METHOD FOR DETERMINING ATTEMPHS IN AN ACOUSTIC SIGNAL, COMPUTER PROGRAM PRODUCT, STORAGE MEDIUM AND CORRESPONDING DEVICE

Abstract

The present invention relates to a method for determining respiratory phases in an acoustic signal which represents an individual's respiratory activity, the respiratory activity comprising inhalation and exhalation phases. The method is such that it comprises the following steps: detecting (S2) pause intervals in the acoustic signal; determining (S4) time intervals corresponding to inhalation phases each between a long pause and a short pause, and time intervals corresponding to exhalation phases each between a short pause and a long pause.

Description

[0001] Method for determining respiratory phases in an acoustic signal, computer program product, storage medium and corresponding device

[0002] Technical field

[0003] The invention falls within the field of processing acoustic signals, in particular tracheal or pulmonary sounds captured from an individual.

[0004] More specifically, the invention relates to a technique for recognizing the respiratory phases of an individual from an acoustic signal representative of the respiratory activity of this individual.

[0005] The invention applies in particular, but not exclusively, in the field of acoustic instrumentation dedicated to the recording and monitoring of the respiratory activity of individuals, for example for the study of respiratory pathologies or respiratory disorders during sleep.

[0006] Technological background

[0007] In the remainder of this document, we will focus more specifically on describing the problems that exist in the context of the study of respiratory activity in patients suffering from "sleep apnea syndrome" (known as SAS syndrome). The invention is of course not limited to this particular context of application, but is of interest for any technique for recognizing respiratory phases that has to deal with a similar or similar problem.

[0008] Sleep apnea syndrome is characterized by repeated and uncontrolled interruptions in breathing during sleep. They cause unconscious micro-awakenings that can affect the quality of sleep. This can result in daytime drowsiness, difficulty concentrating or remembering things, and even cardiovascular complications, which can lead to related accidents such as road or work accidents. It is therefore important to have medical equipment capable of detecting this type of pathology, particularly for screening and treatment purposes.

[0009] The diagnosis of sleep apnea syndrome is mainly based on exploring the individual's ventilation in order to observe breathing movements and the evolution of the upper airways during sleep. Apneas and hypopneas are sought by analyzing the amplitude of acoustic signals obtained, for example, during ventilatory polygraphy or polysomnography. It is generally recommended to use a number of measuring instruments to measure the individual's respiratory behavior during sleep, such as nasal prongs, thoraco-abdominal straps, a pulse oximeter, etc. Analysis software analyzes the signals recorded by the different measuring instruments to identify possible pathological events, such as apneas and hypopneas.Other instruments, such as tracheal sound sensors, can also be used in a complementary manner to study more precisely certain parameters associated with the inspiration and expiration phases of the individual's respiratory activity, and to refine the diagnosis. Indeed, the latest studies carried out on respiratory cycles obtained from tracheal sound signals have made it possible to highlight a certain number of pathological indicators whose consideration proves relevant in the detection and evaluation of respiratory disorders.

[0010] However, even though there are techniques for analyzing respiratory cycles from tracheal sounds, such as the non-invasive phase detection technique proposed by Z.K. Moussavi et al. in the scientific article "Computerized acoustical respiratory phase detection without airflow measurement" (March 2000), these lack precision. The respiratory activity of an individual (typically composed of successive respiratory cycles, each respiratory cycle comprising an inspiration phase and an expiration phase) can be observed from the following three representations: a temporal representation, a frequency representation and a frequency-intensity representation over time ("three-dimensional" representation).However, it turns out that it is often difficult to precisely distinguish the inspiration phase from the expiration phase of a respiratory cycle in the frequency or time domain of a tracheal sound signal, in particular when the captured signal is below a certain sound threshold (in the case of an individual at rest, for example). Furthermore, such known techniques only provide a limited amount of information, which is relatively imprecise, on the patient's respiratory activity.

[0011] Furthermore, some respiratory profiles are particularly complex to process, for example in cases of snoring or apnea during which the reduction in the acoustic signal is accompanied by noises related to the individual's efforts to bring air in or out via the respiratory tract. Other noises, such as swallowing, coughing, throat clearing, or even changes in the individual's position during sleep complicate the recognition of respiratory phases.

[0012] There is therefore a real need to provide a technique that allows effective recognition of the respiratory phases of an individual in a tracheal sound signal, and more generally in an acoustic signal representative of respiratory activity. It would also be particularly interesting to provide such a technique that is minimally invasive and easy to implement. Description of the invention

[0013] In a particular embodiment of the invention, a method is proposed for determining respiratory phases in an acoustic signal representative of a respiratory activity of an individual, the respiratory activity being defined by respiratory cycles each comprising an inspiration phase and an expiration phase, the method is remarkable in that it comprises the following steps: detection of pause intervals in the acoustic signal; determination of activity intervals corresponding to inspiration phases and activity intervals corresponding to expiration phases each by comparing, for each time interval, the duration of the pause interval which precedes said time interval with the duration of the pause interval which follows said time interval.

[0014] Thus, the principle of the invention is based on a search in the acoustic signal for pauses in the signal to deduce the inspiration and expiration phases using their duration and their position in the signal. This new approach is clever because, rather than seeking to directly process the inspiration and expiration phases as in the state of the art, the present invention first focuses on recognizing the pauses in the signal, these being easier to recognize in an acoustic signal. Thus, the invention offers a technique for recognizing respiratory phases that is more effective than the techniques of the state of the art. Furthermore, the fact of being able to determine the inspiratory and expiratory phases using only an acoustic signal offers prospects for simplified examination in terms of medical equipment.

[0015] According to a particular aspect, the method implements a mechanism for distinguishing among the pause intervals, between a first type of pause interval, called a short pause, of shorter duration than a second type of pause interval, called a long pause.

[0016] According to a particular characteristic, the acoustic signal belongs to the group comprising: a tracheal acoustic signal or a pulmonary acoustic signal captured on an individual.

[0017] According to a particular implementation of the method, if at the end of the detection step at least one succession of two pause intervals separated in the signal by a time interval, called an aberrant interval, of duration less than a predetermined duration threshold is identified, the method comprises a step of replacing, for each detected succession, the set consisting of the two pause intervals and said aberrant interval by a new pause interval. The mechanism for recognizing the inspiration and expiration phases according to the invention is thus optimized. Indeed, the predetermined threshold is dimensioned so that when a point defect appears in the signal between two pause intervals, it is considered as an integral part, with the two pause intervals, of a single pause. This makes it possible to overcome the parasitic noises contained in the signal which would disturb the recognition of the respiratory phases.

[0018] According to a particular characteristic, if at the end of the determination step at least one time interval, called an indeterminate interval, meeting a predetermined inconsistency criterion, is identified, the method comprises the following steps, for each indeterminate interval: - processing the portion of signal corresponding to said indeterminate interval, by means of a machine learning method; - association of said at least one indeterminate interval with an inspiration or expiration phase according to the results of the processing step. This further improves the mechanism for recognizing the inspiration and expiration phases according to the invention.

[0019] According to a particular aspect of the invention, the step of detecting pause intervals is based on a processing belonging to the group comprising a frequency processing of the acoustic signal, an energy processing of the acoustic signal. Indeed, it is by observing the energy and time-frequency representation spaces of sound signals that it was found, surprisingly, that respiratory pauses are more easily recognizable in these representation spaces than the inspiration and expiration phases themselves. The pause recognition mechanism according to the invention can be implemented either by frequency processing of the signal, or by energy processing of the signal, or by simultaneous frequency and energy processing of the signal, thus making the method even more reliable.

[0020] According to a particular implementation, the frequency processing comprises the following steps: applying a high-pass anti-noise filter to said signal to remove a first predefined range of frequencies from said signal and obtaining a filtered signal as a function of time; segmenting said filtered signal to obtain a plurality of samples of said filtered signal and, for each sample, estimating the average power spectral density of said sample so as to obtain a frequency signal representing the centroid frequency as a function of time. applying a sliding time window of predetermined duration to said frequency signal and, for each window:

[0021] * detection of a frequency maximum of the frequency signal in said window, * determination of a frequency threshold as a function of the frequency maximum detected in said window; shaping, from said frequency signal, of a first transient logic signal of logic levels defined as a function of the frequency thresholds determined for said frequency signal, the pause intervals being detected as a function of the first transient logic signal.

[0022] According to a particular implementation, the energy processing comprises the steps: applying a high-pass anti-noise filter and a low-pass filter to remove from said signal respectively a first and a second predefined frequency ranges and to obtain a filtered signal as a function of time in the time domain; applying a first sliding time window of predetermined duration to said filtered signal and, for each time window, estimating the acoustic intensity of said filtered signal by applying a quadratic mean envelope in said window, so as to transform said filtered signal into an energy signal as a function of time; applying a second sliding time window of duration determined by autocorrelation to said energy signal and, for each window:

[0023] * detection of a minimum intensity of the energy signal in said window,

[0024] * determination of an intensity threshold as a function of the minimum intensity detected in said window; shaping, from said energy signal, a second transient logic signal of logic levels defined as a function of the intensity thresholds determined for said energy signal, the pause intervals being detected as a function of the second transient logic signal.

[0025] According to a particularly advantageous aspect of the invention, the method comprises a step of shaping, by processing said first and second logic signals by an inclusive OR logic function, a final logic signal whose high logic levels correspond to said detected pause intervals. Since the frequency and energy processing can be complementary, taking these two processings into account can make it possible to detect pauses which would not have been detected by implementing only one of the two processings.

[0026] According to a particular characteristic, the method comprises a step consisting of, if at the end of the shaping step, at least one succession of two pause intervals separated by an aberrant interval detected in said final logic signal of duration less than the predetermined duration threshold is identified: replacing, for each succession detected in said final logic signal, the set consisting of the two pause intervals and said aberrant interval with a new pause interval. This facilitates the distinction between long pauses and short pauses, and in fact allows more reliable recognition of the respiratory phases.

[0027] In another embodiment of the invention, there is provided a computer program product which comprises program code instructions for implementing the aforementioned method (in any of its various embodiments), when said program is executed on a computer.

[0028] In another embodiment of the invention, there is provided a non-transitory, computer-readable storage medium storing a computer program comprising a set of computer-executable instructions for implementing the above-mentioned method (in any of its various embodiments).

[0029] In another embodiment of the invention, a device is proposed for determining respiratory phases in an acoustic signal representative of a respiratory activity of an individual, the respiratory activity being defined by respiratory cycles each comprising an inspiration phase and an expiration phase, the device being characterized in that it comprises: - means for detecting pause intervals in the acoustic signal; - means for determining activity intervals corresponding to inspiration phases and activity intervals corresponding to expiration phases by comparing the duration of the pause intervals.

[0030] Advantageously, the device comprises means for implementing the steps that it carries out in the production method as described previously, in any one of its different embodiments.

[0031] List of figures

[0032] Other characteristics and advantages of the invention will appear on reading the following description, given as an indicative and non-limiting example, and the appended drawings, in which:

[0033] - figure 1 presents a flowchart of a particular embodiment of the method according to the invention;

[0034] - Figure 2 illustrates in a simplified manner the principle of recording an individual's respiratory activity using a tracheal sound sensor;

[0035] - Figure 3 presents a flowchart illustrating a particular implementation of a frequency processing and an energy processing of the tracheal acoustic signal in accordance with the invention; - Figure 4 is a temporal graphic representation illustrating the evolution of the intensity of a tracheal acoustic signal recorded on an individual;

[0036] - figure 5 is a temporal graphic representation illustrating the principle of frequency processing of the acoustic signal according to the invention;

[0037] - figure 6 is a temporal graphic representation of the chronogram type highlighting the respiratory pauses contained in the acoustic signal by frequency processing;

[0038] - figure 7 is a temporal graphic representation illustrating the principle of energy processing of the acoustic signal according to the invention;

[0039] - figure 8 is a time graph representation of the chronogram type highlighting the respiratory pauses detected in the acoustic signal by energy processing;

[0040] - Figure 9 represents a final chronogram highlighting the respiratory pauses detected in the acoustic signal from the frequency and energy processing;

[0041] - Figure 10 represents a final chronogram illustrating the principle of determining the inspiration and expiration phases according to the pauses detected in the acoustic signal;

[0042] - figure 11 represents the simplified structure of a device implementing the method according to a particular embodiment of the invention.

[0043] Detailed description of the invention

[0044] In all figures of this document, identical elements and steps are designated by the same numerical reference.

[0045] In the remainder of the description, an example of implementation of the invention is considered in the context of a tracheal acoustic signal, that is to say an acoustic signal obtained on the trachea of ​​an individual to carry out an examination of the respiratory activity of the latter during sleep (for example to diagnose a sleep apnea syndrome). The invention is of course not limited to this particular context, and can be applied to any type of acoustic signals representative of a respiratory activity of a living being.

[0046] Figure 1 represents, in a generic manner, a flowchart of a particular embodiment of the method according to the invention. This flowchart illustrates the main steps of implementing the method, denoted S1 to S4. These steps are implemented by a device (the principle of which is described later in relation to Figure 11) and aim to determine the inspiration and expiration phases of a respiratory activity of an individual.

[0047] Figure 2 shows an individual X, in a lying position, subjected to a respiratory examination, for example a ventilatory polygraphy. Individual X has an acoustic sensor 1 at the level of his trachea, held by a medical adhesive. Such a sensor 1 is configured to capture sound pressure waves coming from the trachea of ​​individual X during his sleep. These sound pressure waves are transformed by the sensor into analog electrical signals, the latter then being converted into digital signals before being transmitted to a processing unit 2. The processing unit 2 is connected to the sensor 1 via an electrical connection 3 (or via a short-range wireless connection for example). In order to allow processing over a sufficiently large frequency range, the sensor 1 is configured so as to have a bandwidth typically extending between 10 Hz and 10 kHz.Of course, this frequency range is given as an illustrative example and other ranges can be envisaged without departing from the scope of the invention depending on the intended application or the examination carried out. The processing unit 2, for its part, is configured to receive, store and process the signals transmitted by the sensor 1. It has the program code instructions allowing the implementation of the method of the present invention. A human-machine interface connected to the processing unit allows the user (medical personnel in this case) to monitor the evolution of the respiratory activity of the individual X and to execute the method of the present invention for analysis and diagnosis purposes.

[0048] In the remainder of the document, the term "acoustic signal" means the electrical signals representative of the respiratory activity of individual X which were collected and recorded by processing unit 2 during the examination.

[0049] An individual's respiratory activity is typically composed of respiratory cycles, each cycle comprising an inhalation phase and an exhalation phase that produce sound pressure waves within the individual. The inhalation phase corresponds to a filling of the lungs during which the diaphragm and intercostal muscles contract. The exhalation phase corresponds to an emptying of the lungs during which the thoracic muscles are relaxed.

[0050] The process is initiated by activating the recording of the respiratory activity of individual X or after a predetermined recording duration.

[0051] At step SI (referenced “OBT_S”), the device acquires the tracheal acoustic signal of individual X. An example of a tracheal acoustic signal (referenced “SAT”) is shown in Figure 4.

[0052] In step S2 (referenced “DET_PA”), the device proceeds, by signal analysis, to detect the pause intervals contained in the SAT signal. This detection step is based on the implementation, by the device, of a frequency processing of the SAT signal and / or an energy processing of the SAT signal. The principle of these two processing operations is described in detail below in relation to blocks A and B of the flowchart in Figure 3. The detected pause intervals are stored in a local table of the device.

[0053] A "pause interval" is a time interval during which the corresponding portion of the signal is representative of a respiratory pause, in other words an absence of respiratory activity. This absence of respiratory activity, characteristic of a cycle of classic respiratory activity, is easily identified in the signal in both the frequency and energy domains.

[0054] In step S3 (referenced “DIS_P”), the device makes a distinction, among the pause intervals detected in step S2, between a first type of pause interval, called “short pause” and a second type of pause interval, called “long pause”, according to the estimated duration for each of the pause intervals. Here, it is considered that an interval of the “short pause” type is of shorter duration than an interval of the “long pause” type.

[0055] According to a particular implementation, after having estimated the duration of the detected pause intervals, the device carries out a comparison of the duration of the pause intervals which follow one another two by two in time to determine which is the short pause and which is the long pause.

[0056] In a complementary or alternative manner, the device compares the duration of each of the pause intervals according to a predetermined threshold. Such a threshold consists of a duration chosen to differentiate long pauses from short pauses among the pause intervals detected. For example, a pause interval is considered to correspond to a long pause if the estimated duration for this interval is greater than said threshold. Otherwise, it corresponds to a short pause if the estimated duration for this interval is less than said threshold.

[0057] In step S4 (referenced “DET_PH”), the device determines the time intervals of the SAT signal corresponding to the inspiration and expiration phases, taking into account the following ordering rule: a time interval corresponds to an inspiration phase if it is between a long pause and a short pause, and to an expiration phase if it is between a short pause and a long pause. Indeed, in a respiratory cycle in a normal resting situation, the inspiration phase is followed by an inspiration pause (or short pause), which is followed by an expiration phase, itself followed by an expiration pause (or long pause), the short pause being of shorter duration than the long pause. In other words, the principle is based on the comparison, for each time interval between two successive pauses, of the pause preceding and the pause following said interval.An inspiration is followed by a shorter pause than the one preceding it, an expiration is followed by a longer pause than the one preceding it. It is on the basis of this observation that the aforementioned ordering rule was established for the present invention.

[0058] Thus, at the end of step S4 of the method, the device has a segmentation of the SAT signal into time intervals each associated with one of the following three categories: an inspiration phase, an expiration phase, a pause. This information can be provided in the form of a transient logic signal representative of the respiratory activity of individual X, the logic states of which correspond to the respiratory phases and pauses of said individual. The device communicates to the human-machine interface the logic signal representative of the respiratory activity of individual X, for display and diagnostic purposes by medical personnel.

[0059] Thus, the general principle of the method is based on searching in a tracheal acoustic signal for pauses in the respiratory activity of an individual to deduce the inspiration and expiration phases contained in this signal. This technique for recognizing respiratory phases is particularly effective because it focuses on processing, as a priority, portions of the signal corresponding to respiratory pauses, easily recognizable in the frequency and energy domains. It is by observing the temporal evolution of tracheal acoustic signals in the frequency and energy domains that the inventors of the present invention have noticed that pauses are more easily identified than the inspiration and expiration phases as such.By offering the possibility of determining the inspiratory and expiratory phases solely using tracheal sounds captured from an individual, the method of the invention thus opens up prospects for simplified and less invasive examination, also requiring lighter medical diagnostic equipment.

[0060] We now present, in relation to Figure 3, a particular implementation of the method in which steps S2, S3 and S4 of the flowchart described above are more fully detailed.

[0061] After recovering the tracheal acoustic signal SAT at step SOI (referenced “ACQ_S”), the device first applies an anti-noise high-pass filter to the signal at step S02 (referenced “FPH”), for example a Butterworth type filter of order 4 having a cut-off frequency equal to 100 Hz. The function of this high-pass filter is to remove from the SAT signal a predefined frequency range corresponding to the cardiovascular noises emitted by individual X through his trachea. The signal obtained at the output of the high-pass filter is a filtered signal in the time domain, subsequently called the filtered signal 'xf.

[0062] The observation of the frequency-energy temporal representation allowed us to observe that it is on this type of representation that pauses in respiratory activity are easiest to recognize. Two physical quantities distinguish pauses from respiratory phases (inspiration / expiration): frequency content and energy. It appears in fact that the energy of the tracheal acoustic signal is minimal during pauses since it corresponds to an absence of breathing and that the spectrum of the signal corresponding to a pause is close to that of white noise in the frequency band between 100 and 2000 Hz.

[0063] Two specific techniques are proposed for processing the filtered signal 'xf: frequency processing (represented by the dotted block A) and energy processing (represented by the dotted block B). The second technique is described later.

[0064] > Frequency signal processing

[0065] In step SU, the device performs a segmentation of the filtered signal xf to obtain a plurality of samples of this signal. For example, the filtered signal x / is divided into segments of 200 samples each corresponding to 50 ms. Each segment, noted , is further divided into three sub-segments which overlap at 50%. Then, the device estimates the power spectral density (also known as “PSD”) of each segment Z so as to transform the filtered signal x / into a frequency signal, noted 'F cent ', in the time domain.

[0066] The estimated PSD of segment Z, denoted 'P xx [k, Z]', is equal to the average of the PSD of the three sub-segments composing the segment Z. The index k represents the index of the frequency 'F k ' such that F k = k.Fs / Nff t , with frequency Fs equal to 4kHz, Nff tthe number of points of the Fourier transform (assuming that Nff t is an even number) and k an integer in the interval [0 - Nff t / 2] For each segment I of the signal xf, the device estimates in step S12 (“EST_F”) the centroid frequency F cent [l\ by means of the following relation:

[0067] Step S13 (“DET_SF”) consists of determining a variable frequency threshold, denoted Thf, which will be used in step S14 to identify the pause intervals contained in the acoustic signal. To do this, the device defines a sliding time window of predefined size corresponding substantially to the average duration of a respiratory cycle, then applies this sliding window to the frequency signal F cent to determine the frequency threshold whose value is a function of the frequency maximum of the frequency signal F centin the sliding window considered. For example, as illustrated in Figure 5, a time window of predefined size corresponding to 80 samples (i.e. a window of duration substantially equal to 4 seconds) is applied to the frequency signal F cent . For each applied window, the device determines the maximum value of the frequency signal F cent of this window (noted Fcent MAX sur the figure), and subtracts from this maximum value a predefined frequency value AF to deduce the value of the frequency threshold Thf for this window. The predefined frequency value AF is typically between 100 Hz and 300 Hz.

[0068] Thus, rather than defining a frequency threshold of predetermined value, the device according to the invention proposes a calculation of a variable threshold which comes as close as possible to the shape of the frequency signal, which makes it possible to provide a method with increased reliability.

[0069] Note that the centroid frequency is close to 1000 Hz during pauses, which corresponds to the Nyquist frequency divided by two. This result is consistent with the hypothesis of white noise in a frequency band between 100 and 2000 Hz.

[0070] In step S14 (“DET_PA1”), the device carries out the shaping, from the frequency signal F cent , of a transient logic signal PauseS whose logic levels are a function of the frequency threshold values ​​Thf determined in step S13. An example of a logic signal PauseS , resulting from frequency processing, is shown in Figure 6. This signal PauseS is representative of the pauses contained in the signal SAT. Thus, for a given point of the frequency signal F cent, if the frequency value associated with this point is greater than the frequency threshold value Thf determined for this point, then the logic level of the signal PauseS takes the value 1, which means that a pause interval is detected. Conversely, if the frequency value associated with this point is equal to or less than the frequency threshold value 77î / determined for this point, then the logic level of the signal PauseS takes the value 0, which means that no pause interval is detected. The detected pause intervals are then stored in the local table of the device. The frequency processing ends at the end of this step S14.

[0071] > Energy signal processing

[0072] The device first applies, in step S21, a low-pass filter to the filtered signal xf (referenced "FPB") in order to remove the frequencies for which the tracheal sound intensity level is low. The application of a 6th order Butterworth type filter having a cut-off frequency equal to 1,500 Hz, for example, leads to a filtered signal xf whose frequency range is between 100 and 1,500 Hz, corresponding to the most energetic frequency band of tracheal sounds.

[0073] In step S22 (“EST_I”), the device defines a first sliding time window of predefined size, then applies this first window to the filtered signal xf in order to estimate the acoustic intensity of this filtered signal. For example, as illustrated in Figure 7, a root mean square envelope or RMS envelope (for “Root Mean Square”) or root mean square envelope, is calculated from the filtered signal xf using a sliding time window of size equal to 125 samples for example (i.e. a window of duration substantially equal to 0.031 s), so as to obtain an energy signal, denoted 'If, evolving in the time domain (the acoustic intensity level of the filtered signal xf being proportional to the magnitude of the RMS envelope calculated from this signal).

[0074] Step S23 (“DET_SI”) consists of determining the variable intensity threshold, noted Thi, which will be used in step S24 to identify the pause intervals contained in the acoustic signal.

[0075] To do this, the device determines a second sliding time window, but this time of variable size W depending on the respiratory period PR. The respiratory period PR is itself determined by means of an autocorrelation function, noted r If , applied to the energy signal / / using the following equation: with: k, an integer between 0 and N — 1,

[0076] N, the number of points in the autocorrelation window, with N = 240000 (corresponding to 60 seconds at the sampling frequency Fs = 4 kHz),

[0077] Z, an integer between (-N + 1) and (N - 1).

[0078] For Z > 2000 (i.e. 1 / 2 s), the respiratory period PR is deduced from the location of the maximum of the function r If [l]. Then, we consider that the size W of the second sliding time window represents a fraction, less than 0.5, of the respiratory period PR (for example 0.4 x PR) in order to take into account the smallest duration that an inspiration phase can present. We start the search at 1 / 2 second because the autocorrelation function is maximum when Z = 0.

[0079] Then, the device applies the second sliding windows determined above on the energy signal / / in order to identify the minimum value of the sound intensity of the energy signal / / (noted IMI P) appearing for each second sliding window determined above. To do this, the device searches, for a given instant of the signal, for the minimum sound intensity 0.2 x PR before and 0.2 x P^after said instant. Then, for each sliding window considered, a predefined intensity value DI is added to the minimum sound intensity value determined for said window considered, so as to deduce the intensity threshold value to be taken into account for said window considered. The predefined intensity value DI is typically between 1 and 2 dB.

[0080] Thus, the device of the invention proposes a variable threshold calculation which comes as close as possible to the shape of the energy signal, which makes it possible to provide a method with increased reliability.

[0081] In step S24 (“DET_PA2”), the device proceeds to shape, from the energy signal / / , a transient logic signal PauseE whose logic levels are a function of the intensity threshold values ​​Thi determined in step S13. An example of a logic signal PauseE is shown in Figure 8. As for the logic signal PauseS, this signal PauseE is representative of the pauses contained in the signal SAT. Thus, for a given point of the signal / / , if the sound intensity level associated with this point is lower than the intensity threshold determined for this point, then the logic level of the signal PauseE takes the value 1, signifying that a pause interval is detected. Conversely, if the intensity level associated with this point is greater than or equal to the intensity threshold determined for this point, then the logic level of the signal PauseE takes the value 0, signifying that no pause interval is detected.

[0082] The pause intervals thus detected are then stored in the local table of the device. Frequency processing ends at the end of this step S24.

[0083] At the end of processing steps S14 and S24, the device can decide to return the timing diagrams of the current PauseE and PauseS logic signals to the user via the human-machine interface, in order to highlight the respiratory pauses contained in the SAT signal via frequency processing and energy processing.

[0084] In step S03 (“REG_&_DIST-P”), the device has a first set of pause intervals resulting from the frequency processing (timing diagram of the logic signal PauseS) and a second set of pause intervals resulting from the energy processing (timing diagram of the logic signal PauseE). The device will then process the logic signals PauseS and PauseE by an 'OR-Inclusive' logic function so as to obtain a final logic signal 'Pause' whose high logic levels correspond to the detected pause intervals. As illustrated in Figure 9, if there is a logic level of value 1 for at least one of the logic signals PauseS and PauseE, the logic level of the final signal takes the value 1 (signifying that a pause interval is detected), otherwise the logic level of the final signal takes the value 0 (signifying that no pause interval is detected).The device thus groups together the pause intervals from the two chronograms PauseS and PauseE.

[0085] Thus, as described previously, the embodiment described here is based on a simultaneous implementation of the two signal processing operations. Such an embodiment makes the method even more reliable and robust. It is entirely possible, as an alternative, to implement only one of the two aforementioned processing operations to identify the pause intervals in the acoustic signal, for example to gain processing speed or because one of the two processing operations is more suited to the nature of the acoustic signal studied.

[0086] The device first checks whether successions of pause intervals separated by a time interval - called an aberrant interval - of duration less than a predetermined threshold are present in the logic signal obtained at the end of step S03. The value of this predetermined threshold is chosen to be of very short duration, that is to say a duration typically less than 1 / 4 s. Thus, a time interval between two pauses of duration less than the predetermined threshold is considered by the device as an aberration of the signal and must be part of a single pause interval. In the event of a positive verification for two given successive pauses, the time interval grouping the two pauses of said succession and the aberrant interval is replaced, in the final logic signal by a new pause interval (of logic level 1). In the event of a negative verification, no replacement is made.

[0087] In the next step S04 (“DET_PH”), the device determines the inspiration and expiration phases of the acoustic signal by comparing, for each remaining time interval, the duration of the preceding pause relative to the duration following said interval. The device considers that a time interval of the low logic level signal corresponds to:

[0088] - an inspiration phase if it is between a long pause and a short pause; or

[0089] - an expiration phase if it is between a short pause and a long pause.

[0090] Indeed, we recall that in a typical respiratory cycle, an inspiration is preceded by a long pause and followed by a short pause and an expiration is preceded by a short pause and followed by a long pause.

[0091] A simple comparison of the relative duration of the pauses preceding and following each time interval is thus carried out by the device. It is therefore not necessarily useful to measure the duration and then allocate a duration state based on this measurement to the detected pauses. Alternatively, it is possible to configure the device to calculate the absolute value of the duration of the detected pauses, and then to carry out a comparison of the calculated values ​​to deduce the expiration and inspiration phases of the signal.

[0092] This information is stored in a local table of the device.

[0093] As illustrated in Figure 9, in step S04, the device knows, by comparing the durations, that the pause T2 of the Pauses signal is a short pause and that the pause T4 is a long pause. Since an expiration phase is preceded by a short pause and followed by a long pause, it deduces, in step S04, that the respiratory activity interval T3 corresponds to an expiration phase.

[0094] Step S05 (“CLAJND”) consists of further improving the determination algorithm according to the invention by verifying whether, for certain time intervals, the respiratory phase to which they are allocated would not be inconsistent with a conventional respiratory cycle. This step is carried out according to one or more predetermined inconsistency criteria relating to the human respiratory cycle. A succession of at least two inspiration or expiration phases constitutes an example of an inconsistency criterion applicable to the present invention. The cycles which do not respect the consistency criteria are then classified as indeterminate. The person skilled in the art is able to adapt the list of possible inconsistency criteria and possibly combine them according to the weight he wishes to give to this step of the algorithm. In the event of a positive verification for a given interval, the latter is considered to be an “indeterminate interval”.For each indeterminate interval of the signal, the device processes the portion of the signal corresponding to said indeterminate interval by means of a supervised machine learning method, such as for example the method known as “Random forest” based on random decision trees. This method is adapted to each patient by carrying out the learning phase using the supposedly well-classified cycles of the latter. The characteristics are extracted from the filtered signal xf, for example the duration, the energy, the power, the shape, the spectral content, or any other characteristic that a person skilled in the art can determine.

[0095] In a complementary or alternative manner, a simple treatment of indeterminate intervals based on the coherence of the successions of respiratory phases and the known durations of the inspiration and expiration phases, can be implemented prior to or simultaneously with the learning method to allow all or part of the indeterminate intervals to be reclassified simply and quickly.

[0096] Thanks to this step, we further refine the mechanism for recognizing inspiration and expiration phases when certain specific phases meet the said inconsistency criterion.

[0097] Finally, in step S06 (“FOU_SL”), the device provides, via the human-machine interface, the information relating to the respiratory phases previously determined in the form of a transient logic signal capable of being interpreted by qualified medical personnel. As illustrated by way of example in the timing diagram of Figure 10, such a logic signal SL has a low logic level (of value equal to 0) when it is an inspiration phase (denoted “Inspi” in the figure) or an expiration phase (denoted “Expi”), and a high logic level (of value equal to 1) when it is a pause. The parameters associated with the inspiration and expiration phases of the respiratory activity of individual X can be deduced from this logic signal SL for diagnostic purposes.

[0098] Figure 11 shows the simplified structure of a device 100 implementing the determination method according to the invention (for example the particular embodiment described above in relation to Figures 1 to 10). This device comprises a random access memory 130 (for example a RAM memory), a processing unit 110, equipped for example with a processor, and controlled by a computer program stored in a read-only memory 120 (for example a ROM memory or a hard disk). At initialization, the code instructions of the computer program are for example loaded into the random access memory 130 before being executed by the processor of the processing unit 110. The processing unit 110 receives as input the tracheal acoustic signal 140 (for example the SAT signal).The processor of the processing unit 110 processes the signal 140 according to the instructions of the computer program and generates at output 150 a final transient logic signal highlighting the different respiratory phases of the individual. This processing is carried out using means for detecting pause intervals, means for distinguishing between long pauses and short pauses and means for determining respiratory phases as a function of the detected pauses.

[0099] This figure 11 illustrates only one particular way, among several possible ones, of carrying out the different algorithms detailed above, in relation to figures 1 and 3. Indeed, the technique of the invention is carried out indifferently: on a reprogrammable computing machine (a PC computer, a DSP processor or a microcontroller) executing a program comprising a sequence of instructions, or on a dedicated computing machine (for example a set of logic gates such as an FPGA or an ASIC, or any other hardware module).

[0100] In the case where the invention is implemented on a reprogrammable computing machine, the corresponding program (i.e. the sequence of instructions) may be stored in a removable storage medium (such as for example a floppy disk, a CD-ROM or a DVD-ROM) or not, this storage medium being partially or totally readable by a computer or a processor.

[0101] The particular embodiment presented above is based on the processing of a tracheal acoustic signal. Of course, it is entirely possible to apply the method of the invention to an acoustic signal originating from another organ of the individual, such as a pulmonary acoustic signal for example (to cite only one example of application). More generally, the technique of the invention applies to any type of acoustic signal representative of the respiratory activity of an individual.

Claims

DEMANDS 1. Method for determining respiratory phases in an acoustic signal representative of an individual's respiratory activity, respiratory activity being defined by respiratory cycles each comprising an inspiration phase and an expiration phase, the method being characterized in that it comprises the following steps: detection (S2) of pause intervals in the acoustic signal; determination (S4) of time intervals corresponding to inspiration phases and of time intervals corresponding to expiration phases by comparison, for each time interval, of the duration of the pause interval preceding said time interval with the duration of the pause interval following said time interval.

2. Method according to claim 1, wherein, if at the end of the detection step (S2) at least one succession of two pause intervals separated in the signal by a time interval, called aberrant interval, of duration less than a predetermined duration threshold is identified: a replacement step is carried out, for each detected succession, of the set consisting of the two pause intervals and said aberrant interval with a new pause interval.

3. A method according to any one of claims 1 and 2, wherein the following steps are carried out, if at the end of the determination step (S4) at least one time interval, referred to as the indeterminate interval, meeting a predetermined inconsistency criterion, is identified: processing, for each indeterminate interval, of the portion of the signal corresponding to said indeterminate interval, by means of a machine learning method; association of said at least one indeterminate interval with an inspiration or expiration phase according to the results of the processing step.

4. A method according to any one of claims 1 to 3, wherein the pause interval detection step (S2) is based on a processing belonging to the group comprising: a frequency processing of the acoustic signal; an energy processing of the acoustic signal.

5. A method according to claim 4, wherein the frequency processing comprises the following steps: applying a high-pass noise filter to said signal to remove a first predefined range of frequencies from said signal and obtain a time-filtered signal; segmenting said filtered signal to obtain a plurality of samples of said filtered signal and, for each sample, estimating the average power spectral density of said signal sample in such a way as to obtain a frequency signal representing the centroid frequency as a function of time; application of a sliding time window of predetermined duration to said frequency signal and, for each window: * detection of a frequency maximum of the frequency signal within said window, * determination of a frequency threshold as a function of the maximum frequency detected in said window; shaping, from said frequency signal, of a first transient logic signal of logic levels defined as a function of the frequency thresholds determined for said frequency signal, the pause intervals being detected as a function of the first transient logic signal.

6. A method according to any one of claims 4 and 5, wherein the energy processing comprises the following steps: applying a high-pass noise filter and a low-pass filter to remove a first and second predefined frequency ranges from said signal, respectively, and obtain a time-filtered signal; applying a first sliding time window of predetermined duration to said filtered signal and, for each time window, estimating the acoustic intensity of said filtered signal by applying a root mean square envelope to said window, so as to transform said filtered signal into a time-dependent energy signal; applying a second sliding time window of duration determined by autocorrelation to said energy signal and, for each window: * detection of a minimum intensity of the energy signal within said window, * determination of an intensity threshold determined according to the minimum intensity detected in said window; shaping, from said energy signal, of a second transient logic signal of logic levels defined according to the intensity thresholds determined for said energy signal, the pause intervals being detected according to the second transient logic signal.

7. Method according to claim 6, comprising a shaping step, by processing said first and second transient logic signals by an inclusive OR logic function, of a final logic signal of high logic levels corresponding to said detected pause intervals.

8. Method according to claim 7, comprising a step consisting of, if at the end of the shaping step, at least one succession of two pause intervals separated by an aberrant interval detected in said final logic signal of duration less than the predetermined duration threshold is identified: - replace, for each succession detected in said final logic signal, of the set consisting of the two pause intervals and said aberrant interval with a new pause interval.

9. Product computer program, comprising program code instructions for implementing the method according to at least one of claims 1 to 8, when said program is executed on a computer.

10. A computer-readable and non-transient storage medium storing a computer program product according to claim 9.

11. Device for determining respiratory phases in an acoustic signal representative of an individual's respiratory activity, respiratory activity being defined by respiratory cycles each comprising an inspiration phase and an expiration phase, the device being characterized in that it comprises: means for detecting pause intervals in the acoustic signal; means for determining activity intervals corresponding to inspiration phases and activity intervals corresponding to expiration phases, taking into account, by comparison, the duration of the pause intervals.