Method and device for determining liver state of subject

Abstract

To provide a method and a device for determining a liver state of a subject.SOLUTION: The present invention is related to a method and a device (10) for determining a state of the liver (3) of a subject (UR1). The method includes: acquiring scan data (DT1a) of a first group from an ultrasonic wave (W) propagating according to a first scan configuration (CF1) of the liver; acquiring scan data (DT1b) of a second group from the ultrasonic wave (W) propagating according to a second scan configuration (CF2) of a group of tissues of the subject; and determining an index S3 showing the state of the liver by a combination of scan data (DT1a and DT1b) of the first and second groups.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to methods and apparatus for determining the liver status of a subject. [Background technology]

[0002] The present disclosure relates to determining the liver status of a subject, such as a human or animal, and particularly, but not exclusively, covers aiding in the screening or diagnosis of liver disorders such as non-alcoholic hepatic steatosis (NASH), also known as non-alcoholic fatty liver disease (NAFLD) or non-alcoholic steatohepatitis (NASH).

[0003] Fatty liver is a liver disorder characterized by the accumulation of fat in hepatocytes. Fatty liver has numerous causes, including in particular alcohol and metabolic syndrome. Nonalcoholic fatty liver, so-called NASH, affects people who do not drink alcohol excessively. If more than 5% of liver cells contain lipid droplets, we can speak of pathological fatty liver. Simple fatty liver, so-called steatosis, is generally benign and therefore does not result in significant damage to the liver. On the other hand, this condition could develop into more serious disorders, such as nonalcoholic steatohepatitis, so-called NASH, which corresponds to an aggressive disease characterized by the appearance of inflammation in the liver parenchyma. Steatohepatitis itself can cause the accumulation of scar tissue (fibrosis), which can possibly lead to a potentially serious disease of the liver, namely cirrhosis.

[0004] Fatty liver disease, especially NASH, has recently been considered a major public health concern worldwide. Currently, about 2 million new cases of liver disease are identified every year all over the world. It is expected that the prevalence of NAFLD and NASH will increase by 21% and 63% between 2015 and 2030, respectively. This liver condition is related to behavioral (physical activity, diet) and genetic factors. In particular, it affects overweight or obese people. Research has demonstrated that nonalcoholic fatty liver disease increases the overall morbidity and the morbidity related to cardiovascular conditions, and can lead to various pathologies, especially liver damage, tumor formation, etc. [Prior art documents] [Non-patent literature]

[0005] [Non-Patent Document 1] 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 Fraction as Reference: A Prospective Comparison of Three US Machines. Radiology, 305(2), 353-361. https: / / doi.org / 10.1148 / radiol.212846. Summary of the Invention [Problem to be solved by the invention]

[0006] However, fatty liver is a relatively slow reversible process, and it can be effectively treated, especially through better diet, and more generally through better health practices, if it is taken care of early.Therefore, it is important to be able to screen and diagnose fatty liver cases, especially NASH, as early as possible.However, although there are currently several different techniques for diagnosis, and more generally for monitoring the condition of the liver, they do not always provide satisfactory results.

[0007] MRI examination is currently one of the standard non-invasive methods for assessing the condition of the liver, and in particular for diagnosing and quantifying fatty liver. In particular, it allows a uniform and non-invasive examination of the entire liver. Thus, thanks to this technique, the total value of the fat fraction of the liver can be determined, which is the so-called Proton Density Fat Fraction (PDFF). However, this technique has some limitations and restrictions, such as requiring equipment and skills that are not yet widely available (due to issues such as cost, manufacturing complexity, scarcity, maintenance, training, etc.), and may even require complex settings, which makes it almost unsuitable for any examination of the liver, especially for routine examinations for large-scale monitoring of cases, possibly well before the manifestation of potential diseases, since these pathologies are often potentially reversible if detected early enough, so that subjects can benefit from upstream treatment.

[0008] Although liver biopsy is also the standard technique for this type of medical monitoring and diagnosis, it has significant risks and limitations, especially due to its potential lack of reliability related to the inherently very local nature of this test.Therefore, this technique may result in diagnostic errors, especially if the biopsy does not target the liver in its most affected part.It should also be noted that due to its invasive nature, liver biopsy may result in substantial serious complications, such as bleeding.In addition to the issues of reliability and possible complication risks, biopsy has a high cost, both financially and in terms of the time spent by the subject and medical staff.

[0009] Ultrasound technology has been proposed for the non-invasive diagnosis of fatty liver, in particular for NASH in several different stages. Nevertheless, contrary to its efficiency, as is very often demonstrated, this examination technique can sometimes be poorly mastered nowadays, and therefore it does not always provide satisfactory results, in particular in terms of relevance, accuracy and reliability of the data acquired and processed. One limitation of this technique is the strong dependency of the relevance of the results on the skill of the echographer. This can be explained in particular by the fact that this technique is based on an anatomical and qualitative approach and requires the implementation of a large number of parameters, which makes the evaluation of the results more subjective and therefore more difficult, since it depends on the user. This dependency on the user becomes critical if the latter is not well trained and / or does not have enough time to perform the examination in good condition. [Means for solving the problem]

[0010] One of the aims of the present invention is to address at least one of the above problems or shortcomings.

[0011] In particular, it may be desirable to perform an accurate and reliable determination (or assessment) of the liver condition of a subject or patient, such as a human subject.

[0012] In particular, it may be desirable to assess the status of a subject's liver for early screening of dysfunction or symptoms thereof, or to diagnose liver damage, such as fatty liver, in particular non-alcoholic fatty liver (or steatohepatitis) (NASH) or non-alcoholic steatohepatitis (NASH).

[0013] To this end, according to a first aspect, the present disclosure relates to a method for determining a liver status of a subject, said method comprising: - acquiring a first group of scan data from ultrasound propagating according to a first scan configuration of the liver; - acquiring a second group of scan data from ultrasound waves propagating according to a second scan configuration of a group of tissues of the subject; - determining an index S3 representative of the condition of the liver by combining the scan data of the first and second groups.

[0014] The method according to the invention may also comprise other features which may be taken separately or in combination, in particular of the following embodiments, which are described purely by way of example and which may be combined or associated, unless otherwise stated.

[0015] According to one example, the group of tissues of the subject corresponds to parts of the subject other than the liver.

[0016] According to one example, the method comprises: - the first scan configuration is an intercostal scan configuration of the liver; The second scan configuration is made to be a subcostal scan configuration of the liver.

[0017] According to one example, the method comprises: - Comparing the indicator S3 to a reference value.

[0018] According to one example, the method comprises: - assessing a first score (S1) from the scan data of the first group; - assessing a second score (S2) from the scan data of the second group; An index S3 is determined from the first and second scores.

[0019] According to one example, the first index S1 and / or the second index S2 are: - an indicator that defines the damping coefficient, - an indicator that defines the speed of sound, - an indicator defining the backscatter coefficient, - the above-mentioned indicators of liver elasticity, - an index defining the viscoelasticity of the liver, - a measure of propagation nonlinearity, - an indication of ultrasound scattering, and - Ultrasound speckle distribution index Includes at least one of the following:

[0020] According to one example, the method comprises: - the first score is the first damping factor, the second score is made to be the second attenuation factor, Indicator S3 defines a biomarker of the physiopathological state of the liver;

[0021] According to one example, one of the first and second groups of scan data is obtained from a scan according to a pre-scan configuration, a so-called pre-scan, and the other is obtained from a scan performed according to a post-scan configuration, a so-called post-scan, the pre-scan being performed before the post-scan; The pre-scan configuration is one of the first and second scan configurations, and the post-scan configuration is the other of the first and second scan configurations.

[0022] According to one example, the configuration for the post-scan is selected from among the first or second scores obtained from the pre-scan.

[0023] According to one example, the indicator S3 is determined from the average of the first and second scores.

[0024] According to one example, the average is determined by a linear combination of the first and second scores S1, S2.

[0025] According to one example, the average is the least mean squared average.

[0026] According to one example, the average is determined by a non-linear combination of the first and second scores S1, S2.

[0027] According to one example, the determination of the indicator S3 is - processing the first and second groups of data or processing data obtained from the first and second groups of data according to a processing model obtained using the neural network trained from the training data and the reference scores; The training data may include ultrasound scan data or may include data derived from the ultrasound scan data.

[0028] According to one example, prior to processing, the neural network is trained by machine learning during a training phase, The training phase is - acquiring ultrasound scan data representative of waves propagating according to first and second scan configurations in a test subject; - determining training data from the ultrasound scan data; - obtaining a baseline score representative of a liver condition of the test subject from the MRI imaging performed on the test subject; - determining a processing model to be used to estimate the measure S3 from the combination of the scan data of the first and second groups by comparing the training data against a reference score.

[0029] According to one example, the method comprises: - from indicator S3, which includes assessing the subject's liver to body fat ratio.

[0030] According to a second aspect, the present disclosure may be implemented by (or may relate to) a computer program comprising instructions that contribute to carrying out the method according to the first aspect when the program is executed by a computer. In particular, different steps of the method according to the first aspect may comprise computer program instructions.

[0031] Such computer program may use any programming language or equivalent and it may have the form of source code, object code, or an intermediate code between source code and object code, such as a partially compiled form, or any other desired form.

[0032] According to a third aspect, the present disclosure relates to a recording medium (or an information medium) readable by a computer (or a processor) and having recorded thereon a computer program according to the second aspect of the present disclosure.

[0033] On the one hand, the recording medium may be any entity or device capable of storing a program, such as at least one volatile and / or non-volatile memory. For example, the medium may comprise a storage means such as a rewritable non-volatile memory, a ROM, a CD-ROM, or a ROM of the microelectronic circuit type, or a magnetic recording medium, or a hard disk. This memory may comprise, for example, a graphics card (or video card) memory, this type of memory being especially designed to process image data (or video data).

[0034] On the other hand, the recording medium may be a transmissible medium, such as an electrical or optical signal, such as a signal that can be transmitted via electrical or optical cable, via conventional or Hertzian radio, by a self-emitting laser beam, or by other means. The computer program according to the invention may in particular be downloaded locally or otherwise, using a wired or wireless network (e.g. Bluetooth, Wi-Fi, Ethernet, Internet, 4G, 5G or others).

[0035] Alternatively, the recording medium may be an integrated circuit in which the computer program is embedded, the integrated circuit being capable of performing, or usable for performing, the methods described.

[0036] According to a fourth aspect, the present disclosure relates to a decision device (or monitoring device) configured to determine a liver status of a subject by implementing the decision method according to the first aspect of the present disclosure. To this end, the decision device may comprise modules configured to respectively implement a number of different steps of the method according to the first aspect of the present disclosure.

[0037] According to one example, the decision device comprises a memory associated with a processor, the memory comprising a computer program according to the second aspect of the present disclosure.

[0038] According to one example, an apparatus for determining a liver status of a subject includes: - a first acquisition module configured to acquire a first group of scan data from ultrasound waves propagating according to a first scan configuration of the liver; - a second acquisition module configured to acquire a second group of scan data from ultrasound waves propagating according to a second scan configuration of a group of tissues of the subject; - an analysis module configured to determine an index S3 representative of the state of the liver by a combination of the first and second groups of scan data.

[0039] According to an embodiment, the invention is implemented by software and / or hardware components. In particular, the decision making device may comprise modules configured to perform the steps of the method according to the first aspect of the present disclosure. Thus, the different embodiments and associated advantages mentioned herein in relation to the method according to the first aspect of the present disclosure may equally apply to the decision making device according to the fourth aspect of the present disclosure.

[0040] In this respect, the term "module" may correspond in this disclosure to a software component, a hardware component, or a set of hardware and software components, where a software component corresponds to one or more computer programs, one or more subprograms of a program, or more generally, any element of a program or software capable of implementing a function or a set of functions according to what is described below with respect to the module considered.

[0041] Similarly, a hardware component corresponds to any element of hardware configured to perform a function or a set of functions according to what is described below with respect to the modules considered.

[0042] According to a fifth aspect, the present disclosure relates to an apparatus for determining a liver status of a subject, the system comprising: a determination device according to a fourth aspect of the present disclosure; an ultrasound system connected to the determining device.

[0043] Advantageously, the disclosed method and device for determining allows to determine the liver status of a subject, healthy or having any physiopathological condition of the liver, in a reliable, repeatable and effective manner. To do so, the present disclosure is based on the combination of scan data (or ultrasound data) acquired according to two separate scan configurations, namely a first scan configuration CF1 targeting the liver and a second scan configuration CF2 targeting the liver or a group of other tissues of the subject. Advantageously, the combination of these scan data allows to obtain an index S3 representative of the liver status of the subject considered in a more reliable and robust manner than if only one scan configuration was used.

[0044] The method and device thus involve obtaining scan data according to a number of different scan configurations. In the context of the present disclosure, a scan corresponds to a sonographic (or ultrasound) scan, a sonographic (or ultrasound) observation, or a phase of sonographic (or ultrasound) observation. Such a scan comprises the propagation of ultrasound waves in a medium, i.e. in the subject being examined, and the recovery of echographic (or ultrasound) echoes, which are returned and which are representative of the condition of the liver of the subject. Each scan makes it possible to obtain (or generate) scan data representative of one or more target regions (or one or more areas of interest) of the subject.

[0045] The target area or areas of a subject that are examined (or scanned) by ultrasound during an ultrasound examination scan depend on the scan configuration used. Various parameters may define this configuration, including in particular the orientation and / or position of the emitter device during the ultrasound examination scan.

[0046] The combination of two separate acquisition modes, for example the intercostal and subcostal modes, advantageously allows to improve the relevance of the acquired data compared to the prior art, where only ultrasound data acquired in the intercostal mode are considered. The ultrasound data that can be so acquired are more representative of the liver condition. Advantageously, the use of two separate scanning configurations allows to diversify the measurements and therefore improve the reliability and accuracy of the results.

[0047] Furthermore, for example, in the case of fatty liver, all areas of the subject's liver may be affected in multiple different ways. Thus, several cases of heterogeneous steatosis have been noted. Multiplying the ultrasound scans according to multiple different scan configurations allows obtaining a more representative estimate of the overall condition of the subject's liver.

[0048] Thus, the present disclosure may advantageously provide assistance in the diagnosis or monitoring of any physiopathological condition of the liver, such as fatty liver (e.g. of NASH type), inflammatory steatosis, etc. [Brief description of the drawings]

[0049] [Figure 1] 1 illustrates a schematic diagram of an intercostal scanning configuration for an ultrasound scan of a subject's liver, in accordance with certain embodiments. [Diagram 2] 1 is an ultrasound image showing the display of shadowed areas during an ultrasound examination of a subject's liver in intercostal acquisition mode. [Diagram 3] 1 illustrates a schematic diagram of a determination device and an ultrasound system according to an embodiment of the present disclosure. [Figure 4] 1 illustrates a schematic diagram of an ultrasound system according to an embodiment of the present disclosure. [Diagram 5] 1 illustrates a schematic diagram of a decision device according to an embodiment of the present disclosure; [Figure 6] 1 illustrates a schematic diagram of a scanning configuration for performing an ultrasound scan, according to an embodiment of the present disclosure. [Figure 7]1 illustrates a schematic diagram of a scanning configuration for performing an ultrasound scan, according to an embodiment of the present disclosure. [Figure 8] 4 illustrates a schematic diagram of a decision-making method performed by the decision-making device of FIG. 3 according to an embodiment of the present disclosure. [Figure 9] 13A-13C are schematic diagrams illustrating results obtained in an intercostal acquisition mode, according to an embodiment of the present disclosure; [Figure 10] 13A-13C are schematic diagrams illustrating results obtained in a subcostal acquisition mode, according to an embodiment of the present disclosure; [Figure 11] 11A and 11B show schematic diagrams of results obtained according to a determination method by combining the results of FIGS. 9 and 10, according to an embodiment of the present disclosure; [Figure 12] 13A-B show schematic diagrams of the distribution of subjects' liver PDFF scores during a study validating the efficiency of a determination method according to an embodiment of the present disclosure. [Figure 13] 2 illustrates a schematic diagram of a determination method according to an embodiment of the present disclosure. [Figure 14] 2 illustrates a schematic diagram of a determination method according to an embodiment of the present disclosure. [Figure 15] 4 illustrates a schematic diagram of a neural network implemented by the decision device of FIG. 3 according to an embodiment of the present disclosure. [Figure 16] 16 illustrates a schematic diagram of a training phase performed by the neural network of FIG. 15 according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0050] The characteristics and advantages of the present invention will become more apparent on reading the following description, given purely by way of non-limiting example, with reference to the accompanying drawings, in which: In particular, the embodiments shown in the drawings may be combined together, unless otherwise mentioned or in obvious contradiction.

[0051] Other features and advantages of the present disclosure will become apparent from the following description of non-limiting embodiments of the present disclosure, taken in conjunction with the accompanying Figures 1 to 16.

[0052] The present disclosure particularly covers devices and methods for determining the liver status of a subject, for example for screening campaigns, medical monitoring or diagnostic assistance.

[0053] It is known to carry out an examination of a subject's liver by ultrasound examination, in particular to screen or diagnose liver disorders, such as fatty liver (for example of NAFLD type) or steatohepatitis of NASH type. Relying on this technique is advantageous, in particular due to its non-invasive nature, the relative availability in the field of ultrasound examination devices for medical examinations, the ease of transporting them when necessary, and the lower investment and examination costs and risks, compared to, for example, MRI and biopsy.

[0054] Nevertheless, the relevance of the results of this testing technique depends to a large extent on the level of qualification of the practitioner, and this testing technique is still in its infancy and does not always provide satisfactory results, especially in terms of performance and reliability. These challenges may have several origins, as explained below.

[0055] As shown in Figure 1, a widely established practice worldwide is currently to perform such ultrasound examinations of the liver according to the so-called "intercostal" scanning configuration shown as SCx (Figure 1), i.e. by positioning the ultrasound probe such that the ultrasound propagates between the subject's ribs 2 and returns recovering ultrasound echoes representative of the subject's liver 3. To do so, the ultrasound probe, possibly coated with a suitable gel, is placed against the subject's skin at the level of his / her rib cage, so as to scan "over the ribs", i.e. between the ribs.

[0056] This intercostal scanning configuration is considered the most reliable, especially due to the fact that the subject's ribs protect the tissues below and thus make it possible to limit deformations that may occur when the probe touches the patient. Indeed, such deformations may distort the results of the observations, and compressed tissues have different behaviors. The intercostal configuration is also preferred to the extent that it facilitates examination, especially for some subjects that are difficult to examine (especially those with high subcutaneous fat levels). The ultrasound technician may take the subject's ribs as a reference to set the probe of the ultrasound examination system in the best orientation and position.

[0057] For reasons particularly mentioned above, clinical studies currently recommend employing an intercostal scanning configuration for performing liver examinations, particularly for screening or diagnosing liver disorders such as those mentioned above.

[0058] However, it has been noted that ultrasound examination of the liver with the intercostal technique poses some challenges and implies limitations that must be addressed. In particular, the appearance of shadow areas 8 in ultrasound examination images 7 acquired with the intercostal scanning configuration has been observed, as shown by way of example in FIG. 2. These dark areas 8 that impede the observation are explained by the generally convex shape of the ultrasound probe, which does not always allow the latter to make full contact with the subject's skin during the examination, in particular due to the subject's ribs forming irregularities that hardly fit the shape of the probe. Non-contact areas between the probe and the subject's skin during ultrasound examination may impede the propagation of ultrasound waves and result in the formation of these areas 8 that appear dark in the image.

[0059] Nevertheless, it is difficult and undesirable to modify the shape of the probe to better match the profile of the rib, especially since the current configuration is designed to maximize the field of view of the ultrasound inspection system and ensure some versatility of the probe, thereby allowing the latter to be adapted to perform a variety of ultrasound examinations.

[0060] In addition to the aforementioned problems with shadowed areas, ultrasound examination of the liver with conventional intercostal scanning configurations generally suffers from sometimes unsatisfactory results, and it has been noted that the assessment of some liver properties, such as some biomarkers, is not always sufficiently effective or reliable for such use.

[0061] The present disclosure therefore aims to provide a solution, in particular to the problems and shortcomings mentioned above, allowing to determine the liver status of a subject, such as a human or animal, or more generally of a living organism, with greater reliability and better performance, for example, in particular, but not exclusively, to aid in the screening or diagnosis of liver disorders, or more generally to assess the liver status of the subject. In particular, the solution is based on a method and an apparatus for determining the liver status of a subject.

[0062] A determination method and a determination apparatus (also referred to as "method" and "apparatus") are described below according to certain embodiments of the present disclosure with reference to Figures 3 to 16. Unless otherwise noted, common or similar components in several drawings have the same reference numbers, have the same or similar features, and for brevity, generally these common components will not be described again.

[0063] The term "first" (or "first, second", etc.) is used herein by any convention to enable different components (e.g., operations, devices, etc.) implemented or used in the embodiments described below to be identified or distinguished.

[0064] As shown in FIG. 3, an embodiment of the present disclosure is described below by way of example, in which the liver 3 of a subject UR1 is observed by ultrasound examination with an ultrasound system denoted SY1. To do so, ultrasound waves W are emitted by the ultrasound system SY1 in several different regions (or areas of interest) of the subject UR1 to obtain ultrasound data representative of the state of the liver 3. This observation includes several sonographic scans, i.e. several phases during which ultrasound waves propagate and are returned, and ultrasound echoes representative of the state of the liver 3 are restored. In other words, during each scan, incident ultrasound waves are irradiated onto one or more regions of the liver, and the returned backscattered echoes from these regions of the liver are captured by the ultrasound probe. We then use the terms "scan", "sonographic (or ultrasound) scan", "sonographic (or ultrasound) observation", "sonographic (or ultrasound) observation phase", or "acquisition phase" interchangeably.

[0065] In the embodiment considered, the subject is a living organism, i.e. a mammal, such as a human being. Nevertheless, it should be noted that the concepts of the present disclosure are more generally applicable to any subject, (human or animal), living or dead, having a liver, in which the condition of the liver is to be evaluated.

[0066] It should be noted that the subject UR1 used to explain the present disclosure may have a body in any physiological state, particularly at the level of the liver. In particular, the liver 3 of the subject may be healthy (e.g., free of specific liver disorders) or may be affected by any liver disorder or pathology.

[0067] The disclosed method and device are based in particular on obtaining two groups of data relating to the same subject, each from ultrasonic waves W propagating during an ultrasound scan, according to a number of different scan configurations, at least one of which is a liver scan configuration, and on combining these two groups of data to determine an index, denoted S3 (also called global index, global score or parameter), representative of the condition of the liver 3 of the subject UR1. Advantageously, combining these two groups of data makes it possible to determine an index representative of the condition of the liver of the subject.

[0068] In this disclosure, a liver scan configuration refers to a scan configuration used in acquiring ultrasound data representative of a subject's liver, or in other words, a sonography scan performed by a liver scan configuration probes (or is aimed or targeted at) at least in part at the subject's liver so as to acquire sonography data representative of said liver.

[0069] According to some embodiments, the method of determining - acquiring a first group of scan data from ultrasound propagating according to a first scan configuration of the liver; - acquiring a second group of scan data from ultrasound waves propagating according to a second scan configuration of a group of tissues of the subject; - determining an index S3 representative of the condition of the liver by combining the scan data of the first and second groups.

[0070] 3, in the following, a number of different ultrasound examination scans (or observations), i.e. a first scan SC1 and a second scan SC2, performed by an ultrasound system SY1 on the subject UR1 according to a number of different scan configurations (or modes), denoted CF1 and CF2, respectively, are considered to determine the state of the liver 3 of the subject UR1. The scan configurations CF1 and CF2 may vary, in particular with regard to the scan direction and / or position with respect to the subject, to the extent that these configurations may differ slightly from one another or more generally.

[0071] The determining device (also referred to as processing device) 30 is further configured to acquire and process scan data (or ultrasound data) DT1a and DT1b generated by the ultrasound system SY1 from the first and second scans SC1 and SC2 (FIG. 3), respectively. To do so, the determining device 30 cooperates (is connected) with the ultrasound system SY1 to implement a determining method according to at least one particular embodiment.

[0072] As shown in FIG. 3, the determining device 30 and the ultrasound system SY1 together form a determining system (or analysis system) SY2, which is configured to determine the liver status of a subject.

[0073] According to one example, the determining device 30 is an integral part of the ultrasound system SY1. According to one variant, the determining device 30 is external to (separate from) the ultrasound system SY1.

[0074] The system SY1 may be a medical ultrasound system, and thus the emitter device 20 may be (or may be at least partially part of) a medical and / or ultrasound probe.

[0075] The embodiment of ultrasound system SY1 is described here for illustrative purposes only.

[0076] 3 shows a schematic representation of an embodiment of an ultrasound system SY1 comprising a control device (or steering device) 10 and an emitter device 20. The control device 10 is configured to steer the emitter device 20. The emitter device 20 is configured to emit and receive ultrasound waves W towards the medium to be studied, i.e. the subject UR1 in the example considered, under the control of the control device 10.

[0077] According to a particular embodiment, the whole or part of the decision making device 30 is part of the control device 10. According to one example, the devices 10 and 30 form the same device.

[0078] For example, the emitter device 20 is an ultrasound transducer device (or ultrasound probe) configured to emit and / or receive ultrasound waves W. For example, this emitter device 20 is included in an ultrasound probe intended to be in contact with a subject UR1 during an ultrasound examination scan for determining the condition of the liver 3 of the subject.

[0079] It should nevertheless be noted that various configurations of the radiator device 20 are possible. In particular, all or part of the control device 10 may be implemented in the radiator device 20 (e.g. in the probe). All or part of the control device 10 may be external to the radiator device 20 (or the probe).

[0080] The control system 10 may in this embodiment comprise a processing device (or module) 11 and a control device (or module) 12. The control device 12 (also called power control device) is configured to steer the emitter device 20 by means of electrical signals exchanged (or transmitted) between the system 10 and the transducer device 20. The control device 12 thus generates electrical signals, which are transmitted to the transducer device 20 and cause said transducer device 20 to emit ultrasonic waves W1 in the direction of an area of ​​interest located on the subject UR1. The electrical signals SG1 thus generated represent (or define) the ultrasonic waves W1 to be projected on the medium. For this purpose, the control device 12 may for example consist of or comprise at least one electronic pulser, also called "pulser".

[0081] The control device 12 may possibly comprise a receiver device or receiver circuitry (not shown) configured to receive the electrical signals emitted from the transducer device 20 .

[0082] The processing device 11 may be configured to control, for example by controlling electrical signals, the control device 12. For example, the processing device 11 may consist of or comprise at least one processor.

[0083] According to one example, the processing device 11 and / or the pilot device 12 are included in a main body 31 (central component) of a system SY1 exemplarily shown in FIG.

[0084] More specifically, the processing device 11 may be configured to control the electrical signals generated by the control device 12. The processing device 11 may also be configured to process (and / or interpret) electrical signals that may be emitted from the emitter device 20 and received by the control device 12. These signals SG1 represent waves W2 emitted from the subject UR1 and received by the transducer device 20 (FIG. 3). For example, these waves W2 form one or more ultrasound echoes, i.e. the response of the studied medium (i.e. the liver of the subject UR1) to ultrasound waves emitted in the direction of said medium. The processing performed by the processing device 11 on the received signals varies depending on the case and may include, for example, at least any one of the following signal amplification, filtering, digitization and conditioning operations.

[0085] In the present disclosure, the term "medium" refers to one or more areas (or regions) of interest of the subject UR1, i.e. areas that are irradiated or examined by ultrasound, i.e. areas of interest corresponding to areas of interest in the liver 3 and possibly other parts of the subject UR1.

[0086] 3, the emitter device 20 may comprise, for example, one or more ultrasonic transducers (also referred to as transducer elements) 22, each configured to convert an electrical signal received from the control device 10 into ultrasonic waves (and possibly vice versa). The transducers 22 may thus be configured to emit a wave (or ultrasonic impulse, or ultrasonic beam) W1 in the medium, which corresponds to a radiating action.

[0087] The transducers 22 may also be configured to receive ultrasound signals W2 emanating from one or more areas of interest of the subject UR1 during a receiving operation, possibly in response to the transmitted waves W1 for example. These received signals W2 may have the form of a set of echo signals backscattered in response to the previously emitted signals W1. For example, each transducer 22 may convert the received echo signals W2 into an electrical signal. The signals may then be processed by the control device 10 (for example by the processing device 11) or by any associated (dedicated) system, which may or may not be directly connected. For example, the signals W2 may be amplified, filtered, digitized and / or signal conditioning operations may be performed. The transducer elements may be arranged according to a row of transducers, an array, or a network of transducers, or any other configuration.

[0088] It should be noted that one or more of the same transducers 22 may be used to emit the waves (or impulses) W1 and, where appropriate, receive W2 forming the response of the medium, or different transducers may be used to transmit and receive the waves. There may be one or more emitter transducers, and possibly several receiver transducers. In another variant, the same transducer 22 may be used for emitting and receiving ultrasound waves. The transducer 22 may comprise a piezoelectric crystal and / or other components that may be configured to generate, record and / or receive signals.

[0089] The control device 10 may comprise an emitter device 20. Alternatively, the emitter device 20 may be external to the control device 10. For example, the emitter device 20 may be connected to the control device 10 by a cable or may communicate wirelessly therewith. In the latter case, the emitter device 10 may comprise, for example, a battery and may receive a communication signal from the control device 10, which represents an electrical signal (e.g., the steering frequency and / or any information contained in the electrical signal). The emitter device 20 may then internally replicate the electrical signal from the received communication signal.

[0090] For example, the emitter device 20 may be a conventional ultrasound emitter device. Therefore, the difference according to the present disclosure may be in the way that the ultrasound data DT1a and DT1b are acquired and processed by the determination device 30 to determine the status of the liver 3 of the subject UR1, as will be explained in detail below.

[0091] The control device 10 may be fixed or mobile. The emitter device 20 may also be fixed or mobile. For example, the control device 10 may be a fixed system (e.g., comprising a processing device and a display device, as described below) and the emitter device 20 may be mobile (e.g., a sensor device, a measuring device, or a probe). Nevertheless, it is also possible that the emitter device 20 is integrated into the control device 10, the device 10 being a mobile system. For example, the control device 10 may be configured to be steered in a stand-alone manner, for example thanks to an internal battery. Other embodiments are described below.

[0092] According to one example, the controller 10 may comprise at least one memory (not shown) used by the processing unit 11 to control the controller 12. This memory may possibly be part of the processing unit 11. In some embodiments, the processor and memory of the processing unit 11 may be incorporated into the controller 10 shown in FIG. 3 or may be incorporated into a computer or computing device communicatively connected to the latter.

[0093] Depending on the configuration and type of computing device considered, the memory of the control device 10 may be volatile (e.g. RAM), non-volatile (e.g. ROM memory, Flash, EEPROM, etc., or any other storage and / or computer readable medium as described below), or a combination of both. For example, this memory may be created in DMA (standing for "Direct Memory Access") mode. For example, the memory used by the processing device 11 may include all or part of a graphical card (or video card) memory, this type of memory being capable of processing and / or transmitting image data that may be used, among other things, to display one or more images on a display screen (or device).

[0094] More generally, the controller 10 may include storage devices (removable and / or non-removable) including, but not limited to, magnetic or optical disks or tapes.

[0095] Additionally, the control device 10 may include one or more input devices, such as a keyboard, mouse, stylet, voice input, etc., and / or one or more output devices, such as one or more screens, loudspeakers, printers, etc. The environment may also include one or more communication connections, such as a LAN, a WAN, a point-to-point connection, etc. In some embodiments, the connections may be used to establish point-to-point communication, wired communication, wireless communication, etc.

[0096] The control device 10 may be a unique computer operating in a networked environment with logical connections to one or more remote computers. The remote computers may be review stations, personal computers, servers, routers, network PCs, similar devices, or other shared network nodes, and may generally include some or all of the elements mentioned above, or others not mentioned. The logical connections may include any method supported by the available communications media.

[0097] As already indicated, the embodiment of ultrasound system SY1 is described above for illustrative purposes only, and other embodiments are also possible within the context of this disclosure.

[0098] The determining device 30 also comprises processing means for acquiring and processing the scan data (or ultrasound data) DT1a and DT1b generated by the ultrasound system SY1 (FIG. 3). The scan data generated by the system SY1 may be analyzed in real time by the determining device 30, for example by artificial intelligence algorithms and / or modules, or may be analyzed later on and / or in a location different from where the ultrasound system SY1 is located.

[0099] As will be described in more detail below, the nature of the scan data DT1a and DT1b provided by the ultrasound inspection system SY1 to the determiner 30 may vary from case to case, for example, they may include image data (or video data) and / or other data derived from the scan data, or the scan data itself.

[0100] More specifically, in the embodiment shown in Fig. 3, the determination device 30 comprises at least one processor 31 and at least one computer readable medium, such as a non-volatile memory 32. This memory 32, rewritable or of ROM type, forms a recording medium (or information medium) readable by the processor 31, on which a computer program PG1 according to a particular embodiment is recorded. This computer program PG1 comprises instructions for carrying out the steps of the determination method according to at least one particular embodiment. In particular, this program may define instructions for processing ultrasound data and / or instructions for constructing an exemplary image of the observed medium.

[0101] For example, the computer program PG1 may comprise at least one artificial intelligence (AI) algorithm that may be executed by the processor 31 to implement the determination method according to certain embodiments of the present disclosure. In particular, the computer program PG1 may define an artificial intelligence model (or predictive model) trained by training the data to process the acquired ultrasound data according to the determination method of the present disclosure, in particular to determine one or more indices (or scores) as described in some embodiments below.

[0102] The computer-readable media of the decision device 30, such as the memory 32, may comprise any available media accessible to the processor 31 or its operating environment. For example, and without limitation, computer-readable media may comprise computer storage media and communication media. Computer storage media may include fixed and non-fixed, 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 does not include communication media.

[0103] According to one example, the determination device 30 is configured to receive scan data, such as data DT1a and DT1b, provided by the ultrasound system SY1, process these data, and possibly transmit the results of this processing to an external device, such as, for example, a storage device, a display device, a server, or any other external device.

[0104] The communication between the determination device 30 and the ultrasound system SY1 may be performed by any communication link, wired or wireless as the case may be.

[0105] FIG. 4 shows diagrammatically an embodiment of an ultrasound system SY1 as described above with reference to FIG. 3, ie an ultrasound imaging system in the example considered.

[0106] Thus, an ultrasound imaging system 10 as shown in FIG. a radiator device 20 in the form of an ultrasonic probe, a processing device 40 configured to process or generate an image based on the ultrasound signals received from the probe 20 (this device 40 corresponds for example to the processing device 11 of FIG. 3 ); a control panel 42 associated, linked or connected to the processing device 40, said control panel possibly comprising at least one of a button 41 and a touch tablet 42; - one or more screens 50 arranged to display one or more images generated by the processing device 40;

[0107] The probe 20 may be connected to the processing device 40 by any suitable connection means, such as a cable 21 or a wireless connection. The probe 20 can also emit ultrasound waves W into the medium M, and possibly receive ultrasound waves W from the medium M, which may be the substance or result of reflection of the emitted ultrasound waves off scattering particles within the medium.

[0108] The processing device 40 may comprise receiver devices (not shown), for example comprising (or being) receiver circuits, configured to process (for example amplify and / or filter) the electrical signals received from the probe 20. For example, these receiver devices may comprise converters (for example analog-to-digital converters (ADCs) configured to convert voltages into digital codes) for converting the received signals into data representative of the signals. The acquired ultrasound data may be processed in various ways, in particular they may be temporarily stored in a memory accessible by the processing device or may be directly processed to calculate intermediate processed data (data derived from a path formation process, so-called "beamformed data"). The processing device 30 may implement any known processing method for generating and / or processing one or more images or maps or data based on the signals received from the probe, such as the formation of a route.

[0109] The processed data may be associated with ultrasound images of a number of different natures, including: - a B-mode image of the medium, generally shown in shades of grey, which makes it possible to visualize the internal organs of the medium; and / or the movement of fluids in the observed medium, for example so-called Doppler images, which show the movement speed and / or the fluid flow in the medium (images often using a color code), and which are useful for example to visualize blood vessels and their activity in the medium, and / or - Images (e.g. shear wave elastography image data (ShearWave™ Elastography)) that show the mechanical properties (elasticity) of the medium and are useful for identifying areas of different stiffness that may prove to be lesions present within the medium. may be also possible.

[0110] The display screen 50 (e.g. mounted on a support arm 51) may be a screen for displaying images processed by the processing device 30 and / or may display various information depending on the use case, in particular assistance information or context-dependent gesture assistance adapted or adaptable to the touchpad 42.

[0111] As shown diagrammatically in FIG. 5 according to one example, the processor 31 of the determination method 30, operated by a computer program PG1 (FIG. 3), 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.

[0112] More specifically, the first acquisition module MD2 is configured to acquire a first group of scan data DT1a from ultrasound waves W1 propagating according to a first scan configuration CF1 of the liver 3 (FIG. 3). These first scan data DT1a, acquired during a first ultrasound scan SC1, are representative of the liver 3 of the subject UR1.

[0113] The second acquisition module MD4 is configured to acquire a second group of scan data DT1b from ultrasound waves W1 propagating according to a second scan configuration CF2 of a group of tissues of the subject 3 (FIG. 3). As will be explained below, these second scan data DT1a acquired during the second ultrasound scan SC2 represent any group of tissues, which may include all or part of the liver 3 of the subject UR1, or parts (or regions) of him / her other than the liver 3 of the subject UR1 (e.g. abdominal organs other than the liver, such as the pancreas and / or the gallbladder).

[0114] The determination module MD6 is configured to determine an index (or global index) S3 representative of the condition of the liver 3 of the subject UR1 by combining the scan data DT1a and DT1b of the first and second groups. As will be explained later in some embodiments, the processing applied to the data DT1a and DT1b to obtain the index S3 may be of various types. Similarly, depending on the case, the nature of the index S3 may vary.

[0115] Embodiments of the present disclosure will now be described with reference to Figures 6 to 12. In these examples, the above-mentioned determining device 30 executes a program PG1 (Figure 3) to implement the determining method according to some embodiments. To do so, the determining device 30 cooperates with an ultrasound system SY1.

[0116] For example, it is assumed that it is desired to determine the status of the liver 3 of a subject UR1 (FIGS. 6 to 8). To do so, a practitioner, a physician, a qualified technician, an echographer or, more generally, a user, performs, by means of an ultrasound system SY1 (FIG. 3), two ultrasound scans on the subject UR1, namely: a first ultrasound scan SC1 during which ultrasound propagates according to a first scan configuration CF1 of the liver 3; a second ultrasound scan SC2 during propagation of ultrasound according to a second scan configuration CF2 in tissue 5 of subject UR1; Execute.

[0117] During each ultrasound scan SC1 and SC2, the ultrasound system SY1 emits ultrasound waves W1 towards the targeted medium (the part of the subject UR1 being observed) and receives returned ultrasound echoes in the form of waves W2 (FIG. 3). These ultrasound waves W2 represent the area of ​​the subject UR1 through which the emitted waves W1 and the received waves W2 propagate. Thus, the ultrasound system SY1 (and more precisely the control device 10) generates ultrasound data, the so-called first and second scan data DT1a and DT1b, respectively, from the ultrasound echoes captured during the ultrasound scans SC1 and SC2.

[0118] The area or areas of the subject UR1 that are subject to ultrasound observation and the ultrasound echoes W2 acquired during this observation depend on the configurations of the ultrasound scans SC1 and SC2 that are completed. Various parameters may define these configurations, including in particular the orientation and / or position of the emitter device 20 during the ultrasound scan.

[0119] For example, it is assumed that the first ultrasound scan SC1 is configured to scan (scan) all or part of the liver 3 of the subject UR1. In other words, the scan configuration CF1 is such that the ultrasound waves propagating during the first scan SC1 represent an area (or region) of interest in the liver 3. The first ultrasound scan SC1 is thus a scan of one or more areas of interest in the liver.

[0120] It is further assumed, for example, that the second ultrasound scan SC2 is configured to target (or probe) a group of tissues 5 (FIG. 6) of the subject UR1. The nature of these tissues may vary from case to case. In other words, the scan configuration CF2 is such that the ultrasound waves propagating during the second scan SC2 are representative of the group of tissues 5.

[0121] According to one example, the group of tissues 5 examined during the second scan SC2 includes all or part of the liver (liver scan). Thus, the scan configurations (or modes) CF1 and CF2 are liver scan configurations.

[0122] According to one example, the group of tissues 5 examined in detail includes (or corresponds to) parts (or regions) of the subject UR1 other than his / her liver 3, for example all or part of his / her gallbladder, abdominal organs, and / or visceral fat of the subject UR1.

[0123] As explained below, considering information about the status of areas of the subject other than the liver 3 can assist in the analysis and understanding of the status of the liver 3, particularly since the status of the liver 3 may be correlated with that of other areas of the subject.

[0124] For example, since visceral fat may form a biomarker of the pathological condition of the liver, ultrasound observation of the visceral fat of a subject UR1 may provide useful information for determining the condition of the liver 3, in particular for the purpose of helping to screen or diagnose liver damage. For example, the presence of excessive visceral fat may be a sign of fatty liver (e.g. of the NASH type), liver toxicity, or other conditions of the liver.

[0125] The group of tissues 5 may be selected according to the examination type considered and / or according to the supposed condition of the liver that we want to study or ascertain, or its progression in time or with regard to treatment, for example during a medical examination. Independently of the area 5 of the subject that is examined during the second ultrasound scan SC2, the first and second scan configurations CF1 and CF2 differ from one another in order to acquire ultrasound data carrying different and complementary information.

[0126] As shown diagrammatically in FIG. 7, in the following, for illustrative purposes only, ultrasound scans SC1 and SC2 are - the first scan configuration CF1 used in performing the first ultrasound scan SC1 is of the intercostal type, i.e. by propagating ultrasound waves over (or between) the ribs of the subject UR1 (position P1); and so that the second scan configuration CF2 used in performing the second scan SC2 is of the subcostal type, i.e. by propagating ultrasound waves below the rib cage throughout the abdomen (position P2), It is assumed to be configured.

[0127] Therefore, by positioning the ultrasound probe 20 in the abdomen of the subject, the liver of the subject can be observed according to other cutting planes, thus improving the relevance of the results obtained.

[0128] Thus, during a step E2a (FIG. 8), the determination device 30 acquires a first group of scan data DT1a from ultrasound waves propagating during a first ultrasound scan SC1 with a first scan configuration CF1 of the liver 3.

[0129] Similarly, during a step E2b (FIG. 8), the determination device 30 acquires a second group of scan data DT1b from ultrasound waves propagating during a second ultrasound scan SC2 with a second scan configuration CF2 of the group of tissues 5.

[0130] To do so, the ultrasound system SY1 (and more particularly the controller 10) generates scan data DT1a and DT1b from ultrasound echoes received during the first and second ultrasound scans SC1 and SC2, respectively, which are transmitted to the processor 30 for processing according to the determination method.

[0131] Each ultrasound scan SC1 and SC2 may comprise one or more scans in a corresponding scan configuration CF1 and CF2, respectively.

[0132] The acquisition steps E2a and E2b are included in an acquisition phase denoted E2 (FIG. 8). It should nevertheless be noted that various configurations of steps E2a and E2b are possible in time. Steps E2a and E2b may be performed simultaneously (at least partially) or sequentially, immediately after or at a later time (e.g. during different examination sessions). According to one example, the first group of scan data DT1a is received before the second group of scan data DT1b (or vice versa).

[0133] Furthermore, the determination device 30 may receive the scan data DT1a and DT1b in real time while performing the scans SC1 and SC2 or at a later time, in a grouped manner or separately.

[0134] During a determination step E6 (FIG. 8), the determination device 30 determines an index (or score) S3 representative of the state of the liver 3 of the subject UR1 by a combination of the scan data DT1a and DT1b of the first and second groups. This combination may include a processing taking into account the data DT1a and DT1b, the nature of which may be adapted case by case, as will be explained below in some embodiments.

[0135] Steps E2 to E6 may be repeated iteratively to improve or update the metric S3 determined in E6.

[0136] According to one example, the indicator S3 defines (or at least one) biomarker of a physiopathological state of the liver. For example, the indicator S3 may inform about a liver disorder affecting the liver 3 of the subject UR1, such as fatty liver (e.g. of NASH type), steatohepatitis, liver poisoning, etc.

[0137] According to one example, the indicators S3 determined in E6 (FIG. 8) comprise attenuation coefficients representative of the attenuation of ultrasound during propagation in the area of ​​interest of the subject UR1 during the first and second ultrasound scans SC1 and SC2, respectively.

[0138] According to one example, the indicators S3 determined in E6 (FIG. 8) include, for example, an indicator defining the fat mass percentage (or ratio) of the liver (or PDFF), this percentage informing about the average amount of fat present in the liver 3 of the subject UR1.

[0139] 11 shows the index S3 determined (E6) for a group of subjects during the study ET1 carried out by the applicant, in the form of a point cloud 70. The index S3 defines the fat mass ratio (or PDFF) determined respectively for each subject of the study ET1.

[0140] For reference, Fig. 12 shows the PDFF values ​​determined for the same subjects of study ET1 by a technique different from that of the determination method, namely MRI imaging. The evaluation of PDFF by MRI imaging is currently the standard for predicting or diagnosing fatty liver. It should be noted that this study ET1 covers subjects with PDFF below the limit value, i.e. 25% in this case.

[0141] The index S3 determined in E6 (FIG. 8) may represent any physiological, mechanical and / or tissue property (elasticity, stiffness, etc.) of the liver 3 and / or tissue 5 probed by ultrasound during ultrasound scans SC1 and SC2. The index S3 may comprise one index (or score) or multiple indexes (or scores).

[0142] According to an example, during the determination method (FIG. 8), the determination device 30 compares (E8) the indicator S3 obtained in E6 against a reference value RF1. This reference value RF1 may be any criterion indicating a predefined state of the liver (healthy liver, specific liver damage, etc.). For example, if the device 30 detects (E8) that the value of the indicator S3 obtained in E6 exceeds (or is lower than) the reference value, this means that the state of the liver 3 of the subject UR1 complies (or does not) with at least one predefined criterion.

[0143] According to one example, the index S3 defines the PDFF of the liver 3 of the subject UR1. During a comparison step E8, the value of the index S3 is compared with a threshold value RF1. If the obtained value of the PDFF exceeds the threshold value RF1 (or is within a predefined value range), a predefined condition of the liver 3 is detected. For example, the value of the PDFF may be interpreted as follows: - 5.5% for steatosis of grade S1 or higher; - 15.5% for steatosis of grade S2 or higher; and - 20.5% for steatosis of grade S3 or higher. For example, see Non-Patent Document 1.

[0144] It should be noted that during the determination step E6 (FIG. 8), the measure S3 can be determined in various ways by combining the scan data DT1a and DT1b obtained from the ultrasound scans SC1 and SC2.

[0145] According to one example, the scan data DT1a and DT1b are the data that are directly combined by the determination device 30 to derive therefrom the index S3. To do so, the determination method 30 applies, for example, a calculation function denoted "f1" to the scan data DT1a and DT1b so as to generate the index S3. In other words, the function f1 is applied such that f1(DT1a;DT1b)=S3.

[0146] According to another embodiment, the determination device 30 performs a first processing on the scan data DT1a and DT1b before determining the indicator S3. To do so, the device 30 applies functions f2 and f3 to the scan data DT1a and DT1b, respectively, for example, to generate intermediate scores (or indicators) S1 and S2. In other words, the determination device 30 evaluates (or determines) a first score S1 (E4a, FIG. 8) from the first group of scan data DT1a and evaluates (or determines) a second score S2 (E4b, FIG. 8) from the second group of scan data DT1b. The determination device 30 may then determine (E6) a 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.

[0147] The determination E6 of the index S3 then becomes: - f2(DT1a)=S1; f3(DT1b)=S2; and - f4(S1;S2)=S3.

[0148] It should be noted that the types of intermediate scores S1 and S2 may vary from case to case. In particular, each of the indicators S1 and / or S2 may include at least one of any of the indicator types as defined below. For the sake of simplicity of presentation of the present disclosure, in the following examples, it is considered that each of the first and second indicators S1 and S2 includes at least one indicator as defined below in a particular embodiment.

[0149] According to one example, each of the indices S1 and S2 determined in E4 (FIG. 8) comprises a respective indices defining the speed of sound, i.e. the speed of ultrasound propagating in the liver of the subject UR1, or more specifically in one or more areas to which ultrasound is irradiated, during the corresponding ultrasound scans SC1 and SC2.

[0150] According to one example, each of the indices S1 and S2 determined in E4 (FIG. 8) includes a respective index defining a backscatter coefficient, i.e. a coefficient representative of the level of backscatter caused by the propagation of ultrasound in the medium during the corresponding ultrasound scans SC1 and SC2, the backscatter coefficient being one of the physical parameters related to the ability of the medium under examination to produce echoes that propagate towards the ultrasound probe.

[0151] According to one example, the indices S1 and S2 determined in E4 (FIG. 8) each comprise an index representative of the ability of liver tissue to deform in response to an applied mechanical stress.

[0152] According to one example, the indices S1 and S2 determined in E4 (FIG. 8) each comprise a respective index (or score) defining a coefficient representative of the viscoelasticity of the liver, ie the viscous and elastic capacity of the liver.

[0153] According to one example, each of the indices S1 and S2 determined in E4 (FIG. 8) includes a respective scattering nonlinearity (or propagation nonlinearity) index, i.e. an index (or score) representing the propagation nonlinearity of ultrasound in the medium (in the liver) during ultrasound scans SC1 and SC2.

[0154] According to one example, each of the indices S1 and S2 determined in E4 (FIG. 8) comprises a respective scattering index (or score), i.e. an index representative of the level of scattering caused by the propagation of ultrasound waves in the medium during the corresponding ultrasound scans SC1 and SC2. This scattering coefficient may define a scattering mean path (or "mean free path") that depends on the ability of the tissue irradiated with ultrasound to generate echoes due to the phenomenon of multiple scattering.

[0155] The phenomenon of "speckle" in one or more ultrasound images can also be used to determine the condition of the liver of a subject. Ultrasound speckle in ultrasound images (sometimes also called "interference patterns" or "sputtering") is an apparent granularity or texture phenomenon resulting from the coherence of ultrasound waves when interacting with structures of various sizes in tissue in a medium of interest. These granular patterns are the product of constructive and destructive superposition of ultrasound waves reflected by multiple scatterers in tissue, resulting in random variations in the intensity of the received signal. This feature can be used to extract information representative of the condition of the liver of a subject, such as the texture of the observed tissues, their homogeneity, and / or other material properties.

[0156] Thus, according to one example, each of the indices S1 and S2 determined in E4 (FIG. 8) comprises a respective ultrasound speckle distribution index (or score) (or interference pattern distribution index). These indices (also called ultrasound speckle statistical indexes) may characterize the distribution of speckle phenomena (or, more simply, speckles or shades of grey) in one or more ultrasound images generated (E2, FIG. 8) from the first and second groups of scan data DT1a and DT1b, respectively. More specifically, based on the first and / or second groups of scan data (steps E2a and E2b), B-mode ultrasound images may be generated and for each image, the distribution of shades of grey in the image may be determined. Thus, the statistical properties of the speckles may be expressed in the form of at least one speckle statistical index and, if appropriate, may be used to assess the liver condition of the subject.

[0157] 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 the ultrasound propagating in the medium (area of ​​interest) during the ultrasound scans SC1 and SC2, respectively. In this case, the index S3 determined in E6 (FIG. 8) from the combination of the scan data DT1a and DT1b (and more specifically by combining the scores S1 and S2) may define, for example, a biomarker of a physiopathological state of the liver.

[0158] The nature of the function f4 used by the device 30 to determine the measure S3 from the intermediate scores S1 and S2 may be adapted on a case-by-case basis.

[0159] According to one example, the index S3 is determined from the average of the first and second scores S1 and S2. For example, this average is determined by a linear combination of the first and second scores S1 and S2. It may consist of a simple average or a weighted average. In other words, the index S3 may be calculated as S3=aS1+bS2, where the weights a and b are set independently of the values ​​of S1 and S2.

[0160] According to one example, the average used to determine S3 is the least mean-square average (also called LSM) of S1 and S2.

[0161] According to one example, the average of S1 and S2 used to determine the index S3 (E6, FIG. 8) is a non-linear combination of the scores S1 and S2. In other words, the index S3 may be calculated as S3=aS1+bS2, where the weights a and b are variable according to the values ​​of S1 and S2. According to one example, one of the weights a or b may be zero for at least one value of the pair (S1, S2), such that only intermediate scores S1 or S2 with non-zero weights are selected and used to determine S3.

[0162] According to one example, a non-linear combination of the scores S1 and S2 may be defined as f(S1, S2) or f(DT1a, DT1b), where f denotes a non-linear function.

[0163] Figure 9 shows the intermediate score S1 in the form of a point cloud 62 determined in the first scan data DT1a to E4a (Figure 8) of a subject of a study designated ET1 carried out by the applicant. Similarly, Figure 10 shows the intermediate score S2 in the form of a point cloud 66 determined in the second scan data DT1b to E4b (Figure 8) of a subject of the study ET1. In this example, the intermediate scores S1 and S2 define attenuation coefficients characterizing the attenuation of the ultrasound waves propagating in the subject UR1 during the first and second ultrasound scans SC1 and SC2.

[0164] Linear regressions 62a and 66a are determined from points 62 and 66 corresponding to scores S1 and S2 resulting from ultrasound scans SC1 and SC2 (FIGS. 9 and 10), respectively. These linear regressions 62a and 66a represent the approximate change in attenuation coefficient measured at intercostal and subcostal locations, respectively, as a function of the estimated PDFF score for each patient.

[0165] As can be seen from reading study ET1, in this example the performance achieved with the intercostal and subcostal ultrasound scanning configurations is close to each other. 2 CF1 and r 2 CF2 The coefficients of determination, denoted by r and r , respectively, are determined based on attenuation values ​​(index S3) obtained at intercostal and subcostal locations (or modes). Therefore, we 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 lie on the same line. Thus, in this case we obtain a slightly higher correlation in the subcostal configuration than in the intercostal configuration.

[0166] As a note, the coefficient of determination, r, also known as the Pearson linear coefficient of determination 2 represents the quality of prediction of the linear regression.

[0167] 11 shows the determined (E6) index S3 for the group of subjects evaluated during study ET1 in the form of a point cloud 70. Index S3 defines the 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.

[0168] For reference, Fig. 12 shows the determination of the PDFF score for subjects of study ET1, which is determined by a technique different from that of the determination method, namely MRI imaging. The evaluation of PDFF by MRI imaging is currently the standard for predicting or diagnosing fatty liver. It should be noted that this study ET1 covers subjects with PDFF below the limit value, i.e. 25% in this case.

[0169] As shown in FIG. 11, a linear regression 70a is also determined from the points 70 corresponding to the index S3 determined in E6 (FIG. 8) for each subject of the study ET1. This linear regression 70a represents the approximate evolution of the global attenuation coefficient as a function of the PDFF of the subject. As an advantage, one may note in this embodiment the substantial improvement of the coefficient of determination r2, which reaches up to 0.55 in the case of the total linear regression 70a. In other words, the linear regression 70a has a better correlation level of the global attenuation coefficient S3 (compared to S1 and S2) with the PDFF of the subject, compared to the results obtained in the case of only the intercostal mode (FIG. 9) or only the subcostal mode (FIG. 10). This verifies the validity of the determination method, which, for this embodiment, produces better results in terms of accuracy and reliability than if only one acquisition mode (intercostal or subcostal) was used.

[0170] According to the embodiment shown in Fig. 8, once the indicator S3 has been determined in E6, the determination device 30 estimates (E10) from the indicator S3 a fat mass ratio or PDFF of the liver 3 of the subject UR1. The device 30 may then possibly compare (E12) the obtained PDFF against a reference value RF2, for example determined by an MRI imaging technique or another technique.

[0171] Also, the first scan data DT1a may be acquired before, simultaneously or after the second scan data DT1b. In particular, the first and second ultrasound scans SC1 and SC2 may be performed simultaneously or sequentially according to any order (SC1 before SC2 or SC2 before SC1) during the same scanning session or different sessions.

[0172] According to one example, one of the first and second groups of scan data DT1a and DT1b is obtained from a scan performed according to a pre-scan configuration, the so-called pre-scan, and the other is obtained from a scan performed according to a post-scan configuration, the so-called post-scan, the pre-scan being performed before the post-scan. The pre-scan configuration is then one of the first and second scan configurations CF1 and CF2, and the post-scan configuration is the other of the first and second scan configurations CF1 and CF2.

[0173] 13, the pre-scan is a first ultrasound scan SC1 performed according to a pre-scan configuration (i.e., CF1) and the post-scan is a second ultrasound scan SC2 performed according to a scan configuration (i.e., CF2). For example, the pre-scan configuration is the intercostal configuration and the post-scan configuration is the subcostal configuration (or vice versa).

[0174] According to a second embodiment, the pre-scan is a second ultrasound scan SC2 performed according to a pre-scan configuration (i.e., CF2) and the post-scan is a first ultrasound scan SC1 performed according to a scan configuration (i.e., CF1).

[0175] Thus, for example, it is possible to perform a pre-scan and then a post-scan during the same medical examination or during separate medical examinations at different times (e.g., during a first examination and a subsequent medical monitoring). In particular, it is possible to perform the determination method of the present disclosure incrementally, such that the decision device 30 generates a first result (e.g., S1 or S2) from a group of scan data obtained from a pre-scan and then completes this result with scan data obtained from a post-scan to obtain an overall index S3. In this way, it is possible to advantageously immediately obtain a first result regarding the condition of the liver 3 of the subject UR1 and then improve this result with a post-scan.

[0176] According to the embodiment shown in Fig. 14, a post-scan configuration for the post-scan (i.e. in this embodiment configuration CF2 for scan SC2) is selected (E25) from the first or second score S1 or S2 (i.e. SC1 in this embodiment) obtained from the pre-scan (i.e. S1 in this embodiment). Thus, advantageously, it is possible to adapt the way in which the post-scan is performed according to the results previously obtained for the pre-scan. Depending on the results of the pre-scan, it may be advisable to prefer a particular scan configuration to best orient the ultrasound view.

[0177] According to the embodiment shown in Fig. 15, the determination device 30 (Fig. 3) determines the global indicator S3 during a determination step E6 (Fig. 8) by carrying out a processing of the first and second groups of scan data DT1a and DT1b or of data obtained from these data DT1a and DT1b. This processing is carried out according to a processing model ML1 obtained by means of one (or at least one) neural network RN1 trained from training data DT0 and a reference score (or indicator or value) RF0. To do so, the neural network RN1 may execute an algorithm based on an artificial intelligence module. The training data used when the neural network RN1 is trained may comprise ultrasound scan data or data obtained from such ultrasound scan data.

[0178] According to the embodiment shown in FIG. 16, prior to the above-mentioned processing, the neural network RN1 is trained by machine learning during a training phase E40-E46. During this training phase, the neural network RN1 acquires (E40) ultrasound scan data DT0a and DT0b representative of waves propagating according to a first and a second scan configuration CF1 and CF2, respectively, in the subject. The neural network RN1 then determines (E42) training data DT0 from the ultrasound scan data DT0a and DT0b. These training data DT0 may comprise the scan data DT0a and / or DT0b themselves of data obtained from these data DT0a and / or DT0b. The neural network RN1 further acquires (E44) a reference score RF0 representative of the subject's liver condition from an MRI imaging performed on the subject. The neural network RN1 may thus determine (E46) a processing model ML1 used to estimate an index S3 from a combination of the scan data DT1a and DT1b of the first and second groups by comparing the training data DT0 against the reference score RF0.

[0179] According to an example, during a decision step E6 (FIG. 8), the decision device 30 executes successively a first algorithm and then a second algorithm to assess the condition of the liver 3 of the subject UR1. The first algorithm is an estimation algorithm configured to determine a global attenuation coefficient S3 from a first and a second group of scan data DT1a and DT1b acquired in intercostal and subcostal modes, respectively. For example, this first estimation is performed by calculating the average of the attenuation coefficients S1 and S2 acquired for the intercostal or subcostal areas, as described above. The second algorithm is executed by a neural network (such as the network RN1) to estimate the PDFF of the liver 3 of the subject UR1 from the global attenuation coefficient S3, for example from the model ML1 or the linear regression described above. The statistical model used in the second algorithm may thus correlate, at the output, a global measure S3 (representing, for example, at least one of the parameters mentioned above, attenuation coefficient, sound speed, etc.) with an estimate of the PDFF.

[0180] According to one example, the determination device 30 may on the one hand implement a neural network RN1 for generating a model ML1 correlating the ultrasound images obtained from the ultrasound scans SC1 and SC2 at the input with the index S3 or PDFF obtained at the output.

[0181] Advantageously, the disclosed method and device for determining allows to determine effectively with high reliability the liver status of a subject who is healthy or has any physiopathological condition of the liver. To do so, the disclosed concept is based on the combination of scan data (or ultrasound data) acquired according to two separate scan configurations, namely a first scan configuration CF1 targeting the liver and a second scan configuration CF2 targeting the liver or a group of other tissues of the subject. Advantageously, the combination of these scan data allows to obtain an index S3 representative of the liver status of the subject in a more robust manner than if only one scan configuration was used.

[0182] The combination of two separate acquisition modes, e.g. intercostal and subcostal locations (or modes), advantageously allows to improve the quality of the acquired data (using multiple different types of data) compared to the prior art, where only ultrasound data acquired in the intercostal mode are considered. The ultrasound data thus acquired have a lower correlation with each other. Advantageously, the use of two separate scanning configurations allows to diversify the measurements and therefore improve the reliability and accuracy of the results.

[0183] Furthermore, for example, in the case of fatty liver, all areas of the subject's liver may be affected differently. Thus, some cases of non-uniform steatosis were noted. Augmenting the ultrasound scans according to a number of different configurations makes it possible to obtain a more representative estimate of the overall condition of the subject's liver.

[0184] Thus, the present disclosure may advantageously provide assistance in the diagnosis or monitoring of any physiopathological condition of the liver, such as fatty liver (eg of NASH type), fatty liver inflammation, etc.

[0185] As will be understood by those skilled in the art, all of the above-described embodiments and modifications constitute only non-limiting embodiments of the present invention, some of which are intentionally simplified to facilitate the description thereof, and in particular, those skilled in the art may imagine adapting or combining the above-described embodiments and modifications to address their particular needs.

[0186] The present disclosure is therefore not limited to the embodiments described above, but in particular covers navigation methods including secondary steps without departing from the scope of the present disclosure, the same applies to navigation systems for implementing such methods.

Claims

1. A method for determining the status of the liver (3) of a subject (UR1), said method comprising the steps of: acquiring (E2a) a first group of scan data (DT1a) from ultrasound waves propagating according to a first scan configuration (CF1) of said liver, acquiring (E2b) a second group of scan data (DT1b) from ultrasound waves propagating according to a second scan configuration (CF2) of a group of tissues (5) of said subject, determining (E6) an index S3 representative of the state of said liver (3) by a combination of scan data of said first and second groups, method.

2. the group of tissues (5) of the subject corresponds to parts of the subject other than the liver (3); The method of claim 1.

3. the first scan configuration (CF1) is an intercostal scan configuration of the liver, the second scan configuration (CF2) is a subcostal scan configuration of the liver; The method of claim 1.

4. - comparing said indicator S3 against a reference value (RF1), The method according to any one of claims 1 to 3.

5. The above method is evaluating (E4a) a first score (S1) from said first group of scan data (DT1a); evaluating (E4b) a second score (S2) from said second group of scan data (DT1b), The index S3 is determined from the first and second scores. The method according to any one of claims 1 to 4.

6. The first index S1 and / or the second index S2 are - an indicator defining the damping coefficient, - a measure defining the speed of sound, - a parameter defining the backscatter coefficient, - the above-mentioned index of liver elasticity, - an index defining the viscoelasticity of the liver, - a measure of propagation nonlinearity, - an indication of ultrasound scattering, and - Ultrasonic speckle distribution index At least one of: The method of claim 5.

7. said first score (S1) being a first damping coefficient, said second score (S2) being a second damping coefficient, The indicator S3 defines a biomarker of the physiopathological state of the liver; 7. The method according to claim 5 or 6.

8. One of the first and second groups of scan data (DT1a, DT1b) is obtained from a scan performed by a pre-scan configuration, i.e., a pre-scan, and the other is obtained from a scan performed by a post-scan configuration, i.e., a post-scan, the pre-scan being performed before the post-scan; The pre-scan configuration is one of the first and second scan configurations (CF1, CF2), and the post-scan configuration is the other of the first and second scan configurations. The method of claim 7.

9. The post-scan configuration is selected from the first or second scores (S1, S2) obtained from the pre-scan. The method of claim 8.

10. The index S3 is determined from the average of the first and second scores (S1, S2). The method according to any one of claims 6 to 9.

11. the average being determined by a linear combination of the first and second scores (S1, S2); The method of claim 10.

12. The above average is the least mean squared average. The method of claim 11.

13. the average being determined by a non-linear combination of the first and second scores (S1, S2); The method of claim 10.

14. Determining the index S3 includes: processing said first and second groups of data (DT1a, DT1b) or processing data obtained from said first and second groups of data according to a processing model obtained by means of a neural network (RN1) trained from training data (DT0) and a reference score (RF0), the training data includes ultrasound scan data or includes data derived from the ultrasound scan data; 14. The method of claim 13.

15. Prior to the processing, the neural network (RN1) is trained by machine learning during a training phase, The training phase is - acquiring (E40) ultrasound scan data representative of waves propagating according to said first and second scan configurations in a test subject; - determining (E42) said training data from said ultrasound scan data; obtaining (E44) a normative score representative of the liver status of said test subject from the MRI imaging carried out on said test subject; determining (E46) a processing model (ML1) used to estimate said measure S3 from the combination of scan data of said first and second groups, by comparing said training data against said reference scores, 15. The method of claim 14.

16. The above method is - evaluating the subject's liver fat ratio from the indicator S3; The method according to any one of claims 1 to 15.

17. A computer program (PG1) comprising instructions for carrying out the method according to any one of claims 1 to 16 when executed by a processor.

18. A device (30) for determining the condition of the liver (3) of a subject (UR1), said device comprising: a first acquisition module (MD2) configured to acquire a first group of scan data from ultrasound waves propagating according to a first scan configuration of said liver; a second acquisition module (MD4) configured to acquire a second group of scan data from ultrasound waves propagating according to a second scan configuration of a group of tissues of said subject; an analysis module (MD6) adapted to determine, by a combination of the scan data of said first and second groups, an index S3 representative of the state of said liver. Device.

19. 1. A system for determining a liver status of a subject (SY2), comprising: - a determination device (30) according to claim 18, an ultrasound system (SY1) connected to said determination device, system.

Images