Method and apparatus for prenatal hypoxia detection

Abstract

Systems and methods for assessing a level of prenatal hypoxia or placenta maturity. The method comprises transmitting ultrasonic waves into an in-vivo placenta, receiving ultrasonic reflections from the placenta, converting the received ultrasonic reflections into electrical signals, computationally determining, from the electrical signals, at least one measure of placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves, and determining the level of prenatal hypoxia or placenta maturity based on the at least one measure of the placenta tissue properties.

Description

METHOD AND APPARATUS FOR PRENATAL HYPOXIA DETECTIONReference to Related Applications

[0001] This application claims priority to, and for the purposes of the United States of America the benefit under 35 USC § 119 in relation to, US application No. 63 / 694789 filed 13 September 2024, which is hereby incorporated herein by reference.FieldThe present disclosure relates to ultrasound systems and methods. Some embodiments provide systems and methods of quantitative ultrasound (QUS) useful for assessing a level of prenatal hypoxia.Background

[0002] Ultrasound may be applied to obtain quantitative information about a sample (e.g. tissues). To acquire the quantitative information, ultrasound pulses are transmitted into the tissue and reflected ultrasonic waves are received back from the tissue. Properties of the tissue can be derived from the received ultrasonic waves.

[0003] For example, the placenta connects a developing fetus in the uterus to the mother’s blood supply and performs several vital functions for the developing fetus such as transferring nutrient and oxygen to the fetus, removing waste products from the fetus and producing hormones needed to support the pregnancy and fetal development, etc. An unhealthy placenta may not properly perform one or more of these functions. One of the possible complications in an unhealthy placenta is fetal hypoxia, a condition where the fetus does not receive enough oxygen.

[0004] Fetal hypoxia, if undetected and untreated, may result in fetal growth restriction, birth complications, brain damage to the fetus, and in some cases, stillbirth. Therefore, it is desirable for health care providers to be able to detect and assess a level of prenatal fetal hypoxia to provide appropriate care and / or intervention.

[0005] Various techniques have been proposed to detect prenatal hypoxia. One example prior art technique is to construct a biophysical profile of the fetus by combining an ultrasound exam and a non-stress test to assess factors such as: fetal breathing movements, body movements, muscle tone, amniotic fluid volume, and heart rate, etc. The biophysical profile serves as a comprehensive assessment that provides a good indication of fetal well-being. However, a biophysical profile is time-consuming and costly, as it requires various types of specialized equipment.

[0006] There is a general desire for improved and accessible systems and methods for assessing a level of prenatal hypoxia using ultrasound.Summary

[0007] The following embodiments and aspects thereof are described and illustrated in conjunction with systems, tools and methods which are meant to be exemplary and illustrative, not limiting in scope. In various embodiments, one or more of the above-described problems have been reduced or eliminated, while other embodiments are directed to other improvements.

[0008] This invention has a number of aspects. These include, without limitation:• systems and methods for imaging tissue of a patient;• systems and methods for assessing a level of prenatal hypoxia;• systems and methods for assessing a level of prenatal hypoxia based on QUS;• systems and methods for assessing a level of prenatal hypoxia based on at least one measure of one or more placenta tissue properties;• systems and methods for assessing a level of prenatal hypoxia based on at least one of: attenuation, backscatter coefficient, effective scatterer diameter, frequency dependence of attenuation, and speed of sound.

[0009] One aspect of the invention provides a method for assessing a level of prenatal hypoxia. The method comprises transmitting ultrasonic waves into an in-vivo placenta, receiving ultrasonic reflections from the placenta, converting the received ultrasonic reflectionsinto electrical signals, computationally determining, from the electrical signals, at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves, and determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

[0010] In some embodiments, the at least one measure of the one or more placenta tissue properties comprise attenuation.

[0011] In some embodiments, the at least one measure of the one or more placenta tissue properties comprises a backscatter coefficient.

[0012] In some embodiments, the at least one measure of the one or more placenta tissue properties comprises an effective scatterer diameter.

[0013] In some embodiments, the at least one measure of the one or more placenta tissue properties comprises a frequency dependence of attenuation.

[0014] In some embodiments, the at least one measure of the one or more placenta tissue properties comprises a speed of sound.

[0015] In some embodiments, the determining the level of prenatal hypoxia comprises comparing the at least one measure of the one or more placenta tissue properties to known measures of the one or more placenta tissue properties in pregnancies without hypoxia.

[0016] In some embodiments, the determining the level of prenatal hypoxia comprises applying a regression model to classify the at least one measure of the one or more placenta tissue properties, the regression model trained on a data set comprising data points corresponding to prenatal hypoxia and data points corresponding to pregnancies without hypoxia.

[0017] In some embodiments, the determining the level of prenatal hypoxia comprises applying an artificial intelligence model to classify the at least one measure of the one or more placenta tissue properties, the artificial intelligence trained on a data set comprising data points corresponding to prenatal hypoxia and data points corresponding to pregnancies without hypoxia.

[0018] In some embodiments, determining the level of prenatal hypoxia comprises determining a risk percentage.

[0019] In some embodiments, determining the level of prenatal hypoxia comprises determining a risk category, from among a plurality of categories.

[0020] In some embodiments, the electrical signals comprise baseband signals.

[0021] In some embodiments, the electrical signals comprise demodulated signals.

[0022] In some embodiments, the electrical signals comprise radiofrequency signals.

[0023] In some embodiments, the transmitting the ultrasonic waves comprises transmitting multiple pulses of the ultrasonic waves.

[0024] In some embodiments, the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves at multiple frequencies.

[0025] In some embodiments, the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves at multiple amplitudes.

[0026] In some embodiments, the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves from multiple directions.

[0027] In some embodiments, the method comprises the step of regularizing the at least one measure of the one or more placenta tissue properties to remove noise from the at least one measure of the one or more placenta tissue properties prior to the determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

[0028] In some embodiments, determining the level of prenatal hypoxia comprises determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties and additional diagnostic measures. In some embodiments, the additional diagnostic measures comprise one or more biometric measurements of the placenta and / or a fetus connected to the placenta. In some embodiments, the one or more additional diagnostic measurements comprise at least one of: Doppler analysis of blood, B-mode texture of tissue, placenta size, placenta shape, fetal head size, fetal organ size, fetal heart rate, maternal heart rate, chart data, etc.

[0029] The region of interest may be delimited by a configurable distance, the distance extending from transducers configured to transmit the ultrasonic waves. The configurable distance may be about 10cm.

[0030] The region of interest my comprise a plurality of sub-regions collectively forming the region of interest. The received ultrasonic reflections may comprise a spatially resolved dataset of spatially resolved components of the at least one measure of the one or more placentatissue properties wherein each spatially resolved component of the spatially resolved dataset corresponds to a corresponding one of the plurality of sub-regions.

[0031] A value of the at least one measure of the one or more placenta tissue properties may be determined for each of the plurality of sub-regions based on the corresponding spatially resolved component of the spatially resolved dataset.

[0032] Determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties may be based, at least in part, on a timing of data acquisition of the at least one measure of the one or more placenta tissue properties.

[0033] Determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties may be based, at least in part, on data obtained at different times during the pregnancy.

[0034] Determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties based on the data obtained at different times during the pregnancy may comprise evaluating differences or trends in the at least one measure of the one or more placenta tissue properties over time. Evaluating the differences or trends in the at least one measure of the one or more placenta tissue properties over time may comprise determining rate(s) of change of the at least one measure of the one or more placenta tissue properties.

[0035] Determining the level of prenatal hypoxia may comprise, at least in part, evaluating variations in the value of the at least one measure of the one or more placenta tissue properties across different locations within the region of interest. Evaluating the variations in the value of the at least one measure of the one or more placenta tissue properties across the different locations within the region of interest may comprise comparing the variances of the at least one measure of the one or more placenta tissue properties to variances of the at least one measure of the one or more placenta tissue properties in other tissue regions outside the region of interest.

[0036] Another aspect of the invention provides a method for assessing a level of prenatal hypoxia comprising: obtaining ultrasonic data for one or more diagnostic cases, wherein the ultrasonic data for each of the one or more diagnostic cases are associated with corresponding acoustic waves reflected from a corresponding region of interest of that includes an in-vivoplacenta; and providing the ultrasonic data as inputs into a machine learning model, wherein the machine learning model is trained to determine the level of prenatal hypoxia for each of the one or more diagnostic cases based on the corresponding ultrasonic data.

[0037] The machine learning model may be trained to assign, as an output, a probability value to each diagnostic case based on the corresponding ultrasonic data, wherein the probability value reflects the probability of the corresponding diagnostic case being a case of prenatal hypoxia.

[0038] Another aspect of the invention provides a method for assessing a level of prenatal hypoxia. The method comprises receiving acoustic waves reflected from a region of interest that includes in-vivo placenta, computationally determining at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the in-vivo placenta with the acoustic waves, and determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

[0039] Another aspect of the invention provides a method for assessing a level of prenatal hypoxia. The method comprises receiving any one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters determined based on interaction of acoustic waves with an in-vivo placenta, and determining the level of prenatal hypoxia based on the any one or more of the attenuation, backscatter coefficient and effective scatterer diameter parameters.

[0040] Another aspect of the invention provides a system for assessing a level of prenatal hypoxia. The system comprises an ultrasonic unit, the ultrasonic unit comprising: an ultrasonic transducer operable to: transmit ultrasonic waves into an in-vivo placenta; receive ultrasonic reflections from the placenta; and, convert the received ultrasonic reflections into electrical signals; and, a controller, the controller in communication with the ultrasonic transducer and operable to: computationally determine, from the electrical signals, at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; and determine the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

[0041] Another aspect of the invention provides a method for assessing a level of placenta maturity. The method comprises: transmitting ultrasonic waves into an in-vivo placenta;receiving ultrasonic reflections from the placenta; converting the received ultrasonic reflections into electrical signals; computationally determining, from the electrical signals, at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties.

[0042] The at least one measure of the one or more placenta tissue properties may comprise attenuation. The at least one measure of the one or more placenta tissue properties may comprise a backscatter coefficient. The at least one measure of the one or more placenta tissue properties may comprise an effective scatterer diameter. The at least one measure of the one or more placenta tissue properties may comprise a frequency dependence of attenuation. The at least one measure of the one or more placenta tissue properties may comprise a speed of sound.

[0043] Determining the level of placenta maturity may comprise comparing the at least one measure of the one or more placenta tissue properties to known measures of the one or more placenta tissue properties in placentas with known levels of placenta maturity.

[0044] Determining the level of placenta maturity may comprise applying a regression model to classify the at least one measure of the one or more placenta tissue properties, the regression model trained on a data set comprising data points corresponding to placentas with known levels of placenta maturity.

[0045] Determining the level of known levels of placenta maturity may comprise applying an artificial intelligence model to classify the at least one measure of the one or more placenta tissue properties, the artificial intelligence trained on a data set comprising data points corresponding to placentas with known levels of placenta maturity.

[0046] Determining the level of placenta maturity may comprise determining a numerical value.

[0047] Determining the level of placenta maturity may comprise determining a numerical grade, from among a plurality of numerical grades.

[0048] The electrical signals may comprise baseband signals. The electrical signals may comprise demodulated signals. The electrical signals may comprise radiofrequency signals.

[0049] Transmitting the ultrasonic waves may comprise transmitting multiple pulses of the ultrasonic waves. Transmitting the ultrasonic waves may comprise transmitting the ultrasonicwaves at multiple frequencies. Transmitting the ultrasonic waves may comprise transmitting the ultrasonic waves at multiple amplitudes. Transmitting the ultrasonic waves may comprise transmitting the ultrasonic waves from multiple directions.

[0050] The method may further comprise regularizing the at least one measure of the one or more placenta tissue properties to remove noise from the at least one measure of the one or more placenta tissue properties prior to the determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties.

[0051] Determining the level of placenta maturity may comprise determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties and additional diagnostic measures. The additional diagnostic measures may comprise one or more biometric measurements of the placenta and / or a fetus connected to the placenta. The additional diagnostic measures may comprise at least one of: Doppler analysis of blood, B-mode texture of tissue, placenta size, placenta shape, fetal head size, fetal organ size, fetal heart rate, maternal heart rate, chart data.

[0052] The region of interest may be delimited by a configurable distance. The configurable distance may extend from transducers configured to transmit the ultrasonic waves. The configurable distance may be about 10cm.

[0053] The region of interest may comprise a plurality of sub-regions collectively forming the region of interest. The \received ultrasonic reflections may comprise a spatially resolved dataset of spatially resolved components of the at least one measure of the one or more placenta tissue properties wherein each spatially resolved component of the spatially resolved dataset corresponds to a corresponding one of the plurality of sub-regions. A value of the at least one measure of the one or more placenta tissue properties may be determined for each of the plurality of sub-regions based on the corresponding spatially resolved component of the spatially resolved dataset.

[0054] Determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties may be based, at least in part, on a timing of data acquisition of the at least one measure of the one or more placenta tissue properties.

[0055] Determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties may be based, at least in part, on data obtained at different times during the pregnancy.

[0056] Determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties based on the data obtained at different times during the pregnancy may comprise evaluating differences or trends in the at least one measure of the one or more placenta tissue properties over time. Evaluating the differences or trends in the at least one measure of the one or more placenta tissue properties over time may comprise determining rate(s) of change of the at least one measure of the one or more placenta tissue properties.

[0057] Determining the level of placenta maturity may comprise, at least in part, evaluating variations in the value of the at least one measure of the one or more placenta tissue properties across different locations within the region of interest.

[0058] Evaluating the variations in the value of the at least one measure of the one or more placenta tissue properties across the different locations within the region of interest may comprise comparing the variances of the at least one measure of the one or more placenta tissue properties to variances of the at least one measure of the one or more placenta tissue properties in other tissue regions outside the region of interest.

[0059] Another aspect of the invention provides a method for assessing a level of placenta maturity. The method comprises: obtaining ultrasonic data for one or more diagnostic cases, wherein the ultrasonic data for each of the one or more diagnostic cases are associated with corresponding acoustic waves reflected from a corresponding region of interest of that includes an in-vivo placenta; and providing the ultrasonic data as inputs into a machine learning model, wherein the machine learning model is trained to determine the level of placenta maturity for each of the one or more diagnostic cases based on the corresponding ultrasonic data.

[0060] The machine learning model may be trained to assign, as an output, a numerical value to each diagnostic case based on the corresponding ultrasonic data, wherein the numerical value reflects the level of placenta maturity.

[0061] Another aspect of the invention provides a method for assessing a level of placenta maturity. The method comprises: receiving acoustic waves reflected from a region of interestthat includes an in-vivo placenta; computationally determining at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the in-vivo placenta with the acoustic waves; and determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties.

[0062] Another aspect of the invention provides a method for assessing a level of placenta maturity. The method comprises: receiving one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters determined based on interaction of acoustic waves with an in-vivo placenta; and determining the level of placenta maturity based on the one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters.

[0063] Another aspect of the invention provides a system for assessing a level of placenta maturity. The system comprises: an ultrasonic unit, the ultrasonic unit comprising: an ultrasonic transducer operable to: transmit ultrasonic waves into an in-vivo placenta; receive ultrasonic reflections from the placenta; and, convert the received ultrasonic reflections into electrical signals; and, a controller, the controller in communication with the ultrasonic transducer and operable to: computationally determine, from the electrical signals, at least one measure of placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; and, determine the level of placenta maturity based on the at least one measure of placenta tissue properties.

[0064] Other aspects of the invention provide methods and systems according to any feature, combination of features or sub-combination of features described herein.

[0065] In addition to the exemplary aspects and embodiments described above, further aspects and embodiments will become apparent by reference to the drawings and by study of the following detailed descriptions.

[0066] It is emphasized that the invention relates to all combinations of the above features, even if these are recited in different claims.Brief Description of the Drawings

[0067] Exemplary embodiments are illustrated in referenced figures of the drawings. It is intended that the embodiments and figures disclosed herein are to be considered illustrative rather than restrictive.

[0068] Figure 1 is a schematic illustration of an ultrasound system according to an example embodiment of the present technology.

[0069] Figure 2 is a flowchart of a method for assessing a level of prenatal hypoxia according to an example embodiment.

[0070] Figure 3A is a boxplot comparing experimental data of attenuation measurements in a control group to attenuation measurements in a pathology group.

[0071] Figure 3B is a boxplot comparing experimental data of backscatter coefficient measurements in a control group to backscatter coefficient measurements in a pathology group.

[0072] Figure 3C is a boxplot comparing experimental data of effective scatterer diameter measurements in a control group to effective scatterer diameter measurements in a pathology group.

[0073] Figure 4 is a feature analysis plot visualizing experimental QUS data points from an experimental study.

[0074] Figure 5 is flowchart of a method for assessing a level of placenta maturity according to an example embodiment.

[0075] Figure 6A is a plot showing a receiver operator curve (ROC) based on experimental data.

[0076] Figure 6B is a plot showing a calibration curve based on experimental data.Detailed Description

[0077] Throughout the following description specific details are set forth in order to provide a more thorough understanding to persons skilled in the art. However, well known elements maynot have been shown or described in detail to avoid unnecessarily obscuring the disclosure. Accordingly, the description and drawings are to be regarded in an illustrative, rather than a restrictive, sense.

[0078] One aspect of the invention described herein provides systems and methods for assessing a level of prenatal hypoxia. The method comprises transmitting ultrasonic waves into an in-vivo placenta, receiving ultrasonic reflections from the in-vivo placenta, and converting the received ultrasonic reflections into electrical signals. The transmission, reception and conversion of ultrasonic waves may be performed by transducers under the control of a controller. A controller may then computationally determine, based on the electrical signals, at least one measure of placenta tissue properties relating to the acoustic interaction of the placenta with the transmitted ultrasonic waves. A level of prenatal hypoxia may then be determined based on the at least one measure of the placenta tissue properties. The at least one measure of placenta tissue properties may include at least one of: attenuation, backscatter coefficient, effective scatterer diameter, frequency dependence of attenuation, and speed of sound.

[0079] Figure 1 schematically shows an example ultrasound system 10 operable to perform QUS according to an example embodiment. System 10 is operable to transmit ultrasonic waves into a region of interest of a patient P1 located on a bed 17 (or in some other suitable location) and receive ultrasonic reflections from the region of interest. The region of interest may be an in-vivo placenta.

[0080] System 10 comprises an ultrasound unit 12 having a controller 13. An ultrasound transducer 14 is coupled to ultrasound unit 12. Transducer 14 is positioned proximate to a region or volume of tissue of interest to acoustically couple transducer 14 to patient P1 . Transducer 14 may, for example, comprise a 1 D or 2D array of transducer elements. Transducer 14 may have a linear or non-linear transducer face. Transducer 14 may be moved relative to patient P1 to acquire ultrasound data from different regions of patient P1 . For example, as shown in illustrated Figure 1 , transducer 14 may be pivoted angularly about an axis A and / or translated along the skin of patient P1 .

[0081] Transducer 14 may be positioned relative to patient P1 in any suitable manner. For example, in an application of system 10 to measure one or more properties of an in-vivo placenta, transducer 14 may be positioned adjacent to the skin of patient P1 at a location proximate to the in-vivo placenta or transducer 14 may be inserted into the vagina of patient P1 for performing trans-vaginal measurements.

[0082] In some embodiments, transducer 14 is positioned manually relative to patient P1 by an operator of system 10. In some embodiments transducer 14 is positioned and / or moved by a mechanical system. In some embodiments a robotic system is controlled to position transducer 14.

[0083] In some embodiments, system 10 comprises a display 16. Display 16 may display information such as:• settings of system 10 (e.g. set parameters (frequency, amplitude, etc.) of pulse signals);• one or more measures of quality of the quantitative data;• one or more measures of health of the measured tissue;• patient particulars;• ultrasound image;• region of interest;• labels of organs;• etc.

[0084] Ultrasound unit 12 is operative to transmit ultrasonic waves into a region or volume of tissue of interest (e.g. an in vivo placenta) and receive ultrasonic reflections from the region or volume of tissue of interest. For example, controller 13 of ultrasonic unit 12 may control transducers 14 to transmit ultrasonic waves and receive ultrasonic reflections. The basic principles of transmitting and receiving ultrasound waves are well known and are not described further herein.

[0085] Transducer 14 is operative to convert the received ultrasonic reflections into electrical signals. In some embodiments, the electrical signals comprise baseband signals. In some embodiments, the electrical signals comprise demodulated signals. In some embodiments, theelectrical signals comprise radiofrequency (RF) signals. The conversion of received ultrasonic reflections into electrical signals is well known and is not described further herein.

[0086] In some embodiments, system 10 comprises a classifier model 20 accessible to and applicable by controller 13 for assessing a level of prenatal hypoxia in a patient based on the electrical signals received from transducer 14. The application of classifier model 20 by controller 13 is described in more details below. System 10 may be applied to perform one or more methods described herein.

[0087] Figure 2 is a flowchart of a method 100 for assessing a level of prenatal hypoxia according to an example embodiment. Method 100 may be performed by any ultrasonic systems described herein (e.g. system 10).

[0088] Method 100 begins with block 101 which comprises the step of transmitting (e.g. by transducer 14 of system 10) ultrasonic waves into a region of interest that includes an in-vivo placenta. Ultrasonic waves may be transmitted into the region of interest in any suitable manner. For example, ultrasonic waves can be transmitted using a two-dimensional (2D) matrix transducer array or by using a one-dimensional (1 D) transducer array. The transducer may be moved relative to the patient having the in-vivo placenta to acquire ultrasound data from different regions of the patient. For example, as shown in the illustrated Figure 1 , transducer 14 may be pivoted angularly about an axis A and / or translated along the skin of patient P1. In some embodiments, the region of interest is delimited by a configurable distance parameter extending from the transducers 14. For example, if transducers 14 are placed on a skin surface of the patient, then the region of interest may extend into the tissues of the patient up to the configurable delimiting distance from the skin surface. In a non-limiting example embodiment, the configurable distance is about 10cm.

[0089] Ultrasonic waves may be controllably transmitted according to any suitable parameters, including, but not limited to: number of pulses, frequencies, amplitudes, directions, etc. In some embodiments, the ultrasonic waves are transmitted over a range of at least one of the parameters. In some embodiments, transmitting ultrasonic waves comprises transmitting multiple pulses. In some embodiments, transmitting ultrasonic waves comprises transmitting ultrasonic waves at multiple frequencies. In some embodiments, transmitting ultrasonic wavescomprises transmitting ultrasonic waves at multiple amplitudes. In some embodiments, transmitting ultrasonic waves comprises transmitting ultrasonic waves from multiple directions.

[0090] Method 100 then proceeds to block 103 which comprises the step of receiving (e.g. by transducer 14 of system 10) ultrasonic reflections 1 13 from the region of interest that includes an in-vivo placenta. The reception of ultrasonic reflections from a region of interest by a transducer is well known and is not described further herein.

[0091] Method 100 then proceeds to block 105 which comprises the step of converting (e.g. by transducer 14 of system 10) received ultrasonic reflections 113 into electrical signals 1 15. In some embodiments, electrical signals 115 comprise baseband signals. In some embodiments, electrical signals 1 15 comprise demodulated signals. In some embodiments, electrical signals 1 15 comprise radiofrequency (RF) signals. The conversion of received ultrasonic reflections 1 13 into electrical signals 115 is well known and is not described further herein.

[0092] Method 100 then proceeds to block 107 which comprises computationally determining, from electrical signals 115, at least one measure of placenta tissue properties 117 relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves. Step 107 may be performed, for example, by controller 13 of ultrasonic unit 102. In some embodiments, the computation of the at least one measure of placenta tissue properties 1 17 is performed on a region of interest that is delimited by a configurable distance parameter (e.g. a distance from the transducers). In some embodiments, the distance is about 10cm. Ultrasonic reflections associated with tissues located deeper than the configurable distance parameter may be disregarded for the computation of the at least one measure of placenta tissue properties 1 17, such that only ultrasonic reflections generated within region of interest defined by the configurable distance are used in the computation of at least one measure of placenta tissue properties 117. In some embodiments, the measures of placenta tissue properties 1 17 relating to the acoustic interaction of the placenta tissue include at least one of: attenuation, backscatter coefficient, effective scatterer diameter, frequency dependence of attenuation, and speed of sound.

[0093] Attenuation is a quantitative measure of the rate of loss of intensity of the ultrasonic waves as the ultrasonic waves propagate through tissues. The loss may occur due toabsorption, scattering, and reflection of the ultrasonic waves as the waves interact with different types of tissues or materials. Attenuation may be determined by measuring the reduction in signal amplitude as the ultrasound wave propagates through the tissue. A relatively high attenuation number indicates that the tissue is more effective at reducing the intensity of the ultrasound waves. For example, dense tissues, such as bones, or tissues with relatively higher fat content tend to have higher attenuation. On the other hand, a relatively low attenuation number indicates that the tissue allows the ultrasonic waves to pass through with comparatively less loss of intensity. For example, fluid-filled structures (like the bladder or amniotic fluid) tend to have low attenuation.

[0094] The backscatter coefficient is a quantitative measure of the amount of ultrasound energy that is scattered back toward the transducer after interacting with tissues or structures. The backscatter coefficient characterizes how tissues reflect ultrasound waves, providing information about their composition and structure. The backscatter coefficient may be determined as the ratio of the intensity of the scattered ultrasound waves that is returned to the transducer compared to the intensity of incident (transmitted) ultrasound waves. A relatively high backscatter coefficient indicates that the tissues reflect comparatively more ultrasound energy. A relatively low backscatter coefficient indicates that the tissues allow comparatively more of the ultrasound wave to pass through without significant scattering.

[0095] The effective scatterer diameter (ESD) is a quantitative measure used to describe the average size of structures (i.e. scatterers) within a tissue that cause the scattering of ultrasonic waves. ESD may be determined by fitting the measured backscatter data to theoretical scattering models (i.e. models based on Rayleigh or Mie scattering). A relatively larger value of ESD indicates the presence of relatively more larger scatterers (e.g. larger cells or tissue clusters). On the other hand, a relatively smaller value of ESD indicates the presence of relatively more smaller scatterers (e.g. fine capillaries).

[0096] The frequency dependence of attenuation is a quantitative measure reflecting the rate at which the attenuation coefficient changes as a function of frequency of the ultrasonic waves. Frequency dependent of attenuation characterizes a property of the tissue whereby higher- frequency ultrasound waves experience greater attenuation than lower-frequency ultrasoundwaves, resulting in frequency-dependent variation of the attenuation coefficient. The frequency dependence of attenuation is typically estimated by analyzing components of ultrasonic reflections across the frequency bandwidth of the transducer and determining the relative rate at which higher-frequency components are attenuated compared to lower-frequency components over a known propagation distance, often by reference to a calibrated material. A relatively high frequency dependence of attenuation indicates that higher-frequency ultrasound waves are attenuated substantially more than lower-frequency waves, resulting in more rapid signal loss with depth. A relatively low frequency dependence of attenuation indicates that attenuation varies less across frequencies, allowing deeper penetration of higher-frequency waves and reducing any need for frequency-specific compensation.

[0097] The speed of sound is a quantitative measure of how fast ultrasound waves travel through a tissue. The speed of sound characterizes how the composition of tissues affects the timing and path of ultrasonic waves and ultrasonic reflections. In quantitative ultrasound, the speed of sound is typically estimated by timing how long ultrasonic reflections take to return across a known path or by comparing measurements to a calibrated reference. A relatively high speed of sound indicates that waves move faster through the tissue (often associated with stiffer, more tightly bound structures). A relatively low speed of sound indicates slower wave travel (often seen in fattier or fluid-rich tissues).

[0098] In some embodiments, step 107 of determining the measures of placenta tissue properties 1 17 relating to the acoustic interaction of the placenta tissue comprises calibrating the measurement system using a reference phantom of tissue-mimicking material with known acoustic properties. Calibrating the measurement system using the reference phantom may comprise comparing calibration measures to known properties of the phantom. Calibration measures may be obtained from applying ultrasonic waves to the phantom of tissue-mimicking material to obtain electrical signals and compute the relevant quantitative measures (e.g. attenuation, backscatter coefficient, effective scatterer diameter, frequency dependence of attenuation, speed of sound, etc.) based on the electrical signals. Then, the computed values based on measurements of the phantom may be compared to known properties of the phantom to identify any discrepancies. System parameters of the ultrasonic system (e.g.system 10) may then be adjusted, if necessary, to mitigate the discrepancies (e.g. any systemic errors or deviations in the measurements) until the computed measures align with known properties of the phantom.

[0099] Calibration may enable method 100 to obtain comparable accurate values of the measures of placenta tissue properties 1 17 irrespective of the difference in subjects (e.g. difference in location of the placenta relative to transducers), machines (e.g. different types of ultrasonic units 12), transducer arrangement (e.g. transducers 14 positioned on skin of subject vs. transducers 14 used for trans-vaginal placement), timing (e.g. some measurements obtained spaced apart in time from other measurements) and / or the like.

[0100] In some embodiments, the at least one measure of placenta tissue properties 117 relating to the acoustic interaction of the placenta tissue may be determined in a few seconds or less to facilitate near “real-time” execution of step 107. The near “real-time” execution of step 107 has the advantage of allowing a diagnostic opinion to be generated in a relatively short time span, thereby making assessment of hypoxia based on the methods described herein more accessible to patients.

[0101] In some embodiments, the at least one measure of placenta tissue properties 1 17 is determined for each of a plurality of sub-regions within the region of interest to provide spatially resolved data or spatially resolved components of the at least one measure of placenta tissue properties 1 17. For example, by any suitable techniques known in the art (e.g. beamforming), controller 13 of system 10 may correlate specific sub-regions within the region of interest to corresponding spatially resolved components in the dataset of the at least one measure of placenta tissue properties 117. The at least one measure of placenta tissue properties 117 can then be determined for any chosen sub-region in the region of interest to thereby provide a spatially resolved map of values of the at least one measure of placenta tissue properties 117.

[0102] Method 100 proceeds to block 109 which comprises determining a level of prenatal hypoxia 1 19 based on the at least one measure of placenta tissue properties 1 17. In some embodiments, determining the level of prenatal hypoxia 1 19 comprises comparing the at least one measure of placenta tissue properties 1 17 to known measures of placenta tissues properties in pregnancies without hypoxia. The comparison may be performed by a controller(e.g. controller 13) employing any suitable classifier (e.g. classifier 20) for comparing measures 1 17 to known measures in pregnancies without hypoxia.

[0103] In some embodiments, controller 13 comprises a classifier configured to classify the level of prenatal hypoxia 119 based on the at least one measure of placenta tissue properties 117. The classifier may comprise any suitable classification schemes / algorithms. The classifier may be applied to evaluate a level of hypoxia based on values of the at least one measure of placenta tissue properties 1 17. In some embodiments, the classifier comprises a look-up table. In some embodiments, the classifier comprises a regression model trained from data including data points of quantitative measures corresponding to cases of hypoxia and data points of quantitative measures of cases of no hypoxia (i.e. healthy placenta). In some embodiments, the classifier comprises a hyperplane of point cloud configured to classify data points into two or more categories. In some embodiments, the classifier comprises an artificial intelligence model (e.g. a neural network, a machine learning model, etc.) trained from data including data points of quantitative measures corresponding to cases of hypoxia and data points of quantitative measures of cases of no hypoxia (i.e. healthy placenta).

[0104] In some embodiments, the classification schemes / algorithms of the classifier is based, at least in part, on the timing of the data acquisition of the at least one measure of placenta tissue properties 117. The placenta is a transient organ that develops during pregnancy and has a lifespan. The placenta is expected to follow a physical development over the course of the pregnancy from formation, growth to maturity, maintenance and finally expulsion at or shortly after delivery. As a result, the one or more measures of placenta tissue properties 117 also changes over time. The classifier may have different parameterization of the classification schemes / algorithms to account for the changing physical properties of the placenta at different stages of the pregnancy. For example, the classifier schemes / algorithms of the classifier may be different for data acquired at the dating exam / scan, which is typically performed during the first trimester of the pregnancy - around 10-14 weeks of pregnancy, when compared to data acquired at an anatomy scan / exam, which is typically performed during the second trimester of the pregnancy - around 18-22 weeks of pregnancy.

[0105] In some embodiments, the classifier receives QUS data collected at different times of the pregnancy (e.g. placenta tissue properties 1 17 obtained at different times of the pregnancy) as inputs to determine a level of prenatal hypoxia 119. For example, a first set of QUS data may be collected during the first trimester and a second set of QUS data may be collected during the second trimester. The classifier may then receive both the first and second sets of QUS data as input to determine a level of prenatal hypoxia 1 19 based on both the first and second sets of QUS data. It is to be noted that the foregoing example is for illustrative purpose only and is not restrictive. QUS data may be collected at any time during the pregnancy, including, but not limited to, the first, second, third trimesters or at any other time during the pregnancy.

[0106] In some embodiments, determining a level of prenatal hypoxia 1 19 based on QUS data collected at different times of the pregnancy comprises, at least in part, evaluating differences and / or trends in the one or more placenta tissue properties 117 over time. In some embodiments, evaluating differences and / or trends in the one or more placenta tissue properties 117 over time comprises determining rate(s) of change of the at least one placenta tissue properties 1 17 based on the QUS data collected at different temporal stages of the pregnancy.

[0107] In some embodiments, the classifier is configured to determine a level of prenatal hypoxia 1 19 by, at least in part, evaluating variations in the value of the at least one placenta tissue properties 1 17 across different locations within a region of interest. The evaluation of variations in the value of the at least one placenta tissue properties 1 17 across different locations within a region of interest may be performed on spatially resolved data of the at least one measure of placenta tissue properties 1 17. Spatially resolved data may be collected in any suitable manner by any suitable techniques. In some embodiments, evaluating variations in the value of the at least one placenta tissue properties 117 comprises comparing the variances of QUS measures within the region of interest to variances of QUS measures in other tissue regions (outside the region of interest). An advantage of evaluating variations in the value of the at least one placenta tissue properties 117 across different locations within a region of interest is that such evaluation may reveal heterogeneity of placenta properties within theregion of interest, thereby providing key insights into the health of the placenta. For example, a diseased or otherwise non-optimally performing placenta may exhibit greater variance of QUS measures within the region of interest than a healthy placenta.

[0108] In some embodiments, determining a level of prenatal hypoxia 1 19 at step 109 is based on a combination of the at least one measure of placenta tissue properties 1 17 and one or more additional diagnostic measurements. In some embodiments, the one or more additional measurements comprises additional quantitative ultrasound measures. In some embodiments, the additional diagnostic measurements comprise measurements measured independently of the ultrasound system. In some embodiments, the additional diagnostic measurements comprise biometrics of the fetus (e.g. heart rate, size, oxygen level, etc.). In some embodiments, the one or more additional diagnostic measurements comprise at least one of: Doppler analysis of blood, B-mode texture of tissue, placenta size, placenta shape, fetal head size, fetal organ size, fetal heart rate, maternal heart rate, chart data, etc.

[0109] In some embodiments, determining a level of prenatal hypoxia 1 19 comprises determining a risk category from among a plurality of risk categories. For example, the plurality of risk categories may comprise categories of: lower risk, medium risk, and higher risk, and determining a level of prenatal hypoxia 1 19 comprises categorizing the level of prenatal hypoxia 1 19 into one of these risk categories. The risk categories may comprise any suitable categories and / or any suitable discretization of such categories. In some embodiments, the risk categories comprise a binary categorization of “at risk” and “not at risk”. In some embodiments, determining level of prenatal hypoxia 1 19 comprises determining a risk percentage in a range from 0% and 100%.

[0110] In some embodiments, in addition or in the alternative to performing the steps in blocks 107 and 109 of method 100, method 100 proceeds from block 105 to block 122 (shown in dashed lines in Figure 2) which comprises the step of employing a machine learning model which has been trained to receive electrical ultrasonic signals 115 (e.g. from transducer(s) 14) as inputs and to infer a level of prenatal hypoxia 1 19 based on such ultrasound electrical signals 1 15. The block 122 machine learning model may be trained using labelled data (e.g. where each data element comprises a set of ultrasound electrical signal inputs 1 15 labelledwith a corresponding level of prenatal hypoxia), although this is not generally necessary. In some embodiments, the block 122 machine learning model is trained to assign, as an output, a probability value to possible prenatal hypoxia levels based on the corresponding ultrasonic electrical signal inputs 1 15. The block 122 machine learning model may generally comprise any suitable machine learning model(s) with any suitable machine learning architecture(s) and any suitable set of trainable parameters. By way of non-limiting example, in a non-limiting example embodiment where the block 122 machine learning model comprises a neural network, the trainable parameters of the machine learning model may comprise the weights and / or biases of perceptrons of the neural network or otherwise associated with connections between nodes of the neural network.

[0111] In some embodiments, method 100 comprises the optional step 1 11 of regularizing computed measures of placenta tissue properties 117 to remove noise from the at least one measure of placenta tissue properties 1 17 prior to providing the at least one measure of placenta tissue properties 117 to step 109 for determining level of prenatal hypoxia 1 19. Step 1 11 of regularization may comprise any suitable techniques for removing noise. The regularization techniques may include one or more of: smoothing techniques to reduce fluctuations in the data while preserving key structural features, balancing fidelity of fitting with a smoothness constraint to prevent overfitting to noisy data, reducing noise while preserving edges and sharp features in the data, etc. In some embodiments, an artificial intelligence model is applied to determine suitable regularization techniques for removing noise from computed measures of placenta tissue properties 117.

[0112] Determining a level of prenatal hypoxia 119 may assist health care providers (e.g. obstetricians) with decision on actions or necessary interventions for a patient (e.g. prescribing bedrest, prescribing medications, admitting the patient to a hospital for close monitoring, performing a C-section immediately to avoid damage from hypoxia, etc.).

[0113] In some instances, instead of (or in addition to) directly estimating a level of prenatal hypoxia, healthcare providers may prefer obtaining other quantitative measure(s) associated with the placenta to thereby incorporate such quantitative measures within a holistic assessment of the subject. One example of another quantitative measure of the placenta isplacenta maturity. Placenta maturity refers to the development stage of the placenta and may be assessed, for example, by observing calcification patterns of the placenta. Typically, placenta maturity is categorized into numerical grades (e.g. 0 to 3). A higher numerical grade indicates more advanced development and a lower grade indicates comparatively less advanced development.

[0114] FIG. 5 is a flowchart of a method 400 for assessing a level of placenta maturity according to an example embodiment. Method 400 may be performed by any ultrasonic systems described herein (e.g. system 10). Method 400 is similar to method 100 in many aspects. Steps in method 400 that are similar to steps in method 100 are labelled with similar reference numerals except that the reference numerals in method 400 are in the 400-seires and the reference numerals in method 100 are in the 100-series.

[0115] Method 400 starts with block 401 which comprises the step of transmitting (e.g. by transducer 14 of system 10) ultrasonic waves into a region of interest that includes an in-vivo placenta. Block 401 is similar to block 101. The description related to block 101 similarly applies to block 401 , and for the sake of brevity, will not be repeated here.

[0116] Method 400 then proceeds to block 403 which comprises the step of receiving (e.g. by transducer 14 of system 10) ultrasonic reflections 413 from the region of interest that includes an in-vivo placenta. In block 405, the received ultrasonic reflections 413 from the region of interest are converted (e.g. by transducer 14 of system 10) into electrical signals 415. Then in block 407, at least one measure of placenta properties 417 is computationally determined from electrical signals 415. Steps of method 400 in blocks 403, 405 and 407 are similar to the steps of method 100 in blocks 103, 105 and 107. The description related to blocks 103, 105 and 107 similarly applies to blocks 403, 405 and 407, and for the sake of brevity, will not be repeated here.

[0117] Method 400 proceeds to block 423 which comprises determining a level of placenta maturity 425 based on the at least one measure of placenta tissue properties 417. In some embodiments, determining the level of placenta maturity 425 comprises comparing the at least one measure of placenta tissue properties 417 to known measures of placenta tissues properties in pregnancies at known levels of placenta maturity.

[0118] The comparison may be performed by a controller (e.g. controller 13) employing any suitable classifier (e.g. classifier 20) for comparing measures 417 to known measures of placentas with known levels of maturity. In some embodiments, controller 13 comprises a classifier configured to classify the level of placenta maturity 425 based on the at least one measure of placenta tissue properties 417. The classifier may comprise any suitable classification schemes / algorithms. The classifier may be applied to evaluate a level of placenta maturity 425 based on values of the at least one measure of placenta tissue properties 417. In some embodiments, the classifier comprises a look-up table. In some embodiments, the classifier comprises a regression model trained from data including data points of quantitative measures corresponding to placentas at various known levels of maturity. In some embodiments, the classifier comprises a hyperplane of point cloud configured to classify data points into two or more categories. In some embodiments, the classifier comprises an artificial intelligence model (e.g. a neural network, a machine learning model, etc.) trained from data including data points of quantitative measures corresponding to cases of placentas with known levels of maturity.

[0119] In some embodiments, the classification schemes / algorithms of the classifier is based, at least in part, on the timing of the data acquisition of the at least one measure of placenta tissue properties 417. The placenta is a transient organ that develops during pregnancy and has a lifespan. The placenta is expected to follow a physical development over the course of the pregnancy from formation, growth to maturity, maintenance and finally expulsion at or shortly after delivery. As a result, the one or more measure of placenta tissue properties 417 also changes over time. The classifier may have different parameterization of the classification schemes / algorithms to account for the changing physical properties of the placenta at different stages of the pregnancy. For example, the classifier schemes / algorithms of the classifier may be different for data acquired at the dating exam / scan, which is typically performed during the first trimester of the pregnancy - around 10-14 weeks of pregnancy, when compared to data acquired at an anatomy scan / exam, which is typically performed during the second trimester of the pregnancy - around 18-22 weeks of pregnancy.

[0120] In some embodiments, the classifier receives QUS data collected at different times of the pregnancy (e.g. placenta tissue properties 417 obtained at different times of the pregnancy) as inputs to determine a level of placenta maturity 425. For example, a first set of QUS data may be collected during the first trimester and a second set of QUS data may be collected during the second trimester. The classifier may then receive both the first and second sets of QUS data as input to determine a level of placenta maturity 425 based on both the first and second sets of QUS data. It is to be noted that the foregoing example is for illustrative purpose only and is not restrictive. QUS data may be collected at any time during the pregnancy, including, but not limited to, the first, second, third trimesters or at any other time during the pregnancy.

[0121] In some embodiments, determining a level of placenta maturity 425 based on QUS data collected at different times of the pregnancy comprises, at least in part, evaluating differences and / or trends in the one or more placenta tissue properties 417 over time. In some embodiments, evaluating differences and / or trends in the one or more placenta tissue properties 417 over time comprises determining rate(s) of change of the at least one placenta tissue properties 417 based on the QUS data collected at different temporal stages of the pregnancy.

[0122] In some embodiments, the classifier is configured to determine a level of placenta maturity 425 by, at least in part, evaluating variations in the value of the at least one placenta tissue properties 417 across different locations within a region of interest. The evaluation of variations in the value of the at least one placenta tissue properties 417 across different locations within a region of interest may be performed on spatially resolved data of the at least one measure of placenta tissue properties 417. Spatially resolved data may be collected in any suitable manner by any suitable techniques. In some embodiments, evaluating variations in the value of the at least one placenta tissue properties 417 comprises comparing the variances of QUS measures within the region of interest to variances of QUS measures in other tissue regions (outside the region of interest). An advantage of evaluating variations in the value of the at least one placenta tissue properties 417 across different locations within a region ofinterest is that such evaluation may reveal heterogeneity of placenta properties within the region of interest, thereby providing key insights into the state of the placenta.

[0123] In some embodiments, determining a level of placenta maturity 425 at step 423 is based on a combination of the at least one measure of placenta tissue properties 417 and one or more additional diagnostic measurements. In some embodiments, the one or more additional measurements comprises additional quantitative ultrasound measures. In some embodiments, the additional diagnostic measurements comprise measurements measured independently of the ultrasound system. In some embodiments, the additional diagnostic measurements comprise biometrics of the fetus (e.g. heart rate, size, oxygen level, etc.). In some embodiments, the one or more additional diagnostic measurements comprise at least one of: Doppler analysis of blood, B-mode texture of tissue, placenta size, placenta shape, fetal head size, fetal organ size, fetal heart rate, maternal heart rate, chart data, etc.

[0124] In some embodiments, in addition or in the alternative to performing the steps in blocks 407 and 423 of method 100, method 100 proceeds from block 405 to block 422 (shown in dashed lines in Figure 5) which comprises the step of employing a machine learning model which has been trained to receive electrical ultrasonic signals 415 (e.g. from transducer(s) 14) as inputs and to infer a level of placenta maturity 425 based on such ultrasound electrical signals 415. The block 422 machine learning model may be trained using labelled data (e.g. where each data element comprises a set of ultrasound electrical signal inputs 415 labelled with a corresponding level of placenta maturity), although this is not generally necessary. In some embodiments, the block 422 machine learning model is trained to assign, as an output, a probability value to possible placenta maturity levels based on the corresponding ultrasonic electrical signal inputs 415. The block 422 machine learning model may generally comprise any suitable machine learning model(s) with any suitable machine learning architecture(s) and any suitable set of trainable parameters. By way of non-limiting example, in a non-limiting example embodiment where the block 422 machine learning model comprises a neural network, the trainable parameters of the machine learning model may comprise the weights and / or biases of perceptrons of the neural network or otherwise associated with connections between nodes of the neural network.

[0125] In some embodiments, method 400 comprises the optional step 411 of regularizing computed measures of placenta tissue properties 417 to remove noise from the at least one measure of placenta tissue properties 417 prior to providing the at least one measure of placenta tissue properties 417 to step 423 for determining level of placenta maturity 425. Step 41 1 of regularization may comprise any suitable techniques for removing noise. The block 41 1 regularization techniques may include one or more of: smoothing techniques to reduce fluctuations in the data while preserving key structural features, balancing fidelity of fitting with a smoothness constraint to prevent overfitting to noisy data, reducing noise while preserving edges and sharp features in the data, etc. In some embodiments, an artificial intelligence model is applied to determine suitable regularization techniques for removing noise from computed measures of placenta tissue properties 417.

[0126] Determining a level of placenta maturity 425 may assist health care providers (e.g. obstetricians) with diagnosis of health conditions (e.g. pre-natal hypoxia). The level of placenta maturity helps health care providers with assessing risk levels and making decision on actions or necessary interventions for a patient (e.g. prescribing bedrest, prescribing medications, admitting the patient to a hospital for close monitoring, performing a C-section immediately to avoid damage from hypoxia, etc.). In some embodiments, the level of placenta maturity (e.g. determined by method 400) and the level of prenatal hypoxia (e.g. determined by method 100) can be used to determine a risk level for a pregnancy (e.g. a foetus). For example, particular levels of hypoxia may be more or less risky for a pregnancy for different levels of placenta maturity

[0127] Experimental QUS analysis has been conducted to evaluate the effectiveness of assessing a level of prenatal hypoxia based on at least one measure of placenta tissue properties. For the experimental QUS analysis, ultrasound RF data of 45 3rdtrimester participants were analyzed. Of the 45 participants, 7 were cases of hypoxia (i.e. pathology group). The remaining 38 cases comprise cases of healthy babies (i.e. control group).

[0128] Figure 3A is a boxplot 200A comparing attenuation values (dB / cm / MHz) in the control group (labelled as “control”) to attenuation values (dB / cm / MHz) in the pathology group, i.e., cases of hypoxia (labelled as “path.”). As can be seen in illustrated Figure 3A, control grouphas a control group median attenuation 201 of about 0.58 dB / cm / MHz compared to a pathology group median attenuation 203 of about 0.40 dB / cm / MHz. Moreover, the interquartile range (shown by the boxes around median attenuation levels 201 , 203) of the control group does not overlap with the interquartile range of the pathology group in the illustrated experimental data of Figure 3A.

[0129] Figure 3B is a boxplot 200B comparing backscatter coefficient values (dB) in the control group (labelled as “control”) to backscatter coefficient values (dB) in the pathology group (labelled as “path.”). As can be seen in illustrated Figure 3B, control group has a control group median backscatter coefficient 205 of about -24.6 dB compared to a pathology group median backscatter coefficient 207 of about -31.4 dB.

[0130] Figure 3C is a boxplot 200C comparing effective scatterer diameter values (pm) in the control group (labelled as “control”) to effective scatterer diameter values (pm) in the pathology group (labelled as “path.”). As can be seen in illustrated Figure 3C, control group has a control group median effective scatterer diameter 209 of about 155 pm compared to a pathology group median effective scatterer diameter 21 1 of about 201 pm.

[0131] Figure 4 is a feature analysis plot 300 of data points in the experimental study defined by the three QUS quantitative features: attenuation, i.e., ACE (dB / cm / MHz), backscatter coefficient, i.e., BSC (dB), and effective scatterer diameter, i.e., ESD (pm). For the analysis, an ensemble classifier developed for the analysis was fitted using a 5-fold cross-validation with the subgroup data for hypoxia predication.

[0132] Solid black dots represent control group data points. An example control group data point 301 is labelled in the illustrated Figure 4. Solid grey dots represent pathology group data points. An example pathology group data point 303 is labelled in the illustrated Figure 4. “False Positive” results (i.e. control group data points that were falsely attributed as hypoxia cases) are highlighted with annular grey markers. An example “False Positive” data point is labelled as 305 in the illustrated Figure 4. “False Negative” results (i.e. pathology group data points that were falsely attributed as healthy cases) are highlighted with annular black markers. The two “False Negative” data points are both labelled as 307 in the illustrated Figure 4.

[0133] The classifier (represented by the data shown in Figure 4) showed promising performance, with a sensitivity of 71 %, specificity of 74%, and accuracy of 74% as shown in the confusion matrix below.

[0134] Additional data were then collected for the experimental QUS analysis beyond the initial 45 cases to reach a total of 226 cases. Of the 226 cases, 34 were cases of hypoxia (i.e. pathology group) and 192 were cases of healthy pregnancies (i.e. control group). The classifier applied in the experimental QUS analysis outputted probabilistic estimates of either hypoxia or no hypoxia (e.g. 70% probability of hypoxia, etc.). The classifier showed promising performance, with a sensitivity of 0.74 (value between 0 and 1 ; higher being better), a specificity of 0.73 (value between 0 and 1 ; higher being better), and a Brier Score of 0.107 (value between 0 and 1 ; lower being better).

[0135] FIG. 6A is a plot 500A showing a receiver operator characteristic (ROC) curve plotted based on the 226 cases in the experimental QUS analysis. The x-axis of plot 500A is the false positive rate with a range of value between 0 and 1 . The y-axis of plot 500A is the true positive rate with a range of value between 0 and 1 . By plotting the true positive rate against the false positive rate, an ROC curve shows how well a classifier separates two categories across allpossible decision thresholds. Line 501A (illustrated as dashed line in FIG. 6A) is the line of nodiscrimination and represents the expected performance of a random classifier. Line 505A is the ROC curve based on how the classifier (e.g. classifier 20) performed on the 226 cases in the experimental QUS analysis and reflects the observed performance of the classifier. Larger area under the ROC curve 505A, represents superior classifier performance. As can be seen from plot 500A of FIG. 6A, the area under the ROC curve 505A (“Area Under Curve” AUG) is about 0.78 (value between 0 and 1 ; higher being better) and that there is a 95% confidence (Cl) that the true AUG performance of the classifier lies between 0.69 and 0.88, indicating a good performance by the classifier.

[0136] FIG. 6B is a plot 500B showing a calibration curve for the 226 cases in the experimental QUS analysis. The x-axis of plot 500B is the predicted probability (i.e. what the classifier predicts the probability is) and the y-axis is the observed probability (i.e. what the actual probability is from the data of the 226 cases). In other words, the calibration curve compares what the classifier predicts (x-axis) to what truly happens in the data (y-axis). The reference line 502B (illustrated as dashed line in FIG. 6B) is the perfect calibration line, where the predicted probability matches the observed probability at any predicted probability. All of the control cases 503B (illustrated as five-pointed stars in FIG. 6B) have the observed probability of 0 and all of the hypoxia cases 507B (illustrated as triangles in FIG. 6B) have the observed probability of 1. The predicted probabilities outputted by the classifier are grouped / binned into groups. For example, the first bin includes all cases of predicted probabilities between 0 and 0.1 , then second bin includes all cases of predicted probabilities between 0.1 and 0.2, the third bin includes all cases of predicted probabilities between 0.2 and 0.3, and so on and so forth. The example is for illustrative purpose only and the data can be binned in any suitable manner. Then, for each bin / group, the observed probability of the bin / group (e.g. number of hypoxia cases in the bin / group divided by total number of cases in the bin / group) and an averaged predicted probability in the bin are calculated (e.g. sum of the predicted probabilities divided by the total number of cases in the bin / group) to thereby obtain the predicted probability and observed probability for the corresponding bin / group. These pairs of predicted probability and observed probability values for the bins / groups 509B are illustrated as six-pointed stars in FIG. 6B and may be referred to as “calibration points 509B” herein. As can be seen from FIG. 6B,the calibration points 509B in plot 500B cluster around the reference line 502B, suggesting that the classifier has good predictive performance.

[0137] A locally weighted scatterplot smoothing (LOWESS) line 51 1 B was generated based on the calibration points 509B and is shown in Figure 6B. LOWESS line 51 1 B shows the underlying trend in the collection of calibration points 509B. As can be seen in FIG. 6B, LOWESS line 51 1 B aligns well with reference line 502B in the range of 0 and 0.2 of predicted probability and skews slightly below reference line 502B in the range of 0.2 and 0.4 of predicted probability, suggesting a slight tendency by the classifier to overestimate the risk of hypoxia. The overall predictive performance of the classifier is good.Interpretation of Terms

[0138] Unless the context clearly requires otherwise, throughout the description and the claims:• “comprise”, “comprising”, and the like are to be construed in an inclusive sense, as opposed to an exclusive or exhaustive sense; that is to say, in the sense of “including, but not limited to”;• “connected”, “coupled”, or any variant thereof, means any connection or coupling, either direct or indirect, between two or more elements; the coupling or connection between the elements can be physical, logical, or a combination thereof;• “herein”, “above”, “below”, and words of similar import, when used to describe this specification, shall refer to this specification as a whole, and not to any particular portions of this specification;• “or”, in reference to a list of two or more items, covers all of the following interpretations of the word: any of the items in the list, all of the items in the list, and any combination of the items in the list;• the singular forms “a”, “an”, and “the” also include the meaning of any appropriate plural forms. These terms (“a”, “an”, and “the”) mean one or more unless stated otherwise;• “and / or” is used to indicate one or both stated cases may occur, for example A and / or B includes both (A and B) and (A or B);• “approximately” when applied to a numerical value means the numerical value ± 10%;• where a feature is described as being “optional” or “optionally” present or described as being present “in some embodiments” it is intended that the present disclosure encompasses embodiments where that feature is present and other embodiments where that feature is not necessarily present and other embodiments where that feature is excluded. Further, where any combination of features is described in this application this statement is intended to serve as antecedent basis for the use of exclusive terminology such as "solely," "only" and the like in relation to the combination of features as well as the use of "negative" lim itation(s)” to exclude the presence of other features; and• “first” and “second” are used for descriptive purposes and cannot be understood as indicating or implying relative importance or indicating the number of indicated technical features.

[0139] Words that indicate directions such as “vertical”, “transverse”, “horizontal”, “upward”, “downward”, “forward”, “backward”, “inward”, “outward”, “left”, “right”, “front”, “back”, “top”, “bottom”, “below”, “above”, “under”, and the like, used in this description and any accompanying claims (where present), depend on the specific orientation of the apparatus described and illustrated. The subject matter described herein may assume various alternative orientations. Accordingly, these directional terms are not strictly defined and should not be interpreted narrowly.

[0140] Where a range for a value is stated, the stated range includes all sub-ranges of the range. It is intended that the statement of a range supports the value being at an endpoint of the range as well as at any intervening value to the tenth of the unit of the lower limit of the range, as well as any subrange or sets of sub ranges of the range unless the context clearly dictates otherwise or any portion(s) of the stated range is specifically excluded. Where the stated range includes one or both endpoints of the range, ranges excluding either or both of those included endpoints are also included in the invention.

[0141] Certain numerical values described herein are preceded by "about". In this context, "about" provides literal support for the exact numerical value that it precedes, the exactnumerical value ±5%, as well as all other numerical values that are near to or approximately equal to that numerical value. Unless otherwise indicated a particular numerical value is included in “about” a specifically recited numerical value where the particular numerical value provides the substantial equivalent of the specifically recited numerical value in the context in which the specifically recited numerical value is presented. For example, a statement that something has the numerical value of “about 10” is to be interpreted as: the set of statements:• in some embodiments the numerical value is 10;• in some embodiments the numerical value is in the range of 9.5 to 10.5; and if from the context the person of ordinary skill in the art would understand that values within a certain range are substantially equivalent to 10 because the values with the range would be understood to provide substantially the same result as the value 10 then “about 10” also includes:• in some embodiments the numerical value is in the range of C to D where C and D are respectively lower and upper endpoints of the range that encompasses all of those values that provide a substantial equivalent to the value 10.

[0142] Specific examples of systems, methods and apparatus have been described herein for purposes of illustration. These are only examples. The technology provided herein can be applied to systems other than the example systems described above. Many alterations, modifications, additions, omissions, and permutations are possible within the practice of this invention. This invention includes variations on described embodiments that would be apparent to the skilled addressee, including variations obtained by: replacing features, elements and / or acts with equivalent features, elements and / or acts; mixing and matching of features, elements and / or acts from different embodiments; combining features, elements and / or acts from embodiments as described herein with features, elements and / or acts of other technology; and / or omitting combining features, elements and / or acts from described embodiments.

[0143] As will be apparent to those of skill in the art upon reading this disclosure, each of the individual embodiments described and illustrated herein has discrete components and featureswhich may be readily separated from or combined with the features of any other described embodiment(s) without departing from the scope of the present invention.

[0144] Any aspects described above in reference to apparatus may also apply to methods and vice versa.

[0145] Any recited method can be carried out in the order of events recited or in any other order which is logically possible. For example, while processes or blocks are presented in a given order, alternative examples may perform routines having steps, or employ systems having blocks, in a different order, and some processes or blocks may be deleted, moved, added, subdivided, combined, and / or modified to provide alternative or subcombinations. Each of these processes or blocks may be implemented in a variety of different ways. Also, while processes or blocks are at times shown as being performed in series, these processes or blocks may instead be performed in parallel, simultaneously or at different times.

[0146] Various features are described herein as being present in “some embodiments”. Such features are not mandatory and may not be present in all embodiments. Embodiments of the invention may include zero, any one or any combination of two or more of such features. All possible combinations of such features are contemplated by this disclosure even where such features are shown in different drawings and / or described in different sections or paragraphs. This is limited only to the extent that certain ones of such features are incompatible with other ones of such features in the sense that it would be impossible for a person of ordinary skill in the art to construct a practical embodiment that combines such incompatible features. Consequently, the description that “some embodiments” possess feature A and “some embodiments” possess feature B should be interpreted as an express indication that the inventors also contemplate embodiments which combine features A and B (unless the description states otherwise or features A and B are fundamentally incompatible). This is the case even if features A and B are illustrated in different drawings and / or mentioned in different paragraphs, sections or sentences.

[0147] While a number of exemplary aspects and embodiments have been discussed above, those of skill in the art will recognize certain modifications, permutations, additions and subcombinations thereof. It is therefore intended that the following appended claims and claimshereafter introduced are interpreted to include all such modifications, permutations, additions and sub-combinations as are consistent with the broadest interpretation of the specification as a whole.

Claims

CLAIMS:1 . A method for assessing a level of prenatal hypoxia, the method comprising: transmitting ultrasonic waves into an in-vivo placenta; receiving ultrasonic reflections from the placenta; converting the received ultrasonic reflections into electrical signals; computationally determining, from the electrical signals, at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

2. A method according to claim 1 or any other claim herein wherein the at least one measure of the one or more placenta tissue properties comprise attenuation.

3. A method according to claim 1 or 2 or any other claim herein wherein the at least one measure of the one or more placenta tissue properties comprises a backscatter coefficient.

4. A method according to any one of claims 1 to 3 or any other claim wherein the at least one measure of the one or more placenta tissue properties comprises an effective scatterer diameter.

5. A method according to any one of claims 1 to 4 or any other claim wherein the at least one measure of the one or more placenta tissue properties comprises a frequency dependence of attenuation.

6. A method according to any one of claims 1 to 5 or any other claim wherein the at least one measure of the one or more placenta tissue properties comprises a speed of sound.

7. A method according to any of claims 1 to 6 or any other claim wherein the determining the level of prenatal hypoxia comprises comparing the at least one measure of the one or more placenta tissue properties to known measures of the one or more placenta tissue properties in pregnancies without hypoxia.

8. A method according to any one of claims 1 to 7 or any other claim wherein the determining the level of prenatal hypoxia comprises applying a regression model to classify the at least one measure of the one or more placenta tissue properties, the regression model trained on a data set comprising data points corresponding to prenatal hypoxia and data points corresponding to pregnancies without hypoxia.

9. A method according to any one of claims 1 to 8 or any other claim wherein the determining the level of prenatal hypoxia comprises applying an artificial intelligence model to classify the at least one measure of the one or more placenta tissue properties, the artificial intelligence trained on a data set comprising data points corresponding to prenatal hypoxia and data points corresponding to pregnancies without hypoxia.

10. A method according to any one of claims 1 to 9 or any other claim wherein determining the level of prenatal hypoxia comprises determining a risk percentage.

11. A method according to any one of claims 1 to 10 or any other claim wherein determining the level of prenatal hypoxia comprises determining a risk category, from among a plurality of categories.

12. A method according to any one of claims 1 to 11 or any other claim wherein the electrical signals comprise baseband signals.

13. A method according to any one of claims 1 to 12 or any other claim wherein the electrical signals comprise demodulated signals.

14. A method according to any one of claims 1 to 13 or any other claim wherein the electrical signals comprise radiofrequency signals.

15. A method according to any one of claims 1 to 14 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting multiple pulses of the ultrasonic waves.

16. A method according to any one of claims 1 to 15 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves at multiple frequencies.

17. A method according to any one of claims 1 to 16 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves at multiple amplitudes.

18. A method according to any one of claims 1 to 17 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves from multiple directions.

19. A method according to any one of claims 1 to 18 or any other claim comprising the step of regularizing the at least one measure of the one or more placenta tissue properties to remove noise from the at least one measure of the one or more placenta tissue properties prior to the determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

20. A method according to any one of claims 1 to 19 or any other claim wherein determining the level of prenatal hypoxia comprises determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties and additional diagnostic measures.21 . A method according to claim 20 or any other claim wherein the additional diagnostic measures comprise one or more biometric measurements of the placenta and / or a fetus connected to the placenta.

22. A method according to claim 21 or any other claim wherein the additional diagnostic measures comprise at least one of: Doppler analysis of blood, B-mode texture of tissue, placenta size, placenta shape, fetal head size, fetal organ size, fetal heart rate, maternal heart rate, chart data.

23. A method according to any one of claims 1 to 22 or any other claim wherein the region of interest is delimited by a configurable distance, the distance extending from transducers configured to transmit the ultrasonic waves.

24. A method according to claim 23 or any other claim wherein the configurable distance is about 10cm.

25. A method according to any one of claims 1 to 24 or any other claim wherein the region of interest comprises a plurality of sub-regions collectively forming the region of interest and the received ultrasonic reflections comprise a spatially resolved dataset of spatially resolved components of the at least one measure of the one or more placenta tissue properties wherein each spatially resolved component of the spatially resolved dataset corresponds to a corresponding one of the plurality of sub-regions.

26. A method according to claim 25 or any other claim herein wherein a value of the at least one measure of the one or more placenta tissue properties is determined for each of the plurality of sub-regions based on the corresponding spatially resolved component of the spatially resolved dataset.

27. A method according to any one of claims 1 to 26 or any other claim herein wherein determining the level of prenatal hypoxia based on the at least one measure of the one ormore placenta tissue properties is based, at least in part, on a timing of data acquisition of the at least one measure of the one or more placenta tissue properties.

28. A method according to any one of claims 1 to 27 or any other claim herein wherein determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties is based, at least in part, on data obtained at different times during the pregnancy.

29. A method according to claim 28 or any other claim herein wherein determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties based on the data obtained at different times during the pregnancy comprises evaluating differences or trends in the at least one measure of the one or more placenta tissue properties over time.

30. A method according to claim 29 or any other claim herein wherein evaluating the differences or trends in the at least one measure of the one or more placenta tissue properties over time comprises determining rate(s) of change of the at least one measure of the one or more placenta tissue properties.31 . A method according to any one of claims 1 to 30 or any other claim herein wherein determining the level of prenatal hypoxia comprises, at least in part, evaluating variations in the value of the at least one measure of the one or more placenta tissue properties across different locations within the region of interest.

32. A method according to claim 31 or any other claim herein wherein evaluating the variations in the value of the at least one measure of the one or more placenta tissue properties across the different locations within the region of interest comprises comparing the variances of the at least one measure of the one or more placenta tissue properties to variances of the at least one measure of the one or more placenta tissue properties in other tissue regions outside the region of interest.

33. A method for assessing a level of prenatal hypoxia, the method comprising: obtaining ultrasonic data for one or more diagnostic cases, wherein the ultrasonic data for each of the one or more diagnostic cases are associated with corresponding acoustic waves reflected from a corresponding region of interest of that includes an in- vivo placenta; providing the ultrasonic data as inputs into a machine learning model, wherein the machine learning model is trained to determine the level of prenatal hypoxia for each of the one or more diagnostic cases based on the corresponding ultrasonic data.

34. A method according to claim 33 or any other claim herein wherein the machine learning model is trained to assign, as an output, a probability value to each diagnostic case based on the corresponding ultrasonic data, wherein the probability value reflects the probability of the corresponding diagnostic case being a case of prenatal hypoxia.

35. A method according to any one of claims 33 to 34 or any other claim herein comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 1 to 32 or otherwise described herein.

36. A method for assessing a level of prenatal hypoxia, the method comprising: receiving acoustic waves reflected from a region of interest that includes an in-vivo placenta; computationally determining at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the in-vivo placenta with the acoustic waves; determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties.

37. A method according to claim 36 comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 1 to 35 or otherwise described herein.

38. A method for assessing a level of prenatal hypoxia, the method comprising: receiving one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters determined based on interaction of acoustic waves with an in-vivo placenta; determining the level of prenatal hypoxia based on the one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters.

39. A method according to claim 38 comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 1 to 35 or otherwise described herein.

40. A system for assessing a level of prenatal hypoxia, the system comprising: an ultrasonic unit, the ultrasonic unit comprising: an ultrasonic transducer operable to: transmit ultrasonic waves into an in-vivo placenta; receive ultrasonic reflections from the placenta; and, convert the received ultrasonic reflections into electrical signals; and, a controller, the controller in communication with the ultrasonic transducer and operable to: computationally determine, from the electrical signals, at least one measure of placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; and, determine the level of prenatal hypoxia based on the at least one measure of placenta tissue properties.41 . A system according to claim 40 comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 1 to 35 or otherwise described herein.

42. A method for assessing a level of placenta maturity, the method comprising: transmitting ultrasonic waves into an in-vivo placenta; receiving ultrasonic reflections from the placenta; converting the received ultrasonic reflections into electrical signals; computationally determining, from the electrical signals, at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties.

43. A method according to claim 42 or any other claim herein wherein the at least one measure of the one or more placenta tissue properties comprise attenuation.

44. A method according to claim 42 or 43 or any other claim herein wherein the at least one measure of the one or more placenta tissue properties comprises a backscatter coefficient.

45. A method according to any one of claims 42 to 44 or any other claim wherein the at least one measure of the one or more placenta tissue properties comprises an effective scatterer diameter.

46. A method according to any one of claims 42 to 45 or any other claim wherein the at least one measure of the one or more placenta tissue properties comprises a frequency dependence of attenuation.

47. method according to any one of claims 42 to 46 or any other claim wherein the at least one measure of the one or more placenta tissue properties comprises a speed of sound.

48. A method according to any of claims 42 to 47 or any other claim wherein the determining the level of placenta maturity comprises comparing the at least one measure of the one or more placenta tissue properties to known measures of the one or more placenta tissue properties in placentas with known levels of placenta maturity.

49. A method according to any one of claims 42 to 48 or any other claim wherein the determining the level of placenta maturity comprises applying a regression model to classify the at least one measure of the one or more placenta tissue properties, the regression model trained on a data set comprising data points corresponding to placentas with known levels of placenta maturity.

50. A method according to any one of claims 42 to 49 or any other claim wherein the determining the level of known levels of placenta maturity comprises applying an artificial intelligence model to classify the at least one measure of the one or more placenta tissue properties, the artificial intelligence trained on a data set comprising data points corresponding to placentas with known levels of placenta maturity.51 . A method according to any one of claims 42 to 50 or any other claim wherein determining the level of placenta maturity comprises determining a numerical value.

52. A method according to any one of claims 42 to 51 or any other claim wherein determining the level of placenta maturity comprises determining a numerical grade, from among a plurality of numerical grades.

53. A method according to any one of claims 42 to 52 or any other claim wherein the electrical signals comprise baseband signals.

54. A method according to any one of claims 42 to 53 or any other claim wherein the electrical signals comprise demodulated signals.

55. A method according to any one of claims 42 to 54 or any other claim wherein the electrical signals comprise radiofrequency signals.

56. A method according to any one of claims 42 to 55 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting multiple pulses of the ultrasonic waves.

57. A method according to any one of claims 42 to 56 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves at multiple frequencies.

58. A method according to any one of claims 42 to 57 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves at multiple amplitudes.

59. A method according to any one of claims 42 to 58 or any other claim wherein the transmitting the ultrasonic waves comprises transmitting the ultrasonic waves from multiple directions.

60. A method according to any one of claims 42 to 59 or any other claim comprising the step of regularizing the at least one measure of the one or more placenta tissue properties to remove noise from the at least one measure of the one or more placenta tissue properties prior to the determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties.61 . A method according to any one of claims 42 to 60 or any other claim wherein determining the level of placenta maturity comprises determining the level of placenta maturity basedon the at least one measure of the one or more placenta tissue properties and additional diagnostic measures.

62. A method according to claim 61 or any other claim wherein the additional diagnostic measures comprise one or more biometric measurements of the placenta and / or a fetus connected to the placenta.

63. A method according to claim 61 or 62 or any other claim wherein the additional diagnostic measures comprise at least one of: Doppler analysis of blood, B-mode texture of tissue, placenta size, placenta shape, fetal head size, fetal organ size, fetal heart rate, maternal heart rate, chart data.

64. A method according to any one of claims 42 to 63 or any other claim wherein the region of interest is delimited by a configurable distance, the configurable distance extending from transducers configured to transmit the ultrasonic waves.

65. A method according to claim 64 or any other claim wherein the configurable distance is about 10cm.

66. A method according to any one of claims 42 to 65 or any other claim wherein the region of interest comprises a plurality of sub-regions collectively forming the region of interest and the received ultrasonic reflections comprise a spatially resolved dataset of spatially resolved components of the at least one measure of the one or more placenta tissue properties wherein each spatially resolved component of the spatially resolved dataset corresponds to a corresponding one of the plurality of sub-regions.

67. A method according to claim 66 or any other claim herein wherein a value of the at least one measure of the one or more placenta tissue properties is determined for each of the plurality of sub-regions based on the corresponding spatially resolved component of the spatially resolved dataset.

68. A method according to any one of claims 42 to 67 or any other claim herein wherein determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties is based, at least in part, on a timing of data acquisition of the at least one measure of the one or more placenta tissue properties.

69. A method according to any one of claims 42 to 68 or any other claim herein wherein determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties is based, at least in part, on data obtained at different times during the pregnancy.

70. A method according to claim 69 or any other claim herein wherein determining the level of prenatal hypoxia based on the at least one measure of the one or more placenta tissue properties based on the data obtained at different times during the pregnancy comprises evaluating differences or trends in the at least one measure of the one or more placenta tissue properties over time.71 . A method according to claim 70 or any other claim herein wherein evaluating the differences or trends in the at least one measure of the one or more placenta tissue properties over time comprises determining rate(s) of change of the at least one measure of the one or more placenta tissue properties.

72. A method according to any one of claims 42 to 71 or any other claim herein wherein determining the level of placenta maturity comprises, at least in part, evaluating variations in the value of the at least one measure of the one or more placenta tissue properties across different locations within the region of interest.

73. A method according to claim 72 or any other claim herein wherein evaluating the variations in the value of the at least one measure of the one or more placenta tissue properties across the different locations within the region of interest comprises comparingthe variances of the at least one measure of the one or more placenta tissue properties to variances of the at least one measure of the one or more placenta tissue properties in other tissue regions outside the region of interest.

74. A method for assessing a level of placenta maturity, the method comprising: obtaining ultrasonic data for one or more diagnostic cases, wherein the ultrasonic data for each of the one or more diagnostic cases are associated with corresponding acoustic waves reflected from a corresponding region of interest of that includes an in- vivo placenta; providing the ultrasonic data as inputs into a machine learning model, wherein the machine learning model is trained to determine the level of placenta maturity for each of the one or more diagnostic cases based on the corresponding ultrasonic data.

75. A method according to claim 74 or any other claim herein wherein the machine learning model is trained to assign, as an output, a numerical value to each diagnostic case based on the corresponding ultrasonic data, wherein the numerical value reflects the level of placenta maturity.

76. A method according to any one of claims 74 to 75 or any other claim herein comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 42 to 73 or otherwise described herein.

77. A method for assessing a level of placenta maturity, the method comprising: receiving acoustic waves reflected from a region of interest that includes an in-vivo placenta; computationally determining at least one measure of one or more placenta tissue properties relating to the acoustic interaction of the in-vivo placenta with the acoustic waves; determining the level of placenta maturity based on the at least one measure of the one or more placenta tissue properties.

78. A method according to claim 77 comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 42 to 76 or otherwise described herein.

79. A method for assessing a level of placenta maturity, the method comprising: receiving one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters determined based on interaction of acoustic waves with an in-vivo placenta; determining the level of placenta maturity based on the one or more of attenuation, backscatter coefficient and effective scatterer diameter parameters.

80. A method according to claim 49 comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 42 to 76 or otherwise described herein.81 . A system for assessing a level of placenta maturity, the system comprising: an ultrasonic unit, the ultrasonic unit comprising: an ultrasonic transducer operable to: transmit ultrasonic waves into an in-vivo placenta; receive ultrasonic reflections from the placenta; and, convert the received ultrasonic reflections into electrical signals; and, a controller, the controller in communication with the ultrasonic transducer and operable to: computationally determine, from the electrical signals, at least one measure of placenta tissue properties relating to the acoustic interaction of the placenta tissue with the transmitted ultrasonic waves; and, determine the level of placenta maturity based on the at least one measure of placenta tissue properties.

82. A system according to claim 81 comprising any of the features, combinations of features and / or sub-combinations of features of any of claims 42 to 76 or otherwise described herein.

Images