CN117084709A - Ultrasonic imaging system and method - Google Patents
Ultrasonic imaging system and method Download PDFInfo
- Publication number
- CN117084709A CN117084709A CN202210503431.4A CN202210503431A CN117084709A CN 117084709 A CN117084709 A CN 117084709A CN 202210503431 A CN202210503431 A CN 202210503431A CN 117084709 A CN117084709 A CN 117084709A
- Authority
- CN
- China
- Prior art keywords
- endometrium
- volume
- result
- dimensional
- related measurement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003384 imaging method Methods 0.000 title abstract description 20
- 210000004696 endometrium Anatomy 0.000 claims abstract description 339
- 238000005259 measurement Methods 0.000 claims description 205
- 230000002357 endometrial effect Effects 0.000 claims description 94
- 238000011156 evaluation Methods 0.000 claims description 47
- 238000012285 ultrasound imaging Methods 0.000 claims description 45
- 238000013507 mapping Methods 0.000 claims description 38
- 230000017531 blood circulation Effects 0.000 claims description 36
- 239000000523 sample Substances 0.000 claims description 24
- 230000005540 biological transmission Effects 0.000 claims description 19
- 230000010412 perfusion Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000008339 endometrial blood flow Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 210000004291 uterus Anatomy 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 description 40
- 238000004422 calculation algorithm Methods 0.000 description 30
- 238000002604 ultrasonography Methods 0.000 description 23
- 238000013135 deep learning Methods 0.000 description 19
- 238000004364 calculation method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 210000004204 blood vessel Anatomy 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 230000008081 blood perfusion Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000002592 echocardiography Methods 0.000 description 4
- 239000008280 blood Substances 0.000 description 3
- 230000002792 vascular Effects 0.000 description 3
- 241000270295 Serpentes Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 235000013601 eggs Nutrition 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000002632 myometrial effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000001850 reproductive effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000000754 myometrium Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000002054 transplantation Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/06—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0833—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
- A61B8/4444—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device related to the probe
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
- A61B8/461—Displaying means of special interest
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Animal Behavior & Ethology (AREA)
- Radiology & Medical Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Hematology (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
An ultrasonic imaging system and method for automatically evaluating the receptivity of endometrium by acquiring three-dimensional volume data containing endometrium, automatically determining the receptivity result of endometrium based on the three-dimensional volume data, and controlling and outputting the receptivity result of endometrium.
Description
Technical Field
The present invention relates to an ultrasound imaging system and method.
Background
Ultrasound technology is also widely used in reproductive medicine as one of the main means of modern medical imaging examinations, where endometrial receptivity analysis is a hot spot problem in reproductive medicine. Endometrial receptivity refers to the receptivity of the endometrium to fertilized eggs, and is one of the main factors affecting the success rate of artificial conception (IVF) in vitro, and patients with poor endometrial receptivity have a high probability of causing pregnancy failure after fertilized egg transplantation. Ultrasound imaging is used clinically to assess endometrial receptivity.
Disclosure of Invention
In view of evaluating the receptivity of endometrium using ultrasound imaging, the present invention proposes an ultrasound imaging system and an ultrasound imaging method, which are described in detail below.
According to a first aspect, an embodiment provides an ultrasound imaging system comprising:
a probe for transmitting ultrasonic waves to a tissue of interest including endometrium and receiving corresponding ultrasonic echo signals;
a transmission and reception control circuit for controlling the probe to perform transmission of ultrasonic waves and reception of ultrasonic echo signals;
a receptivity evaluation key for generating a receptivity evaluation instruction in response to a user operation;
a processor for processing the corresponding ultrasonic echo signals to obtain three-dimensional volume data containing endometrium; in response to the acceptance assessment instruction:
the processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium;
the processor automatically calculates volume-related measurement items and non-volume-related measurement items according to the divided endometrium; the volume-related measurement comprises any one or more of endometrial thickness, endometrial volume, and an endometrial blood flow perfusion index, and the non-volume-related measurement comprises any one or more of endometrial typing and endometrial myolayer echo uniformity;
The processor automatically determines the result of the capacity evaluation related measurement item according to the capacity related measurement item and the non-capacity related measurement item;
the processor determines the tolerability results of the endometrium based on the results of the tolerability assessment related measurements.
In one embodiment, the processor automatically segments the three-dimensional volumetric data including endometrium to segment out endometrium, comprising:
the processor segments the endometrium from the three-dimensional volume data containing the endometrium by feature detection according to image feature differences of the endometrium and the basal layer tissue of the uterus and/or morphological features of the endometrium which can be periodically changed;
or,
a model trained by machine learning is acquired and based on the model, endometrium is segmented from the three-dimensional volumetric data comprising endometrium.
In one embodiment, the processor determines the tolerability of the endometrium based on the results of the tolerability assessment related measurements, comprising:
the processor calculates a score of the receptivity of the endometrium according to the result of the receptivity evaluation related measurement item;
the processor determines an endometrial receptivity outcome based on the endometrial receptivity score.
According to a second aspect, an embodiment provides an ultrasound imaging system comprising:
a probe for transmitting ultrasonic waves to a tissue of interest including endometrium and receiving corresponding ultrasonic echo signals;
a transmission and reception control circuit for controlling the probe to perform transmission of ultrasonic waves and reception of ultrasonic echo signals;
and the processor is used for processing the corresponding ultrasonic echo signals to acquire three-dimensional volume data containing endometrium, automatically determining the acceptation result of the endometrium based on the three-dimensional volume data and controlling and outputting the acceptation result of the endometrium.
In one embodiment, the processor automatically determines the tolerability result of the endometrium based on the three-dimensional volumetric data, comprising:
the processor automatically determines the result of the measurement related to the capacity acceptance evaluation based on the three-dimensional volume data;
the processor determines the tolerability results of the endometrium based on the results of the tolerability assessment related measurements.
In one embodiment, the processor automatically determines the results of the acceptance assessment-related measurements based on the three-dimensional volumetric data, comprising: the processor automatically determines at least a result of a volume-related measurement based on the three-dimensional volume data, the volume-related measurement including any one or more of an endometrium thickness, an endometrium volume, and a blood flow perfusion index of the endometrium.
In one embodiment, the processor automatically determines at least a result of a volume-related measurement based on the three-dimensional volume data, comprising:
the processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium; calculating a result of the volume-related measurement based on the segmented endometrium; or,
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and the result of volume-related measurement items; the processor identifies preset features in the acquired three-dimensional volume data containing the endometrium and calculates the result of the volume-related measurement item according to the mapping relation.
In one embodiment, the processor calculates the results of the volume-related measurements based on the segmented endometrium, comprising:
the processor counts the number of all pixels belonging to the endometrium based on the divided endometrium so as to obtain the pixel volume of the endometrium; the processor converts the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrium volume through the conversion relation between the pixel distance and the actual physical distance;
And/or the number of the groups of groups,
the processor locates a sagittal plane of the endometrium based on the segmented endometrium and calculates a thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrium thickness;
and/or the number of the groups of groups,
the processor calculates a blood flow perfusion index of the endometrium by counting color Doppler blood flow signal intensity and pixel number in the endometrium area based on the divided endometrium.
In one embodiment, the processor automatically determines the results of the acceptance assessment-related measurements based on the three-dimensional volumetric data, comprising: the processor automatically determines at least a result of a non-volume-related measurement based on the three-dimensional volume data, the non-volume-related measurement including any one or more of endometrial typing and endometrial myolayer echo uniformity.
In one embodiment, the processor automatically determines at least the results of non-volume-related measurements based on the three-dimensional volume data, including:
the processor calculates the result of the non-volume-related measurement item through a classification algorithm based on the three-dimensional volume data;
or,
pre-establishing a mapping relation of preset characteristics of three-dimensional volume data containing endometrium and results of non-volume related measurement items; the processor identifies preset features in the acquired three-dimensional volume data containing the endometrium and calculates the result of the non-volume-related measurement item according to the mapping relation.
In one embodiment, the processor automatically determines the tolerability result of the endometrium based on the three-dimensional volumetric data, comprising:
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and a receptive result;
the processor identifies preset features in the acquired three-dimensional volumetric data including endometrium, and calculates a tolerability result according to the mapping relationship.
According to a third aspect, an embodiment provides an ultrasound imaging method comprising:
acquiring three-dimensional volume data comprising endometrium;
automatically segmenting the three-dimensional volume data comprising endometrium to segment out endometrium;
automatically calculating a volume-related measurement item and a non-volume-related measurement item according to the divided endometrium; the volume-related measurement comprises any one or more of endometrial thickness, endometrial volume, and an endometrial blood flow perfusion index, and the non-volume-related measurement comprises any one or more of endometrial typing and endometrial myolayer echo uniformity;
according to the volume-related measurement items and the non-volume-related measurement items, automatically determining the result of the volume acceptance evaluation-related measurement items;
And determining the tolerability result of the endometrium according to the result of the acceptance evaluation related measurement.
In one embodiment, the automatically segmenting the three-dimensional volume data containing endometrium to segment out endometrium comprises:
segmenting the endometrium from the three-dimensional volume data comprising the endometrium by feature detection according to image feature differences of the endometrium and the basal layer tissue of the uterus and/or periodically changeable morphological features of the endometrium;
or,
a model trained by machine learning is acquired and based on the model, endometrium is segmented from the three-dimensional volumetric data comprising endometrium.
In one embodiment, the determining the tolerability of the endometrium based on the results of the tolerability assessment related measurements comprises:
calculating a score of the endometrial receptivity according to the result of the receptivity evaluation related measurement item;
and determining the endometrial receptivity result according to the endometrial receptivity score.
According to a fourth aspect, an embodiment provides an ultrasound imaging method comprising:
acquiring three-dimensional volume data comprising endometrium;
Automatically determining a tolerability result of the endometrium based on the three-dimensional volumetric data;
and controlling and outputting the receptivity result of the endometrium.
In one embodiment, the automatically determining the tolerability of the endometrium based on the three-dimensional volumetric data comprises:
automatically determining a result of a capacity acceptance evaluation related measurement item based on the three-dimensional volume data;
and determining the tolerability result of the endometrium according to the result of the acceptance evaluation related measurement.
In one embodiment, the automatically determining the result of the measurement related to the capacity assessment based on the three-dimensional volume data includes: automatically determining at least a result of a volume-related measurement based on the three-dimensional volume data, the volume-related measurement including any one or more of an endometrium thickness, an endometrium volume, and an endometrial blood flow perfusion index.
In an embodiment, the automatically determining at least a result of the volume-related measurement based on the three-dimensional volume data comprises:
automatically segmenting the three-dimensional volume data comprising endometrium to segment out endometrium; calculating a result of the volume-related measurement based on the segmented endometrium; or,
Pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and the result of volume-related measurement items; and identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating the result of the volume-related measurement according to the mapping relation.
In an embodiment, the calculating the result of the volume-related measurement based on the segmented endometrium comprises:
counting the number of all pixels belonging to the endometrium based on the divided endometrium to obtain the pixel volume of the endometrium; converting the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrium volume through a conversion relation between the pixel distance and the actual physical distance;
and/or the number of the groups of groups,
locating a sagittal plane of the endometrium based on the segmented endometrium, and calculating a thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrium thickness;
and/or the number of the groups of groups,
based on the divided endometrium, the color Doppler blood flow signal intensity and the pixel number in the endometrium area are counted to calculate the blood flow perfusion index of the endometrium.
In one embodiment, the automatically determining the result of the measurement related to the capacity assessment based on the three-dimensional volume data includes: results of at least automatically determining non-volume-related measurements based on the three-dimensional volume data, the non-volume-related measurements including any one or more of endometrial typing and endometrial myolayer echo uniformity.
In an embodiment, the automatically determining at least a result of the non-volume-related measurement based on the three-dimensional volume data includes:
calculating the result of a non-volume-related measurement item through a classification algorithm based on the three-dimensional volume data;
or,
pre-establishing a mapping relation of preset characteristics of three-dimensional volume data containing endometrium and results of non-volume related measurement items; and identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating the result of the non-volume-related measurement item according to the mapping relation.
In one embodiment, the automatically determining the tolerability of the endometrium based on the three-dimensional volumetric data comprises:
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and a receptive result;
And identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating a toleration result according to the mapping relation.
According to a fifth aspect, an embodiment provides a computer readable storage medium storing a program executable by a processor to implement a method as described in any of the embodiments herein
According to the ultrasonic imaging system, the ultrasonic imaging method and the computer readable storage medium of the above embodiments, by acquiring three-dimensional volume data including endometrium, automatically determining the tolerability result of the endometrium based on the three-dimensional volume data, and controlling the output of the tolerability result of the endometrium, the automatic evaluation of the endometrial tolerability is realized.
Drawings
FIG. 1 is a schematic diagram of the structure of an ultrasound imaging system of one embodiment;
FIG. 2 is a schematic diagram of the conversion relationship between the measured value and the score of the acceptance evaluation related measurement item;
FIG. 3 is a flow chart of an ultrasound imaging method of an embodiment;
FIG. 4 is a flow chart of an embodiment for automatically determining the tolerability results of the endometrium based on three dimensional volumetric data;
FIG. 5 is a flow chart of an embodiment for automatically determining the tolerability results of the endometrium based on three dimensional volumetric data;
Fig. 6 is a flow chart of an ultrasound imaging method of an embodiment.
Detailed Description
The application will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted, or replaced by other elements, materials, or methods in different situations. In some instances, related operations of the present application have not been shown or described in the specification in order to avoid obscuring the core portions of the present application, and may be unnecessary to persons skilled in the art from a detailed description of the related operations, which may be presented in the description and general knowledge of one skilled in the art.
Furthermore, the described features, operations, or characteristics of the description may be combined in any suitable manner in various embodiments. Also, various steps or acts in the method descriptions may be interchanged or modified in a manner apparent to those of ordinary skill in the art. Thus, the various orders in the description and drawings are for clarity of description of only certain embodiments, and are not meant to be required orders unless otherwise indicated.
The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning. The term "coupled" as used herein includes both direct and indirect coupling (coupling), unless otherwise indicated.
The present application addresses the problem of endometrial receptivity assessment, in some embodiments, proposes a receptivity assessment-related measurement, such as a volume-related measurement and/or a non-volume-related measurement; in some embodiments, the volume-related measurement includes any one or more of endometrial thickness, endometrial volume, and endometrial blood flow perfusion indicators, which may be, for example, vascular index VI, blood flow index FI, vascular-blood flow index VFI, etc.; in some embodiments, the non-volume related measurement comprises any one or more of endometrial typing and endometrial myolayer echo uniformity.
In some cases, the doctor can obtain the results of the related measurement items of the acceptance evaluation by means of an ultrasonic imaging system, in particular, the volume related measurement items such as the measurement items of the acceptance evaluation also need to be obtained based on the three-dimensional segmentation results of the endometrium, for example, the doctor manually outlines the endometrium on a plurality of sections of the three-dimensional volume data to perform three-dimensional segmentation on the endometrium, so that the three-dimensional segmentation results can be obtained, and the more the doctor outlines, the more accurate the three-dimensional segmentation results are; after obtaining the results of the above-mentioned acceptance evaluation related measurement items, the doctor then manually gathers the results of the acceptance evaluation related measurement items, and comprehensively evaluates the acceptance of endometrium; obtaining accurate results of endometrial receptivity assessment often consumes a great deal of time and effort from the physician.
In other schemes, a scheme for automatically evaluating the endometrial receptivity is provided, for example, after 3D/4D ultrasonic endometrial data acquisition is completed, an ultrasonic imaging system can automatically calculate and obtain an endometrial receptivity evaluation result only by one function key (an entity key or a virtual key); in some embodiments, in the process, by automatically dividing the endometrium from the volume data, a plurality of measurement items related to the receptivity evaluation such as the thickness, the volume, the blood perfusion and the like of the endometrium are obtained, so that automatic evaluation of the receptivity of the endometrium is realized, the time for a doctor to manually measure each measurement item can be greatly reduced, the working efficiency of the doctor is improved, and meanwhile, the accuracy and the stability of an evaluation result can be ensured.
The present application may be implemented in an ultrasound imaging system, referring to fig. 1, which includes a probe 10, transmit and receive control circuitry 20, an echo processing module 30, a processor 40, and a display module 50, which are described below.
The probe 10 may be a matrix probe or a four-dimensional probe with a mechanical device, which is not limited in the present application, as long as the ultrasound probe used can obtain the ultrasound echo signal or data of the target area of the subject. In some embodiments, the ultrasound probe acquires a set of four-dimensional image data (i.e., dynamic three-dimensional ultrasound images) or acquires a volume of three-dimensional ultrasound image data. In some embodiments, the probe 10 includes a plurality of array elements for performing interconversion of electrical pulse signals and ultrasound waves to effect transmission of ultrasound waves to the biological tissue 60 being examined (biological tissue in the human or animal body, such as tissue of interest including endometrium) and reception of ultrasound echoes reflected back from the tissue to obtain ultrasound echo signals. The plurality of array elements included in the probe 10 may be arranged in a row to form a linear array, or may be arranged in a two-dimensional matrix to form an area array, and the plurality of array elements may also form a convex array. The array elements may emit ultrasonic waves according to an excitation electrical signal or may convert received ultrasonic waves into an electrical signal. Each array element may thus be used to transmit ultrasound waves to biological tissue in the region of interest, as well as to receive ultrasound echoes returned through the tissue. In the ultrasonic detection, the transmitting sequence and the receiving sequence can control which array elements are used for transmitting ultrasonic waves and which array elements are used for receiving ultrasonic waves, or control the time slots of the array elements to be used for transmitting ultrasonic waves or receiving ultrasonic echoes. All array elements participating in ultrasonic wave transmission can be excited by the electric signals at the same time, so that ultrasonic waves are transmitted at the same time; or the array elements participating in the ultrasonic wave transmission can be excited by a plurality of electric signals with a certain time interval, so that the ultrasonic wave with a certain time interval can be continuously transmitted.
The transmission and reception control circuit 20 is for controlling the probe 10 to perform transmission of ultrasonic waves and reception of ultrasonic echo signals, in particular, the transmission and reception control circuit 20 is for controlling the probe 10 to transmit an ultrasonic beam to a biological tissue 60 such as a tissue of interest including endometrium on the one hand and for controlling the probe 10 to receive ultrasonic echoes reflected by the tissue of the ultrasonic beam on the other hand. In a specific embodiment, the transmit and receive control circuit 20 is configured to generate a transmit sequence and a receive sequence and output the transmit sequence to the probe 10. The transmit sequence is used to control the transmission of ultrasound waves to a portion or all of a plurality of array elements in the probe 10 to biological tissue 60, such as tissue of interest including the endometrium, and the parameters of the transmit sequence include the number of array elements used for transmission and the ultrasound wave transmission parameters (e.g., amplitude, frequency, number of waves transmitted, transmission interval, transmission angle, mode, and/or focus position, etc.). The receiving sequence is used for controlling part or all of the plurality of array elements to receive the echo of the ultrasonic wave after being organized, and the parameters of the receiving sequence comprise the number of array elements for receiving and the receiving parameters (such as receiving angle, depth and the like) of the echo. The ultrasound echo is used differently or the image generated from the ultrasound echo is different, so are the ultrasound parameters in the transmit sequence and the echo parameters in the receive sequence.
The echo processing module 30 is configured to process the ultrasonic echo signal received by the probe 10, for example, perform filtering, amplifying, beam forming, etc. on the ultrasonic echo signal, so as to obtain ultrasonic echo data. In a specific embodiment, the echo processing module 30 may output the ultrasonic echo data to the processor 40, or may store the ultrasonic echo data in a memory, and when an operation based on the ultrasonic echo data is required, the processor 40 reads the ultrasonic echo data from the memory. Those skilled in the art will appreciate that in some embodiments, the echo processing module 30 may be omitted when filtering, amplifying, beam forming, etc., of the ultrasound echo signals is not required.
The processor 40 is configured to acquire ultrasound echo data or signals and to use correlation algorithms to obtain desired parameters or images. For example, probe 10 transmits ultrasound waves to tissue of interest including the endometrium, and receives corresponding ultrasound echo signals; the processor 40 processes the corresponding ultrasonic echo signals to obtain three-dimensional volumetric data including the endometrium.
The display module 50 may be used to display information such as parameters and images calculated by the processor 40. Those skilled in the art will appreciate that in some embodiments, the ultrasound imaging system itself may not incorporate a display module, but rather may be connected to a computer device (e.g., a computer) through which information is displayed via the display module (e.g., a display screen) of the computer device.
The ultrasound imaging system in some embodiments may complete the assessment of the endocardial acceptance. Specifically, the probe 10 transmits ultrasound waves to tissue of interest including the endometrium, and receives corresponding ultrasound echo signals; the processor 40 is configured to process the corresponding ultrasonic echo signals to obtain three-dimensional volume data including endometrium, and automatically determine the receptivity result of the endometrium based on the three-dimensional volume data, and control output the receptivity result of the endometrium, for example, to the display module 50 for display. In some embodiments, processor 40 automatically determines the above-described endometrial receptivity results based on three-dimensional volumetric data, including: the processor 40 automatically determines the results of the acceptance assessment-related measurements, such as the measured values of the acceptance assessment-related measurements or the scores converted from the measured values, based on the three-dimensional volumetric data; processor 40 determines the results of the endometrial receptivity based on the results of the receptivity evaluation related measurements.
The results of the automatic determination of the acceptance assessment-related measurements by the processor 40 based on the three-dimensional volumetric data are described in more detail below.
In some embodiments, the acceptance assessment-related measurement term includes a volume-related measurement term and/or a non-volume-related measurement term. In addition to calculating volume-related measurements such as endometrial volume, intima thickness, and endometrium blood flow perfusion based on an endometrial three-dimensional segmentation implementation, measurements of non-volume-related measurements such as endometrial typing, echo uniformity of the myometrium, etc., may also be implemented using machine learning or deep learning algorithms based on ultrasound imaging features of the uterus and endometrium.
In some embodiments, the volume-related measurement may be calculated as follows: the volume-related measurement (volume, thickness, blood flow, etc.) may be obtained by accurate three-dimensional segmentation of the endometrium, or by algorithmic direct regression of the measurement or score (score) of the corresponding measurement.
Calculation of volume-related measurements by accurate three-dimensional segmentation of the endometrium will be described first.
The purpose of accurate three-dimensional segmentation is to determine whether each voxel in the three-dimensional volume data belongs to the endometrium. According to the three-dimensional segmentation result, the number of body pixels belonging to the endometrium can be counted, so that measurement items such as the volume, the thickness and the like of the endometrium are obtained; after obtaining the endometrial volume, the blood flow signal duty cycle can also be calculated, so that a measurement item related to blood flow perfusion is obtained. The direct regression method is to directly predict a final measured term value or score value through an algorithm. Both implementations can be implemented using image algorithms, or can be implemented using deep learning based algorithms.
Taking an image algorithm to realize three-dimensional endometrial segmentation as an example: in three-dimensional data of endometrium, there is obvious difference between echo of endometrium and echo of surrounding tissues, and along with change of female physiological cycle, the shape of endometrium also shows periodic change, and according to the image characteristics, traditional gray scale and/or morphology and other methods can be adopted to realize segmentation of endometrium, such as methods of division such as Otsu Threshold (OTSU), level set (level set), graph Cut (Graph Cut), snake model (Snake) and the like.
Taking the concentration learning-based method for realizing endometrial segmentation as an example: firstly, the characteristics or rules of a target area and a non-target area can be distinguished in a learning database, and then, key anatomical parts of other images are positioned and identified according to the learned characteristics or rules, and the method comprises the following main steps:
step 1, a database construction step
The database typically contains a plurality of endometrial data and calibration results for critical anatomy. The calibration result can be set according to the actual task requirement, and for the segmentation task, the calibration is usually Mask for precisely segmenting the endometrial region.
Step 2, positioning and identifying step
After the database is built, a deep learning network algorithm is designed, and features or rules of a target area (an endometrium area) and a non-target area (a background area) can be distinguished in the learning database to realize accurate segmentation of the endometrium. This implementation step includes, but is not limited to, the following.
The first case is an end-to-end semantic segmentation network method based on deep learning, semantic segmentation needs to classify each pixel of an input image, determine which class each pixel in the image belongs to, and in the invention, determine whether each pixel belongs to endometrium or not; the form of the method can be as follows: the constructed database is subjected to feature learning by stacking a base layer convolution layer and a full connection layer; adding an up-sampling or deconvolution layer behind the feature extraction network, recovering the extracted features to be close to the original image or have the same resolution as the original image, and outputting segmentation masks, wherein values of different positions in the masks represent categories of corresponding positions in the original image (whether the corresponding positions belong to endometrium or not), so that pixel positions of the endometrium in the input image are directly obtained; some networks may be FCNs, U-NETs, deeplab families, etc.
The second case is an end-to-end instance split network based on deep learning; similar to the first type of semantic segmentation method, the method is realized by stacking different deep learning network layers, and the difference is that the instance segmentation also needs to distinguish different targets of the same category. The common implementation mode of the deep learning example segmentation algorithm is combined with a target detection network, the position and the size of a target are obtained through detection and positioning of different targets in different categories in an image, and then two-category semantic segmentation is carried out on each target area, so that whether each pixel in the target area belongs to the target or the background is determined. Endometrial segmentation is also achieved using an example segmentation network, which includes Mask-RCNN, FCIS, etc.
The third case is a method of combining deep learning with image segmentation; for example, a deep learning algorithm is used to obtain an initial segmentation result or feature, and a traditional segmentation algorithm is used to further optimize the result; in addition, the segmentation parameters of the traditional segmentation algorithm can be predicted by using a deep learning algorithm, for example, the initial contour and the optimization parameters of the traditional level set algorithm can be predicted by using the deep learning algorithm, and a better segmentation result can be obtained.
Determining which pixels of the volume data belong to endometrium through an image segmentation method or a deep learning algorithm, thereby obtaining a plurality of related measurement items; specifically, after obtaining a three-dimensional segmentation of the endometrium, the endometrial volume may be measured as follows: the pixel volume of the endometrium can be obtained by counting the number of all the pixel points belonging to the endometrium, and the actual physical volume of the endometrium is obtained by the conversion relation between the pixel distance and the actual physical distance during scanning and reconstruction of an ultrasonic imaging system; the endometrium can be measured as follows: positioning to a sagittal plane through the three-dimensional segmentation result of the endometrium, and calculating the thickest part of the segmentation result of the sagittal plane to obtain the endometrium thickness; blood perfusion can be measured as follows: for color Doppler 3D data, calculating the blood flow perfusion condition of the endometrium according to the three-dimensional segmentation result of the endometrium; the blood vessel index VI, the blood flow index FI and the blood vessel-blood flow index VFI on the endometrium can be obtained by counting the intensity and the quantity of the color Doppler blood flow signals in the endometrium region; vascular Index (VI), blood Flow Index (FI) and vascular blood flow index (VFI) are important indicators for evaluating blood flow; the blood Vessel Index (VI) is a blood flow voxel in the region of interest/total voxel value in the region of interest, namely the number of pixels of the blood vessel occupying the whole pixel of the endometrium is a ratio, and represents the number of the blood vessels in the unit volume in the region of interest (such as the endometrium region), and represents the abundance or sparseness degree of the blood vessels in the tissue; the blood Flow Index (FI) is the average intensity of blood flow voxels (voxels without blood flow signal) in the region of interest, i.e. the average signal intensity of pixels with blood flow in the endometrium, is the average value or blood flow density of all blood flows in the region of interest, representing the average intensity of blood flow signals in the target volume; the vascularized blood flow index (VFI) is the average of the blood flow signals of all voxels (including voxels without blood flow signals) within the region of interest, and is a combination of the blood vessel information and blood flow information present within the target tissue.
The calculation of volume-related measurements by accurate three-dimensional segmentation of the endometrium is described above, followed by a description of the measurement or score (score) of the corresponding measurement by direct regression through an algorithm.
The direct regression scheme is to identify the characteristics of the volume data through an algorithm and establish a mapping relationship between the characteristics and corresponding measured values (or score values). When a datum is entered, the algorithm predicts a particular measurement based on the characteristics of the datum. Similar to the segmentation method described above, the direct regression scheme may also be implemented using a deep learning algorithm and/or an image method. The implementation steps of the parameter regression scheme based on deep learning are similar to the three-dimensional segmentation implementation method of endometrium, and the implementation steps can be divided into steps of constructing a database, designing and training a regression network and the like, and the used deep learning network can be a Convolutional Neural Network (CNN), a three-dimensional convolutional neural network (3D-CNN), a cyclic neural network (RNN) and the like. The traditional regression method needs to manually design a feature extraction method to extract features of the data, and common features include gray features, texture features, pixel gradients, statistical features of pixel distribution and the like; after the features are extracted, the corresponding relation between the features and the specific measured values can be established by using algorithms such as linear regression, and therefore regression results are obtained. Similar to the segmentation scheme, the regression scheme can be implemented by combining the conventional method and the deep learning method as well.
The above describes the realization of the measurement of volume-related measurements by three-dimensional segmentation of the endometrium, and the direct regression of the measurements or scores of the corresponding measurements by an algorithm; the measurement of non-volume related measurement items is further described below.
As mentioned above, in addition to measurement items related to the endometrial volume, there are also some parameters for the evaluation of endometrial receptivity that do not need to depend on the calculation of the endometrial volume, such as endometrial typing and endometrial myometrial echo uniformity. Such non-volume-related measurements may be calculated by means of classification or direct regression, etc.
And (5) classification calculation: the endometrial data is automatically classified by an algorithm, so that the type of the endometrium can be judged, and whether the endometrial echo is uniform or not can be judged. The classification method can be realized based on a deep learning algorithm or a traditional machine learning algorithm; the classification based on the deep learning algorithm is similar to the implementation steps of the deep learning segmentation algorithm described above, and will not be repeated here. The traditional machine learning classification algorithm is as follows: adaboost algorithm, support Vector Machine (SVM), random Forest (Random Forest), etc.; the classification process can be realized based on three-dimensional volume data or can be realized on a two-dimensional section-by-section basis. After the classification result is obtained, the specific measurement score can be also corresponding to the classification result.
Regression calculation: the regression calculation of the other classes of parameters is similar to the regression method of the volume-related parameters described above and will not be repeated here.
In some embodiments, when the image quality is poor and the endometrial volume segmentation result calculated by the algorithm has deviation, the user can delete and recalibrate the segmentation result by means of a keyboard, a mouse and other tools, so that semi-automatic measurement item calculation is realized.
The above describes the measurement or calculation of the measure related to the acceptance evaluation.
When applied to an ultrasound imaging system, in some embodiments, processor 40 automatically determines at least a result of a volume-related measurement based on the three-dimensional volume data, wherein the volume-related measurement includes any one or more of an endometrium thickness, an endometrium volume, and a blood flow perfusion index of the endometrium. In some embodiments, the processor 40 may automatically determine at least the results of the volume-related measurements based on the three-dimensional volume data as described above:
(1) The processor 40 automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium; processor 40 calculates the results of the volume-related measurements based on the segmented endometrium; for example, taking calculating the endometrial volume as an example, the processor 40 counts the number of all pixels belonging to the endometrium based on the divided endometrium to obtain the pixel volume of the endometrium, and the processor 40 converts the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrial volume through the conversion relation between the pixel distance and the actual physical distance; for another example, taking the calculation of the endometrium as an example, the processor 40 locates the sagittal plane of the endometrium based on the divided endometrium, and calculates the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrium thickness; for example, the processor 40 calculates the blood perfusion index of the endometrium by counting the color Doppler blood flow signal intensity and the number of pixels in the endometrium region based on the divided endometrium;
Alternatively, the processor 40 may also automatically determine at least the results of the volume-related measurements based on the three-dimensional volume data as described above:
(2) Pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and the result of volume-related measurement items; the processor 40 recognizes preset features in the acquired three-dimensional volume data containing the endometrium and calculates the result of the volume-related measurement item according to the above-described mapping relationship.
In some embodiments, the processor automatically determines at least a result of a non-volume-related measurement based on the three-dimensional volume data, wherein the non-volume-related measurement includes any one or more of endometrial typing and endometrial myolayer echo uniformity. In some embodiments, the processor 40 may automatically determine at least the results of the non-volume-related measurements based on the three-dimensional volume data:
(1) The processor 40 calculates the results of the non-volume-related measurements by a classification algorithm based on the three-dimensional volume data;
alternatively, the processor 40 may also automatically determine at least the results of the non-volume-related measurements based on the three-dimensional volume data:
(2) Pre-establishing a mapping relation of preset characteristics of three-dimensional volume data containing endometrium and results of non-volume related measurement items; the processor 40 recognizes a preset feature in the acquired three-dimensional volume data including endometrium and calculates a result of the non-volume-related measurement item according to a mapping relationship of the preset feature of the three-dimensional volume data including endometrium to the result of the non-volume-related measurement item.
After automatically determining the results of the receptivity evaluation related measurements based on the three-dimensional volumetric data, processor 40 determines the receptivity results of the endometrium based on the results of the receptivity evaluation related measurements. The results of the above-mentioned acceptance evaluation-related measurement items may be measured values of the acceptance evaluation-related measurement items or scores (scores) converted from the measured values. For example, fig. 2 is an example of a conversion relationship between a measured value and a score of a measurement item related to the acceptance evaluation; it should be noted that, fig. 2 only shows the correspondence between the measured value and the score (grading) of the partial acceptance evaluation related measurement, and the corresponding specific numerical value may be modified according to different clinical standards.
When the result of the acceptance assessment-related measurement is a measurement value, the processor 40 may calculate a score from the result of the acceptance assessment-related measurement as an acceptance result of the endometrium; when the outcome of the acceptance assessment related measurement is a score, processor 40 may perform a weighted summation of the scores to obtain an endometrial acceptance outcome.
In some embodiments, obtaining the tolerability results of the endometrium may also be achieved using regression; in the scheme of realizing the measured value of the acceptance evaluation related measurement item by the regression, replacing the regression of the measured value with direct scoring regression; for example, the step of regressing the endometrial volume values in the previous protocol may be replaced with a score regressing the endometrial volume. The scheme of directly using the algorithm regression score is to skip the step of regression measurement, and directly using the algorithm to learn the mapping relation between the image characteristics and the specific acceptance score.
The tolerability result of the endometrium may also be a grade of the tolerability directly, e.g. the processor 40 may set a threshold value, and after scoring the endometrial receptivity, compare it to the threshold value and thereby divide it into different grades; in some embodiments, the measured value and the corresponding score of the measurement item related to the receptivity evaluation may also be displayed, and these are displayed as the receptivity result of the endometrium, and the result of the receptivity analysis is specifically judged by the doctor.
In still other embodiments, the processor 40 automatically determines the tolerability results of the endometrium based on the three-dimensional volumetric data, including: pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and a receptive result; the processor 40 recognizes preset features in the acquired three-dimensional volume data including endometrium and calculates the tolerability result based on the mapping relationship of the preset features of the three-dimensional volume data including endometrium and the tolerability result. Similarly, the acceptance result here may be a score, a grade of acceptance, or the like.
One operational procedure may be such;
the doctor generates and displays a two-dimensional ultrasonic image through an ultrasonic imaging system, then selects a region of interest in the two-dimensional ultrasonic image through an input tool such as a mouse, for example, a box is drawn through the mouse to select the region of interest containing endometrium, or the doctor can also automatically select the region of interest through the ultrasonic imaging system, for example, the ultrasonic imaging system identifies the region of interest containing endometrium on the two-dimensional ultrasonic image; then, the user manually or automatically starts three-dimensional ultrasonic data acquisition by the ultrasonic imaging system, three-dimensional volume data containing the endometrium are scanned and acquired by the ultrasonic imaging system, and after the three-dimensional volume data containing the endometrium are acquired by the ultrasonic imaging system, the acceptance result of the endometrium is automatically determined and displayed.
The ultrasound imaging system in some embodiments may also include a receptivity assessment key, which may be a physical structure or a virtual key, which when it is a virtual key may then be clicked by a user via a mouse. In some embodiments, the acceptance assessment key is capable of generating acceptance assessment instructions in response to user operation; in response to the acceptance assessment instructions, processor 40 acquires three-dimensional volume data comprising endometrium and determines an acceptance result of endometrium based on the three-dimensional volume data; how processor 40 determines the tolerability results of the endometrium based on the three-dimensional volumetric data is described in detail above and is not described in detail herein.
One operational procedure may be such;
the doctor generates and displays a two-dimensional ultrasonic image through an ultrasonic imaging system, then selects a region of interest in the two-dimensional ultrasonic image through an input tool such as a mouse, for example, a box is drawn through the mouse to select the region of interest containing endometrium, or the doctor can also automatically select the region of interest through the ultrasonic imaging system, for example, the ultrasonic imaging system identifies the region of interest containing endometrium on the two-dimensional ultrasonic image; then the user manually or automatically starts the three-dimensional ultrasonic data acquisition by the ultrasonic imaging system, the three-dimensional volume data containing the endometrium is scanned and acquired by the ultrasonic imaging system, and then the user can trigger the acceptance evaluation key, so that the ultrasonic imaging system automatically determines and displays the acceptance result of the endometrium after acquiring the three-dimensional volume data containing the endometrium.
The foregoing is illustrative of an ultrasound imaging system. Also disclosed in some embodiments is a method of ultrasound imaging, described in detail below.
Referring to fig. 3, the ultrasound imaging method of some embodiments includes the following steps:
step 100: three-dimensional volumetric data including endometrium is acquired.
Step 110: the tolerability results of the endometrium are automatically determined based on the three-dimensional volumetric data.
In some embodiments, referring to fig. 4, step 110 of automatically determining the tolerability of the endometrium based on the three-dimensional volume data comprises the steps of:
step 111: and automatically determining the result of the capacity acceptance evaluation related measurement item based on the three-dimensional volume data.
For example, step 111 automatically determines the results of at least volume-related measurements based on the three-dimensional volume data described above, wherein the volume-related measurements include any one or more of endometrial thickness, endometrial volume, and endometrial blood flow perfusion indicators.
In some embodiments, step 111 automatically segments the three-dimensional volume data including endometrium to segment out endometrium; based on the segmented endometrium, the results of the volume-related measurements described above are calculated. Taking calculating the endometrial volume as an example, step 111 counts the number of all pixels belonging to the endometrial based on the divided endometrial to obtain the endometrial pixel volume, and step 111 converts the endometrial pixel volume into the endometrial actual physical volume as the endometrial volume through the conversion relation between the pixel distance and the actual physical distance; for example, taking the calculation of the endometrium as an example, step 111 locates the sagittal plane of the endometrium based on the divided endometrium, and calculates the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrium thickness; for example, in the case of calculating the blood perfusion index, step 111 calculates the blood perfusion index of the endometrium by counting the color Doppler blood flow signal intensity and the number of pixels in the endometrium region based on the segmented endometrium.
In some embodiments, a mapping relationship of preset features comprising three-dimensional volumetric data of the endometrium and the results of the volume-related measurements is pre-established; step 111 identifies a preset feature in the acquired three-dimensional volume data including endometrium, and calculates a result of the volume-related measurement item according to a mapping relation of the preset feature of the three-dimensional volume data including endometrium and the result of the volume-related measurement item established in advance.
For another example, step 111 automatically determines at least the results of non-volume-related measurements based on the three-dimensional volume data, wherein the non-volume-related measurements include any one or more of endometrial typing and endometrial myolayer echo uniformity.
In some embodiments, step 111 calculates the results of the non-volume-related measurements by a classification algorithm based on the three-dimensional volume data.
In some embodiments, a mapping relationship of preset features comprising three-dimensional volumetric data of the endometrium to results of non-volume-related measurements is pre-established; step 111 identifies a preset feature in the acquired three-dimensional volume data including endometrium, and calculates a result of the non-volume-related measurement item according to a mapping relation of the preset feature of the three-dimensional volume data including endometrium to the result of the non-volume-related measurement item established in advance.
Step 113: and determining the tolerability result of the endometrium according to the result of the measurement item related to the tolerability evaluation.
In some embodiments, referring to fig. 5, step 110 of automatically determining the tolerability of the endometrium based on the three-dimensional volume data comprises the steps of:
step 115: pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and a receptive result;
step 117: and identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating the acceptance result according to the mapping relation between the preset features of the three-dimensional volume data containing the endometrium and the acceptance result.
Step 120: and controlling and outputting the tolerability result of the endometrium.
The foregoing is a few descriptions of ultrasound imaging methods.
Referring to fig. 6, in some embodiments, the ultrasound imaging method comprises the steps of:
step 200: three-dimensional volumetric data including endometrium is acquired.
Step 210: the three-dimensional volume data containing the endometrium is automatically segmented to segment the endometrium. For example, step 210 may segment the endometrium from the three-dimensional volume data containing the endometrium by feature detection based on differences in image features of the endometrium and the basal layer tissue, and/or periodically variable morphological features of the endometrium. For another example, step 210 obtains a model trained by machine learning and segments the endometrium from the three-dimensional volumetric data comprising the endometrium based on the model.
Step 220: automatically calculating a volume-related measurement item and a non-volume-related measurement item according to the divided endometrium; the volume-related measurement includes any one or more of endometrial thickness, endometrial volume, and an endometrial blood flow perfusion index, and the non-volume-related measurement includes any one or more of endometrial typing and endometrial myometrial echo uniformity.
Step 230: and automatically determining the result of the capacity evaluation related measurement according to the capacity related measurement and the non-capacity related measurement.
Step 240: and determining the tolerability result of the endometrium according to the result of the measurement item related to the tolerability evaluation. For example, step 240 calculates a score for the endometrial receptivity based on the results of the measurement associated with the receptivity evaluation, and determines the endometrial receptivity result based on the score for the endometrial receptivity.
Reference is made to various exemplary embodiments herein. However, those skilled in the art will recognize that changes and modifications may be made to the exemplary embodiments without departing from the scope herein. For example, the various operational steps and components used to perform the operational steps may be implemented in different ways (e.g., one or more steps may be deleted, modified, or combined into other steps) depending on the particular application or taking into account any number of cost functions associated with the operation of the system.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. Additionally, as will be appreciated by one of skill in the art, the principles herein may be reflected in a computer program product on a computer readable storage medium preloaded with computer readable program code. Any tangible, non-transitory computer readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-to-ROM, DVD, blu-Ray disks, etc.), flash memory, and/or the like. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including means which implement the function specified. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified.
While the principles herein have been shown in various embodiments, many modifications of structure, arrangement, proportions, elements, materials, and components, which are particularly adapted to specific environments and operative requirements, may be used without departing from the principles and scope of the present disclosure. The above modifications and other changes or modifications are intended to be included within the scope of this document.
The foregoing detailed description has been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes may be made without departing from the scope of the present disclosure. Accordingly, the present disclosure is to be considered as illustrative and not restrictive in character, and all such modifications are intended to be included within the scope thereof. Also, advantages, other advantages, and solutions to problems have been described above with regard to various embodiments. The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, system, article, or apparatus. Furthermore, the term "couple" and any other variants thereof are used herein to refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections, and/or any other connection.
Those skilled in the art will recognize that many changes may be made to the details of the above-described embodiments without departing from the underlying principles of the invention. Accordingly, the scope of the invention should be determined only by the following claims.
Claims (23)
1. An ultrasound imaging system, comprising:
a probe for transmitting ultrasonic waves to a tissue of interest including endometrium and receiving corresponding ultrasonic echo signals;
a transmission and reception control circuit for controlling the probe to perform transmission of ultrasonic waves and reception of ultrasonic echo signals;
a receptivity evaluation key for generating a receptivity evaluation instruction in response to a user operation;
a processor for processing the corresponding ultrasonic echo signals to obtain three-dimensional volume data containing endometrium; in response to the acceptance assessment instruction:
the processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium;
the processor automatically calculates volume-related measurement items and non-volume-related measurement items according to the divided endometrium; the volume-related measurement comprises any one or more of endometrial thickness, endometrial volume, and an endometrial blood flow perfusion index, and the non-volume-related measurement comprises any one or more of endometrial typing and endometrial myolayer echo uniformity;
The processor automatically determines the result of the capacity evaluation related measurement item according to the capacity related measurement item and the non-capacity related measurement item;
the processor determines the tolerability results of the endometrium based on the results of the tolerability assessment related measurements.
2. The ultrasound imaging system of claim 1, wherein the processor automatically segments the three-dimensional volumetric data including endometrium to segment out endometrium, comprising:
the processor segments the endometrium from the three-dimensional volume data containing the endometrium by feature detection according to image feature differences of the endometrium and the basal layer tissue of the uterus and/or morphological features of the endometrium which can be periodically changed;
or,
a model trained by machine learning is acquired and based on the model, endometrium is segmented from the three-dimensional volumetric data comprising endometrium.
3. The ultrasound imaging method of claim 1, wherein the processor determining the tolerability of the endometrium from the results of the tolerability assessment related measurements comprises:
the processor calculates a score of the receptivity of the endometrium according to the result of the receptivity evaluation related measurement item;
The processor determines an endometrial receptivity outcome based on the endometrial receptivity score.
4. An ultrasound imaging system, comprising:
a probe for transmitting ultrasonic waves to a tissue of interest including endometrium and receiving corresponding ultrasonic echo signals;
a transmission and reception control circuit for controlling the probe to perform transmission of ultrasonic waves and reception of ultrasonic echo signals;
and the processor is used for processing the corresponding ultrasonic echo signals to acquire three-dimensional volume data containing endometrium, automatically determining the acceptation result of the endometrium based on the three-dimensional volume data and controlling and outputting the acceptation result of the endometrium.
5. The ultrasound imaging system of claim 4, wherein the processor automatically determines the tolerability results of the endometrium based on the three dimensional volumetric data, comprising:
the processor automatically determines the result of the measurement related to the capacity acceptance evaluation based on the three-dimensional volume data;
the processor determines the tolerability results of the endometrium based on the results of the tolerability assessment related measurements.
6. The ultrasound imaging system of claim 5, wherein the processor automatically determines results of the volume-based assessment-related measurements based on the three-dimensional volumetric data, comprising: the processor automatically determines at least a result of a volume-related measurement based on the three-dimensional volume data, the volume-related measurement including any one or more of an endometrium thickness, an endometrium volume, and a blood flow perfusion index of the endometrium.
7. The ultrasound imaging system of claim 6, wherein the processor automatically determines at least a result of a volume-related measurement based on the three-dimensional volume data, comprising:
the processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium; calculating a result of the volume-related measurement based on the segmented endometrium; or,
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and the result of volume-related measurement items; the processor identifies preset features in the acquired three-dimensional volume data containing the endometrium and calculates the result of the volume-related measurement item according to the mapping relation.
8. The ultrasound imaging system of claim 7, wherein the processor calculates results of the volume-related measurements based on the segmented endometrium, comprising:
the processor counts the number of all pixels belonging to the endometrium based on the divided endometrium so as to obtain the pixel volume of the endometrium; the processor converts the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrium volume through the conversion relation between the pixel distance and the actual physical distance;
and/or the number of the groups of groups,
the processor locates a sagittal plane of the endometrium based on the segmented endometrium and calculates a thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrium thickness;
and/or the number of the groups of groups,
the processor calculates a blood flow perfusion index of the endometrium by counting color Doppler blood flow signal intensity and pixel number in the endometrium area based on the divided endometrium.
9. The ultrasound imaging system of claim 5, wherein the processor automatically determines results of the volume-based assessment-related measurements based on the three-dimensional volumetric data, comprising: the processor automatically determines at least a result of a non-volume-related measurement based on the three-dimensional volume data, the non-volume-related measurement including any one or more of endometrial typing and endometrial myolayer echo uniformity.
10. The ultrasound imaging system of claim 9, wherein the processor at least automatically determines a result of a non-volume-related measurement based on the three-dimensional volume data, comprising:
the processor calculates the result of the non-volume-related measurement item through a classification algorithm based on the three-dimensional volume data;
or,
pre-establishing a mapping relation of preset characteristics of three-dimensional volume data containing endometrium and results of non-volume related measurement items; the processor identifies preset features in the acquired three-dimensional volume data containing the endometrium and calculates the result of the non-volume-related measurement item according to the mapping relation.
11. The ultrasound imaging system of claim 4, wherein the processor automatically determines the tolerability results of the endometrium based on the three dimensional volumetric data, comprising:
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and a receptive result;
the processor identifies preset features in the acquired three-dimensional volumetric data including endometrium, and calculates a tolerability result according to the mapping relationship.
12. An ultrasound imaging method, comprising:
Acquiring three-dimensional volume data comprising endometrium;
automatically segmenting the three-dimensional volume data comprising endometrium to segment out endometrium;
automatically calculating a volume-related measurement item and a non-volume-related measurement item according to the divided endometrium; the volume-related measurement comprises any one or more of endometrial thickness, endometrial volume, and an endometrial blood flow perfusion index, and the non-volume-related measurement comprises any one or more of endometrial typing and endometrial myolayer echo uniformity;
according to the volume-related measurement items and the non-volume-related measurement items, automatically determining the result of the volume acceptance evaluation-related measurement items;
and determining the tolerability result of the endometrium according to the result of the acceptance evaluation related measurement.
13. The ultrasound imaging method of claim 12, wherein said automatically segmenting the three-dimensional volumetric data including endometrium to segment out endometrium comprises:
segmenting the endometrium from the three-dimensional volume data comprising the endometrium by feature detection according to image feature differences of the endometrium and the basal layer tissue of the uterus and/or periodically changeable morphological features of the endometrium;
Or,
a model trained by machine learning is acquired and based on the model, endometrium is segmented from the three-dimensional volumetric data comprising endometrium.
14. The ultrasound imaging method of claim 12, wherein said determining the tolerability of the endometrium from the results of the tolerability assessment related measurements comprises:
calculating a score of the endometrial receptivity according to the result of the receptivity evaluation related measurement item;
and determining the endometrial receptivity result according to the endometrial receptivity score.
15. An ultrasound imaging method, comprising:
acquiring three-dimensional volume data comprising endometrium;
automatically determining a tolerability result of the endometrium based on the three-dimensional volumetric data;
and controlling and outputting the receptivity result of the endometrium.
16. The ultrasound imaging method of claim 15, wherein the automatically determining the tolerability outcome of the endometrium based on the three dimensional volumetric data comprises:
automatically determining a result of a capacity acceptance evaluation related measurement item based on the three-dimensional volume data;
and determining the tolerability result of the endometrium according to the result of the acceptance evaluation related measurement.
17. The ultrasound imaging method of claim 16, wherein said automatically determining the outcome of the acceptance assessment-related measurements based on the three-dimensional volumetric data comprises: automatically determining at least a result of a volume-related measurement based on the three-dimensional volume data, the volume-related measurement including any one or more of an endometrium thickness, an endometrium volume, and an endometrial blood flow perfusion index.
18. The ultrasound imaging method of claim 17, wherein the automatically determining at least a result of a volume-related measurement based on the three-dimensional volume data comprises:
automatically segmenting the three-dimensional volume data comprising endometrium to segment out endometrium; calculating a result of the volume-related measurement based on the segmented endometrium; or,
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and the result of volume-related measurement items; and identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating the result of the volume-related measurement according to the mapping relation.
19. The ultrasound imaging method of claim 18, wherein the calculating the results of the volume-related measurements based on the segmented endometrium comprises:
Counting the number of all pixels belonging to the endometrium based on the divided endometrium to obtain the pixel volume of the endometrium; converting the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrium volume through a conversion relation between the pixel distance and the actual physical distance;
and/or the number of the groups of groups,
locating a sagittal plane of the endometrium based on the segmented endometrium, and calculating a thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrium thickness;
and/or the number of the groups of groups,
based on the divided endometrium, the color Doppler blood flow signal intensity and the pixel number in the endometrium area are counted to calculate the blood flow perfusion index of the endometrium.
20. The ultrasound imaging method of claim 16, wherein said automatically determining the outcome of the acceptance assessment-related measurements based on the three-dimensional volumetric data comprises: results of at least automatically determining non-volume-related measurements based on the three-dimensional volume data, the non-volume-related measurements including any one or more of endometrial typing and endometrial myolayer echo uniformity.
21. The ultrasound imaging method of claim 20, wherein the automatically determining at least a result of a non-volume-related measurement based on the three-dimensional volume data comprises:
calculating the result of a non-volume-related measurement item through a classification algorithm based on the three-dimensional volume data;
or,
pre-establishing a mapping relation of preset characteristics of three-dimensional volume data containing endometrium and results of non-volume related measurement items; and identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating the result of the non-volume-related measurement item according to the mapping relation.
22. The ultrasound imaging method of claim 15, wherein the automatically determining the tolerability outcome of the endometrium based on the three dimensional volumetric data comprises:
pre-establishing a mapping relation between preset characteristics of three-dimensional volume data containing endometrium and a receptive result;
and identifying preset features in the acquired three-dimensional volume data containing the endometrium, and calculating a toleration result according to the mapping relation.
23. A computer readable storage medium having stored thereon a program executable by a processor to implement the method of any of claims 12 to 22.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210503431.4A CN117084709A (en) | 2022-05-09 | 2022-05-09 | Ultrasonic imaging system and method |
| PCT/CN2022/140190 WO2023216594A1 (en) | 2022-05-09 | 2022-12-20 | Ultrasonic imaging system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210503431.4A CN117084709A (en) | 2022-05-09 | 2022-05-09 | Ultrasonic imaging system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117084709A true CN117084709A (en) | 2023-11-21 |
Family
ID=88729561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210503431.4A Pending CN117084709A (en) | 2022-05-09 | 2022-05-09 | Ultrasonic imaging system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117084709A (en) |
| WO (1) | WO2023216594A1 (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150038778A1 (en) * | 2012-03-14 | 2015-02-05 | Cewntree Hospitalier Universitaire Pontchaillou | Itih5 as a diagnostic marker of uterine development and functional defects |
| WO2018222006A1 (en) * | 2017-06-02 | 2018-12-06 | Samsung Electronics Co., Ltd. | Apparatus and method for assessing uterine parameters |
| CN109805963B (en) * | 2019-03-22 | 2022-07-05 | 深圳开立生物医疗科技股份有限公司 | Method and system for judging endometrium typing |
| CN113066093A (en) * | 2021-04-08 | 2021-07-02 | 南华大学附属第一医院 | Automatic segmentation and parting and thickness measuring method based on endometrial ultrasound image |
| CN113576534A (en) * | 2021-08-17 | 2021-11-02 | 陈智毅 | Endometrium imaging device, scoring system and scoring method based on multi-modal imaging |
-
2022
- 2022-05-09 CN CN202210503431.4A patent/CN117084709A/en active Pending
- 2022-12-20 WO PCT/CN2022/140190 patent/WO2023216594A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023216594A1 (en) | 2023-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110325119B (en) | Ovarian follicle count and size determination | |
| CN114027880B (en) | Method for measuring parameters in ultrasonic image and ultrasonic imaging system | |
| US20170367685A1 (en) | Method for processing 3d image data and 3d ultrasonic imaging method and system | |
| CN111354006B (en) | Method and device for tracing target tissue in ultrasonic image | |
| JP2012506283A (en) | 3D ultrasound imaging | |
| CN107518920A (en) | Ultrasonic image processing method and device, supersonic diagnostic appts and storage medium | |
| CN112638273A (en) | Biometric measurement and quality assessment | |
| WO2022141083A1 (en) | Periodic parameter analysis method and ultrasonic imaging system | |
| CN113194837B (en) | System and method for frame indexing and image review | |
| WO2022099705A1 (en) | Early-pregnancy fetus ultrasound imaging method and ultrasound imaging system | |
| CN114680929A (en) | Ultrasonic imaging method and system for measuring diaphragm | |
| CN114699106A (en) | Ultrasonic image processing method and equipment | |
| CN117084709A (en) | Ultrasonic imaging system and method | |
| CN112654299A (en) | Ultrasonic imaging method, ultrasonic imaging apparatus, storage medium, processor, and computer apparatus | |
| WO2016049681A1 (en) | Ultrasound image processing system and method | |
| CN112294361A (en) | Ultrasonic imaging equipment and method for generating section image of pelvic floor | |
| CN114652353A (en) | Ultrasonic imaging system and carotid plaque stability assessment method | |
| EP2533684B1 (en) | Method of characterizing tissue of a patient | |
| CN111493931A (en) | Ultrasonic imaging method and device and computer readable storage medium | |
| CN111383323A (en) | Ultrasonic imaging method and system and ultrasonic image processing method and system | |
| CN113974688B (en) | Ultrasonic imaging method and ultrasonic imaging system | |
| CN117934356A (en) | Ultrasonic imaging system and automatic quantitative analysis method for ovarian interstitial | |
| EP3848892A1 (en) | Generating a plurality of image segmentation results for each node of an anatomical structure model to provide a segmentation confidence value for each node | |
| CN113939236B (en) | Ultrasonic imaging equipment and ultrasonic echo signal processing method thereof | |
| Khazendar | Computer-aided diagnosis of gynaecological abnormality using B-mode ultrasound images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |