WO2024256807A1 - Apparatus for analysing medical images - Google Patents

Apparatus for analysing medical images Download PDF

Info

Publication number
WO2024256807A1
WO2024256807A1 PCT/GB2024/051491 GB2024051491W WO2024256807A1 WO 2024256807 A1 WO2024256807 A1 WO 2024256807A1 GB 2024051491 W GB2024051491 W GB 2024051491W WO 2024256807 A1 WO2024256807 A1 WO 2024256807A1
Authority
WO
WIPO (PCT)
Prior art keywords
patient
fibrosis
data
ultrasound
degree
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.)
Ceased
Application number
PCT/GB2024/051491
Other languages
French (fr)
Inventor
Stephen MARGETTS
Martin Benson
Nicholas Sleep
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Intelligent Ultrasound Ltd
Original Assignee
Intelligent Ultrasound Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Intelligent Ultrasound Ltd filed Critical Intelligent Ultrasound Ltd
Priority to CN202480034499.XA priority Critical patent/CN121175762A/en
Publication of WO2024256807A1 publication Critical patent/WO2024256807A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/42—Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
    • A61B5/4222—Evaluating particular parts, e.g. particular organs
    • A61B5/4244—Evaluating particular parts, e.g. particular organs liver
    • 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
    • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30056—Liver; Hepatic

Definitions

  • the present invention relates to apparatus for analysing medical images , and is concerned particularly, though not exclusively, with an apparatus for identi fying a probability of the existence of a medical condition from an analysis of ultrasound images of a patient ' s abdomen .
  • Metabolic Associated Fatty Liver Disease is a very common disease in which fat accumulates in the liver in people who do not have an exces sive intake of alcohol . Around 30% of the population worldwide are thought to have MAFLD . Most have simple fatty infiltration ( steatosis ) . Nonalcoholic steatohepatitis , or metabolic-associated steatohepatitis (known as MASH) is a less common ( 2 . 5% of population) but aggres sive form of MALFD in which the liver cells become inflamed and damaged . It may eventually lead to scarring ( f ibrosis/cirrhosis ) or liver cancer .
  • MASH metabolic-associated steatohepatitis
  • ultrasound is not commonly used in diagnosis or monitoring fatty liver conditions at present as it is challenging to accurately assess fatty infiltration, inflammation (MASH) and scarring by human interpretation of ultrasound images .
  • Embodiments of the present invention aim to provide a system to distinguish MASH from MAFLD using ultrasound and deep learning .
  • apparatus for analysing ultrasound images of a patient ' s abdomen, the apparatus comprising : a first input arranged to receive at least one ultrasound image of the abdomen of a patient ; and a processor arranged to process the data from the first input using a trained machine learning model ; wherein the processor is arranged to determine a probability that the , or each, ultrasound image of the patient exhibits one or more medical conditions .
  • the apparatus comprises a second input arranged to receive at least one item of metadata related to the patient .
  • the apparatus may be arranged to process the data from the second input .
  • the first input may be arranged to receive data of a plurality of ultrasound images of the patient ' s abdomen .
  • the second input is arranged to receive a plurality of items of metadata related to the patient .
  • the trained model comprises a machine learning model trained using both supervised and unsupervised machine learning techniques , respectively in an unsupervised phase and a supervised phase .
  • a supervised learning phase we mean the process of training a machine learning by supplying to it a quantity of example inputs along with their classi fications ( often referred to as "ground-truths" ) and then using optimisation methods to encourage the model to emit predictions that correspond as closely as possible to those classi fications .
  • an unsupervised learning phase we mean a process of training a machine learning model in which no ground-truth data is present in the training data, and instead the optimisation task is crafted in such a way that the resulting model has some desired properties .
  • Methods for doing this include contrastive learning, de-noising autoencoders and sel f-distillation, for example .
  • Unsupervised techniques may be used to generate generic features of ultrasound images from ultrasound data, more preferably from unannotated ultrasound date , and still more preferably from a large amount o f such data .
  • the supervised learning phase may take features found during the unsupervised phase and may use them together with the metadata and appropriate ground-truth to produce models that predict various clinical indications . This two-phase process allows an ef fective model to developed from the very limited quantity of labelled data that is available .
  • the unsupervised techniques are used to generate features of a large quantity of unannotated ultrasound data .
  • the supervised learning techniques are arranged to take features found during the unsupervised phase and use them, optionally together with patient metadata, to make a model that predicts a cl inical indication .
  • the apparatus is preferably arranged to produce a probability density function for one or more of the following :
  • o F0/ F1 No fibrosis or Zone 3 mild/ moderate perisinusoidal or portal fibrosis
  • o F2 Zone 3 and portal/periportal fibrosis
  • o F3 Bridging fibrosis
  • o F4 Cirrhosis .
  • a method of analysing ultrasound images of a patient comprising : receiving at least one ultrasound image of the abdomen of a patient ; processing the data using a trained machine learning model ; and determining a probability that the , or each, ultrasound image of the patient ' s abdomen exhibits one or more medical conditions .
  • the method includes receiving at least one item of metadata related to the patient .
  • the method may include processing the meta data .
  • the method may comprise training the machine learning model using both supervised and unsupervised learning techniques .
  • the unsupervised techniques may be used to generate generic features of ultrasound images from ultrasound data, more preferably from unannotated data, still more preferably from a large amount of such data .
  • the supervised learning phase may take features found during the unsupervised phase and may use them together with the metadata and appropriate ground-truth to produce models that predict the various clinical indications listed above . This two-phase process allows an ef fective model to developed from the very limited quantity of labelled data that is available .
  • the method may include incorporating proxy ground-truth data from several associated indicators . These may include MRI- PDFF results which may be used to measure the degree of steatosis ; shear wave or other elastography results which may be used to measure the degree of fibrosis ; or blood test results for biomarkers speci fic to fibrosis , steatosis and/or MASH .
  • the invention provides a computer programme product on a computer readable medium, comprising instructions that , when executed by a computer, cause the computer to perform a method of analysing ultrasound images of a patient , the method comprising : receiving at least one ultrasound image of the abdomen of a patient ; and processing the data from the first input using a trained machine learning model ; determine a probability that the , or each, ultrasound image of the patient exhibits one or more medical conditions .
  • the method may include receiving at least one item of metadata related to the patient .
  • the method may include processing the metadata from the second input .
  • the invention also comprises a program for causing a device to perform a method of analysing ultrasound images of a patient , the method comprising : receiving at least one ultrasound image of the abdomen of a patient ; and processing the data from the first input using a trained machine learning model ; determine a probability that the , or each, ultrasound image of the patient exhibits one or more medical conditions .
  • the method may include receiving at least one item of metadata related to the patient .
  • the method may include processing the metadata from the second input .
  • the invention may include any combination of the features or limitations referred to herein, except such a combination of features as are mutually exclus ive , or mutually inconsistent .
  • Figure 1 shows schematically an apparatus for analysing ultrasound images of a patient , according to an embodiment of the present invention.
  • Figure 2 shows schematically a method for analysing ultrasound images of a patient according to an embodiment of the present invention .
  • embodiments of the present invention include a system to distinguish MASH from MAFLD using ultrasound and deep learning .
  • the inputs to the system are ultrasound images of the abdomen and easily obtained metadata about the patient (for example , but not limited to : BMI , age , liver function test results , alcohol intake etc . ) .
  • the system uses machine learning to analyse the images and metadata to produce the following outputs :
  • NAS non-alcoholic fatty liver activity score
  • liver fibrosis as a probabi lity distribution over the following bands : o F0/ F1 : no fibrosis or Zone 3 mild/moderate perisinusoidal or portal fibrosis o F2 : Zone 3 and portal/periportal fibrosis o F3 : Bridging fibrosis o F4 : Cirrhosis
  • Supervised model training requires suitable ground-truth corresponding to the desired clinical indications .
  • the "gold-standard" for measuring steatosis , fibrosis and the presence of MASH is liver biopsy, so the ideal ground truth data would consist of abdominal ultrasound images with contemporaneous liver biopsy results .
  • liver biopsies carry a degree of risk, obtaining large numbers of biopsy results for model training may be di f ficult .
  • proxy ground-truth data from several associated indicators .
  • These may include MRI-PDFF results which may be used to measure the degree of steatosis ; shear wave results which may be used to measure the degree of fibrosis ; or blood test results for biomarkers speci fic to fibrosis , steatosis and/or MASH .
  • Data for these is more readily available . While this may only act as a weak signal of the outcome of interest (MASH) , it is nevertheless helpful in boosting the ef fectiveness of the model for a given quantity of labelled data for that outcome .
  • the system is trained using both supervised and unsupervised learning techniques .
  • the unsupervised techniques are used to generate generic features of ultrasound images from a large amount of unannotated ultrasound data .
  • the quantity of available unannotated data will exceed that of annotated data by at least an order of magnitude , and sometimes by several orders of magnitude .
  • the supervised learning phase takes features found during the unsupervised phase and uses them together with the metadata and appropriate ground-truth to produce models that predict the various clinical indications listed above . This two-phase process allows an ef fective model to be developed from the very limited quantity of labelled data that is available .
  • FIG. 1 this shows generally at 100 an apparatus for analysing ultrasound images of a patient .
  • the apparatus comprises a processor 110 having a first input 120 .
  • the first input 120 is arranged to receive ultrasound image data from an ultrasound scan of a patient ' s abdomen .
  • a second input 130 is arranged to receive one or more items of metadata relating to the patient (not shown) .
  • the processor 110 uses a trained, machine learning model 140 to predict the probability that the ultrasound images depict one or more conditions present in the liver of the patient , and the calculated probabilities are output at 150 .
  • Figure 2 shows schematically a method of analysing the image data of a patient .
  • the ultrasound image data of the patient ' s abdomen is acquired .
  • one or more items of metadata relating to the patient are acquired .
  • a processor uses a trained machine learning model to predict the probability that the image ( s ) acquired at step S I depicts one or more medical conditions , and at step S4 the or each probability is output .

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Gastroenterology & Hepatology (AREA)
  • Computational Linguistics (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physiology (AREA)
  • Quality & Reliability (AREA)
  • Endocrinology (AREA)
  • Image Analysis (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
  • Image Processing (AREA)

Abstract

Figure 1 shows generally at (100) an apparatus for analysing ultrasound images of a patient. The apparatus comprises a processor (110) having a first input (120). The first input (120) is arranged to receive ultrasound image data from an ultrasound scan of a patient's abdomen. A second input (130) is arranged to receive one or more items of metadata relating to the patient (not shown). The processor (110) uses a trained, machine learning model (140) to predict the probability that the ultrasound images depict one or more conditions present in the liver of the patient, and the calculated probabilities are output at (150).

Description

Apparatus for Analysing Medical Images
The present invention relates to apparatus for analysing medical images , and is concerned particularly, though not exclusively, with an apparatus for identi fying a probability of the existence of a medical condition from an analysis of ultrasound images of a patient ' s abdomen .
Metabolic Associated Fatty Liver Disease (MAFLD) is a very common disease in which fat accumulates in the liver in people who do not have an exces sive intake of alcohol . Around 30% of the population worldwide are thought to have MAFLD . Most have simple fatty infiltration ( steatosis ) . Nonalcoholic steatohepatitis , or metabolic-associated steatohepatitis ( known as MASH) is a less common ( 2 . 5% of population) but aggres sive form of MALFD in which the liver cells become inflamed and damaged . It may eventually lead to scarring ( f ibrosis/cirrhosis ) or liver cancer .
Currently, the most reliable way of distinguishing MASH from MAFLD is to perform a liver biopsy on the patient . However, this can be painful and can have signi ficant side ef fects , including a risk of mortality of around 0 . 2 % . While non- invasive techniques for measuring some components of MASH have been developed, such as Magnetic Resonance Imaging Proton Density Fat Fraction (MRI-PDFF) for steatosis , and transient elastography [ Fibroscan] or shear wave propagation for fibrosis , these imaging modalities are slow, expensive and cannot currently distinguish MASH from MAFLD .
There is currently no inexpensive , fast , and reliable method to screen a large proportion of the population to determine who is likely to have MASH . One potential imaging medium that could be deployed at scale is ultrasound . Unfortunately, ultrasound is not commonly used in diagnosis or monitoring fatty liver conditions at present as it is challenging to accurately assess fatty infiltration, inflammation (MASH) and scarring by human interpretation of ultrasound images .
Embodiments of the present invention aim to provide a system to distinguish MASH from MAFLD using ultrasound and deep learning .
The present invention is defined in the attached independent claims , to which reference should now be made . Further, preferred features may be found in the sub-claims appended thereto .
According to a first aspect of the present invention there is provided apparatus for analysing ultrasound images of a patient ' s abdomen, the apparatus comprising : a first input arranged to receive at least one ultrasound image of the abdomen of a patient ; and a processor arranged to process the data from the first input using a trained machine learning model ; wherein the processor is arranged to determine a probability that the , or each, ultrasound image of the patient exhibits one or more medical conditions .
In a preferred arrangement , the apparatus comprises a second input arranged to receive at least one item of metadata related to the patient . The apparatus may be arranged to process the data from the second input . The first input may be arranged to receive data of a plurality of ultrasound images of the patient ' s abdomen . Preferably, the second input is arranged to receive a plurality of items of metadata related to the patient .
In a preferred arrangement , the trained model comprises a machine learning model trained using both supervised and unsupervised machine learning techniques , respectively in an unsupervised phase and a supervised phase .
By a supervised learning phase , we mean the process of training a machine learning by supplying to it a quantity of example inputs along with their classi fications ( often referred to as "ground-truths" ) and then using optimisation methods to encourage the model to emit predictions that correspond as closely as possible to those classi fications .
By an unsupervised learning phase , we mean a process of training a machine learning model in which no ground-truth data is present in the training data, and instead the optimisation task is crafted in such a way that the resulting model has some desired properties . Methods for doing this include contrastive learning, de-noising autoencoders and sel f-distillation, for example .
While the descriptions above were framed in terms of a classi fication task, the skilled practitioner will recognise that they any be easily adapted to equivalently describe other prediction types , including, for example , regression tasks . Unsupervised techniques may be used to generate generic features of ultrasound images from ultrasound data, more preferably from unannotated ultrasound date , and still more preferably from a large amount o f such data . The supervised learning phase may take features found during the unsupervised phase and may use them together with the metadata and appropriate ground-truth to produce models that predict various clinical indications . This two-phase process allows an ef fective model to developed from the very limited quantity of labelled data that is available .
Preferably, the unsupervised techniques are used to generate features of a large quantity of unannotated ultrasound data .
In a preferred arrangement the supervised learning techniques are arranged to take features found during the unsupervised phase and use them, optionally together with patient metadata, to make a model that predicts a cl inical indication .
The apparatus is preferably arranged to produce a probability density function for one or more of the following :
• the degree of steatosis ,
• the probability that the non-alcoholic fatty liver activity score [NAS ] is greater than or equal to 4 [whether the patient has MASH or not ] ,
• the degree of liver fibrosis , as a probabi lity distribution over the following bands : o F0/ F1 : No fibrosis or Zone 3 mild/ moderate perisinusoidal or portal fibrosis , o F2 : Zone 3 and portal/periportal fibrosis , o F3 : Bridging fibrosis , o F4 : Cirrhosis .
According to another aspect of the present invention, there is provided a method of analysing ultrasound images of a patient , the method comprising : receiving at least one ultrasound image of the abdomen of a patient ; processing the data using a trained machine learning model ; and determining a probability that the , or each, ultrasound image of the patient ' s abdomen exhibits one or more medical conditions .
In a preferred arrangement , the method includes receiving at least one item of metadata related to the patient . The method may include processing the meta data .
The method may comprise training the machine learning model using both supervised and unsupervised learning techniques . The unsupervised techniques may be used to generate generic features of ultrasound images from ultrasound data, more preferably from unannotated data, still more preferably from a large amount of such data . The supervised learning phase may take features found during the unsupervised phase and may use them together with the metadata and appropriate ground-truth to produce models that predict the various clinical indications listed above . This two-phase process allows an ef fective model to developed from the very limited quantity of labelled data that is available .
The method may include incorporating proxy ground-truth data from several associated indicators . These may include MRI- PDFF results which may be used to measure the degree of steatosis ; shear wave or other elastography results which may be used to measure the degree of fibrosis ; or blood test results for biomarkers speci fic to fibrosis , steatosis and/or MASH .
In a further aspect , the invention provides a computer programme product on a computer readable medium, comprising instructions that , when executed by a computer, cause the computer to perform a method of analysing ultrasound images of a patient , the method comprising : receiving at least one ultrasound image of the abdomen of a patient ; and processing the data from the first input using a trained machine learning model ; determine a probability that the , or each, ultrasound image of the patient exhibits one or more medical conditions .
The method may include receiving at least one item of metadata related to the patient . The method may include processing the metadata from the second input . The invention also comprises a program for causing a device to perform a method of analysing ultrasound images of a patient , the method comprising : receiving at least one ultrasound image of the abdomen of a patient ; and processing the data from the first input using a trained machine learning model ; determine a probability that the , or each, ultrasound image of the patient exhibits one or more medical conditions .
The method may include receiving at least one item of metadata related to the patient . The method may include processing the metadata from the second input .
The invention may include any combination of the features or limitations referred to herein, except such a combination of features as are mutually exclus ive , or mutually inconsistent .
A preferred embodiment of the present invention will now be described, by way of example only, with reference to the accompanying diagrammatic drawings , in which :
Figure 1 shows schematically an apparatus for analysing ultrasound images of a patient , according to an embodiment of the present invention; and
Figure 2 shows schematically a method for analysing ultrasound images of a patient according to an embodiment of the present invention . Some recent studies have suggested that machine learning techniques applied to ultrasound images of the liver can reliably predict the degree of steatosis and fibrosis . I f ultrasound could also be used to distinguish MASH from MALFD, this could enable large-scale screening of the population for MASH .
In some implementations , embodiments of the present invention include a system to distinguish MASH from MAFLD using ultrasound and deep learning . The inputs to the system are ultrasound images of the abdomen and easily obtained metadata about the patient ( for example , but not limited to : BMI , age , liver function test results , alcohol intake etc . ) .
The system uses machine learning to analyse the images and metadata to produce the following outputs :
• The degree of steatosis ( the percentage of fat in the liver )
• The probability that the non-alcoholic fatty liver activity score (NAS ) is greater than or equal to 4 ( does the patient have MASH or not )
• The degree of liver fibrosis , as a probabi lity distribution over the following bands : o F0/ F1 : no fibrosis or Zone 3 mild/moderate perisinusoidal or portal fibrosis o F2 : Zone 3 and portal/periportal fibrosis o F3 : Bridging fibrosis o F4 : Cirrhosis
These outputs cover the key clinical markers that describe the health of the liver .
Supervised model training requires suitable ground-truth corresponding to the desired clinical indications . The "gold-standard" for measuring steatosis , fibrosis and the presence of MASH is liver biopsy, so the ideal ground truth data would consist of abdominal ultrasound images with contemporaneous liver biopsy results . However, because liver biopsies carry a degree of risk, obtaining large numbers of biopsy results for model training may be di f ficult .
To obtain adequate model performance , it is preferable to incorporate proxy ground-truth data from several associated indicators . These may include MRI-PDFF results which may be used to measure the degree of steatosis ; shear wave results which may be used to measure the degree of fibrosis ; or blood test results for biomarkers speci fic to fibrosis , steatosis and/or MASH . Data for these is more readily available . While this may only act as a weak signal of the outcome of interest (MASH) , it is nevertheless helpful in boosting the ef fectiveness of the model for a given quantity of labelled data for that outcome .
Additionally, the system is trained using both supervised and unsupervised learning techniques . The unsupervised techniques are used to generate generic features of ultrasound images from a large amount of unannotated ultrasound data . In a typical example (but not exclusively) , the quantity of available unannotated data will exceed that of annotated data by at least an order of magnitude , and sometimes by several orders of magnitude . The supervised learning phase takes features found during the unsupervised phase and uses them together with the metadata and appropriate ground-truth to produce models that predict the various clinical indications listed above . This two-phase process allows an ef fective model to be developed from the very limited quantity of labelled data that is available .
Turning to Figure 1 , this shows generally at 100 an apparatus for analysing ultrasound images of a patient . The apparatus comprises a processor 110 having a first input 120 . The first input 120 is arranged to receive ultrasound image data from an ultrasound scan of a patient ' s abdomen . A second input 130 is arranged to receive one or more items of metadata relating to the patient (not shown) . The processor 110 uses a trained, machine learning model 140 to predict the probability that the ultrasound images depict one or more conditions present in the liver of the patient , and the calculated probabilities are output at 150 .
Figure 2 shows schematically a method of analysing the image data of a patient . At step S I the ultrasound image data of the patient ' s abdomen is acquired . At step S2 one or more items of metadata relating to the patient are acquired . At Step S3 a processor uses a trained machine learning model to predict the probability that the image ( s ) acquired at step S I depicts one or more medical conditions , and at step S4 the or each probability is output .
Whilst endeavouring in the foregoing speci fication to draw attention to those features of the invention believed to be of particular importance , it should be understood that the applicant claims protection in respect of any patentable feature or combination of features referred to herein, and/or shown in the drawings , whether or not particular emphasis has been placed thereon .

Claims

1 . Apparatus for analysing ultrasound images of a patient, the apparatus comprising : a first input arranged to receive data of at least one ultrasound image of a patient ; and a processor arranged to process the data from the first input using a trained machine learning model ; wherein the processor is arranged to determine a probability that the or each ultrasound image of the patient exhibits one or more medical conditions , wherein the apparatus includes a second input arranged to receive at least one item of metadata related to the patient, and the apparatus is arranged to process data from the second input and wherein the apparatus is arranged to produce a probability density function for one or more of the following :
• the degree of steatosis ,
• the probabi lity that the non-alcoholic fatty liver activity score [NAS ] is greater than or equal to 4 [whether the patient has MASH or not ] ,
• the degree of liver fibrosis , as a probability distribution over the following bands : o F0/ F1 : No fibrosis or Zone 3 mild/ moderate perisinusoidal or portal fibrosis , o F2 : Zone 3 and portal/periportal fibrosis , o F3 : Bridging fibrosis , o F4 : Cirrhosis .
2 . Apparatus according to Claim 1 , wherein the machine learning model is trained using both supervised and unsupervised machine learning techniques , respectively in an unsupervised phase and a supervised phase .
3 . Apparatus according to Claim 2 , wherein the unsupervised techniques are used to generate features of a large quantity of unannotated ultrasound data .
4 . Apparatus according to Claim 2 or 3 , wherein the apparatus is arranged to incorporate proxy ground-truth data from a number of associated indicators into the training of the model .
5 . Apparatus according to Claim 2 , wherein the supervi sed learning techniques are arranged to take features found during the unsupervised phase and use them, together with the or each item of patient metadata, to make a model that predicts a clinical indication .
6 . A method of analysing ultrasound images of a patient , the method comprising : receiving data of at least one ultrasound image of a patient ; processing the data using a trained machine learning model ; and determining a probability that the or each ultrasound image of the patient exhibits one or more medical conditions , wherein the method includes receiving at least one item of metadata related to the patient and processing the metadata , and wherein the method comprises producing a probability density function for one or more of the following :
• the degree of steatosis ,
• the probabi lity that the non-alcoholic fatty liver activity score [NAS ] is greater than or equal to 4 [whether the patient has MASH or not ] ,
• the degree of liver fibrosis , as a probability distribution over the following bands : o F0/ F1 : No fibrosis or Zone 3 mild/ moderate perisinusoidal or portal fibrosis , o F2 : Zone 3 and portal/periportal fibrosis , o F3 : Bridging fibrosis , o F4 : Cirrhosis .
7 . A method according to Claim 6 , compris ing training the machine learning model using both supervised and unsupervised learning techniques .
8 . A method according to Claim 7 wherein the unsupervi sed techniques are used to generate generic features of ultrasound images from unannotated ultrasound data .
9 . A method according to Claim 7 or 8 , wherein the supervised learning phase comprises taking features found during the unsupervised phase and using them together with the metadata and appropriate ground-truth to produce models that predict the various clinical indications listed above .
10 . A method according to any of Claims 7 - 9 , wherein the method includes incorporating proxy ground-truth data from a number of associated indicators into the training of the model.
11. A method according to Claim 10, wherein the proxy ground-truth data include MRI-PDFF results which may be used to measure the degree of steatosis.
12. A method according to Claim 10 or 11, wherein the proxy ground-truth data includes shear wave or other elastography results to measure the degree of fibrosis.
13. A method according to any of Claims 10-12, wherein the proxy ground-truth data includes one or more of: MRI- PDFF results which may be used to measure the degree of steatosis; shear wave results which may be used to measure the degree of fibrosis; or blood test results for biomarkers specific to fibrosis, steatosis and/or MASH.
14. A computer programme product on a computer readable medium, comprising instructions that, when executed by a computer, cause the computer to perform a method of analysing ultrasound images of a patient's liver, the method being in accordance with any of Claims 6-13.
15. A program for causing a device to perform a method of analysing ultrasound images of a patient, the method being in accordance with any of Claims 6-13.
PCT/GB2024/051491 2023-06-15 2024-06-11 Apparatus for analysing medical images Ceased WO2024256807A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202480034499.XA CN121175762A (en) 2023-06-15 2024-06-11 Device for analyzing medical images

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB2308938.6 2023-06-15
GB2308938.6A GB2630963A (en) 2023-06-15 2023-06-15 Apparatus for analysing medical images

Publications (1)

Publication Number Publication Date
WO2024256807A1 true WO2024256807A1 (en) 2024-12-19

Family

ID=91739022

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2024/051491 Ceased WO2024256807A1 (en) 2023-06-15 2024-06-11 Apparatus for analysing medical images

Country Status (3)

Country Link
CN (1) CN121175762A (en)
GB (1) GB2630963A (en)
WO (1) WO2024256807A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240428947A1 (en) * 2023-06-21 2024-12-26 Histoindex Pte Ltd Method And System For Predicting A Clinical Outcome Of Metabolic Dysfunction-Associated Steatotic Liver Disease

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010097472A1 (en) * 2009-02-26 2010-09-02 Universite D'angers Improved diagnosis of liver fibrosis or cirrhosis
WO2018178212A1 (en) * 2017-03-28 2018-10-04 Koninklijke Philips N.V. Ultrasound clinical feature detection and associated devices, systems, and methods
CA3095784A1 (en) * 2018-04-03 2019-10-10 The Children's Mercy Hospital Systems and methods for detecting flow of biological fluids

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3467770B1 (en) * 2017-10-05 2022-11-23 Siemens Healthcare GmbH Method for analysing a medical imaging data set, system for analysing a medical imaging data set, computer program product and a computer-readable medium
US11087463B2 (en) * 2019-06-21 2021-08-10 StraxCorp Pty. Ltd. Image analysis method and system for assessing bone fragility
US12430402B2 (en) * 2021-01-26 2025-09-30 Nvidia Corporation Confidence generation using a neural network
US20250104226A1 (en) * 2021-12-22 2025-03-27 Geonomy, Ltd. Automated ultrasound imaging analysis and feedback
EP4453958A1 (en) * 2021-12-23 2024-10-30 Koninklijke Philips N.V. Methods and systems for clinical scoring of a lung ultrasound

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010097472A1 (en) * 2009-02-26 2010-09-02 Universite D'angers Improved diagnosis of liver fibrosis or cirrhosis
WO2018178212A1 (en) * 2017-03-28 2018-10-04 Koninklijke Philips N.V. Ultrasound clinical feature detection and associated devices, systems, and methods
CA3095784A1 (en) * 2018-04-03 2019-10-10 The Children's Mercy Hospital Systems and methods for detecting flow of biological fluids

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
ALSHAGATHRH FAHAD MUFLIH ET AL: "Artificial Intelligence for Detecting and Quantifying Fatty Liver in Ultrasound Images: A Systematic Review", BIOENGINEERING, vol. 9, no. 12, 1 December 2022 (2022-12-01), pages 748, XP093203640, ISSN: 2306-5354, DOI: 10.3390/bioengineering9120748 *
BARRAGÁN-MONTERO ANA ET AL: "Artificial intelligence and machine learning for medical imaging: A technology review", PHYSICA MEDICA, ACTA MEDICA EDIZIONI E CONGRESSI, ROME, IT, vol. 83, 1 March 2021 (2021-03-01), pages 242 - 256, XP086596520, ISSN: 1120-1797, [retrieved on 20210509], DOI: 10.1016/J.EJMP.2021.04.016 *
JIANGLI LIN ET AL: "Recognition of Fatty Liver Using Hybrid Neural Network", 1 January 2006, ADVANCES IN NEURAL NETWORKS - ISNN 2006 LECTURE NOTES IN COMPUTER SCIENCE;;LNCS, SPRINGER, BERLIN, DE, PAGE(S) 754 - 759, ISBN: 978-3-540-34482-7, XP019033885 *
LEE JEONG HYUN ET AL: "Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network", EUROPEAN RADIOLOGY, SPRINGER BERLIN HEIDELBERG, BERLIN/HEIDELBERG, vol. 30, no. 2, 2 September 2019 (2019-09-02), pages 1264 - 1273, XP036986870, ISSN: 0938-7994, [retrieved on 20190902], DOI: 10.1007/S00330-019-06407-1 *
XUE LI-YUN ET AL: "Transfer learning radiomics based on multimodal ultrasound imaging for staging liver fibrosis", EUROPEAN RADIOLOGY, SPRINGER BERLIN HEIDELBERG, BERLIN/HEIDELBERG, vol. 30, no. 5, 21 January 2020 (2020-01-21), pages 2973 - 2983, XP037092530, ISSN: 0938-7994, [retrieved on 20200121], DOI: 10.1007/S00330-019-06595-W *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240428947A1 (en) * 2023-06-21 2024-12-26 Histoindex Pte Ltd Method And System For Predicting A Clinical Outcome Of Metabolic Dysfunction-Associated Steatotic Liver Disease

Also Published As

Publication number Publication date
CN121175762A (en) 2025-12-19
GB2630963A (en) 2024-12-18

Similar Documents

Publication Publication Date Title
CN110292396B (en) Predicted Uses of Quantitative Imaging
Marshall et al. Hepatorenal index as an accurate, simple, and effective tool in screening for steatosis
Kane et al. Musculoskeletal ultrasound—a state of the art review in rheumatology. Part 1: current controversies and issues in the development of musculoskeletal ultrasound in rheumatology
McQueen Magnetic resonance imaging in early inflammatory arthritis: what is its role?
Heuft-Dorenbosch et al. Magnetic resonance imaging changes of sacroiliac joints in patients with recent-onset inflammatory back pain: inter-reader reliability and prevalence of abnormalities
Rickes et al. Impact of the operator's experience on value of high-resolution transabdominal ultrasound in the diagnosis of choledocholithiasis: a prospective comparison using endoscopic retrograde cholangiography as the gold standard
US12620497B2 (en) Disease feature recognition in diagnostic images and disease progression prediction
US20240225588A1 (en) Method and Apparatus of Intelligent Analysis for Liver Tumor
Amin et al. Wavelet-based computationally-efficient computer-aided characterization of liver steatosis using conventional B-mode ultrasound images
EP2624155A2 (en) Method and apparatus for providing ultrasound image data
Wong et al. Do reader characteristics affect diagnostic efficacy in screening mammography? A systematic review
US20220207719A1 (en) System, method, apparatus, and computer program product for ultrasonic clinical decision support
Phelps et al. Ultrasound elastography: is there a shear wave speed cutoff for pediatric liver fibrosis and inflammation?
GB2630963A (en) Apparatus for analysing medical images
Klingensmith et al. Spectral analysis of ultrasound radiofrequency backscatter for the identification of epicardial adipose tissue
US20220139528A1 (en) Analysis support apparatus, analysis support system, and analysis support method
Shahbazi et al. Machine learning-based prediction of diabetes risk by combining exposome and electrocardiographic predictors
US20080021302A1 (en) Method and device for evaluation of an image and/or of a time sequence of images of tissue or tissue samples
Chen et al. Performance of ATT and UDFF in the diagnosis of non-alcoholic fatty liver: An animal experiment
Nagy et al. Ultrasound Image Computerized Analysis for Non-invasive Quantitative Evaluation of Hepatic Fibrosis
Limchareon et al. Radiologist’s Role in Artificial Intelligence Era
Singla et al. Automatic measurement of kidney dimensions in two-dimensional ultrasonography is comparable to expert sonographers
Beevi et al. Stroke Lesion Prediction by Bille-Viper-Segmentation with Tandem-MU-net Model.
US20250366818A1 (en) Method and Apparatus of Intelligent Analysis for Liver Tumor
Li et al. Temporal enhanced ultrasound and shear wave elastography for tissue classification in cancer interventions: an experimental evaluation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24737147

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE