Method and device for determining condition of liver of subject

Abstract

The present disclosure relates to a method and a device (10) for determining a condition of a liver (3) of a subject (UR1). The method comprises: acquiring a first set of scan data (DT1a) from ultrasonic waves propagating according to a first scan configuration (CF1) of the liver; acquiring a second set of scan data (DT1b) from ultrasonic waves propagating according to a second scan configuration (CF2) of the tissue set of the subject; and determining, by a combination of the first set of scan data (DT1a) and the second set of scan data (DT1b), an indicator (S3) representative of the condition of the liver.

Description

Technical Field

[0001] The present disclosure relates to determining the condition of the liver of a subject (e.g., a human or animal), and particularly, but not exclusively, encompasses aiding in screening or diagnosing liver diseases, such as non-alcoholic hepatic steatosis (NASH), which is also known as so-called non-alcoholic fatty liver disease (NAFLD) or non-alcoholic steatohepatitis (NASH). Background Art

[0002] Hepatic steatosis is a liver disease characterized by the accumulation of fat within the liver cells. There are many causes of hepatic steatosis, including in particular alcohol and metabolic syndrome. Non-alcoholic hepatic steatosis, the so-called NASH, affects people who do not drink alcohol excessively. When more than 5% of the liver cells contain lipid droplets, it is said that the hepatic steatosis is pathological. Simple hepatic steatosis, the so-called steatosis, is generally benign and therefore does not cause significant damage to the liver. On the other hand, the condition may develop into more serious diseases such as non-alcoholic steatohepatitis, the so-called NASH, which corresponds to an aggressive infection characterized by the appearance of inflammation within the liver parenchyma. Steatohepatitis itself may lead to the accumulation of scar tissue (fibrosis), which may lead to the potentially serious liver disease cirrhosis.

[0003] Hepatic steatosis, and NASH in particular, is currently considered a major public health problem worldwide. Approximately 2 million new cases of liver disease are currently detected worldwide each year. It is currently believed that the prevalence of NAFLD and NASH will increase by 21% and 63%, respectively, between 2015 and 2030. This liver condition is associated with behavioral (physical activity, diet) and genetic factors. In particular, it affects people who are overweight or obese. Studies have shown that non-alcoholic hepatic steatosis increases the overall morbidity and the morbidity associated with cardiovascular diseases and may lead to various pathologies, especially liver diseases, the formation of tumors, etc.

[0004] However, hepatic steatosis is a relatively slow and reversible process that can be effectively treated, especially with a better diet and, more generally, better health habits, provided that care is taken early. Therefore, being able to screen and diagnose cases of hepatic steatosis, and NASH in particular, as early as possible is crucial. However, there are currently different technologies for diagnosing and, more generally, monitoring the condition of the liver, but these do not always provide satisfactory results.

[0005] Currently, the MRI examination is a reference non-invasive method for assessing the condition of the liver, in particular for diagnosing and quantifying hepatic steatosis. In particular, it enables a uniform and non-invasive examination of the entire liver. Thus, with the help of this technique, it is possible to determine an overall value for the liver fat ratio, which is the so-called PDFF, which refers to "proton density fat fraction". However, this technique involves some constraints and limitations, since it requires equipment and skills that are not yet widely available (cost issues, manufacturing complexity, scarcity, maintenance, training, etc.), and may even require a complex setup; this makes it hardly suitable for certain liver examinations, in particular routine examinations, large-scale surveillance cases, and, where possible, long before the development of potential diseases, so that the subject can benefit from upstream treatment, since these pathologies are often potentially reversible if they are discovered early enough.

[0006] Liver biopsy is also a reference technique for this type of medical monitoring and diagnosis, but has significant risks and limitations, especially because of its potential lack of reliability related to the essentially very local nature of this examination. Therefore, this technique may lead to diagnostic errors, especially if the biopsy is not targeted to the most affected part of the liver. It should also be noted that, due to its invasive nature, liver biopsy may cause serious complications, such as bleeding. In addition to the reliability issues and possible risks of complications, biopsy is also expensive in terms of financial aspects and the time invested by the subject and medical staff.

[0007] The use of ultrasound technology has been proposed for the non-invasive diagnosis of hepatic steatosis, in particular for NASH at different stages. However, despite its often demonstrated efficiency, this examination technique is currently sometimes not well mastered and, therefore, it does not always provide satisfactory results, in particular in terms of relevance, accuracy and reliability of the data obtained and processed. One limitation of this technique is, in particular, the high dependence of the relevance of the results on the skills of the ultrasound practitioner. This can be explained, in particular, by the fact that the technique is based on an anatomical and qualitative approach and requires the implementation of a large number of parameters, which makes the assessment of the results more subjective and therefore more difficult, as it depends on the user. This dependence on the user becomes critical if the user is not adequately trained and / or does not have enough time to perform the examination under good conditions. Summary of the invention

[0008] One of the objects of the present invention is to solve at least one of the above problems or disadvantages.

[0009] In particular, it may be desirable to accurately and reliably determine (or assess) the condition of the liver of a subject or patient (eg, a human subject).

[0010] In particular, it may be desirable to assess the condition of a subject's liver for early screening of dysfunction or signs thereof, or for diagnosis of liver disease, such as hepatic steatosis, particularly nonalcoholic hepatic steatosis (or steatohepatitis) (NASH), or nonalcoholic steatohepatitis (NASH).

[0011] To this end, according to a first aspect, the present disclosure relates to a method for determining a condition of a subject's liver, the method comprising:

[0012] - acquiring a first scan data set from ultrasound waves propagated according to a first scan configuration of the liver;

[0013] - acquiring a second set of scan data from ultrasound waves propagated according to a second scan configuration of a set of tissues of the subject;

[0014] - Determining an indicator S3 representing the condition of the liver by combining the first scan data set and the second scan data set.

[0015] The method according to the invention may include other features, in particular in the following embodiments, which may be used alone or in combination. The following embodiments are described purely as examples and may be combined or linked unless otherwise stated.

[0016] According to one example, the set of tissues of the subject corresponds to a portion of the subject other than the liver.

[0017] According to one example, the method is such that:

[0018] - the first scanning configuration is an intercostal scanning configuration of the liver; and

[0019] - The second scan configuration is a subcostal scan configuration of the liver.

[0020] According to one example, the method includes:

[0021] - Compare the indicator S3 with a reference value.

[0022] According to one example, the method includes:

[0023] - from the first scan data set, evaluating a first score S1; and

[0024] - from the second scan data set, evaluating a second score S2;

[0025] Here, the indicator S3 is determined from the first score and the second score.

[0026] According to an example, the first indicator S1 and / or the second indicator S2 includes at least one of the following:

[0027] - Indicators defining the attenuation coefficient;

[0028] - Indicators that limit the speed of sound;

[0029] - Indicators that define the backscatter coefficient;

[0030] -Indicators of liver elasticity;

[0031] - Indicators defining the viscoelastic properties of the liver;

[0032] - indicators of propagation nonlinearity;

[0033] - an indicator of ultrasonic scattering; and

[0034] -Indicators of ultrasonic speckle distribution.

[0035] According to one example, the method is such that:

[0036] - the first fraction is a first attenuation coefficient; and

[0037] - the second fraction is the second attenuation coefficient;

[0038] Among them, the index S3 defines a biological index of the physiological and pathological condition of the liver.

[0039] According to one example, one of the first scan data set and the second scan data set is acquired from a scan configured according to a prior scan (i.e., a so-called prior scan), and the other is acquired from a scan configured according to a subsequent scan (i.e., a so-called subsequent scan), the prior scan being performed before the subsequent scan;

[0040] The prior scanning configuration is one of the first scanning configuration and the second scanning configuration, and the subsequent scanning configuration is the other of the first scanning configuration and the second scanning configuration.

[0041] According to one example, the post-scan configuration is selected from the first score or the second score obtained by the prior scan.

[0042] According to one example, the indicator S3 is determined from an average of the first score and the second score.

[0043] According to one example, the average value is determined by a linear combination of the first and second scores S1 , S2 .

[0044] According to one example, the average is a least mean square average.

[0045] According to an example, the average value is determined by a non-linear combination of the first and second scores S1 , S2 .

[0046] According to one example, determining the indicator S3 includes:

[0047] - processing the first data set and the second data set, or data obtained from the first data set and the second data set, according to a processing model obtained using a neural network trained with training data and reference scores (or indicators),

[0048] The training data includes ultrasound scan data or data obtained from ultrasound scan data.

[0049] According to one example, prior to processing, during a training phase, the neural network is trained by machine learning, the training phase comprising:

[0050] - acquiring ultrasound scanning data representative of waves propagating on the test object according to the first scanning configuration and the second scanning configuration;

[0051] -determining training data from ultrasound scan data;

[0052] - obtaining a reference score representing the condition of the test subject's liver from MRI imaging performed on the test subject; and

[0053] - determining a processing model for estimating the indicator S3 from a combination of the first scan dataset and the second scan dataset by comparing the training data with the reference scores.

[0054] According to one example, the method includes:

[0055] - From index S3, the fat mass ratio of the subject's liver is evaluated.

[0056] According to a second aspect, the present disclosure may be implemented by or relate to a computer program, the computer program comprising instructions which, when executed by a computer, facilitate implementation of the method according to the first aspect. In particular, each step of the method according to the first aspect may relate to computer program instructions.

[0057] The computer program may use any programming language or equivalent language, and its form may be source code, object code, or an intermediate code between source code and object code, such as a partially compiled form, or any other desirable form.

[0058] According to a third aspect, the present disclosure relates to a computer (or processor) readable recording medium (or information medium) on which the computer program according to the second aspect of the present disclosure is recorded.

[0059] On the other hand, the recording medium can be any individual or device capable of storing a program, such as at least one volatile and / or non-volatile memory. For example, the medium may include a storage medium, such as a rewritable non-volatile memory, a ROM, a CD-ROM or a microelectronic circuit type ROM, or a magnetic recording medium or a hard disk. The memory may, for example, include a graphics card (or video card) memory, which is particularly designed for processing image data (or video data).

[0060] On the other hand, the recording medium may also be a transmissible medium, such as an electrical or optical signal, which can be transmitted via an electrical or optical cable, by conventional or Hertzian radio or by a self-guided laser beam or by other means. The computer program according to the invention may in particular be used to transmit data using a local or other wired or wireless network (e.g. Wi-Fi, Ethernet, Internet, 4G, 5G, etc.) to download.

[0061] Alternatively, the recording medium may be an integrated circuit in which the computer program is integrated, the integrated circuit being capable of executing the method or being used in executing the method.

[0062] According to a fourth aspect, the present disclosure relates to a determination device (or monitoring device) configured to determine the condition of the liver of a subject by implementing the determination method of the first aspect of the present disclosure. To this end, the determination device may include modules configured to respectively implement the various steps of the method of the first aspect of the present disclosure.

[0063] According to an example, the determination device comprises a memory associated with a processor, the memory comprising a computer program according to the second aspect of the present disclosure.

[0064] According to one example, an apparatus for determining a condition of a subject's liver, the apparatus comprising:

[0065] - a first acquisition module configured to acquire a first set of scan data from ultrasound waves propagated according to a first scan configuration of the liver;

[0066] - a second acquisition module configured to acquire a second set of scan data from ultrasound waves propagated according to a second scan configuration of a set of tissues of the subject; and

[0067] An analysis module configured to determine an indicator S3 representing the condition of the liver by combining the first scan data set and the second scan data set.

[0068] According to one embodiment, the present invention is implemented by software and / or hardware components. In particular, the determination device may include a module configured to implement each step of the method according to the first aspect of the present disclosure. Thus, the various embodiments described herein in conjunction with the method according to the first aspect of the present disclosure, and the associated advantages, may be similarly applicable to the determination device according to the fourth aspect of the present disclosure.

[0069] In this respect, in the present disclosure, the term "module" may correspond to a software component, as well as a hardware component, or a collection of hardware and software components. A software component corresponds to one or more computer programs, one or more subroutines of a program, or more generally, any element of a program or software capable of implementing a function or set of functions as described below for the module referred to.

[0070] Similarly, a hardware means corresponds to any element of a hardware set capable of implementing a function or a set of functions according to the functions described below for the module concerned.

[0071] According to a fifth aspect, the present disclosure relates to a system for determining a condition of a subject's liver, the system comprising:

[0072] - a determination device according to the fourth aspect of the present disclosure; and

[0073] - an ultrasound system coupled to the determination device.

[0074] Advantageously, the determination method and device disclosed herein allow determining the condition of the liver of a subject, which may be healthy or have any physiological-pathological condition of the liver, in a reliable, reproducible and effective manner. To this end, the disclosure is based on combining scan data (or ultrasound data) obtained according to two different scan configurations, namely according to a first scan configuration CF1 for the liver and a second scan configuration CF2 for the liver or another tissue set of the subject, respectively. Advantageously, the combination of these scan data allows obtaining an indicator S3 representative of the condition of the liver of the subject under consideration in a more reliable and more robust manner than in the case of using only one scan configuration.

[0075] Therefore, the determination method and device involve obtaining scan data according to different scanning configurations. Within the scope of the present disclosure, a scan corresponds to an echographic (or ultrasound) scan, an echographic (or ultrasound) observation or an echographic (or ultrasound) observation phase. Such a scan includes the propagation of ultrasound waves in a medium (i.e., the object being examined) and the recovery of echographic echoes (or ultrasound echoes) representing the condition of the liver of the object. Each scan allows obtaining (or generating) scan data representing one or more target areas (or areas of interest) of the object.

[0076] The target area or areas of the object that are examined (or scanned) by ultrasound during an echographic scan depend on the scanning configuration used. The configuration may be defined by various parameters, including, among other things, the orientation and / or position of the transmitting device during the echographic scan.

[0077] The combination of two different acquisition modes, such as intercostal mode and subcostal mode, advantageously allows for improved correlation of acquired data compared to conventional techniques that would only consider ultrasound data acquired in intercostal mode. The ultrasound data so acquired are more representative of the condition of the liver. Advantageously, the use of two different scanning configurations allows for diversification of measurements and thereby enhances reliability and accuracy of the results.

[0078] Moreover, in the case of, for example, hepatic steatosis, all areas of a subject's liver may be affected in different ways. Therefore, some cases of heterogeneous steatosis have been noted. The addition of ultrasound scanning according to different scanning configurations allows obtaining a more representative estimate of the overall condition of a subject's liver.

[0079] Thus, the present disclosure can advantageously assist in diagnosing or monitoring certain physiological and pathological conditions of the liver, such as hepatic steatosis (eg, NASH-type), inflammatory steatosis, and the like.

[0080] The characteristics and advantages of the present invention will become clearer upon reading the following description provided purely as non-limiting examples and with reference to the accompanying drawings. In particular, the examples shown in the drawings may be combined together, as long as there are no stated or obvious inconsistencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] By the following reference attached Figures 1 to 16 , other features and advantages of the present disclosure will become apparent from the description of the non-limiting embodiments of the present disclosure, in the accompanying drawings:

[0082] Figure 1 schematically illustrates an intercostal scanning configuration for ultrasound scanning of a subject's liver according to one specific example;

[0083] Figure 2 is an echographic image showing the appearance of a shadowed area during an echographic examination of a subject's liver in an intercostal acquisition mode;

[0084] Figure 3 Schematically illustrates a determination device and an ultrasound system according to an embodiment of the present disclosure;

[0085] Figure 4 Schematically illustrates an ultrasound system according to one embodiment of the present disclosure;

[0086] Figure 5 Schematically illustrating a determination device according to an embodiment of the present disclosure;

[0087] Figure 6 Schematically illustrates a scanning configuration according to which ultrasound scanning is performed according to one embodiment of the present disclosure;

[0088] Figure 7 Schematically illustrates a scanning configuration according to which ultrasound scanning is performed according to one embodiment of the present disclosure;

[0089] Figure 8 Schematically illustrating an embodiment of the present disclosure, Figure 3 The determination method performed by the determination device;

[0090] Fig. 9 Schematically illustrating the results obtained in the intercostal acquisition mode according to one embodiment of the present disclosure;

[0091] Fig.10 Schematically showing the results obtained in the subcostal acquisition mode according to one embodiment of the present disclosure;

[0092] Fig.11 Schematically illustrating an embodiment of the present disclosure, by combining Fig. 9 and Fig.10 The result obtained by the determined method;

[0093] Fig.12 Schematically illustrates the distribution of PDFF scores of a liver of a test subject during a study to verify the effectiveness of a determination method according to one embodiment of the present disclosure;

[0094] Fig.13 Schematically illustrating a determination method according to an embodiment of the present disclosure;

[0095] Fig.14 Schematically illustrating a determination method according to an embodiment of the present disclosure;

[0096] Fig.15 Schematically illustrating an embodiment of the present disclosure, Figure 3 determining a neural network implemented by the device; and

[0097] Fig.16 Schematically illustrating an embodiment of the present disclosure, Fig.15 The training phase of a neural network is performed. DETAILED DESCRIPTION

[0098] The present disclosure particularly encompasses apparatus and methods for determining the condition of a subject's liver, for example for screening activities, medical monitoring, or diagnostic assistance.

[0099] It is known to examine the liver of a subject by echography, in particular in order to screen for or diagnose liver diseases, such as hepatic steatosis (e.g. of the NAFLD type) or NASH type steatohepatitis. The use of this technology is advantageous, in particular because of its non-invasive nature, the relative availability of echographs in the field for medical examinations, the ease of moving them as needed, and the lower investment and examination costs and risks compared to, for example, MRI and biopsy.

[0100] However, since the relevance of its results is significantly limited by the qualification level of the practitioner, this inspection technology is still in its infancy and does not always provide satisfactory results, especially in terms of performance and reliability. As described below, these problems may have multiple sources.

[0101] like Figure 1 As shown, the current practice widely adopted worldwide is to scan the patient according to the so-called "intercostal" scanning configuration (denoted as SCx ( Figure 1 )), i.e. an echographic examination of the liver is performed by positioning the ultrasound probe so that ultrasound waves propagate between the subject's ribs 2 to recover in response ultrasound echoes representing the subject's liver 3. To this end, the ultrasound probe, possibly covered with a suitable gel, is positioned in contact with the subject's skin at the subject's thorax to scan "through the ribs" (i.e. between the ribs).

[0102] This intercostal scanning configuration is considered the most reliable, in particular because the subject's ribs protect the underlying tissue, thus allowing limiting the deformation that the probe may cause when it is applied to the patient. In fact, such deformation may distort the observation results because the compressed tissue behaves differently. The intercostal configuration is also preferred because it facilitates the examination, especially for some difficult to examine subjects (especially those with high subcutaneous fat levels). The echography technician may regard the subject's ribs as a reference to best orient and position the probe of the echography system.

[0103] For the reasons mentioned above in particular, clinical studies currently recommend the use of an intercostal scanning configuration for examining the liver, in particular for the purpose of screening or diagnosing liver diseases such as those mentioned above.

[0104] However, it has been noted that echographic examination of the liver according to the intercostal technique poses some problems and has limitations that need to be addressed. Figure 2 As shown exemplarily in FIG. 7 , it has been observed that, in particular, shadow areas 8 appear in the echographic images 7 obtained according to the intercostal scanning configuration. These dark areas 8 that hinder observation originate from the overall convex shape of the ultrasound probe, which does not always allow the ultrasound probe to fully contact the subject's skin during the examination, in particular because the subject's ribs form protrusions that are hardly compatible with the probe shape. During the echographic observation, the non-contact areas between the probe and the subject's skin hinder the propagation of ultrasound waves, resulting in the formation of areas 8 that appear dark in the image.

[0105] However, it is difficult, or even undesirable, to change the shape of the probe to better match the contours of the ribs, particularly because current configurations are designed to maximize the field of view of the echographic system and ensure a certain versatility of the probe, allowing it to be adapted for a variety of echographic examinations.

[0106] In addition to the above-mentioned shadow area problem, echographic observation of the liver according to conventional intercostal scanning configurations generally has sometimes unsatisfactory results. It has been noted that the assessment of certain characteristics of the liver, such as biomarkers, is not always sufficiently reliable or valid for such use.

[0107] Therefore, the present disclosure aims to provide a solution, in particular to the above-mentioned problems and drawbacks, which allows to determine the condition of the liver of a subject (e.g. a human or animal), or more generally, the condition of the liver of a living being, with higher reliability and better performance, for example but not exclusively, in particular to assist in screening or diagnosing liver diseases, or more generally, to assess the condition of the liver of a subject. In particular, the solution is based on a method and a device for determining the condition of the liver of a subject.

[0108] According to the specific embodiments of the present disclosure, Figures 3 to 16 Together, the determination method and the determination device (also referred to as "method" and "device") are described. Unless otherwise specified, common or similar elements in multiple figures have the same reference numerals and have the same or similar features. For the sake of brevity, these common elements are generally not repeated.

[0109] The words “first” (or “first, second”, etc.) are used herein according to arbitrary conventions to identify or distinguish different elements (eg, operations, devices, etc.) implemented or used in the following embodiments.

[0110] like Figure 3 As shown, an embodiment of the present disclosure is described below as an example, in which the liver 3 of the object UR1 is observed by echography through an ultrasound system denoted as SY1. To this end, ultrasound waves W are emitted into different regions (or regions of interest) of the object UR1 by the ultrasound system SY1 to obtain ultrasound data representing the condition of the liver 3. The observation includes multiple echographic scans, i.e., multiple phases during which ultrasound waves propagate and, in response, ultrasound echoes representing the condition of the liver 3 are recovered. In other words, during each scan, one or more regions of the liver are sonified with incident ultrasound waves by the ultrasound probe, and, in response, echoes backscattered by these regions of the liver are captured. The terms "scan", "echographic (or ultrasound) scan", "echographic (or ultrasound) observation", "phase of observation by echographic (or ultrasound)" or "acquisition phase" will be used interchangeably hereinafter.

[0111] In the example considered, the subject is a living being, ie a mammal, such as a human being. However, it is noted that the concepts of the present disclosure are more generally applicable to any subject (human or animal), living or dead, having a liver, the condition of which is to be assessed.

[0112] It is noted that the subject UR1 used to illustrate the present disclosure may have a body in any physiological condition, especially with respect to the liver. In particular, the subject's liver 3 may be healthy (eg, without a specific liver disease), or suffer from any liver disease or pathology.

[0113] The method and device disclosed herein are based in particular on obtaining two data sets from ultrasound waves W propagated during ultrasound scanning, respectively according to different scanning configurations, and combining these two data sets to determine an indicator, denoted S3, representative of the condition of the liver 3 of the subject UR1 (which is also called an overall indicator, or an overall score or parameter). Advantageously, combining these two data sets allows determining an indicator representative of the condition of the subject's liver.

[0114] In the present disclosure, a scan configuration of the liver refers to a scan configuration according to which echographic data representative of the liver of a subject is obtained. In other words, an echographic scan performed according to the scan configuration of the liver at least partially scrutinizes (or is intended for or is directed to) the liver of a subject to obtain echographic data representative of the liver.

[0115] According to some embodiments, the determining method comprises:

[0116] - acquiring a first scan data set by propagating ultrasound waves according to a first scan configuration of the liver;

[0117] - acquiring a second scan data set by propagating ultrasound waves according to a second scan configuration of the subject's tissue set; and

[0118] - Determining an indicator S3 representing the condition of the liver by combining the first scan data set and the second scan data set.

[0119] like Figure 3 As shown in the example in , different echographic scans (or observations), namely a first scan SC1 and a second scan SC2, are performed by an ultrasound system SY1 on an object UR1 according to different scan configurations (or modes) - respectively denoted as CF1 and CF2 - to determine the condition of the liver 3 of the object UR1. The scan configurations CF1 and CF2 may vary according to the situation, and in particular, these configurations differ from each other slightly or more generally in terms of the scan direction and / or the position relative to the object.

[0120] The determination device (which is also referred to as the processing device) 30 is further configured to acquire and process the scan data (or ultrasound data) DT1a and DT1b ( ) generated by the ultrasound system SY1 by the first scan SC1 and the second scan SC2, respectively. Figure 3 ). To this end, the determination device 30 cooperates (is coupled) with the ultrasound system SY1 to implement a determination method according to at least one specific embodiment.

[0121] like Figure 3 As shown, the determination device 30 and the ultrasound system SY1 together form a determination system (or analysis system) SY2 which is configured to determine the condition of the subject's liver.

[0122] According to one example, the determination device 30 is an integral part of the ultrasound system SY1. According to a variant, the determination device 30 is external to (distinct from) the ultrasound system SY1.

[0123] The system SY1 may be a medical ultrasound system. Thus, the transmitting device 20 may be a medical and / or ultrasound probe (or at least a part thereof).

[0124] For illustration purposes only, an embodiment of an ultrasound system SY1 is now described.

[0125] Figure 3 An embodiment of an ultrasound system SY1 is schematically shown, which comprises a control device (or steering device) 10 and a transmitting device 20. The control device 10 is configured to steering the transmitting device 20. The transmitting device 20 is configured to transmit and receive ultrasonic waves W to and from a medium under investigation (i.e., the object UR1 in the example considered) under the control of the control device 10.

[0126] According to a specific example, the whole or a part of the determination device 30 is part of the control device 10. According to an example, the devices 10 and 30 form the same device.

[0127] For example, the transmitting device 20 is an ultrasonic transducer device (or an ultrasonic probe) configured to transmit and / or receive ultrasonic waves W. For example, the transmitting device 20 is included in an ultrasonic probe that is applied to contact the subject UR1 to determine the condition of the liver 3 thereof during an echography scan.

[0128] However, it is noted that various configurations of the transmitting device 20 are possible. In particular, the whole or part of the control device 10 may be implemented in the transmitting device 20 (eg in the probe). The whole or part of the control device 10 may be located outside the transmitting device 20 (or the probe).

[0129] In this example, the control system 10 may include a processing unit (or module) 11 and a control unit (or module) 12. The control unit 12 (which is also referred to as a power control unit) is configured to manipulate the transmitting device 20 through electrical signals that interact (or transmit) between the system 10 and the transducer device 20. Thus, the control unit 12 generates an electrical signal, which is transmitted to the transducer device 20 to cause the transducer device 20 to transmit an ultrasonic wave W1 in the direction of a region of interest located in the object UR1. The electrical signal thus generated represents (or defines) an ultrasonic wave projected into the medium. To this end, the control unit 12 may, for example, be composed of (or include) at least one electronic pulse generator (which is also referred to as a "pulser").

[0130] Optionally, the control unit 12 may include a receiving device or receiving circuit (not shown) configured to receive the electrical signal originating from the transducer device 20 .

[0131] The processing unit 11 may be configured to control the control unit 12, for example, by controlling an electrical signal. For example, the processing unit 11 may be composed of (or include) at least one processor.

[0132] According to one example, the processing unit 11 and / or the manipulation unit 12 are included in Figure 4 In the body 31 (central element) of the system SY1 shown for illustration.

[0133] More specifically, the processing unit 11 may be configured to control the electrical signals generated by the control unit 12. The processing unit 11 may also be configured to process (and / or interpret) electrical signals originating from the transmitting device 20 that may be received by the control unit 12. These signals represent waves W2 ( Figure 3 ). For example, these waves W2 form one or more ultrasound echoes, i.e. the response of the investigated medium (i.e. the liver of the subject UR1) to the ultrasound waves emitted in the direction of said medium. The processing of the received signals by the processing unit 11 may vary according to the situation and may include, for example, at least one of the operations of signal amplification, filtering, digitization and conditioning.

[0134] In the present disclosure, the term "medium" refers to one or more regions of interest (or areas) of the object UR1, ie the areas being sonified or scrutinized by ultrasound, ie the regions of interest of the liver 3 and possibly, regions of interest corresponding to other parts of the object UR1.

[0135] like Figure 3As shown, the transmitting device 20 may include, for example, one or more ultrasonic transducers (which are also referred to as transducer elements) 22, each of which is configured to convert an electrical signal received from the control device 10 into an ultrasonic wave (and possibly, also conversely convert the ultrasonic wave into an electrical signal). Thus, the transducer 22 may be configured to transmit a wave (or ultrasonic pulse or ultrasonic beam) W1 into a medium, which corresponds to a transmitting operation.

[0136] Optionally, the transducer 22 may also be configured to receive, during a receiving operation, ultrasonic signals W2 originating from one or more regions of interest of the object UR1, for example in response to the transmitted wave W1. These received signals W2 may be in the form of a set of backscattered echo signals in response to the previously transmitted signal W1. For example, each transducer 22 may convert the received echo signal W2 into an electrical signal. The signal may then be processed by the control device 10 (e.g., by the processing unit 11) or any associated (dedicated) system (directly connected or not directly connected). For example, the signal W2 may be amplified, filtered, digitized, and / or operations to adjust the signal may be performed. The transducer elements may be arranged according to rows, arrays, or networks of transducers or any other configuration.

[0137] It is noted that the same one or more transducers 22 may be used to transmit waves (or pulses) W1 and, where appropriate, receive waves W2 that form a medium response, or different transducers may be used to transmit and receive waves. There may be one or more transmitting transducers, and possibly, multiple receiving transducers. In another variation, the same transducer 22 may be used to transmit and receive ultrasonic waves. The transducer 22 may include a piezoelectric crystal and / or other components that may be configured to generate and / or record and / or receive signals.

[0138] The control device 10 may include a transmitting device 20. Alternatively, the transmitting device 20 may be located outside the control device 10. For example, the transmitting device 20 may be connected to the control device 10 via a cable, or may communicate wirelessly therewith. In the latter case, the transmitting device 20 may, for example, include a battery and receive a communication signal representing the electrical signal (e.g., the operating frequency and / or any information included in the electrical signal) from the control device 10. The transmitting device 20 may then replicate the electrical signal internally from the received communication signal.

[0139] For example, the transmitting device 20 may be a conventional ultrasound transmitting device. Thus, the difference according to the present disclosure may lie in the way the determining device 30 acquires and processes the ultrasound data DT1a and DT1b to determine the condition of the liver 3 of the subject UR1 as explained in more detail below.

[0140] The control device 10 can be static or movable. The transmitting device 20 can also be static or movable. For example, the control device 10 can be a fixed system (which, as described below, for example includes a processing unit and a display device), while the transmitting device 20 can be movable (for example a sensor device, a measuring device, or a probe). However, it is also feasible that the transmitting device 20 is integrated in the control device 10 and that the device 10 is a movable system. For example, the control device 10 can be configured to be operated in an independent manner, for example with the aid of a built-in battery. Other examples are described below.

[0141] According to one example, the control device 10 may include at least one memory (not shown), which is used by the processing unit 11 to control the control unit 12. Optionally, the memory may be a part of the processing unit 11. In some examples, the processor and the memory of the processing unit 11 may be integrated in Figure 3 The control device 10 is shown, or may be integrated in a computer or computer device connected to communicate with the control device 10 .

[0142] Depending on the configuration and the kind of computer device under consideration, the memory of the control device 10 may be volatile (for example RAM), non-volatile (for example ROM memory, flash memory, EEPROM, etc., or any other storage device and / or computer-readable medium as described below), or a combination of both. For example, the memory may be generated in DMA (this means “Direct Memory Access” in English) mode. For example, the memory used by the processing unit 11 may include the whole or a part of the memory of a graphics card (or video card), this type of memory being particularly capable of processing and / or transmitting image data that can be used to display one or more images on a display screen (or unit).

[0143] More generally, the control device 10 may include storage devices (removable and / or non-removable) including, but not limited to, magnetic or optical disks or tapes.

[0144] Furthermore, the control device 10 may include one or more input devices, such as a keyboard, a mouse, a stylus, voice input, etc., and / or one or more output devices, such as one or more screens, speakers, printers, etc. The environment may also include one or more communication connections, such as a LAN, a WAN, a point-to-point type connection, etc. In some embodiments, the connection may be used to establish point-to-point communication, wired communication, wireless communication, etc.

[0145] The control device 10 may be a single computer operating in a networked environment using a logical connection to one or more remote computers. The remote computer may be an audit station, a personal computer, a server, a router, a network PC, a similar device, or other common network node, and may generally include multiple or all of the above elements, as well as other elements not mentioned. The logical connection may include any method supported by the available communication medium.

[0146] As noted above, an embodiment of the ultrasound system SY1 is described above for illustrative purposes only, and other implementations are possible within the scope of the present disclosure.

[0147] Furthermore, the determination device 30 comprises a processing means ( Figure 3 ). The scan data generated by the system SY1 may be analyzed by the determination device 30, either in real time, for example by an artificial intelligence algorithm and / or module, or at a later time and / or at a location other than the location where the ultrasound system SY1 is located.

[0148] As explained in more detail below, the nature of the scan data DT1a and DT1b provided by the echographic system SY1 to the determination device 30 may vary depending on the circumstances. For example, these data may include image data (or video data) and / or other data derived from the scan data or the scan data itself.

[0149] More specifically, in Figure 3 In the example shown, the determination device 30 comprises at least one processor 31 and at least one computer-readable medium, such as a non-volatile memory 32. The rewritable or ROM-type memory 32 forms a recording medium (or information medium) according to a specific embodiment, which can be read by the processor 31 and on which a computer program PG1 according to a specific embodiment is recorded. The computer program PG1 comprises instructions for executing the steps of the determination method according to at least one specific embodiment. In particular, the program may define instructions for processing ultrasound data and / or instructions for constructing an illustrative image of the observed medium.

[0150] For example, the computer program PG1 may include at least one artificial intelligence (AI) algorithm that can be executed by the processor 31 to implement the determination method according to a specific embodiment of the present disclosure. In particular, the computer program PG1 may define an artificial intelligence model (or prediction model) trained with training data, which is used to process ultrasound data obtained according to the determination method of the present disclosure, in particular to determine one or more indicators (or scores) as described in some embodiments below.

[0151] The computer readable media of the determination device 30, such as the memory 32, may be comprised of any available media accessible to the processor 31 or its operating environment. For example and without limitation, computer readable media may include computer storage media and communication media. Computer storage media include removable and non-removable, volatile and non-volatile media implemented in any information storage method or technology, such as computer readable instructions, data structures, program modules or other data. Computer storage media do not include communication media.

[0152] According to an example, the determination device 30 is configured to receive scanning data provided by the ultrasound system SY1, such as data DT1a and DT1b, process the data, and optionally send the processing results to an external device, such as a storage device, a display device, a server or any other external device.

[0153] The communication between the determination device 30 and the ultrasound system SY1 may be implemented according to any communication link, which may be wired or wireless as the case may be.

[0154] Figure 4 Schematically shown as above reference Figure 3 An embodiment of the ultrasound system SY1 is, in the example considered, an ultrasound imaging system.

[0155] Therefore, if Figure 4 The ultrasound imaging system 10 shown includes:

[0156] - a transmitting device 20 in the form of an ultrasound probe;

[0157] - a processing unit 40 configured to process or generate an image based on the ultrasound signal received from the probe 20 (the unit 40 corresponds to, for example, Figure 3 Processing unit 11);

[0158] a control panel 42 associated, linked or connected to the processing unit 40, said control panel optionally comprising at least one of a key 41 and a touchpad 42; and

[0159] one or more screens 50 configured to display one or more images generated by the processing unit 40 .

[0160] The probe 20 may be connected to the processing unit 40 by any suitable connection means, such as a cable 21 or a wireless connection. The probe 20 is also capable of transmitting ultrasonic waves W into the medium M and possibly also receiving ultrasonic waves W from the medium M, which may be caused or resulted from reflections of the transmitted ultrasonic waves on the sweeping particles in the medium.

[0161] The processing unit 40 may include a receiving device (not shown) configured to process (e.g., amplify and / or filter) the electrical signals received from the probe 20, the receiving device including (or being) for example a receiving circuit. For example, these receiving devices may include a converter for converting the received signal into data representing the signal (e.g., an analog-to-digital converter (ADC) configured to convert a voltage into a digital code). The acquired ultrasound data may be processed in various ways, in particular, they may be temporarily stored in a memory accessible to the processing unit or directly processed to calculate intermediate processing data (referred to in English as "beamforming data", data derived from a route formation process). The processing unit 40 may generate and / or process one or more images or maps or data based on the signals received from the probe, implementing any known processing method such as route formation.

[0162] The processed data may be associated with ultrasound images of different natures, which may be:

[0163] - a B-mode image of the medium (B-mode image), which is generally displayed in grayscale, allowing visualization of organs within the medium; and / or

[0164] so-called Doppler images, which show the movement of a fluid in the observed medium, for example the velocity and / or the flow rate of the fluid in the medium (color-coded images are often used), which images are useful, for example, for visualizing blood vessels and their activity in the medium; and / or

[0165] - Images showing the mechanical characteristics (elasticity) of the medium (e.g. Shear Wave Elastography image data) TM Elastography)) is useful, for example, for identifying areas of different hardness, which may be lesions present in the medium.

[0166] The display screen 50 (which is, for example, mounted on a support arm 51) can be a screen for displaying images processed by the processing unit 40 and / or can display various information, in particular auxiliary information or situational gesture assistance that is suitable or capable of being suitable for the touchpad 42, depending on the usage.

[0167] As an example in Figure 5 As schematically shown in FIG. 1 , the determining device 30 is operated by a computer program PG1 ( Figure 3 )'s processor 31 implements a given number of modules, namely a first acquisition module MD2, a second acquisition module MD4 and a determination module (or analysis module) MD6.

[0168] More specifically, the first acquisition module MD2 is configured to acquire a set of first scanning data DT1a from the ultrasound waves W1 propagated according to the first scanning configuration CF1 of the liver 3 ( Figure 3 ). These first scan data DT1a obtained during the first ultrasound scan SC1 represent the liver 3 of the subject UR1.

[0169] The second acquisition module MD4 is configured to acquire a set of second scanning data DT1b from the ultrasonic wave W1 propagated according to the second scanning configuration CF2 of the tissue set of the object 3 ( Figure 3 ). As described below, these second scan data DT1b obtained during the second ultrasound scan SC2 represent any tissue set, which may include the entirety or a portion of the liver 3 of the subject UR1 or a portion (or region) of the subject UR1 outside its liver 3 (e.g., abdominal organs other than the liver, such as the pancreas and / or gallbladder).

[0170] The determination module MD6 is configured to determine an indicator (or overall indicator) S3 representing the condition of the liver 3 of the object UR1 by combining the first set of scan data DT1a and the second set of scan data DT1b. As described below in some examples, the processing applied to the data DT1a and DT1b to obtain the indicator S3 can be of various types. Similarly, the nature of the indicator S3 can be changed according to the situation.

[0171] Now refer to Figures 6 to 12 In these examples, the aforementioned determination device 30 executes the program PG1 ( Figure 3 ), implements the determination method according to some embodiments. To this end, the determination device 30 cooperates with the ultrasound system SY1.

[0172] For example, suppose you want to determine the condition of the liver 3 of the subject UR1 ( Figures 6 to 8 To this end, a practitioner, a doctor, a qualified technician, an echographer, or more generally a user, uses an ultrasound system SY1 ( Figure 3 ), two ultrasound scans were performed on the object UR1, namely:

[0173] a first ultrasound scan SC1 during which ultrasound waves propagate according to a first scanning configuration CF1 of the liver 3; and

[0174] - A second ultrasound scan SC2, during which ultrasound waves are propagated according to a second scanning configuration CF2 of the tissue 5 of the object UR1.

[0175] During each ultrasound scan SC1 and SC2, the ultrasound system SY1 transmits an ultrasonic wave W1 to the target medium (the portion of the object UR1 being observed), and in response, receives an ultrasonic echo in the form of a wave W2 ( Figure 3). These ultrasonic waves W2 represent the area in which the transmitted waves W1 and the received waves W2 of the object UR1 propagate. Thus, the ultrasound system SY1 (and more particularly, the control device 10) generates ultrasound data, namely the so-called first scanning data DT1a and second scanning data DT1b, from the ultrasound echoes captured during the ultrasound scans SC1 and SC2, respectively.

[0176] The one or more regions of the object UR1 subjected to ultrasound observation, and the ultrasound echoes W2 obtained during this observation, depend on the configuration of the ultrasound scans SC1 and SC2 performed. These configurations may be defined by various parameters, including in particular the orientation and / or position of the transmitting device 20 during the ultrasound scan.

[0177] For example, assume that the first ultrasound scan SC1 is configured to scan (closely examine) the entire or a portion of the liver 3 of the subject UR1. In other words, the scan configuration CF1 is such that the ultrasound waves propagated during the first scan SC1 represent the region (or area) of interest of the liver 3. Therefore, the first ultrasound scan SC1 is a scan of one or more regions of interest of the liver.

[0178] Furthermore, it is assumed that, for example, the second ultrasound scan SC2 is configured to target (or scrutinize) a set of tissues 5 of the object UR1 ( Figure 6 ), the properties of these tissues may vary depending on the situation. In other words, the scanning configuration CF2 makes the ultrasound waves propagated during the second scanning SC2 represent a collection of tissues 5.

[0179] According to one example, the set of tissues 5 scrutinized during the second scan SC2 comprises the whole or a part of the liver (a scan of the liver).Thereby, the scan configurations (or modes) CF1 and CF2 are scan configurations of the liver.

[0180] According to one example, the set of examined tissues 5 includes (or corresponds to) parts (or regions) of the subject UR1 outside of its liver 3, such as the whole or a part of its gall bladder, organs of the abdomen, and / or visceral fat of the subject UR1.

[0181] As described below, considering information about the condition of regions other than the subject's liver 3 may aid in analyzing and understanding the condition of the liver 3, particularly because the condition of the liver 3 and the condition of other regions of the subject may be related.

[0182] For example, ultrasound observation of the visceral fat of subject UR1 may provide information useful for determining the condition of the liver 3, in particular to aid in screening or diagnosing liver disease, since visceral fat may form a biomarker of pathological conditions of the liver. For example, the presence of excess visceral fat may be a symptom of liver steatosis (e.g., of the NASH type), liver toxicity, or other conditions of the liver.

[0183] The set of tissues 5 may be selected depending on the type of examination considered, and / or for example during a medical examination, a hypothesized condition of the liver which one wants to study or confirm or which one wants to study its evolution over time or in relation to a certain treatment. Whichever object region 5 is examined in detail during the second ultrasound scan SC2, the first scan configuration CF1 and the second scan configuration CF2 are different in order to obtain ultrasound data carrying different and complementary information.

[0184] like Figure 7 Schematically shown, in the following for illustration purposes only, it is assumed that the ultrasound scans SC1 and SC2 are configured such that:

[0185] - the first scan configuration CF1 according to which the first ultrasound scan SC1 is performed is of the intercostal type, ie by propagating ultrasound waves through (or between) the ribs of the subject UR1 (position P1 ); and

[0186] The second scan configuration CF2 according to which the second scan SC2 is performed is of the subcostal type, ie by propagating ultrasound waves below the thorax through the entire abdomen (position P2).

[0187] Thus, by positioning the ultrasound probe 20 on the abdomen of the subject, it is possible to observe the subject's liver from another cross section and thereby improve the relevance of the obtained results.

[0188] Thus, in step E2a ( Figure 8 ), the determination device 30 obtains a set of first scan data DT1a from ultrasonic waves propagated during a first ultrasound scan SC1 according to a first scan configuration CF1 of the liver 3.

[0189] Similarly, in step E2b( Figure 8 ), the determination device 30 obtains a set of second scan data DT1b from ultrasonic waves propagated during a second ultrasound scan SC2 according to a second scan configuration CF2 of the set of tissues 5.

[0190] To this end, the ultrasound system SY1 (and more specifically the control device 10) generates scan data DT1a and DT1b from ultrasound echoes received during the first ultrasound scan SC1 and the second ultrasound scan SC2, respectively. These scan data DT1a and DT1b are transmitted to the processing device 30 for processing according to the determination method.

[0191] Each ultrasound scan SC1 and SC2 may include one or more scans in a corresponding scan configuration CF1 and CF2, respectively.

[0192] The acquisition steps E2a and E2b are included in the acquisition phase denoted as E2 ( Figure 8). However, it is noted that various arrangements of steps E2a and E2b in time are possible. Steps E2a and E2b may be performed either (at least partially) simultaneously or one after the other (either immediately after the other or later (e.g. during different inspection periods)). According to one example, a set of first scanning data DT1a is received before a set of second scanning data DT1b (or vice versa).

[0193] Furthermore, the determination device 30 may receive the scanning data DT1a and DT1b in real time while performing the scanning SC1 and SC2, or may receive them afterwards in a combined or separate manner.

[0194] In determining step E6 ( Figure 8 ), the determination device 30 determines an indicator (or score) S3 representing the condition of the liver 3 of the object UR1 by combining the first set of scan data DT1a and the second set of scan data DT1b. The combination may include processing taking into account the data DT1a and DT1b, as described in some examples below, the nature of which may be adjusted according to the situation.

[0195] Steps E2 to E6 may be repeated iteratively in order to improve or update the indicator S3 determined in E6 .

[0196] According to one example, the indicator S3 defines one (or at least one) biological indicator of the physiological and pathological condition of the liver. For example, the indicator 3 may inform about a liver disease affecting the liver 3 of the subject UR1, such as hepatic steatosis (e.g. of NASH type), steatohepatitis, hepatotoxicity, etc.

[0197] According to one example, in E6( Figure 8 ) includes an attenuation coefficient, which represents the attenuation of ultrasound waves propagating in the region of interest of the object UR1 during the first ultrasound scan SC1 and the second ultrasound scan SC2, respectively.

[0198] According to one example, in E6( Figure 8 ) comprises an indicator defining for example the fat mass percentage (or ratio) of the liver, ie PDFF. This percentage tells about the average amount of fat present in the liver 3 of the subject UR1.

[0199] Fig.11 The index S3 determined (E6) for a group of test subjects during a study ET1 conducted by the applicant is shown in the form of a cloud of points 70. The index S3 defines the fat mass fraction, PDFF, determined for each subject in the study DT1.

[0200] For reference, Fig.12The PDFF values ​​determined by a technique other than the determination method described, namely by MRI imaging, for the same subjects in study ET1 are shown. The evaluation of PDFF by MRI imaging is currently the reference for the prediction or diagnosis of hepatic steatosis. It is to be noted that in this example, this study ET1 includes subjects with a PDFF below the limit value, namely 25%.

[0201] In E6( Figure 8 ) may represent any physiological, mechanical and / or tissue properties (elasticity, hardness, etc.) of the liver 3 and / or tissue 5 that are carefully examined with ultrasound during ultrasound scans SC1 and SC2. The indicator S3 may include one indicator (or score) or multiple indicators (or scores).

[0202] According to one example, in determining a method ( Figure 8 ), the determination device 30 compares (E8) the indicator S3 obtained in E6 with a reference value RF1. The reference value RF1 may be any reference indicating a predetermined condition of the liver (healthy liver, specific liver disease, etc.). For example, if the device 30 detects (E8) that the value of the indicator S3 obtained in E6 exceeds (or falls below) the reference value, this means that the condition of the liver 3 of the subject UR1 meets (or does not meet) at least one predetermined criterion.

[0203] According to one example, the indicator S3 defines the PDFF of the liver 3 of the subject UR1. During the comparison step E8, the value of the indicator S3 is compared with the threshold RF1. If the PDFF value obtained exceeds the threshold RF1 (or is within a predetermined value range), a predetermined condition of the liver 3 is detected. For example, as described, for example, in the document Cassinotto, C., Jacq, T., Anselme, S., Ursic-Bedoya, J., Blanc, P., Faure, S., Belgour, A., & Guiu, B. (2022). Diagnostic Performance of Attenuation to Stage Liver Steatosis with MRI Proton Density Fat Fractionas Reference: A Prospective Comparison of Three US Machines. Radiology, 305 (2), 353–361. https: / / doi.org / 10.1148 / radiol.212846, the value of the PDFF can be interpreted as follows:

[0204] -5.5% for S1 steatosis or higher;

[0205] -15.5% for S2 steatosis or higher;

[0206] -20.5% for grade S3 steatosis or higher.

[0207] It should be noted that in determining step E6 ( Figure 8 ) during the ultrasound scans SC1 and SC2, the index S3 may be determined in various ways by combining the scan data DT1a and DT1b obtained by the ultrasound scans SC1 and SC2.

[0208] According to one example, the scanning data DT1a and DT1b are data directly combined by the determination device 30 to deduce the index S3 therefrom. To this end, the determination method applies a calculation function, for example denoted "f1", to the scanning data DT1a and DT1b to obtain the index S3. In other words, the function f1 is applied so that: f1(DT1a; DT1b)=S3.

[0209] According to another example, the determination device 30 performs a first processing on the scanning data DT1a and DT1b before determining the index S3. To this end, the device 30 applies, for example, functions f2 and f3 to the scanning data DT1a and DT1b to generate intermediate scores (or indexes) S1 and S2. In other words, the determination device 30 evaluates (or determines) the first score S1 ( Figure 8 E4a in FIG. 4 , and evaluate (or determine) a second score S2 ( Figure 8 Then, the determination device 30 may determine (E6) the score S3 from the first and second scores S1 and S2, for example by applying the function f4 to the intermediate scores S1 and S2.

[0210] The determination E6 of the indicator S3 is thus summarized as follows:

[0211] -f2(DT1a)=S1;

[0212] - f3(DT1b) = S2; and

[0213] -f4(S1;S2)=S3.

[0214] It is noted that the types of the intermediate scores S1 and S2 may vary according to the situation. In particular, each of the indicators S1 and / or S2 may include at least one of the following indicator types. In order to simplify the description of the present disclosure, in the following examples, it is considered that each of the first indicator and the second indicator S1 and S2 includes at least one indicator defined in the specific examples below.

[0215] According to one example, in E4( Figure 8) each includes a corresponding indicator defining the speed of sound, ie the speed of ultrasound waves propagating in the liver of the subject UR1 (or more specifically, in one or more sound-transmitted regions) during the corresponding ultrasound scans SC1 and SC2.

[0216] According to one example, in E4( Figure 8 Each of the indicators S1 and S2 determined in the ultrasonic scanning SC1 and SC2 includes a corresponding indicator defining a backscatter coefficient (i.e., a coefficient representing the backscatter level caused by the propagation of ultrasonic waves in the medium during the corresponding ultrasonic scanning SC1 and SC2). The backscatter coefficient is one of the physical parameters related to the ability of the medium under inspection to generate echoes propagating toward the ultrasonic probe.

[0217] According to one example, in E4( Figure 8 ) each comprises an indicator representing the ability of the tissues of the liver to deform in response to the mechanical stresses to which they are subjected.

[0218] According to one example, in E4( Figure 8 ) each of the indices S1 and S2 determined in ) comprises a corresponding index (or score) defining the viscoelasticity of the liver (ie a coefficient representing the viscous and elastic capacity of the liver).

[0219] According to one example, in E4( Figure 8 ) each of the indicators S1 and S2 determined in ) includes a corresponding scattering nonlinearity (or propagation nonlinearity) indicator (or score), i.e., an indicator representing the propagation nonlinearity of ultrasound waves in the medium (in the liver) during ultrasound scans SC1 and SC2.

[0220] According to one example, in E4( Figure 8 Each of the indices S1 and S2 determined in the ultrasound scans SC1 and SC2 comprises a corresponding scattering index (or score), i.e., an index representing the level of scattering caused by the propagation of ultrasound waves in the medium during the corresponding ultrasound scans SC1 and SC2. The scattering coefficient may define a scattering mean path (i.e., a "mean free path" in English), which depends on the ability of the tissue being insonified to generate echoes caused by multiple scattering phenomena.

[0221] The condition of the subject's liver can also be determined using the phenomenon of "speckle" in one or more ultrasound images. Ultrasonic speckle (sometimes also referred to as "interference pattern" or "spatter") in ultrasound images is a distinct granular or textural phenomenon caused by the coherence of ultrasound waves as they interact with structures of various sizes within tissue in the medium of interest. These granular patterns are the product of constructive and destructive superposition of ultrasound waves reflected by multiple scatterers within the tissue, which results in random variations in the intensity of the received signal. This feature can be used to extract information representative of the condition of the subject's liver, such as the texture of the observed tissue, its uniformity and / or other material properties.

[0222] Thus, according to one example, in E4( Figure 8 ) each of the indicators S1 and S2 determined in the first scanning data set DT1a and the second scanning data set DT1b comprises a corresponding ultrasonic speckle distribution indicator (or score) (or interference pattern distribution indicator). These indicators (also referred to as ultrasonic speckle statistical indicators) can characterize the ultrasonic speckle distribution indicators generated by the first scanning data set DT1a and the second scanning data set DT1b, respectively ( Figure 8 The invention relates to a method for determining the distribution of speckle phenomena (or, more simply, speckle or gray shades) in one or more ultrasound images of the present invention (steps E2 in step E2a). More specifically, based on the first scan data set and / or the second scan data set (steps E2a and E2b), B-mode ultrasound images may be generated, and for each image, the distribution of gray shades in the image may be determined. Thus, the statistical characteristics of the speckle may be represented in the form of at least one speckle statistical indicator and, where appropriate, used to assess the condition of the liver of the subject.

[0223] According to one example, the first score S1 is (or includes) a first attenuation coefficient, and the second score S2 is (or includes) a second attenuation score. Thus, the intermediate scores S1 and S2 represent the attenuation of ultrasound waves propagating in the medium (region of interest) during ultrasound scans SC1 and SC2, respectively. In this case, in E6 ( Figure 8 ) The indicator S3 determined from the combination of the scan data DT1a and DT1b (more specifically, by combining the scores S1 and S2) may define, for example, a biological indicator of the physiological and pathological condition of the liver.

[0224] The nature of the function f4 used by the device 30 to determine the indicator S3 from the intermediate scores S1 and S2 can be adjusted according to the circumstances.

[0225] According to one example, the indicator S3 is determined from the average of the first score S1 and the second score S2. For example, the average is determined by a linear combination of the first score and the second score S1 and S2. It may include a simple or weighted average. In other words, the indicator S3 may be calculated such that S3=aS1+bS2, wherein the setting of the weights a and b is independent of the values ​​of S1 and S2.

[0226] According to one example, the average value used to determine S3 is the least mean square average (also referred to as LSM average, LSM stands for “Least mean-square”) of S1 and S2.

[0227] According to one example, for determining ( Figure 8 E6) The average of S1 and S2 of the indicator S3 is a nonlinear combination of the scores S1 and S2. In other words, the indicator S3 can be calculated such that S3=aS1+bS2, where the weights a and b can vary according to the values ​​of S1 and S2. According to one example, for at least one value of the (S1, S2) pair, one of the weights a or b can be zero so that only the intermediate scores S1 or S2 with non-zero weights are selected and used to determine S3.

[0228] According to one example, a non-linear combination of scores S1 and S2 may be defined as f(S1, S2) or f(DT1a, DT1b), where f refers to a non-linear function.

[0229] Fig. 9 In the form of a cloud of points 62, it is shown that Figure 8 ), for the test subjects of the study conducted by the applicant and denoted as ET1, the intermediate score S1 is determined from the first scan data DT1a. Similarly, Fig.10 In the form of a cloud of points 66, it is shown that Figure 8 ), for the test object of study ET1, an intermediate score S2 is determined from the second scan data DT1b. In this example, the intermediate scores S1 and S2 define attenuation coefficients characterizing the attenuation of ultrasound waves propagating in the object UR1 during the first and second ultrasound scans SC1 and SC2.

[0230] From the points 62 and 66 ( Fig. 9 and Fig.10 ), linear regressions 62a and 66a are determined, respectively. These linear regressions 62a and 66a represent the overall evolution of the attenuation coefficients measured at the intercostal and subcostal locations, respectively, as a function of the estimated PDFF score for each patient.

[0231] As will become apparent after reading Study ET1, in this example, the performance achieved in the intercostal and subcostal ultrasound scanning configurations is similar. Based on the attenuation values ​​(index S3) obtained at the intercostal and subcostal locations (or patterns), the attenuation values ​​denoted as r and r are determined. 2 CF1 and r 2 CF2 The coefficient of determination is obtained. 2 CF1=0.51 and r 2 CF2 =0.50. The correlation coefficient reflects the correlation between the PDFF score and the attenuation index. If this coefficient is equal to 1, all points are located on the same line. Thus, in this case, in the subcostal configuration, a slightly higher correlation is obtained than in the intercostal configuration.

[0232] It should be noted that the coefficient of determination r 2 (which is also called Pearson's coefficient of linear determination) represents the quality of the linear regression prediction.

[0233] Fig.11 The index S3 determined (E6) for the group of test subjects evaluated during study ET1 is shown in the form of a cloud of points 70. The index S3 defines an attenuation index determined, respectively for each subject of study ET1, from a combination of the subcostal and intercostal attenuation coefficients for each subject of the group.

[0234] For reference, Fig.12 The distribution of PDFF scores of subjects of study ET1 determined by a technique different from the determination method described, namely by MRI imaging, is shown. Currently, the assessment of PDFF by MRI imaging is the reference for the prediction or diagnosis of hepatic steatosis. It is noted that in this case, this study ET1 covers subjects with a PDFF below the limit value, namely 25%.

[0235] like Fig.11 As shown, also from the corresponding in E6 ( Figure 8 ) for each test subject of study ET1, a linear regression 70a is determined. This linear regression 70a represents the overall evolution of the overall attenuation coefficient as a function of the PDFF of the subject. Advantageously, it can be noted in this example that for the linear regression 70a, the coefficient r is determined 2 (which reached 0.55) significantly improved. In other words, compared with the intercostal mode only ( Fig. 9 ) or in subcostal only mode ( Fig.10 ) compared to the results obtained in the linear regression 70a, the linear regression 70a has a better level of correlation with the overall attenuation coefficient S3 (compared to S1 and S2) of the PDFF of the object. For this example, this verifies the effectiveness of the determination method, which produces better results in terms of accuracy and reliability than using only one acquisition mode (intercostal or subcostal).

[0236] according to Figure 8In the example shown, once the indicator S3 is determined in E6, the determination device 30 evaluates (E10) the fat mass ratio (i.e. PDFF) of the liver 3 of the object UR1 according to the indicator S3. Afterwards, the device 30 may optionally compare (E12) the obtained PDFF with a reference value RF2, which is determined, for example, by MRI imaging technology or other technology.

[0237] Moreover, the first scanning data DT1a may be obtained before, simultaneously or after the second scanning data DT1b. In particular, the first ultrasound scan SC1 and the second ultrasound scan SC2 may be performed simultaneously, one after the other, in any order (SC1 before SC2 or SC2 before SC1), in the same scanning period or in different scanning periods.

[0238] According to one example, one of the set of first scan data DT1a and the second scan data DT1b is obtained from a scan performed according to a previous scan configuration (i.e., the so-called previous scan), and the other is obtained from a scan performed according to a subsequent scan configuration (i.e., the so-called subsequent scan), the previous scan being performed before the subsequent scan. The previous scan configuration is thus one of the first scan configuration CF1 and the second scan configuration CF2, and the subsequent scan configuration is the other of the first scan configuration CF1 and the second scan configuration CF2.

[0239] Therefore, in Fig.13 In the first example shown, the first scan is a first ultrasound scan SC1 implemented according to the first scan configuration (i.e., CF1), and the second scan is a second ultrasound scan SC2 implemented according to the scan configuration (i.e., CF2). For example, the first scan configuration is an intercostal configuration, and the second scan is a subcostal configuration (conversely, it is also possible).

[0240] According to a second example, the preceding scan is a second ultrasound scan SC2 performed according to the preceding scan configuration (ie, CF2), and the following scan is a first ultrasound scan SC1 performed according to the scan configuration (ie, CF1).

[0241] Thus, a prior scan can be performed, followed by a subsequent scan, for example during the same medical examination, or during different medical examinations at different times (for example during a first examination and then during medical monitoring). In particular, the determination method of the present disclosure can be performed in an incremental manner, so that the determination device 30 generates a first result (for example S1 or S2) from a set of scan data obtained from a prior scan, and then supplements this result with scan data obtained from a subsequent scan to obtain an overall indicator S3. In this way, it is advantageously possible to quickly obtain a first result about the condition of the liver 3 of the subject UR1, and then to improve this result with the help of a subsequent scan.

[0242] according to Fig.14In the example shown, a subsequent scan configuration (in this example, configuration CF2 of scan SC2) is selected (E25) for a subsequent scan from a first score S1 or a second score S2 (in this example, S1) obtained from a prior scan (in this example, SC1). Thus, the manner in which the subsequent scan is performed can advantageously be adjusted according to the results previously obtained for the prior scan. Depending on the results of the prior scan, it may be advisable to prefer a particular scan configuration to best guide the ultrasound observation.

[0243] according to Fig.15 In the example shown, the determination device 30 ( Figure 3 ) in determining step E6 ( Figure 8 ), a processing of the first scan data set DT1a and the second scan data set DT1b, or data obtained from these data DT1a and DT1b, is performed to determine the overall indicator S3. The processing is performed according to a processing model ML1, wherein the processing model ML1 is obtained using one (or at least one) neural network RN1 trained with training data DT0 and a reference score (or indicator, or value) RF0. To this end, the neural network RN1 may execute an algorithm based on an artificial intelligence module. The training data for training the neural network RN1 may include ultrasound scan data or data obtained from the ultrasound scan data.

[0244] according to Fig.16 In the example shown, prior to the above-described processing, the neural network RN1 is trained by machine learning during a training phase E40 to E46. During this training phase, the neural network RN1 obtains (E40) ultrasound scan data DT0a and DT0b representing waves propagating on the test object according to the first scan configuration CF1 and the second scan configuration CF2, respectively. Afterwards, the neural network RN1 determines (E42) training data DT0 from the ultrasound scan data DT0a and DT0b. These training data DT0 may include the scan data DT0a and / or DT0b themselves, or data obtained from these data DT0a and / or DT0b. The neural network RN1 also obtains (E44) a reference score RF0 representing the condition of the liver of the test object from MRI imaging performed on the test object. Thereby, the neural network RN1 can determine (E46) a processing model ML1 for estimating the indicator S3 from the combination of the first scan data DT1a set and the second scan data DT1b set by comparing the training data DT0 with the reference score RF0.

[0245] According to one example, in determining step E6 ( Figure 8), the determination device 30 successively executes a first algorithm and then a second algorithm to evaluate the condition of the liver 3 of the object UR1. The first algorithm is an estimation algorithm configured to determine the overall attenuation coefficient S3 from a set of first scan data DT1a and a set of second scan data DT1b obtained in intercostal and subcostal modes, respectively. For example, the first estimation is achieved by averaging the attenuation coefficients S1 and S2 obtained intercostally or subcostally as described above. The second algorithm is executed by a neural network (e.g., network RN1) to estimate the PDFF of the liver 3 of the object UR1 from the overall attenuation coefficient S3, for example from the model ML1 or from a linear regression as described above. Thus, the statistical model used in the second algorithm can associate the overall indicator S3 (which represents, for example, at least one of the above-mentioned parameters: attenuation coefficient, speed of sound, etc.) with the estimate of the PDFF at the output.

[0246] According to an example, the determination device 30 may implement a neural network RN1 to generate a model ML1 that relates, at input, on the one hand, an ultrasound image obtained from ultrasound scans SC1 and SC2 and, at output, an indicator S3 or PDFF.

[0247] Advantageously, the determination method and device disclosed herein allow for reliable and efficient determination of the condition of the liver of a subject, which may be healthy or have any physiological or pathological condition of the liver. To this end, the concept of the present disclosure is based on a combination of scan data (or ultrasound data) obtained according to two different scan configurations, namely according to a first scan configuration CF1 for the liver and a second scan configuration CF2 for the liver or another tissue set of the subject, respectively. Advantageously, the combination of these scan data allows obtaining an indicator S3 representing the condition of the liver of the subject in a more robust manner than when only one scan configuration is used.

[0248] The combination of two different acquisition modes, such as intercostal and subcostal positions (modes), advantageously allows to improve the quality of the acquired data (with different types of data) compared to conventional techniques that would only take into account ultrasound data acquired in intercostal mode. The ultrasound data thus obtained are less correlated with each other. Advantageously, the use of two different scanning configurations allows to diversify the measurements and thereby enhance the reliability and accuracy of the results.

[0249] Moreover, in the case of, for example, hepatic steatosis, all areas of a subject's liver may be affected in different ways. Thus, some cases of non-uniform steatosis have been noted. The addition of ultrasound scanning according to different scanning configurations allows obtaining a more representative estimate of the overall condition of a subject's liver.

[0250] Thus, the present disclosure can advantageously assist in diagnosing or monitoring certain physiological and pathological conditions of the liver, such as hepatic steatosis (eg, NASH-type), steatohepatitis, and the like.

[0251] As those skilled in the art will appreciate, all of the above embodiments and variations (some of which have been intentionally simplified to make them easier to explain) constitute only non-limiting exemplary embodiments of the present invention. In particular, those skilled in the art may consider adjusting or combining the above embodiments and variations to address specific needs.

[0252] Therefore, the present disclosure is not limited to the above-described embodiments, but specifically covers the manipulation method which will include the secondary steps without departing from the scope of the present disclosure. The same applies to the manipulation system used to implement the method.

Claims

1. A method for determining the condition of a liver (3) of a subject (UR1), the method comprising: - acquiring (E2a) a first set of scan data (DT1a) from ultrasound waves propagated according to a first scan configuration (CF1) of the liver; - acquiring (E2b) a set of second scan data (DT1b) from ultrasound waves propagated in a second scan configuration (CF2) according to a set of tissues (5) of the subject; - determining (E6) an indicator S3 representative of the condition of the liver (3) by combining the first scan data set and the second scan data set.

2. The method of claim 1, wherein: The set of tissues (5) of the subject corresponds to parts other than the liver (3) of the subject.

3. The method of claim 1, wherein: - said first scanning configuration (CF1) is an intercostal scanning configuration of the liver; and - The second scanning configuration (CF2) is a subcostal scanning configuration of the liver.

4. A method according to any one of the preceding claims, comprising: - Comparing said indicator S3 with a reference value (RF1).

5. A method as claimed in any one of the preceding claims, wherein: The method comprises: - from said first set of scan data (DT1a), evaluating (E4a) a first score (S1); and - from said second set of scan data (DT1b), evaluating (E4b) a second score (S2); The indicator S3 is determined based on the first score and the second score.

6. The method of claim 5, wherein: The first indicator S1 and / or the second indicator S2 includes at least one of the following: - Indicators defining the attenuation coefficient; - Indicators that limit the speed of sound; - Indicators that define the backscatter coefficient; -Indicators of liver elasticity; - Indicators defining the viscoelastic properties of the liver; - indicators of propagation nonlinearity; - an indicator of ultrasonic scattering; and -Indicators of ultrasonic speckle distribution.

7. The method of claim 5 or 6, wherein: - said first fraction (S1) is a first attenuation coefficient; and - said second fraction (S2) is a second attenuation coefficient; The index S3 defines a biological index of the physiological and pathological condition of the liver.

8. The method of claim 7, wherein: deriving one of the first set of scan data (DT1a) and the second set of scan data (DT1b) from a scan configured according to a prior scan, the so-called prior scan, and deriving the other from a scan configured according to a subsequent scan, the so-called subsequent scan, the prior scan being performed before the subsequent scan; The preceding scanning configuration is one of the first scanning configuration (CF1) and the second scanning configuration (CF2), and the succeeding scanning configuration is the other of the first scanning configuration and the second scanning configuration.

9. The method of claim 8, wherein: The subsequent scan configuration is selected from a first score (S1) or a second score (S2) obtained by the prior scan.

10. The method according to any one of claims 6 to 9, wherein: The indicator S3 is determined from an average of the first score (S1) and the second score (S2).

11. The method of claim 10, wherein: The average value is determined by a linear combination of the first score (S1) and the second score (S2).

12. The method of claim 11, wherein: The average is the least square mean.

13. The method of claim 10, wherein: The average value is determined by a non-linear combination of the first score (S1) and the second score (S2).

14. The method of claim 13, wherein: Determining the indicator S3 includes: - processing said first set of data (DT1a) and said second set of data (DT1b), or data obtained from said first set of data and said second set of data, according to a processing model obtained using a neural network (RN1), said neural network being trained using training data (DT0) and reference scores (RF0), The training data comprises ultrasound scan data or data obtained from the ultrasound scan data.

15. The method of claim 14, wherein: Prior to said processing, said neural network (RN1) is trained by machine learning during a training phase, said training phase comprising: - obtaining (E40) ultrasound scanning data representative of waves propagating on the test object according to said first scanning configuration and said second scanning configuration; - determining (E42) said training data from said ultrasound scan data; - obtaining (E44) a reference score representative of the condition of the liver of the test subject from the MRI imaging performed on the test subject; and - determining (E46) a processing model (ML1) for estimating said indicator S3 from a combination of said first scan data set and said second scan data set by comparing said training data with said reference score.

16. A method as claimed in any one of the preceding claims, wherein: The method comprises: - From the index S3, the fat mass ratio of the subject's liver is evaluated.

17. A computer program (PG1) comprising instructions for implementing the method as claimed in any one of the preceding claims when the instructions are executed by a processor.

18. A device (30) for determining the condition of a liver (3) of a subject (UR1), the device comprising: - a first acquisition module (MD2) configured to acquire a first set of scan data from ultrasound waves propagated according to a first scan configuration of the liver; - a second acquisition module (MD4) configured to acquire a second set of scan data from ultrasound waves propagated according to a second scan configuration of a set of tissues of the subject; as well as An analysis module (MD6) configured to determine an indicator S3 representative of the condition of the liver by combining the first scan data set and the second scan data set.

19. A system (SY2) for determining a condition of a subject's liver, comprising: - A determination device (30) as claimed in claim 18; as well as - an ultrasound system (SY1) coupled to said determination device.

Images