay-off position (view): when the CT machine scans, each circle of scanning (slice) is equally divided into a plurality of pay-off positions, for example, 1000-3000, and the scanning of each pay-off position is subjected to the integration and normalization of X photons as one sampling, wherein each pay-off position is called as a view.
Fig. 2 illustrates a scan dose modulation method according to some embodiments of the present invention, which can be used for automatically adjusting a scan dose during a radiation scan, the method including:
and S10, acquiring plain film data of the measured object.
Specifically, the object to be measured may be, for example, a human bone, an internal tissue, or any other object suitable for radiation scanning, and the plain film data is obtained by performing a plain film inspection on the object to be measured. In an exemplary implementation, taking a human head as an example, the bulb is stationary at the position shown in fig. 1, and is paid off, the tested person moves along the z-axis under the driving of the scanning bed, and the head of the tested person can be detected to the neck of the tested person, so that the plain film detection is completed, and the plain film data of the head of the tested person can be obtained. It should be noted that the above examples are only used for illustrating the present invention, and those skilled in the art may also obtain the plain film data of the measured object by any other suitable implementation manner, and the present invention is not limited to this.
And S20, obtaining attenuation curve data of each slice according to the plain slice data.
In particular, in the z-axis direction, the flat slices are sampled at a distance apart, resulting in several slices perpendicular to the z-axis, which may be sampled, for example, 1mm apart. In one exemplary implementation, a series of corrections, such as air corrections, are applied to the tile data to obtain attenuation domain data corresponding to the tiles. And obtaining attenuation curve data of the measured object at each slice position according to the attenuation domain data.
And S30, inputting the attenuation curve data into a preset attenuation curve data and scanning attenuation data relation network, and outputting corresponding scanning attenuation data.
The scan attenuation data is used for representing the attenuation degree of the ray after penetrating through the measured object, and the scan attenuation data of each view of the measured object at each slice position can be obtained according to the ray signal received by the detector. In some embodiments, the scan attenuation data may be a maximum attenuation value, an average attenuation value, or an attenuation value of a location of interest for each view at each slice position, and the like, which is not limited by the invention.
In some embodiments, the attenuation curve data and scan attenuation data relationship network may be trained in advance, so that the acquired attenuation curve data is input into the relationship network, and the corresponding scan attenuation data may be output. The two-relationship network can be constructed, for example, using a deep learning algorithm, as described in detail below.
And S40, obtaining the corresponding scanning dose according to the scanning attenuation data.
Through the output scanning attenuation data, the attenuation intensity of the corresponding position can be determined, and therefore the corresponding scanning dose can be provided for different positions.
According to the embodiment, the scanning dose modulation method provided by the invention has the advantages that the attenuation curve data of the object to be scanned is input into the relation network through training the relation network between the attenuation curve data and the scanning attenuation data, so that the scanning attenuation data of the corresponding position can be output, the scanning doses of different pay-off positions are modulated according to the scanning attenuation data, the consistency of imaging noise is better ensured, and the imaging quality is improved.
Meanwhile, compared with the scanning dose modulation method in the prior art, the scanning dose modulation method can realize more efficient and accurate scanning dose modulation. For example, compared with the prior art that dose recommendation is performed by an equivalent circle method, scanned flat slice and spiral data need to be acquired, and attenuation values of non-scanned positions are estimated through the scanned flat slice and spiral data, the method has the advantages of large dose recommendation calculation amount, low efficiency and poor accuracy of the estimated attenuation values. The modulation method in the embodiment of the invention trains the relation network of the attenuation curve data and the scanning attenuation data through the deep learning network, so that the output result is more accurate, and the dosage adjustment is more timely and efficient.
In some embodiments, the scan dose modulation method provided by the present invention further comprises: and pre-training to obtain a relation network of attenuation curve data and scanning attenuation data. The scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slicing position.
FIG. 3 illustrates a flow chart for training a network of attenuation curve data versus scan attenuation data in accordance with some embodiments of the present invention. As shown in fig. 3, in this embodiment, taking the training of the relationship network between attenuation curve data of a human head and scan attenuation data as an example, the method of the present invention includes:
and S31, acquiring plain film data and scanning data of the measured object.
Specifically, a large number of plain film data and scan data samples of the human head may be acquired from the historical database, and the scan data may be, for example, tomographic data or helical scan data. Both the plain and scanned data are the products of routine clinical scanning and therefore do not add additional scanning procedures.
In the present embodiment, the tile data includes first start position data and first end position data, which are denoted as PltStartCouch and PltEndCouch, respectively. The scan data includes second start position data and second end position data, which are denoted as ScanStartCouch and scanendtouch, respectively. Taking the CT apparatus as an example, the start position data and the end position data may be represented by bed code data, and the movement data in the z-axis direction by the scanning bed is taken as the start and end position data.
And S32, obtaining attenuation curve data of each slice position according to the plain film data.
In some embodiments, as shown in fig. 4, obtaining attenuation curve data for each slice location from the sliced data comprises:
s321, correcting the plain film data to obtain first attenuation domain data corresponding to the plain film data;
and S322, obtaining attenuation curve data of each slice position according to the first attenuation domain data.
Specifically, a series of corrections may be performed on the tile data to obtain first attenuation domain data, denoted as PltUOri, corresponding to the tile data. To ensure the validity of the scan data, only the slab data within the valid distance is sliced, and sampling distances from max (pltstart, ScanStartCouch) to min (PltEndCouch, scanendtouch) are determined based on the first start and end position data and the second start and end position data, thereby ensuring the accuracy of the sampling data. Within the above sampling distance, slice sampling is performed at intervals in the z-axis direction, for example, the number of slices is N, and a slice position i is obtained, where i is 1,2,3,4 … … N. In the first attenuation field data PltUOri, attenuation curve data of the N slice positions are obtained in accordance with the corresponding positional relationship and are denoted as PltU.
In some embodiments, when obtaining attenuation curve data for each slice position, data within a range around the slice position may be merged to the slice position, resulting in smoother attenuation curve data.
In an exemplary implementation, the above process is illustrated with reference to fig. 5, 6. In the present embodiment, the plain film data is subjected to, for example, air correction to obtain first attenuation domain data, which is denoted as PltUOri. Within the interval of (ScanStartCouch, scanendcuch), slice sampling was performed at intervals of 1mm in the z-axis direction, resulting in N slice positions. The first attenuation domain data PltUOri is mapped to N slice positions, and the attenuation curve data of the N slice positions is obtained and is marked as PltU. The attenuation curve at N ═ 2 is shown in fig. 6, denoted PltU (2). The attenuation curves at the other positions are similar and are not described in detail herein.
And S33, obtaining the scanning attenuation data corresponding to each line-releasing position of the measured object on each slice position according to the scanning data.
In some embodiments, as shown in fig. 7, obtaining the scan attenuation value corresponding to each line-out position of the measured object at each slice position according to the scan data includes:
and S331, correcting the scanning data to obtain second attenuation domain data corresponding to the scanning data.
And S332, obtaining a scanning attenuation value corresponding to each unwrapping wire position of each slice position according to the second attenuation domain data.
Specifically, the scan data may be tomographic data or helical scan data. In some embodiments, a series of corrections are applied to the scan data to obtain second attenuation domain data corresponding to the scan data, denoted ScanUOri. And calculating a scanning attenuation data set of M views on each slice position by scanning according to attenuation domain data of the scanning data corresponding to the N slice positions. In the present embodiment, the scan attenuation data is exemplified by a maximum attenuation value, which is the maximum attenuation value in K channels of the detector at each pay-off position view, and a set of maximum attenuation values of M views may be represented as maxu (j), where j is 1,2,3,4 … … M.
In one exemplary implementation, the above process is illustrated with reference to FIG. 8. In the present embodiment, the scan data is subjected to, for example, air correction to obtain second attenuation region data, which is denoted as scanuoori. The second attenuation domain data is mapped to each slice position shown in fig. 5, the slice at N-2 is as shown in fig. 8, the scanner scans one turn at this position, divides the scan into M projection sampling region views, and calculates the maximum attenuation value of each view, thereby obtaining the maximum attenuation value set of M views at N-2 position, which can be denoted as MaxU (2, j). The same reason for obtaining the scanning attenuation data at other positions is not described herein.
And S34, inputting the attenuation curve data into the untrained attenuation curve data and scanning attenuation data relation network to obtain the predicted attenuation data output by the relation network.
S35, obtaining a loss between the predicted attenuation data and the scan attenuation data.
And S36, adjusting the network parameters of the relational network according to the loss to obtain the trained relational network of the attenuation curve data and the scanning attenuation data.
Specifically, in the above steps S34 to S36, a relational network of attenuation curve data and scanning attenuation data is established in advance, the attenuation curve data set PltU is input as a training set, and the maximum attenuation value set maxu (j) is adjusted as a label. The attenuation curve set PltU contains N pieces of attenuation curve data, denoted PltU (i), i ═ 1,2,3 … … N, PltU (i) denotes the attenuation curve at position i, the attenuation curve at each slice position contains K pieces of data, K being the number of detector channels. Corresponding to this is a maximum attenuation value set MaxU (i, j), where j is 1,2,3 … … M, which represents the maximum attenuation of each of M views scanned at position i, and contains M data. Pltu (i) and MaxU (i, j) are in a one-to-one correspondence, i.e., the attenuation curve data pltu (i) for each slice position corresponds to a set of maximum attenuation values MaxU (j) at that position.
Deep learning network notation netWWhere W is the weight in the network. The one-time training process is as follows:
inputting data of 2n +1 positions from PltU (i-n) to PltU (i + n) into a network to obtain an output prediction maximum attenuation value MaxU', wherein n is a constant and is expressed as:
MaxU′(i)＝netW(PltU(i-n,i-n+ 1…,i-1,i,i+1,…i+n-1,i+n))
MaxU (i) is used as a label, the loss between the preset maximum attenuation value MaxU' and MaxU (i) is obtained and is recorded as loss, and the loss function is recorded as floss. When the difference between MaxU' (i) and MaxU (i) is smaller, the loss is smaller, and the output result is more accurate. Note that, when the input data at the i position is less than 2n +1 in outputting the predicted valueThe data can be complemented by adopting a mirror image filling mode, so that the data accuracy of the edge position is guaranteed.
MaxU (i) as a label to adjust the network, and the training loss is:
loss＝floss(MaxU′(i),MaxU(i))
in the present embodiment, BP neural network algorithm may be adopted for the netWThe weight W in (1) is trained to make loss as small as possible. The BP algorithm is a commonly used neural network algorithm, which will not be described herein, and will be understood by those skilled in the art. And (5) repeating the iterative training process, and finally outputting MaxU' (i) which is extremely close to the maximum attenuation value MaxU (i), so as to obtain the trained relation network, and finishing the training.
In some embodiments, the deep learning algorithm modifies the output class prediction to the attenuation prediction based on the Resnet-50 network structure, which can be implemented by those skilled in the art based on the above disclosure. It should be noted that the above network structure is only used to illustrate the embodiment of the present invention, and those skilled in the art should understand that the deep learning network structure of the present invention is not limited to the Resnet-50, and the same effect can be achieved on any other network structure suitable for implementation, such as AlexNet, VGG network structure, etc., and the present invention is not limited to this.
The above description of the training of the attenuation curve data and the scan attenuation data relation network in some embodiments of the present invention is made, and after the relation network training is completed, the attenuation curve data of the plain film data is input, so that the scan attenuation value data corresponding to the position can be output, and the scan dose modulation is performed according to the scan attenuation data, thereby realizing the dose modulation of different scan positions, achieving more reasonable and accurate dose modulation, ensuring the consistency of imaging noise, and improving the imaging quality.
On the basis of the above embodiments, a scanning dose modulation method in some embodiments of the present invention will be described below with reference to fig. 2 by taking a CT apparatus as an example to scan a head of a human body.
And S10, acquiring plain film data of the head of the tested person. In an exemplary implementation, the bulb is stationary at the position shown in fig. 1, and the head of the subject is subjected to plain film detection to obtain plain film data of the head of the subject.
S20, obtaining attenuation curve data of each slice according to the plain film data of the head of the tested person. For details, refer to step S32 described above, and will not be described herein.
S30, inputting the data of the attenuation curve of the head of the subject into the relationship network between the trained attenuation curve and the maximum attenuation value in the above embodiment, so as to output the maximum attenuation value set at the corresponding position.
And S40, obtaining the corresponding scanning dose according to the maximum attenuation value set.
Specifically, when the scan dose is determined, the scan dose determination may be performed on the basis of the maximum noise at each position. The noise formula is as follows:
wherein, delta2Is noise, No is the scan dose, ul is the attenuation value. By making the noise equal at each location, the scanning dose at each location can be determined. For example, in an exemplary scanning implementation, attenuation curve data of a certain sampling position is input, and the maximum attenuation values of M projection sampling regions view at the slice position are output, that is, the maximum attenuation value of each view can be used as the attenuation value ul of the region, and then a noise value is given by a user, so that the scanning dose of each position can be obtained, and thus, the dose modulation at each position is realized.
It should be noted that the scan dose modulation method provided by the present invention is not limited to head scanning, and can be applied to different parts, such as internal tissues, bones of human body, etc., according to different training data. The method of the present invention is not limited to CT devices, but can be any other device suitable for radiation scanning. The scan attenuation data is not limited to the maximum attenuation value of the M projection sampling region views, and may be an average attenuation value or an attenuation value of a position of interest, and the like.
In a second aspect, the present invention provides a scan dose modulation apparatus, which can be applied to, for example, a CT apparatus, to automatically adjust the scan dose during a radiation scan. As shown in fig. 9, the apparatus includes:
the first acquisition module 10 is used for acquiring plain film data of a measured object;
the first processing module 20 is configured to obtain attenuation curve data of each slice according to the plain film data;
the second processing module 30 is configured to input attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network, and output corresponding scanning attenuation data; the scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slicing position; and
and the third processing module 40 is used for obtaining the corresponding scanning dose according to the scanning attenuation data.
According to the scanning dose modulation device provided by the invention, the attenuation curve and the scanning attenuation value relation network are constructed, the attenuation curve data of the object to be scanned is input into the relation network, and then the scanning attenuation value of the corresponding position can be output, so that the scanning dose modulation of different positions is realized according to the scanning attenuation value, the consistency of imaging noise is better ensured, and the imaging quality is improved. Meanwhile, compared with the existing dose modulation method, the output result is more accurate, so that the dose modulation is more timely and efficient.
In some embodiments, the scan dose modulation device of the present invention is further configured to obtain a trained attenuation curve and a scan attenuation value relationship network, comprising:
the second acquisition module is used for acquiring plain film data and scanning data of the object to be detected;
the fourth processing module is used for obtaining attenuation curve data of each slice position according to the plain film data;
the fifth processing module is used for obtaining scanning attenuation data corresponding to each pay-off position of the measured object at each slice position according to the scanning data;
the sixth processing module is used for inputting attenuation curve data into an untrained attenuation curve data and scanning attenuation data relation network to obtain predicted attenuation data output by the relation network;
a third obtaining module for obtaining loss between the predicted attenuation data and the scan attenuation data;
and the seventh processing module is used for adjusting the network parameters of the relational network according to the loss to obtain the trained relational network of the attenuation curve data and the scanning attenuation data.
In some embodiments, the scanning dose modulation device of the present invention further comprises:
the first correction module is used for correcting the plain film data to obtain first attenuation domain data corresponding to the plain film data;
and the first obtaining module is used for obtaining attenuation curve data of each slice position according to the first attenuation domain data.
In some embodiments, the scanning dose modulation device of the present invention further comprises:
the second correction module is used for correcting the scanning data to obtain second attenuation domain data corresponding to the scanning data;
and the second obtaining module is used for obtaining the scanning attenuation data of each pay-off position of each slice position according to the second attenuation domain data.
In a third aspect, the present invention provides a scanning device, which may be, for example, a CT device or any other radiation scanning device suitable for implementation. The apparatus comprises:
a processor; and
a memory communicatively coupled to the processor and storing computer readable instructions executable by the processor, wherein the processor executes the scan dose modulation method of any of the above embodiments when the computer readable instructions are executed.
In a fourth aspect, the present invention provides a storage medium storing computer instructions for causing a computer to execute the scan dose modulation method in any of the above embodiments.
In particular, fig. 10 shows a schematic structural diagram of a computer system 600 suitable for implementing the method or processor of the present invention, and the electronic device and the storage medium provided in the third and fourth aspects are implemented by the system shown in fig. 10.
As shown in fig. 10, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, the above method processes may be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the above-described method. In such embodiments, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It should be understood that the above embodiments are only examples for clearly illustrating the present invention, and are not intended to limit the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (11)
1. A method of scanning dose modulation, comprising:
acquiring plain film data of a measured object;
obtaining attenuation curve data of each slice position according to the plain film data;
inputting the attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network, and outputting corresponding scanning attenuation data; wherein, the scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slice position;
and obtaining the corresponding scanning dose according to the scanning attenuation data.
2. The method of claim 1, wherein the training of the attenuation curve data versus scan attenuation data relationship network comprises:
acquiring plain film data and scanning data of a measured object;
obtaining attenuation curve data of each slice position according to the plain film data;
obtaining scanning attenuation data corresponding to each unwrapping wire position of the measured object at each slice position according to the scanning data;
inputting the attenuation curve data into an untrained attenuation curve data and scanning attenuation data relation network to obtain predicted attenuation data output by the relation network;
obtaining a loss between the predicted attenuation data and the scan attenuation data;
and adjusting the network parameters of the relation network according to the loss to obtain the trained relation network of the attenuation curve data and the scanning attenuation data.
3. A method of scanning dose modulation according to claim 1 or 2, wherein said deriving attenuation curve data for each slice position from said flat slice data comprises:
correcting the plain film data to obtain first attenuation domain data corresponding to the plain film data;
and obtaining attenuation curve data of each slice position according to the first attenuation domain data.
4. The method of claim 2, wherein obtaining scan attenuation data corresponding to each of the plurality of line positions of the object at each of the plurality of slice positions based on the scan data comprises:
correcting the scanning data to obtain second attenuation domain data corresponding to the scanning data;
and obtaining scanning attenuation data corresponding to each pay-off position of each slice position according to the second attenuation domain data.
5. The method of claim 1, wherein the scan attenuation data comprises:
a maximum attenuation value; or
Average attenuation values; or
Attenuation values of the location of interest.
6. A scanning dose modulation device, comprising:
the first acquisition module is used for acquiring plain film data of the object to be measured;
the first processing module is used for obtaining attenuation curve data of each slice according to the plain film data;
the second processing module is used for inputting the attenuation curve data into a pre-trained attenuation curve data and scanning attenuation data relation network and outputting corresponding scanning attenuation data; wherein, the scanning attenuation data is the scanning attenuation data corresponding to each unwrapping wire position of the measured object at the slice position; and
and the third processing module is used for obtaining the corresponding scanning dose according to the scanning attenuation data.
7. The device of claim 6, further comprising:
the second acquisition module is used for acquiring plain film data and scanning data of the object to be detected;
the fourth processing module is used for obtaining attenuation curve data of each slice position according to the plain film data;
the fifth processing module is used for obtaining scanning attenuation data corresponding to each unwrapping wire position of the measured object at each slice position according to the scanning data;
the sixth processing module is used for inputting the attenuation curve data into an untrained attenuation curve data and scanning attenuation data relation network to obtain predicted attenuation data output by the relation network;
a third acquisition module that acquires a loss between the predicted attenuation data and the scan attenuation data;
and the seventh processing module is used for adjusting the network parameters of the relational network according to the loss to obtain the trained relational network of the attenuation curve data and the scanning attenuation data.
8. A scanning dose modulation device according to claim 6 or 7, further comprising:
the first correction module is used for correcting the plain film data to obtain first attenuation domain data corresponding to the plain film data;
and the first obtaining module is used for obtaining attenuation curve data of each slice position according to the first attenuation domain data.
9. The device of claim 7, further comprising:
the second correction module is used for correcting the scanning data to obtain second attenuation domain data corresponding to the scanning data;
and the second obtaining module is used for obtaining scanning attenuation data corresponding to each pay-off position of each slice position according to the second attenuation domain data.
10. A scanning device, characterized by comprising:
a processor; and
a memory communicatively coupled to the processor and storing computer readable instructions executable by the processor, the processor executing the scan dose modulation method of any of claims 1 to 5 when the computer readable instructions are executed.
11. A storage medium storing computer instructions for causing a computer to perform the scan dose modulation method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911060483.3A CN110916703B (en) | 2019-11-01 | 2019-11-01 | Scanning dose modulation method, scanning device, scanning apparatus and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911060483.3A CN110916703B (en) | 2019-11-01 | 2019-11-01 | Scanning dose modulation method, scanning device, scanning apparatus and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110916703A true CN110916703A (en) | 2020-03-27 |
| CN110916703B CN110916703B (en) | 2023-08-29 |
Family
ID=69850054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911060483.3A Active CN110916703B (en) | 2019-11-01 | 2019-11-01 | Scanning dose modulation method, scanning device, scanning apparatus and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110916703B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111528891A (en) * | 2020-05-11 | 2020-08-14 | 东软医疗系统股份有限公司 | Dose modulation method and device, CT (computed tomography) equipment and CT system |
| CN113749680A (en) * | 2021-08-05 | 2021-12-07 | 中国人民解放军总医院 | Scanning positioning method, device, storage medium and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5400378A (en) * | 1993-11-19 | 1995-03-21 | General Electric Company | Dynamic dose control in multi-slice CT scan |
| US20070081704A1 (en) * | 2005-03-17 | 2007-04-12 | The University Of Texas System | System, program product, and methods for attenuation correction of emission data on PET/CT and SPECT/CT |
| US20110091008A1 (en) * | 2008-07-04 | 2011-04-21 | Koichi Hirokawa | X-ray ct apparatus |
| CN102100562A (en) * | 2009-12-16 | 2011-06-22 | 东软飞利浦医疗设备系统有限责任公司 | On-line dose modulation method of X-ray CT (Computed Tomography) machine |
| CN102472824A (en) * | 2009-07-07 | 2012-05-23 | 皇家飞利浦电子股份有限公司 | Dynamic pet imaging with isotope contamination compensation |
| CN109060849A (en) * | 2018-06-29 | 2018-12-21 | 上海联影医疗科技有限公司 | A kind of mthods, systems and devices of determining dose of radiation modulation lines |
-
2019
- 2019-11-01 CN CN201911060483.3A patent/CN110916703B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5400378A (en) * | 1993-11-19 | 1995-03-21 | General Electric Company | Dynamic dose control in multi-slice CT scan |
| US20070081704A1 (en) * | 2005-03-17 | 2007-04-12 | The University Of Texas System | System, program product, and methods for attenuation correction of emission data on PET/CT and SPECT/CT |
| US20110091008A1 (en) * | 2008-07-04 | 2011-04-21 | Koichi Hirokawa | X-ray ct apparatus |
| CN102472824A (en) * | 2009-07-07 | 2012-05-23 | 皇家飞利浦电子股份有限公司 | Dynamic pet imaging with isotope contamination compensation |
| CN102100562A (en) * | 2009-12-16 | 2011-06-22 | 东软飞利浦医疗设备系统有限责任公司 | On-line dose modulation method of X-ray CT (Computed Tomography) machine |
| CN109060849A (en) * | 2018-06-29 | 2018-12-21 | 上海联影医疗科技有限公司 | A kind of mthods, systems and devices of determining dose of radiation modulation lines |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111528891A (en) * | 2020-05-11 | 2020-08-14 | 东软医疗系统股份有限公司 | Dose modulation method and device, CT (computed tomography) equipment and CT system |
| CN111528891B (en) * | 2020-05-11 | 2023-05-02 | 东软医疗系统股份有限公司 | Dose modulation method, device, CT equipment and CT system |
| CN113749680A (en) * | 2021-08-05 | 2021-12-07 | 中国人民解放军总医院 | Scanning positioning method, device, storage medium and computer equipment |
| CN113749680B (en) * | 2021-08-05 | 2023-08-04 | 中国人民解放军总医院 | Scanning positioning method, scanning positioning device, storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110916703B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11341613B2 (en) | System and method for image reconstruction | |
| US7778381B2 (en) | X-ray CT apparatus | |
| US10255696B2 (en) | System and method for image reconstruction | |
| US9020220B2 (en) | X-ray computed tomography scanner, dose calculation method, and program | |
| US8483471B2 (en) | Method and system for scatter correction in X-ray imaging | |
| CN109709503B (en) | Magnetic resonance system control method, magnetic resonance system and computer equipment | |
| US11191509B2 (en) | System and method for computed tomography | |
| US20110286651A1 (en) | Projection-Space Denoising with Bilateral Filtering in Computed Tomography | |
| US10052080B2 (en) | Medical imaging apparatus and control method thereof | |
| CN110349236B (en) | Image correction method and system | |
| JP2002345808A (en) | Method and system for process of scouting ct images | |
| US9895128B2 (en) | X-ray CT apparatus and correction processing device | |
| CN110916703B (en) | Scanning dose modulation method, scanning device, scanning apparatus and storage medium | |
| JP2017189392A (en) | Image processing device, image processing method, image processing system, and program | |
| US11779288B2 (en) | Methods, systems, and apparatus for determining radiation doses | |
| US7239730B2 (en) | Method and apparatus for volume scoring calcification concentrations of a CT scan | |
| US20080086052A1 (en) | Methods and apparatus for motion compensation | |
| JP2019024747A (en) | X-ray CT apparatus, image generation method, and image generation program | |
| US10685461B1 (en) | Apparatus and method for context-oriented iterative reconstruction for computed tomography (CT) | |
| US6826252B2 (en) | Computed tomography scanner and method for controlling the computed tomography scanner | |
| KR20160061555A (en) | Method and system of tomography for region-of-interest with arbitrary shape using dynamic collimation | |
| EP4201338A1 (en) | Ct scanning method and system, electronic device, and computer-readable storage medium | |
| US20240046534A1 (en) | Systems and methods for imaging | |
| WO2018018087A1 (en) | A method and system for automating radiation dose parameters | |
| JPH10155787A (en) | Projection data correction method and x-ray ct apparatus |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |