CN112168168A - System and method for automatically and quantitatively evaluating whole body fat by using MR (magnetic resonance) technology - Google Patents
System and method for automatically and quantitatively evaluating whole body fat by using MR (magnetic resonance) technology Download PDFInfo
- Publication number
- CN112168168A CN112168168A CN202011096361.2A CN202011096361A CN112168168A CN 112168168 A CN112168168 A CN 112168168A CN 202011096361 A CN202011096361 A CN 202011096361A CN 112168168 A CN112168168 A CN 112168168A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- fat
- anatomical
- interval
- 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
- 210000000577 adipose tissue Anatomy 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 238000003745 diagnosis Methods 0.000 claims abstract description 73
- 238000004364 calculation method Methods 0.000 claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 210000004003 subcutaneous fat Anatomy 0.000 claims abstract description 26
- RGCLLPNLLBQHPF-HJWRWDBZSA-N phosphamidon Chemical group CCN(CC)C(=O)C(\Cl)=C(/C)OP(=O)(OC)OC RGCLLPNLLBQHPF-HJWRWDBZSA-N 0.000 claims abstract description 25
- 238000011158 quantitative evaluation Methods 0.000 claims abstract description 22
- 238000002224 dissection Methods 0.000 claims abstract description 21
- 210000001596 intra-abdominal fat Anatomy 0.000 claims abstract description 21
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 239000000284 extract Substances 0.000 claims abstract description 6
- 230000011218 segmentation Effects 0.000 claims description 67
- 210000001015 abdomen Anatomy 0.000 claims description 6
- 210000000038 chest Anatomy 0.000 claims 2
- 210000004197 pelvis Anatomy 0.000 claims 2
- 210000001519 tissue Anatomy 0.000 abstract description 16
- 238000003384 imaging method Methods 0.000 abstract description 14
- 235000013861 fat-free Nutrition 0.000 abstract description 13
- 238000004458 analytical method Methods 0.000 abstract 1
- 210000003484 anatomy Anatomy 0.000 description 16
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000011002 quantification Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 6
- 230000029058 respiratory gaseous exchange Effects 0.000 description 6
- 230000035945 sensitivity Effects 0.000 description 6
- 238000013480 data collection Methods 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 230000008021 deposition Effects 0.000 description 3
- 208000030159 metabolic disease Diseases 0.000 description 3
- 210000003205 muscle Anatomy 0.000 description 3
- 206010018852 Haematoma Diseases 0.000 description 2
- 206010024612 Lipoma Diseases 0.000 description 2
- 210000000683 abdominal cavity Anatomy 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 210000003486 adipose tissue brown Anatomy 0.000 description 2
- 210000001185 bone marrow Anatomy 0.000 description 2
- 210000000028 corpus adiposum pararenale Anatomy 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000004013 groin Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003387 muscular Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000016097 disease of metabolism Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4869—Determining body composition
- A61B5/4872—Body fat
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- High Energy & Nuclear Physics (AREA)
- Radiology & Medical Imaging (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention provides an automatic quantitative evaluation system for whole body fat by using MR technology, which comprises: when a patient finishes shooting a magnetic resonance examination item of fat detection, an image recognition module extracts a GRE DIXON sequence image and/or a T1WI sequence image, an image quality judgment module performs quality analysis on the extracted sequence image, a first dissection module dissects non-fat tissues on an image with qualified quality, a second dissection module dissects subcutaneous fat, musculoskeletal fat, visceral fat and special regions on a third image, coordinates of fat intervals and fat interval dissection labels are set for each region, a calculation module calculates the measurement value of each fat interval, and a structured report module integrates all processed data and images, saves and outputs a diagnosis impression. The invention also discloses an automatic quantitative evaluation method for the whole body fat by using the MR technology. The invention can accurately and quantitatively measure the volume of the adipose tissues and automatically transmit the volume into a report, thereby improving the working efficiency of imaging doctors and being applicable to actual clinic.
Description
Technical Field
The invention relates to the field of medical information, in particular to a system and a method for automatically and quantitatively evaluating whole body fat by using an MR (magnetic resonance) technology.
Background
In recent years, due to the increasing incidence of obesity and related metabolic disorders, evaluation of quantitative information on total body fat is required for clinical evaluation of liver metabolic disorders and diabetic patients. In addition to fat quantification, fat distribution is also associated with disease, and there is clear evidence that excessive deposition of visceral fat leads to a significant increase in the risk of cardiovascular and metabolic disease in patients. The need to non-invasively segment and accurately measure adipose tissue volume is becoming apparent.
There are many methods for measuring the whole body fat volume and the local fat volume, such as simple parametric measurement, bioelectrical impedance, dual-energy X-ray absorption, CT, MRI, ultrasound, and the like. These methods are either only qualitative measurements; or damage can not be done frequently; or the time is extremely long and the operation is not practical.
The GRE DIXON sequence or the T1WI sequence of the MR can be used for selectively imaging the adipose tissue, the distribution of the whole body fat can be displayed noninvasively and accurately, the scanning only needs about 10 minutes, and the method has obvious advantages compared with other imaging examinations. Although fat tissue can be well displayed on an MR image, fat is distributed in a body too much, and manual measurement cannot be realized at all, so that the volume of the fat tissue cannot be accurately and quantitatively measured for each case in clinical real work, the fat volumes of various parts and different areas of the body cannot be generated in an imaging report, the practical clinical application of MR fat quantification is limited, and the work efficiency of an imaging doctor is reduced.
Disclosure of Invention
In view of the above, the main objective of the present invention is to provide an automatic quantitative evaluation system and method for whole body fat by MR technology, which can solve the problems in the prior art that the volume of adipose tissue cannot be accurately and quantitatively measured for each case and automatically transmitted into a structured report, so that the work efficiency of imaging doctors is reduced and the system and method cannot be used in practical clinical applications.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
on one hand, the invention provides an automatic quantitative evaluation system for whole body fat by using MR technology, which comprises an image information management module, an image identification module, an image quality judgment module, a first anatomy segmentation module, a second anatomy segmentation module, a calculation module and a structured report module, wherein the image information management module is connected with the image identification module and is used for transmitting a DICOM image of a patient to the image identification module through a DICOM protocol when the patient finishes shooting a magnetic resonance examination item for whole body fat detection; the image identification module is connected with the image information management module, the image quality judgment module and the structural report module and is used for identifying the body position of the DICOM image based on DICOM image header file information, judging whether the DICOM image is matched with a magnetic resonance examination item for whole body fat detection, if the DICOM image is matched with the magnetic resonance examination item for whole body fat detection, extracting a GRE DIXON sequence image and/or a T1WI sequence image, defining the GRE DIXON sequence image and/or the T1WI sequence image as a first image and respectively sending the first image to the image quality judgment module and the structural report module; if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, the diagnosis process is stopped and first prompt information is sent to a structured report module; wherein the body positions comprise the chest, the abdomen and the basin; the image quality judging module is respectively connected with the image recognition module, the first anatomical segmentation module and the structured report module, and is used for analyzing the quality of the first image based on preset conditions, respectively sending the first image meeting the preset conditions to the first anatomical segmentation module and the structured report module, and defining the first image meeting the preset conditions as a second image; if the quality of the first image does not meet the preset condition, stopping the diagnosis process; sending the judgment result and the second prompt message to a structured report module; wherein the judgment result is that the image quality is unqualified or the image quality is qualified; the first anatomical segmentation module is connected with the image quality judgment module, the second anatomical segmentation module and the structural report module, and is used for segmenting non-adipose tissues with the volume larger than a first preset threshold value on the second image based on a first preset rule, setting anatomical coordinates of each non-adipose tissue, measuring the volume and radial line of each non-adipose tissue, judging the type of the non-adipose tissues based on the volume and radial line, setting an anatomical label for each non-adipose tissue, outputting the region of the anatomical label of each non-adipose tissue, namely a third image, sending the third image to the second anatomical segmentation module, and sending the volume and radial line of each non-adipose tissue, the type of the non-adipose tissues and the third image to the structural report module; the second anatomical segmentation module is respectively connected with the first anatomical segmentation module, the calculation module and the structural report module, and is used for segmenting subcutaneous fat, musculoskeletal fat, visceral fat and a special region on a third image based on a second preset rule, setting coordinates of fat intervals for the subcutaneous fat, musculoskeletal fat, visceral fat and the special region, outputting diagnosis data, setting a fat interval anatomical label for the coordinates of each fat interval, outputting the region of each fat interval anatomical label, namely a fourth image, and respectively sending the diagnosis data and the fourth image to the calculation module and the structural report module; the calculation module is respectively connected with the second anatomical segmentation module and the structured report module and is used for automatically calculating the measured value of each fat interval based on the diagnostic data and the fourth image, generating a key image and sending the measured value and the key image to the structured report module; the structured report module is respectively connected with the image identification module, the image quality judgment module, the first anatomical segmentation module, the second anatomical segmentation module and the calculation module and is used for automatically generating a diagnosis impression for a doctor to check the measured value based on a built-in rule; and stores all the received data and all the images.
Preferably, the second anatomical segmentation module further comprises a label judgment unit for judging whether the fat interval anatomical label is in compliance based on the diagnosis data, and the judgment rule is as follows: judging whether the radial line volume of the maximum connected domain of each fat interval anatomical label is within a second preset threshold value, judging whether the spatial relationship of adjacent fat interval anatomical labels is correct, judging the shapes of different fat interval anatomical labels, and sending the judgment result to a structured report module; if the fat interval anatomical label is in compliance, the diagnostic data is sent to the calculation module, and if the fat interval anatomical label is in non-compliance, third prompt information and the type of non-compliance are sent to the structured report module.
In another aspect, the present invention provides a method for automated quantitative evaluation of whole body fat by MR technique, comprising: when a patient finishes shooting a magnetic resonance examination item for detecting the whole body fat, the image information management module transmits a DICOM image of the patient to the image identification module through a DICOM protocol; the image identification module identifies the body position of the DICOM image based on DICOM image header file information, judges whether the DICOM image is matched with a magnetic resonance examination item for whole-body fat detection, extracts a GRE DIXON sequence image and/or a T1WI sequence image if the DICOM image is matched with the magnetic resonance examination item for whole-body fat detection, defines the GRE DIXON sequence image and/or the T1WI sequence image as a first image, and respectively sends the first image to the image quality judgment module and the structured report module; if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, the diagnosis process is stopped and first prompt information is sent to a structured report module; wherein the body positions comprise the chest, the abdomen and the basin; the image quality judging module analyzes the quality of the first image based on a preset condition, the first image which meets the preset condition is respectively sent to the first anatomical segmentation module and the structured report module, and the first image which meets the preset condition is defined as a second image; if the quality of the first image does not meet the preset condition, stopping the diagnosis process; sending the judgment result and the second prompt message to a structured report module; wherein the judgment result is that the image quality is unqualified or the image quality is qualified; the first anatomy segmentation module segments non-adipose tissues with the volume larger than a first preset threshold value on the second image based on a first preset rule, sets an anatomy coordinate of each non-adipose tissue, measures the volume and radial lines of each non-adipose tissue, judges the type of the non-adipose tissues based on the volume and radial lines, sets an anatomy label for each non-adipose tissue, outputs the region of the anatomy label of each non-adipose tissue, namely a third image, sends the third image to the second anatomy segmentation module, and sends the volume and radial lines of each non-adipose tissue, the type of the non-adipose tissues and the third image to the structured report module; the second dissection module is used for segmenting subcutaneous fat, musculoskeletal fat, visceral fat and a special region on the third image based on a second preset rule, setting coordinates of fat intervals for the subcutaneous fat, the musculoskeletal fat, the visceral fat and the special region, outputting diagnosis data, setting a fat interval dissection label for the coordinates of each fat interval, outputting a region of each fat interval dissection label, namely a fourth image, and respectively sending the diagnosis data and the fourth image to the calculation module and the structured report module; the calculation module automatically calculates the measured value of each fat interval based on the diagnostic data and the fourth image, generates a key image and sends the measured value and the key image to the structured report module; the structured report module automatically generates a diagnosis impression for a doctor to check according to a built-in rule; and stores all the received data and all the images.
Preferably, the method further comprises: the label judgment unit in the second dissection module judges whether the fat interval dissection labels are in compliance or not based on the diagnosis data, and the judgment rule is as follows: judging whether the radial line volume of the maximum connected domain of each fat interval anatomical label is within a second preset threshold value, judging whether the spatial relationship of adjacent fat interval anatomical labels is correct, judging the shapes of different fat interval anatomical labels, and sending the judgment result to a structured report module; if the fat interval anatomical label is in compliance, the diagnostic data is sent to the calculation module, and if the fat interval anatomical label is in non-compliance, third prompt information and the type of non-compliance are sent to the structured report module.
The invention has the technical effects that:
because the invention is provided with the image identification module, the image quality judgment module, the first anatomy segmentation module, the second anatomy segmentation module, the calculation module and the structuralization report module, when a patient finishes the magnetic resonance examination item of the whole body fat detection, the image identification module identifies the GRE DIXON sequence image and/or the T1WI sequence image, the image quality judgment module analyzes and judges the quality of the GRE DIXON sequence image and/or the T1WI sequence image, the DICOM image which influences the diagnosis due to low image signal-to-noise ratio, magnetic sensitivity artifact, breathing artifact, motion artifact and the like is identified to prevent the subsequent diagnosis from being influenced, the first anatomy segmentation module segments the non-fat tissue on the DICOM image sequence with qualified quality so as to better segment the fat tissue, and the second anatomy segmentation module segments the subcutaneous fat, the musculoskeletal fat, the fat tissue, the calculation module and the structuralization report module, The calculation module automatically calculates various measured values of each adipose tissue for the adipose tissues and transmits the measured values to the structured report module, and the structured report module integrates all processed data and images, stores the data and the images and outputs a diagnosis impression for doctors to refer; the system carries out automatic marking, part identification and quantitative statistical analysis on adipose tissues of all parts of the whole body under the conditions of controlling image quality and eliminating various influences on diagnosis through the combination of a series of deep learning models and logical reasoning, so that the cost of the MR scanning technology for quantitative evaluation of the adipose tissues of the whole body is greatly reduced, various measured values of all the adipose tissues are automatically transmitted to a structural report to generate a diagnosis impression, the working efficiency of an imaging doctor is greatly improved, the system can be used for clinical work and standardized data collection of clinical research, and the clinical value of an imaging service is improved; meanwhile, the label judging unit is arranged, whether the fat interval anatomical label is in compliance or not can be judged based on the diagnosis data, if the fat interval anatomical label is in compliance, the diagnosis data are sent to the calculating module, and if the fat interval anatomical label is in non-compliance, third prompt information is sent to the structured reporting module, so that the diagnosis inaccuracy caused by disqualification of the fat interval anatomical label is avoided, meanwhile, the prompt information is sent, manual intervention and processing are facilitated in time, an AI diagnosis model is perfected, and the whole diagnosis process is more perfect and more systematic.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic structural diagram of an automated quantitative evaluation system for whole body fat by MR technology according to a first embodiment of the invention;
FIG. 2 is a schematic diagram of a structured report interface of the system for the automated quantitative evaluation of total body fat by MR technique according to the first embodiment of the present invention;
FIG. 3 is a schematic diagram of a system for automated quantitative evaluation of total body fat by MR technique according to a second embodiment of the present invention;
FIG. 4 is a flow chart of a method for automated quantitative evaluation of whole body fat by MR technique according to a third embodiment of the invention;
FIG. 5 is a schematic diagram of a structured report interface in the method for the automated quantitative evaluation of total body fat by MR technique according to the third embodiment of the present invention;
fig. 6 shows a specific processing flow chart of the system method for the automated quantitative evaluation of the whole body fat by the MR technology according to the fourth embodiment of the invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example one
Fig. 1 is a schematic structural diagram of an automated quantitative evaluation system for whole body fat by MR technology according to a first embodiment of the invention; as shown in fig. 1, the system includes: image information management module 10, image recognition module 20, image quality determination module 30, first anatomical segmentation module 40, second anatomical segmentation module 50, calculation module 60, and structured reporting module 70, wherein,
the image information management module 10 is connected with the image identification module 20 and is used for transmitting the DICOM image of the patient to the image identification module 20 through a DICOM protocol when the patient finishes shooting the magnetic resonance examination item of the whole body fat detection;
the image Information management module is an ris (radio Information system) system.
An image recognition module 20, connected to the image information management module 10, the image quality determination module 30 and the structured report module 70, for recognizing a posture of the DICOM image based on DICOM image header file information, determining whether the DICOM image matches a magnetic resonance examination item for whole body fat detection, if the DICOM image matches the magnetic resonance examination item for whole body fat detection, extracting a GRE DIXON sequence image and/or a T1WI sequence image, defining the GRE DIXON sequence image and/or the T1WI sequence image as a first image, and sending the first image to the image quality determination module and the structured report module respectively; if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, the diagnosis process is stopped and first prompt information is sent to a structured report module; wherein the body positions comprise the chest, the abdomen and the basin;
wherein the first image is sent to a corresponding control for a technical assessment (scan sequence) in the structured reporting interface.
And if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, sending first prompt information to the structured report module, processing the first prompt information by related personnel, and storing the first prompt information in a database of the structured report module for calling and checking by subsequent personnel.
The image quality judging module 30 is respectively connected with the image recognition module 20, the first anatomical segmentation module 40 and the structured report module 70, and is configured to analyze the quality of the first image based on a preset condition, respectively send the first image meeting the preset condition to the first anatomical segmentation module 40 and the structured report module 70, and define the first image meeting the preset condition as a second image; if the quality of the first image does not meet the preset condition, stopping the diagnosis process; and sends the judgment result and the second prompt message to the structured report module 70; wherein the judgment result is that the image quality is unqualified or the image quality is qualified;
the conditions that the preset conditions are not met comprise low image signal-to-noise ratio, magnetic sensitivity artifacts, breathing artifacts, motion artifacts and the like;
wherein, the judgment result is sent to a corresponding control of the technical evaluation (image quality) of the structured report interface. And if the image quality is not qualified, sending second prompt information to the structured report module, processing the second prompt information by related personnel, and storing the second prompt information in a database of the structured report module for calling and checking subsequent personnel.
A first anatomical segmentation module 40, connected to the image quality determination module 30, the second anatomical segmentation module 50, and the structural reporting module 70, configured to segment non-adipose tissues with a volume greater than a first preset threshold on a second image based on a first preset rule, set anatomical coordinates of each non-adipose tissue, measure a volume and a radial line of each non-adipose tissue, determine a type of the non-adipose tissue based on the volume and the radial line, set an anatomical label for each non-adipose tissue, output a region of the anatomical label of each non-adipose tissue, that is, a third image, send the third image to the second anatomical segmentation module 50, and send the volume and the radial line of each non-adipose tissue, the type of the non-adipose tissue, and the third image to the structural reporting module 70;
generally, a non-fat high-signal region with a large volume (a first preset threshold) is segmented on the GRE DIXON sequence image and/or the T1WI sequence image, such as hematoma, lipoma, abnormal substance deposition, and the like, and the high signal, the volume and radial line of the non-fat tissue, and the type of the non-fat tissue are fed back to a corresponding control of the overall evaluation (the non-fat high-signal region) in the structured reporting interface.
The second anatomical segmentation module 50 is connected to the first anatomical segmentation module 40, the calculation module 60 and the structured report module 70, and configured to segment subcutaneous fat, musculoskeletal fat, visceral fat and a special region on a third image based on a second preset rule, set coordinates of fat intervals for the subcutaneous fat, musculoskeletal fat, visceral fat and the special region, output diagnostic data, set a fat interval anatomical label for the coordinates of each fat interval, output a region of each fat interval anatomical label, that is, a fourth image, and send the diagnostic data and the fourth image to the calculation module 60 and the structured report module 70, respectively;
wherein the subcutaneous fat is the structure of superficial subcutaneous fat, deep subcutaneous fat, etc.; the musculoskeletal fat is the structures of intermuscular fat, muscular fat, bone marrow fat and the like; visceral fat is abdominal cavity fat, perirenal fat, renal sinus fat, pericardial fat, mediastinal fat registration structure; the special area is the armpit, groin and other structures; the diagnostic data are coordinates of each fat after segmentation.
A calculation module 60, respectively connected to the second anatomical segmentation module 50 and the structured reporting module 70, for automatically calculating a measurement value of each fat interval based on the diagnostic data and the fourth image, generating a key image, and sending the measurement value and the key image to the structured reporting module 70;
wherein the measurements include the following: the ratio of subcutaneous fat to visceral fat, the total fat volume of each region, the average fat area of each region, the average body diameter line of each region, etc. are measured and sent to a lesion list in a structured report interface, and the key image is sent to the key image in the lesion list in the structured report interface.
The structured report module 70 is respectively connected with the image recognition module 20, the image quality judgment module 30, the first anatomy segmentation module 40, the second anatomy segmentation module 50 and the calculation module 60, and is used for automatically generating a diagnosis impression for a doctor to check the measured value based on a built-in rule; and stores all the received data and all the images.
FIG. 2 is a schematic diagram of a structured report interface of the system for the automated quantitative evaluation of total body fat by MR technique according to the first embodiment of the present invention; as shown in fig. 2, the interface includes part of the report content for a simple illustration, and the image representation is displayed in the interface: adipose tissue quantification, visceral fat quantification, brown fat quantification, etc., and various measurements are automatically sent to the interface through the computing module and form a diagnostic impression for the physician to view.
The embodiment of the invention is provided with an image identification module, an image quality judgment module, a first anatomical segmentation module, a second anatomical segmentation module, a calculation module and a structural report module, wherein when a patient finishes the magnetic resonance examination item of whole body fat detection, the image identification module identifies GRE DIXON sequence images and/or T1WI sequence images, the image quality judgment module analyzes and judges the quality of the GRE DIXON sequence images and/or T1WI sequence images, the DICOM images which influence diagnosis due to low image signal-to-noise ratio, magnetic sensitivity artifacts, breathing artifacts, motion artifacts and the like are identified to prevent influencing subsequent diagnosis, the first anatomical segmentation module segments non-fat tissues on DICOM image sequences with qualified quality to better segment fat tissues, the second anatomical segmentation module segments subcutaneous fat, musculoskeletal fat, muscle fat and the like, The calculation module automatically calculates various measured values of each adipose tissue for the adipose tissues and transmits the measured values to the structured report module, and the structured report module integrates all processed data and images, stores the data and the images and outputs a diagnosis impression for doctors to refer; the system carries out automatic marking, part identification and quantitative statistical analysis on adipose tissues of all parts of the whole body under the conditions of controlling image quality and eliminating various influences on diagnosis through the combination of a series of deep learning models and logical reasoning, so that the cost of the MR scanning technology for quantitative evaluation of the adipose tissues of the whole body is greatly reduced, various measured values of all the adipose tissues are automatically transmitted to a structural report to generate a diagnosis impression, the working efficiency of imaging doctors is greatly improved, the system can be used for clinical work and standardized data collection of clinical research, and the clinical value of imaging services is improved.
Example two
Fig. 3 is a schematic structural diagram illustrating a system for performing an automated quantitative evaluation on a whole body fat by using an MR technique according to a second embodiment of the present invention, and as shown in fig. 3, the second anatomical segmentation module 50 further includes a label determination unit 502 for determining whether a fat interval anatomical label is in compliance based on the diagnosis data, where the determination rule is: judging whether the radial line volume of the maximum connected domain of each fat interval anatomical label is within a second preset threshold value, judging whether the spatial relationship of adjacent fat interval anatomical labels is correct, judging the shapes of different fat interval anatomical labels, and sending the judgment result to the structured report module 70; if the fat interval anatomical tag is compliant, the diagnostic data is sent to the calculation module 60, and if the fat interval anatomical tag is non-compliant, the third prompt message, the type of non-compliance, is sent to the structured report module 70.
For example, it is determined whether the radial line volume of the largest connected component of each fat compartment anatomical tag is within a predetermined threshold, such as a predetermined threshold of 10% -90%, if the diagnostic data outside of the range is not compliant.
The embodiment of the invention is provided with the label judging unit which can judge whether the fat interval anatomical label is in compliance or not based on the diagnosis data, if the fat interval anatomical label is in compliance, the diagnosis data is sent to the calculating module, and if the fat interval anatomical label is in non-compliance, the third prompt message is sent to the structured reporting module, so that the diagnosis inaccuracy caused by unqualified fat interval anatomical labels is avoided.
EXAMPLE III
FIG. 4 is a flow chart of a method for automated quantitative evaluation of whole body fat by MR technique according to a third embodiment of the invention; as shown in fig. 4, the method comprises the steps of:
step S301, when the patient finishes shooting the magnetic resonance examination item of the whole body fat detection, the image information management module transmits the DICOM image of the patient to the image identification module through the DICOM protocol;
wherein, the image Information management module is an RIS (radio Information System) system;
step S302, an image identification module identifies the body position of the DICOM image based on DICOM image header file information, judges whether the DICOM image is matched with a magnetic resonance examination item for whole body fat detection, extracts a GRE DIXON sequence image and/or a T1WI sequence image if the DICOM image is matched with the magnetic resonance examination item for whole body fat detection, defines the GRE DIXON sequence image and/or the T1WI sequence image as a first image, and respectively sends the first image to an image quality judgment module and a structured report module; if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, the diagnosis process is stopped and first prompt information is sent to a structured report module; wherein the body positions comprise the chest, the abdomen and the basin;
wherein the first image is sent to a corresponding control for a technical assessment (scan sequence) in the structured reporting interface.
And if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, sending first prompt information to the structured report module, processing the first prompt information by related personnel, and storing the first prompt information in a database of the structured report module for calling and checking by subsequent personnel.
Step S303, the image quality judging module analyzes the quality of the first image based on a preset condition, the first image meeting the preset condition is respectively sent to the first anatomy segmentation module and the structured report module, and the first image meeting the preset condition is defined as a second image; if the quality of the first image does not meet the preset condition, stopping the diagnosis process; sending the judgment result and the second prompt message to a structured report module; wherein the judgment result is that the image quality is unqualified or the image quality is qualified;
the conditions that the preset conditions are not met comprise low image signal-to-noise ratio, magnetic sensitivity artifacts, breathing artifacts, motion artifacts and the like;
wherein, the judgment result is sent to a corresponding control of the technical evaluation (image quality) of the structured report interface. And if the image quality is not qualified, sending second prompt information to the structured report module, processing the second prompt information by related personnel, and storing the second prompt information in a database of the structured report module for calling and checking subsequent personnel.
Step S304, the first dissection module dissects non-adipose tissues with the volume larger than a first preset threshold value on the second image based on a first preset rule, sets dissection coordinates of each non-adipose tissue, measures the volume and radial lines of each non-adipose tissue, judges the type of the non-adipose tissues based on the volume and radial lines, sets dissection labels for each non-adipose tissue, outputs the region of the dissection labels of each non-adipose tissue, namely a third image, sends the third image to the second dissection module, and sends the volume and radial lines of each non-adipose tissue, the type of the non-adipose tissues and the third image to the structured report module;
generally, a non-fat high-signal region with a large volume (a first preset threshold) is segmented on the GRE DIXON sequence image and/or the T1WI sequence image, such as hematoma, lipoma, abnormal substance deposition, and the like, and the high signal, the volume and radial line of the non-fat tissue, and the type of the non-fat tissue are fed back to a corresponding control of the overall evaluation (the non-fat high-signal region) in the structured reporting interface.
Step S305, a second dissection module dissects subcutaneous fat, musculoskeletal fat, visceral fat and a special region on a third image based on a second preset rule, sets fat interval coordinates for the subcutaneous fat, musculoskeletal fat, visceral fat and the special region, outputs diagnosis data, sets a fat interval dissection label for the coordinates of each fat interval, outputs a region of each fat interval dissection label, namely a fourth image, and respectively sends the diagnosis data and the fourth image to a calculation module and a structured report module;
wherein the subcutaneous fat is the structure of superficial subcutaneous fat, deep subcutaneous fat, etc.; the musculoskeletal fat is the structures of intermuscular fat, muscular fat, bone marrow fat and the like; visceral fat is abdominal cavity fat, perirenal fat, renal sinus fat, pericardial fat, mediastinal fat registration structure; the special area is the armpit, groin and other structures; the diagnostic data are coordinates of each fat after segmentation.
Step S306, the calculation module automatically calculates the measured value of each fat interval based on the diagnostic data and the fourth image, generates a key image and sends the measured value and the key image to the structured report module;
wherein the measurements include the following: the ratio of subcutaneous fat to visceral fat, the total fat volume of each region, the average fat area of each region, the average body diameter line of each region, etc. are measured and sent to a lesion list in a structured report interface, and the key image is sent to the key image in the lesion list in the structured report interface.
Step S307, the structured report module automatically generates a diagnosis impression for a doctor to check the measured value based on a built-in rule; and stores all the received data and all the images.
FIG. 5 is a schematic diagram of a structured report interface in the method for the automated quantitative evaluation of total body fat by MR technique according to the third embodiment of the present invention; as shown in fig. 5, the interface includes part of the report content for a simple illustration, and the image representation is displayed in the interface: adipose tissue quantification, visceral fat quantification, brown fat quantification, etc., and various measurements are automatically sent to the interface through the computing module and form a diagnostic impression for the physician to view.
Wherein, the method also comprises: the label judgment unit in the second dissection module judges whether the fat interval dissection labels are in compliance or not based on the diagnosis data, and the judgment rule is as follows: judging whether the radial line volume of the maximum connected domain of each fat interval anatomical label is within a second preset threshold value, judging whether the spatial relationship of adjacent fat interval anatomical labels is correct, judging the shapes of different fat interval anatomical labels, and sending the judgment result to a structured report module; if the fat interval anatomical label is in compliance, the diagnostic data is sent to the calculation module, and if the fat interval anatomical label is in non-compliance, third prompt information and the type of non-compliance are sent to the structured report module.
For example, it is determined whether the radial line volume of the largest connected component of each fat compartment anatomical tag is within a predetermined threshold, such as a predetermined threshold of 10% -90%, if the diagnostic data outside of the range is not compliant.
In the embodiment of the invention, the image identification module, the image quality judgment module, the first anatomical segmentation module, the second anatomical segmentation module, the calculation module and the structured report module are used for identifying GRE DIXON sequence images and/or T1WI sequence images when a patient finishes shooting a magnetic resonance examination item for detecting the whole body fat, the image quality judgment module analyzes and judges the quality of the GRE DIXON sequence images and/or T1WI sequence images, the DICOM images influencing diagnosis due to low image signal-to-noise ratio, magnetic sensitivity artifacts, breathing artifacts, motion artifacts and the like are identified to prevent influencing subsequent diagnosis, the first anatomical segmentation module segments non-fat tissues on DICOM image sequences with qualified quality to better segment fat tissues, and the second anatomical segmentation module segments subcutaneous fat, musculoskeletal fat, and the like, The calculation module automatically calculates various measured values of each adipose tissue for the adipose tissues and transmits the measured values to the structured report module, and the structured report module integrates all processed data and images, stores the data and the images and outputs a diagnosis impression for doctors to refer; the system carries out automatic marking, part identification and quantitative statistical analysis on adipose tissues of all parts of the whole body under the conditions of controlling image quality and eliminating various influences on diagnosis through the combination of a series of deep learning models and logical reasoning, so that the cost of the MR scanning technology for quantitative evaluation of the adipose tissues of the whole body is greatly reduced, various measured values of all the adipose tissues are automatically transmitted to a structural report to generate a diagnosis impression, the working efficiency of an imaging doctor is greatly improved, the system can be used for clinical work and standardized data collection of clinical research, and the clinical value of an imaging service is improved; meanwhile, the label judging unit in the embodiment of the invention can judge whether the fat interval anatomical label is in compliance or not based on the diagnosis data, if the fat interval anatomical label is in compliance, the diagnosis data is sent to the calculating module, and if the fat interval anatomical label is in non-compliance, third prompt information is sent to the structured reporting module, so that the diagnosis inaccuracy caused by unqualified fat interval anatomical labels is avoided, and meanwhile, the prompt information is sent, so that manual intervention and processing are facilitated in time, an AI diagnosis model is perfected, the whole diagnosis process is more perfect, and the system is more realized.
Example four
Fig. 6 shows a specific processing flow chart of the system method for the automated quantitative evaluation of the whole body fat by the MR technology according to the fourth embodiment of the invention, as shown in fig. 6, the method comprises the following steps:
in step S401, the image recognition module recognizes whether the DICOM image matches the magnetic resonance examination item for the whole body fat detection? If not, sending a first prompt message to the structured report module, and if so, executing a step S402;
step S402, the image identification module extracts a GRE DIXON sequence image and/or a T1WI sequence image, and sends the first image to the structural report module and the image quality judgment module respectively;
in step S403, is the image quality meet a preset condition? If not, sending the judgment result and the second prompt message to a structured report module; if yes, go to step S404;
step S404, the first anatomy segmentation module segments the non-adipose tissues with the volume larger than the first preset threshold, sends the volume and radial lines of the non-adipose tissues, the types of the non-adipose tissues and the third image to the structured report module, sends the third image to the second anatomy segmentation module and executes the step S405;
step S405, the second dissection module dissects subcutaneous fat, musculoskeletal fat, visceral fat and a special region, sends the diagnosis data and the fourth image to the structural report module, sends the diagnosis data to the label judgment unit and executes the step S406;
step S406, whether the fat interval anatomical label is in compliance or not is judged, if not, third prompt information and the type of non-compliance are sent to the structured report module, and if yes, the step S407 is executed;
step S407, the calculation module calculates the measured value of each fat interval and generates a key image, and the measured value and the key image are sent to the structured report module;
step S408, the structured report module automatically generates a diagnosis impression based on built-in rules and measurement values for a doctor to check; and stores all the received data and all the images.
From the above description, it can be seen that the above-described embodiments of the present invention achieve the following technical effects: because the embodiment of the invention is provided with the image identification module, the image quality judgment module, the first anatomical segmentation module, the second anatomical segmentation module, the calculation module and the structural report module, when a patient finishes the magnetic resonance examination item of the whole body fat detection, the image identification module identifies the GRE DIXON sequence image and/or the T1WI sequence image, the image quality judgment module analyzes and judges the quality of the GRE DIXON sequence image and/or the T1WI sequence image, the DICOM image which influences the diagnosis due to low image signal-to-noise ratio, magnetic sensitivity artifact, breathing artifact, motion artifact and the like is identified to prevent the subsequent diagnosis from being influenced, the first anatomical segmentation module segments the non-fat tissue on the DICOM image sequence with qualified quality so as to better segment the fat tissue, and the second anatomical segmentation module segments the subcutaneous fat, the musculoskeletal fat, the muscle fat and the muscle fat, The calculation module automatically calculates various measured values of each adipose tissue for the adipose tissues and transmits the measured values to the structured report module, and the structured report module integrates all processed data and images, stores the data and the images and outputs a diagnosis impression for doctors to refer; the system carries out automatic marking, part identification and quantitative statistical analysis on adipose tissues of all parts of the whole body under the conditions of controlling image quality and eliminating various influences on diagnosis through the combination of a series of deep learning models and logical reasoning, so that the cost of the MR scanning technology for quantitative evaluation of the adipose tissues of the whole body is greatly reduced, various measured values of all the adipose tissues are automatically transmitted to a structural report to generate a diagnosis impression, the working efficiency of an imaging doctor is greatly improved, the system can be used for clinical work and standardized data collection of clinical research, and the clinical value of an imaging service is improved; meanwhile, the embodiment of the invention is provided with the label judging unit, so that whether the fat interval anatomical label is in compliance or not can be judged based on the diagnosis data, if the fat interval anatomical label is in compliance, the diagnosis data is sent to the calculating module, and if the fat interval anatomical label is in non-compliance, the third prompt message is sent to the structured reporting module, so that the diagnosis inaccuracy caused by unqualified fat interval anatomical labels is avoided, and meanwhile, the prompt message is sent, so that manual intervention and processing can be conveniently carried out in time, an AI diagnosis model can be perfected, the whole diagnosis process is more perfect, and the system is more realized.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. An automatic quantitative evaluation system for whole body fat by using MR technology is characterized by comprising an image information management module, an image identification module, an image quality judgment module, a first anatomical segmentation module, a second anatomical segmentation module, a calculation module and a structural report module,
the image information management module is connected with the image identification module and is used for transmitting the DICOM image of the patient to the image identification module through a DICOM protocol when the patient finishes shooting a magnetic resonance examination item for detecting the whole body fat;
the image identification module is connected with the image information management module, the image quality judgment module and the structural report module, and is configured to identify a body position of the DICOM image based on the DICOM image header file information, judge whether the DICOM image matches a magnetic resonance examination item for whole-body fat detection, extract a GRE DIXON sequence image and/or a T1WI sequence image if the DICOM image matches the magnetic resonance examination item for whole-body fat detection, define the GRE DIXON sequence image and/or the T1WI sequence image as a first image, and send the first image to the image quality judgment module and the structural report module respectively; if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, stopping a diagnosis process and sending first prompt information to the structured report module; wherein the body positions include the chest, abdomen, and pelvis;
the image quality judging module is respectively connected with the image recognition module, the first anatomical segmentation module and the structured report module, and is used for analyzing the quality of the first image based on a preset condition, respectively sending the first image meeting the preset condition to the first anatomical segmentation module and the structured report module, and defining the first image meeting the preset condition as a second image; if the quality of the first image does not meet the preset condition, stopping the diagnosis process; sending the judgment result and the second prompt message to the structured report module; wherein the judgment result is that the image quality is unqualified or the image quality is qualified;
the first anatomical segmentation module is connected with the image quality judgment module, the second anatomical segmentation module and the structured report module and is used for calculating the structural relationship of the image quality of the image, segmenting non-adipose tissue with a volume greater than a first preset threshold on the second image, setting anatomical coordinates of each non-adipose tissue, and measuring a volume and a radial line of each of the non-adipose tissues, judging a type of the non-adipose tissue based on the volume and the radial line, and setting an anatomical label for each of the non-adipose tissues, outputting a region of the anatomical label for each of the non-adipose tissues, a third image, sending the third image to the second anatomical segmentation module, sending the volume and radial line of each of the non-adipose tissue, the type of the non-adipose tissue and the third image to the structured reporting module;
the second anatomical segmentation module is connected to the first anatomical segmentation module, the calculation module and the structured report module, and configured to segment subcutaneous fat, musculoskeletal fat, visceral fat and a special region on the third image based on a second preset rule, set coordinates of fat intervals for the subcutaneous fat, musculoskeletal fat, visceral fat and the special region, output diagnostic data, set a fat interval anatomical label for each of the coordinates of the fat intervals, output a region of each of the fat interval anatomical labels, i.e., a fourth image, and send the diagnostic data and the fourth image to the calculation module and the structured report module, respectively;
the calculation module is respectively connected with the second anatomical segmentation module and the structured report module, and is used for automatically calculating the measured value of each fat interval based on the diagnostic data and the fourth image, generating a key image and sending the measured value and the key image to the structured report module;
the structured report module is respectively connected with the image identification module, the image quality judgment module, the first anatomical segmentation module, the second anatomical segmentation module and the calculation module, and is used for automatically generating a diagnosis impression for a doctor to check the measured value based on a built-in rule; and stores all the received data and all the images.
2. The system for automated quantitative assessment of whole body fat using MR technique according to claim 1, wherein said second anatomical segmentation module further comprises a label determination unit for determining whether said fat interval anatomical label is compliant based on said diagnostic data, the rule of determination being: judging whether the radial line volume of the maximum connected domain of each fat interval anatomical label is within a second preset threshold value, judging whether the spatial relationship of the adjacent fat interval anatomical labels is correct, judging the shapes of the different fat interval anatomical labels, and sending the judgment result to the structured report module; and if the fat interval anatomical label is in compliance, sending the diagnostic data to the calculation module, and if the fat interval anatomical label is in non-compliance, sending third prompt information and the type of non-compliance to the structured report module.
3. An automated quantitative assessment method of whole body fat by MR technique, comprising:
when a patient finishes shooting a magnetic resonance examination item for detecting the whole body fat, the image information management module transmits a DICOM image of the patient to the image identification module through a DICOM protocol;
the image identification module identifies the body position of the DICOM image based on the DICOM image header file information, judges whether the DICOM image is matched with a magnetic resonance examination item for whole-body fat detection, extracts a GRE DIXON sequence image and/or a T1WI sequence image if the DICOM image is matched with the magnetic resonance examination item for whole-body fat detection, defines the GRE DIXON sequence image and/or the T1WI sequence image as a first image, and respectively sends the first image to an image quality judgment module and a structural report module; if the DICOM image is not matched with the magnetic resonance examination item of the whole body fat detection, stopping a diagnosis process and sending first prompt information to the structured report module; wherein the body positions include the chest, abdomen, and pelvis;
the image quality judging module analyzes the quality of the first image based on a preset condition, the first image which meets the preset condition is respectively sent to a first anatomical segmentation module and the structured report module, and the first image which meets the preset condition is defined as a second image; if the quality of the first image does not meet the preset condition, stopping the diagnosis process; sending the judgment result and the second prompt message to the structured report module; wherein the judgment result is that the image quality is unqualified or the image quality is qualified;
the first anatomical segmentation module segments non-adipose tissues with the volume larger than a first preset threshold value on the second image based on a first preset rule, sets anatomical coordinates of each non-adipose tissue, measures the volume and radial lines of each non-adipose tissue, judges the type of the non-adipose tissues based on the volume and the radial lines, sets an anatomical label for each non-adipose tissue, outputs a region of the anatomical label of each non-adipose tissue, namely a third image, sends the third image to the second anatomical segmentation module, and sends the volume and radial lines of each non-adipose tissue, the type of the non-adipose tissues and the third image to the structural report module;
the second anatomical segmentation module segments subcutaneous fat, musculoskeletal fat, visceral fat and a special region on the third image based on a second preset rule, sets coordinates of fat intervals for the subcutaneous fat, the musculoskeletal fat, the visceral fat and the special region, outputs diagnosis data, sets a fat interval anatomical label for each of the coordinates of the fat intervals, outputs a fourth image which is a region of each of the fat interval anatomical labels, and sends the diagnosis data and the fourth image to the calculation module and the structural report module respectively;
the calculation module automatically calculates a measurement value for each of the fat intervals based on the diagnostic data and the fourth image and generates a key image, and sends the measurement value and the key image to the structured report module;
the structured report module automatically generates a diagnosis impression for a doctor to check on the measured value based on a built-in rule; and stores all the received data and all the images.
4. The method for the automated quantitative assessment of whole body fat using MR technique according to claim 3, characterized in that it further comprises: a label judgment unit in the second dissection module judges whether the fat interval dissection label is in compliance or not based on the diagnosis data, and the judgment rule is as follows: judging whether the radial line volume of the maximum connected domain of each fat interval anatomical label is within a second preset threshold value, judging whether the spatial relationship of the adjacent fat interval anatomical labels is correct, judging the shapes of the different fat interval anatomical labels, and sending the judgment result to the structured report module; and if the fat interval anatomical label is in compliance, sending the diagnostic data to the calculation module, and if the fat interval anatomical label is in non-compliance, sending third prompt information and the type of non-compliance to the structured report module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011096361.2A CN112168168A (en) | 2020-10-14 | 2020-10-14 | System and method for automatically and quantitatively evaluating whole body fat by using MR (magnetic resonance) technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011096361.2A CN112168168A (en) | 2020-10-14 | 2020-10-14 | System and method for automatically and quantitatively evaluating whole body fat by using MR (magnetic resonance) technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112168168A true CN112168168A (en) | 2021-01-05 |
Family
ID=73950398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011096361.2A Pending CN112168168A (en) | 2020-10-14 | 2020-10-14 | System and method for automatically and quantitatively evaluating whole body fat by using MR (magnetic resonance) technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112168168A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114298974A (en) * | 2021-11-30 | 2022-04-08 | 北京赛迈特锐医疗科技有限公司 | Intelligent diagnosis method and system for MR (magnetic resonance) image of fetal head |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1767788A (en) * | 2003-04-08 | 2006-05-03 | 株式会社日产医药 | Apparatus and method of supporting diagnostic imaging for medical use |
| KR101359685B1 (en) * | 2013-01-18 | 2014-02-07 | 국립암센터 | Method for estimating body fat |
| CN105427273A (en) * | 2014-09-19 | 2016-03-23 | 香港中文大学深圳研究院 | Abdominal fat segmentation method and device based on nuclear magnetic resonance image |
| CN108573490A (en) * | 2018-04-25 | 2018-09-25 | 王成彦 | A kind of intelligent read tablet system for tumor imaging data |
| US20190259159A1 (en) * | 2018-02-10 | 2019-08-22 | The Trustees Of The University Of Pennsylvania | Quantification And Staging Of Body-Wide Tissue Composition And Of Abnormal States On Medical Images Via Automatic Anatomy Recognition |
| CN110555825A (en) * | 2019-07-23 | 2019-12-10 | 北京赛迈特锐医疗科技有限公司 | Intelligent diagnostic system and diagnostic method for chest X-ray image |
-
2020
- 2020-10-14 CN CN202011096361.2A patent/CN112168168A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1767788A (en) * | 2003-04-08 | 2006-05-03 | 株式会社日产医药 | Apparatus and method of supporting diagnostic imaging for medical use |
| KR101359685B1 (en) * | 2013-01-18 | 2014-02-07 | 국립암센터 | Method for estimating body fat |
| CN105427273A (en) * | 2014-09-19 | 2016-03-23 | 香港中文大学深圳研究院 | Abdominal fat segmentation method and device based on nuclear magnetic resonance image |
| US20190259159A1 (en) * | 2018-02-10 | 2019-08-22 | The Trustees Of The University Of Pennsylvania | Quantification And Staging Of Body-Wide Tissue Composition And Of Abnormal States On Medical Images Via Automatic Anatomy Recognition |
| CN108573490A (en) * | 2018-04-25 | 2018-09-25 | 王成彦 | A kind of intelligent read tablet system for tumor imaging data |
| CN110555825A (en) * | 2019-07-23 | 2019-12-10 | 北京赛迈特锐医疗科技有限公司 | Intelligent diagnostic system and diagnostic method for chest X-ray image |
Non-Patent Citations (2)
| Title |
|---|
| HANS-PETER MÜLLER等: "Quantification of human body fat tissue percentage by MRI", 《NMR BIOMED.》, vol. 24, pages 17 - 24 * |
| UTE A. LUDWIG等: "Whole-Body MRI-Based Fat Quantification: A Comparison to Air Displacement Plethysmography", 《JOURNAL OF MAGNETIC RESONANCE IMAGING》, vol. 40, pages 1437 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114298974A (en) * | 2021-11-30 | 2022-04-08 | 北京赛迈特锐医疗科技有限公司 | Intelligent diagnosis method and system for MR (magnetic resonance) image of fetal head |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112263236B (en) | System and method for intelligent evaluation of whole-body tumor MRI | |
| KR102243830B1 (en) | System for providing integrated medical diagnostic service and method thereof | |
| US7596401B2 (en) | Method for expanding the domain of imaging software in a diagnostic work-up | |
| US20050010098A1 (en) | Method and apparatus for knowledge based diagnostic imaging | |
| US20100217123A1 (en) | Methods and systems of managing ultrasonographic diagnosis | |
| CN105051784A (en) | Image quality assessment for simulation accuracy and performance | |
| KR101716039B1 (en) | Method and apparatus for computing diagnosis of sickness based on ct or mri image | |
| WO2005023086B1 (en) | Systems, methods, and computer program products for analysis of vessel attributes for diagnosis, disease staging, and surgical planning | |
| CA2918260A1 (en) | Systems and methods for determining hepatic function from liver scans | |
| CN103249358A (en) | Medical image processing device | |
| Balasooriya et al. | Intelligent brain hemorrhage diagnosis using artificial neural networks | |
| US20100260399A1 (en) | Scanner data collection | |
| CN107887002A (en) | A kind of medical imaging diagnosis quality control system | |
| CN112168168A (en) | System and method for automatically and quantitatively evaluating whole body fat by using MR (magnetic resonance) technology | |
| WO2019112050A1 (en) | Imaging device, imaging method, imaging program and storage medium | |
| US11836921B2 (en) | Artificial-intelligence-based global cardiac motion classification | |
| CN112545479B (en) | System and method for segmenting prostate and seminal vesicle zonal anatomy on mpMRI | |
| JP7425508B2 (en) | Severity assessment device and model generation device | |
| CN113270168B (en) | Method and system for improving medical image processing capability | |
| CN114298974A (en) | Intelligent diagnosis method and system for MR (magnetic resonance) image of fetal head | |
| CN108720870A (en) | A kind of fatty liver detecting system based on ultrasonic attenuation coefficient | |
| CN112259197A (en) | Intelligent analysis system and method for acute abdomen plain film | |
| KR102425843B1 (en) | Method and apparatus for evaluating internal organ using kurtosis map based on medical images | |
| Tech et al. | Neural network based classification and diagnosis of brain hemorrhages | |
| US20240164709A1 (en) | Apparatus for Monitoring Treatment Side Effects |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |