Description:FIELD
The present disclosure relates to the field of healthcare domain.
More particularly, focuses on analyzing fetal ultrasound images in early pregnancy.
DEFINITION
As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used indicates otherwise.
• Midsagittal Plane (MSP): The term "midsagittal plane", refers to an imaginary line dividing the body into left and right halves symmetrically, often used in fetal imaging to view and analyze key facial and brain structures with precise alignment.
• Doppler Ultrasound: The term "Doppler ultrasound", refers to a type of ultrasound that measures blood flow and velocity within blood vessels and the heart by detecting shifts in frequency caused by moving blood cells, commonly used to assess fetal cardiovascular health.
• Three-dimensional (3D) Ultrasound: The term "three-dimensional (3D) ultrasound", refers to an imaging technique that provides detailed, volumetric views of fetal anatomy, enabling clinicians to examine structures from multiple angles and identify anomalies more precisely than standard 2D ultrasound.
• Frontomaxillary Facial (FMF) Angle: The term "Frontomaxillary Facial (FMF) angle", refers to the angle formed between the forehead and upper jaw, often used in prenatal screenings to evaluate craniofacial development and detect anomalies.
• Facial Maxillary Angle (FMA): The term "Facial Maxillary Angle (FMA)" refers to the angle between the face and the maxilla (upper jaw) that helps assess the facial structure and detect potential anomalies in the development of the upper jaw and surrounding areas.
• Profile Line (PL) Distance: The term "Profile Line (PL) distance", refers to the measurement representing the projection of the frontal bone relative to other facial structures, used to assess cranial development and detect abnormalities.
• Naseon line (MNM): The term "Naseon line (MNM)", refers to an imaginary line extending from the nasion (bridge of the nose) to the mandible (lower jaw), often used to evaluate the position of the chin and assess potential indicators of craniofacial anomalies, such as micrognathia.
• Midbrain Position: The term "midbrain position", refers to the location and alignment of the midbrain within the fetal head, which can be an indicator of neural development and may highlight certain structural anomalies if abnormal.
• Maxillary Continuity: The term "maxillary continuity", refers to the integrity of the upper jaw (maxilla) structure, which is assessed to detect any breaks or gaps that may indicate conditions such as cleft lip and palate (CLCP).
• Brain Stem: The term "brain stem", refers to the lower part of the brain that connects to the spinal cord, controlling vital functions such as breathing and heart rate, and its assessment is important in prenatal imaging to ensure proper fetal brain development.
• 4th Ventricle: The term "4th ventricle", refers to one of the fluid-filled spaces within the brain, located in the hindbrain near the brainstem, which is assessed in fetal imaging to check for normal brain and spinal cord development.
• Cisterna Magna: The term "cisterna magna", refers to a large space filled with cerebrospinal fluid located near the back of the brain, which is measured in fetal ultrasound to check for potential anomalies related to brain and skull formation.
• Nuchal Translucency (NT): The term "nuchal translucency (NT)", refers to the fluid-filled space at the back of a fetus's neck, which is measured in early pregnancy as an indicator for chromosomal abnormalities, including Down syndrome.
• Cleft Lip And Palate (CLCP): The term "cleft lip and palate (CLCP)", refers to a congenital condition where there is an opening or split in the upper lip and/or roof of the mouth (palate), which can be detected by assessing maxillary continuity in fetal imaging.
The above definitions are in addition to those expressed in the art.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Prenatal ultrasound imaging plays a crucial role in monitoring fetal development and detecting potential anomalies during pregnancy. Early trimester screening is particularly valuable as it provides an opportunity to identify critical structural and developmental markers at a formative stage. Traditional ultrasound imaging methods, however, face certain limitations in early pregnancy due to the small size and complexity of fetal anatomy, as well as variability in image quality. These limitations can lead to inconsistent assessments and may require specialized expertise for accurate interpretation.
Efforts to improve early trimester fetal assessment have included the use of two-dimensional (2D) and three-dimensional (3D) ultrasound imaging, as well as attempts to develop standardized protocols for measuring specific fetal markers. However, challenges remain in achieving consistent image quality, identifying specific anatomical structures accurately, and reducing the subjectivity in interpreting these images. Furthermore, advances in AI and machine learning have shown promise in various imaging fields but have yet to be fully adapted for early pregnancy assessments in a standardized and practical clinical tool.
There is, therefore, a need for an improved approach to early-trimester fetal ultrasound imaging that combines advanced image processing and machine learning techniques. Such an approach would aim to standardize fetal assessments, enhance accuracy, and provide meaningful guidance to clinicians, thereby improving the overall quality of prenatal care.
Therefore, there is a need for a system and method for early trimester fetal ultrasound analysis that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the present disclosure is to provide a system for early trimester fetal ultrasound analysis.
Another object of the present disclosure is to provide a system that enhances the accuracy and consistency of fetal anatomical marker identification during early trimester ultrasound imaging.
Still another object of the present disclosure is to provide a system that facilitates the automatic detection of specific fetal structures and markers, minimizing variability in interpretation.
Yet another object of the present disclosure is to provide a system that offers real-time guidance and feedback to clinicians during ultrasound exams, thereby improving the quality of fetal imaging and reducing the potential for missed observations.
Still another object of the present disclosure is to provide a system that enables a standardized, evidence-based approach to early fetal anomaly assessment that can be seamlessly integrated into existing clinical workflows and electronic health record systems.
Yet another object of the present disclosure is to provide a system that supports remote consultations and telemedicine applications for fetal ultrasound analysis, allowing healthcare providers to access expert insights regardless of geographic location.
Still another object of the present disclosure is to provide a system that provides a scalable and adaptive system that learns from ongoing data and clinician feedback, continuously improving its assessment accuracy over time.
Yet another object of the present disclosure is to provide a method for early trimester fetal ultrasound analysis.
Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure provides a system for detecting fetal anomalies in first trimester ultrasound imaging. The system comprising: an ultrasound imaging device, a pre-processing unit, an artificial intelligence (AI) based analysis module, a nomogram-based risk assessment module, and a reporting module.
The ultrasound imaging device is configured to capture a sequence of ultrasound images of a fetal in various orientations.
The pre-processing unit is configured to receive the ultrasound images and preprocesses the ultrasound images by applying preprocessing techniques including noise reduction, contrast enhancement, and normalization, to enhance quality and standardize format of the ultrasound images for generating pre-processed images.
The artificial intelligence (AI) based analysis module is configured to analyse the pre-processed images with a pre-trained AI model which is configured to:
- identify and segment key fetal structures in the preprocessed images, comprising the frontal bone, nasal skin, nasal bone, midbrain, tip of the nose, maxilla, mandible, brainstem, fourth ventricle, cisterna magna, and nuchal translucency (NT).
- identify midsagittal plane (MSP) based on the positions and orientations of the key fetal structures by locating at least the nasal bone, nasal skin, and a tip of a nose in a single image frame; and
- automatically measure key fetal markers in the mid-sagittal plane (MSP) for anomaly detection, the key fetal markers including Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Naseon line, midbrain position, maxilla continuity, NT thickness, and visibility of the brainstem, fourth ventricle, and cisterna magna.
The nomogram-based risk assessment module is configured to calculate a risk score for fetal anomalies based on a nomogram that integrates the fetal markers, gestational age, and other relevant clinical data. and
The reporting module is configured to generate a comprehensive report including the risk score, visual representation of fetal measurements, highlighted areas of potential concern, and recommendations for further action.
In an embodiment, the ultrasound imaging device is further configured to perform real-time analysis of ultrasound images during the scan to provide feedback for optimal image capture and orientation adjustments, thereby enhancing the accuracy of MSP identification.
In an embodiment, the AI based analysis module is configured to perform an iterative analysis of multiple images to identify the best mid-sagittal plane (MSP) based on an optimal alignment of the nasal bone, the nasal skin, and the nasal tip.
In an embodiment, the nomogram integrates the other relevant clinical data, including maternal age, prior pregnancy history, and genetic testing data, to refine the risk assessment score.
In an embodiment, the AI based analysis module includes a machine learning component that continuously improves segmentation and marker identification based on feedback from subsequent scans and clinician input.
In an embodiment, the AI model is a deep learning model trained on a dataset of diverse fetal ultrasound images dataset, to enhance the detection of fetal markers even in low-quality or ambiguous images.
In an embodiment, the system further comprises a user interface configured to integrate the system with hospital information systems (HIS) or electronic health records (EHR) to automate the storage and retrieval of ultrasound measurements and diagnostic reports.
In an embodiment, the AI model provides a confidence score for each identified fetal marker to guide the sonographer in image acquisition quality.
In an embodiment, the risk score generated by the nomogram includes a breakdown of individual anomaly risks, comprising Down syndrome, cleft lip, and neural tube defects, based on the measurements and presence of associated markers.
In an embodiment, the nomogram incorporates population-based fetal development data to benchmark the measurements against normative values for the corresponding gestational age.
In an embodiment, the system further comprises a user interface configured to display real-time risk assessments, measurement guides, and suggestions for optimal imaging based on live ultrasound feed.
In an embodiment, the system further comprises an alert module configured to indicate suboptimal imaging when the AI based analysis module detects an inadequate view of critical anatomical markers, prompting a sonographer to adjust the image capture angle.
In an embodiment, the system further comprises a mobile application associated with the reporting module so as to receive remote access to fetal health assessments and risk scores for telemedicine applications.
The present disclosure provides a method for detecting fetal anomalies in first trimester ultrasound imaging, comprising:
• acquiring, by an ultrasound imaging device, a sequence of ultrasound images of a fetal in various orientations;
• preprocessing, by a pre-processing unit, the acquired ultrasound images by applying preprocessing techniques including noise reduction, contrast enhancement, and normalization, to enhance quality and standardize format of the ultrasound images for generating pre-processed images;
• identifying and segmenting, by an artificial intelligence (AI) based analysis module, key fetal structures in the pre-processed images, comprising the frontal bone, nasal skin, nasal bone, midbrain, tip of the nose, maxilla, mandible, brainstem, fourth ventricle, cisterna magna, and nuchal translucency (NT);
• identifying, by the AI based analysis module, midsagittal plane (MSP) based on the positions and orientations of the key fetal structures by locating at least the nasal bone, nasal skin, and tip of the nose in a single image frame;
• automatically measuring key fetal markers in the mid-sagittal plane (MSP) for anomaly detection, the key fetal markers including Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Naseon line, midbrain position, maxilla continuity, NT thickness, and visibility of the brainstem, fourth ventricle, and cisterna magna;
• calculating, by a nomogram-based risk assessment module, a risk score for fetal anomalies based on a nomogram that integrates the fetal markers, gestational age, and other relevant clinical data; and
• generating, by a reporting module, a comprehensive report including the risk score, visual representation of fetal measurements, highlighted areas of potential concern, and recommendations for further action.
In an embodiment, the method further comprises real-time analysis of ultrasound images during the scan to provide feedback for optimal image capture and orientation adjustments, thereby enhancing the accuracy of MSP identification.
In an embodiment, the method includes performing, by the AI based analysis module, an iterative analysis of multiple images to identify the best mid-sagittal plane based on an optimal alignment of the nasal bone, the nasal skin, and the nasal tip.
In an embodiment, the method includes the nomogram and integrates the other relevant clinical data, including maternal age, prior pregnancy history, and genetic testing data, to refine the risk assessment score.
In an embodiment, the method further comprises exporting the generated report containing fetal marker measurements and anomaly risk scores from the nomogram-based risk assessment module to an electronic health record (EHR) system through a user interface.
In an embodiment, the method further comprises the step of validating the fetal marker measurements by comparing them with normative values stored in a memory unit to detect potential deviations that indicate anomalies.
In an embodiment, the method further comprises the step of adapting the method for remote operation by transmitting ultrasound image data and analysis results over a telemedicine platform for specialist consultation.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system and method for early trimester fetal ultrasound analysis, of the present disclosure will now be described with the help of the accompanying drawing in which:
Figure 1 illustrates a block diagram of the present disclosure, in accordance with an embodiment of the present disclosure;
Figures 2A and 2B illustrate a method for early trimester fetal ultrasound analysis, in accordance with an embodiment of the present disclosure;
Figure 3 illustrates the nomogram approach, in accordance with an embodiment of the present disclosure;
Figure 4 illustrates the key structures of the fetal face, in accordance with an embodiment of the present disclosure;
Figure 5 illustrates midsagittal plane (MSP) identification Markers, in accordance with an embodiment of the present disclosure;
Figure 6 illustrates Midsagittal Plane (MSP) detection, in accordance with an embodiment of the present disclosure;
Figure 7 illustrates a Frontomaxillary Facial (FMF) angle, in accordance with an embodiment of the present disclosure;
Figure 8 illustrates a Facial Maxillary Angle (FMA), in accordance with an embodiment of the present disclosure;
Figure 9 illustrates a profile line, in accordance with an embodiment of the present disclosure;
Figure 10 illustrates the MNM Angle, in accordance with an embodiment of the present disclosure;
Figure 11 illustrates integration of several markers for structural assessment, in accordance with an embodiment of the present disclosure;
Figure 12 illustrates Maxilla's Continuity, in accordance with an embodiment of the present disclosure; and
Figure 13 illustrates the Nuchal Translucency (NT) thickness, in accordance with an embodiment of the present disclosure; and
Figure 14 illustrates the Midbrain Position, in accordance with an embodiment of the present disclosure.
LIST OF REFERENCE NUMERALS
100 System
110 Ultrasound imaging device
120 Pre-processing unit
130 AI-based analysis module
140 Nomogram-based risk assessment module
150 Reporting module
160 User interface
170 Alert module
135 Memory unit
200-214 Method and method steps
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well known processes, well known apparatus structures, and well known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a,” "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms “including,” and “having,” are open ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
When an element is referred to as being “engaged to,” "connected to," or "coupled to" another element, it may be directly engaged, connected, or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
Referring to Figure 1, The present disclosure provides a system for detecting fetal anomalies in first trimester ultrasound imaging. The system (100) comprises: an ultrasound imaging device (110), a pre-processing unit (120), an artificial intelligence (AI) based analysis module (130), a nomogram-based risk assessment module (140), and a reporting module (150).
The ultrasound imaging device (110) is configured to capture a sequence of ultrasound images of a fetal in various orientations.
The pre-processing unit (120) is configured to receive the ultrasound images and preprocesses the ultrasound images by applying preprocessing techniques including noise reduction, contrast enhancement, and normalization, to enhance quality and standardize format of the ultrasound images for generating pre-processed images.
The artificial intelligence (AI) based analysis module (130) is configured to analyse the pre-processed images with a pre-trained AI model which is configured to:
- identify and segment key fetal structures in the preprocessed images, comprising the frontal bone, nasal skin, nasal bone, midbrain, tip of the nose, maxilla, mandible, brainstem, fourth ventricle, cisterna magna, and nuchal translucency (NT).
- identify midsagittal plane (MSP) based on the positions and orientations of the key fetal structures by locating at least the nasal bone, nasal skin, and tip of the nose in a single image frame; and
- automatically measure key fetal markers in the mid-sagittal plane (MSP) for anomaly detection, the key fetal markers including Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Naseon line, midbrain position, maxilla continuity, NT thickness, and visibility of the brainstem, fourth ventricle, and cisterna magna.
The nomogram-based risk assessment module (140) is configured to calculate a risk score for fetal anomalies based on a nomogram that integrates the fetal markers, gestational age, and other relevant clinical data. and
The reporting module (150) is configured to generate a comprehensive report including the risk score, visual representation of fetal measurements, highlighted areas of potential concern, and recommendations for further action.
In an embodiment, the ultrasound imaging device (110) is further configured to perform real-time analysis of ultrasound images during the scan to provide feedback for optimal image capture and orientation adjustments, thereby enhancing the accuracy of MSP identification.
In an embodiment, the AI based analysis module (130) is configured to perform an iterative analysis of multiple images to identify the best mid-sagittal plane (MSP) based on an optimal alignment of the nasal bone, the nasal skin, and the nasal tip.
In an embodiment, the nomogram integrates the other relevant clinical data, including maternal age, prior pregnancy history, and genetic testing data, to refine the risk assessment score.
In an embodiment, the AI based analysis module (130) includes a machine learning component that continuously improves segmentation and marker identification based on feedback from subsequent scans and clinician input.
In an embodiment, the AI model is a deep learning model trained on a dataset of diverse fetal ultrasound images dataset, to enhance the detection of fetal markers even in low-quality or ambiguous images.
In an embodiment, the system (100) further comprises a user interface (160) configured to integrate the system (100) with hospital information systems (HIS) or electronic health records (EHR) to automate the storage and retrieval of ultrasound measurements and diagnostic reports.
In an embodiment, the AI model provides a confidence score for each identified fetal marker to guide the sonographer in image acquisition quality.
In an embodiment, the risk score generated by the nomogram includes a breakdown of individual anomaly risks, comprising Down syndrome, cleft lip, and neural tube defects, based on the measurements and presence of associated markers.
In an embodiment, the nomogram incorporates population-based fetal development data to benchmark the measurements against normative values for the corresponding gestational age.
In an embodiment, the system (100) further comprises a user interface (160) configured to display real-time risk assessments, measurement guides, and suggestions for optimal imaging based on live ultrasound feed.
In an embodiment, the system (100) further comprises an alert module (170) configured to indicate suboptimal imaging when the AI based analysis module (130) detects an inadequate view of critical anatomical markers, prompting a sonographer to adjust the image capture angle.
In an embodiment, the system (100) further comprises a mobile application associated with the reporting module (150) so as to receive remote access to fetal health assessments and risk scores for telemedicine applications.
In exemplary implementation, the system (100) described in this disclosure is designed to detect fetal anomalies in first trimester ultrasound imaging. The system (100) includes several hardware elements working in coordination to analyze ultrasound images and assess the likelihood of fetal anomalies. The ultrasound imaging device (110) captures images of the fetus in various orientations, which are then sent to the pre-processing unit (120). The pre-processing unit applies noise reduction, contrast enhancement, and normalization to standardize image quality, thus producing pre-processed images that are optimized for further analysis.
Following pre-processing, the AI-based analysis module (130) processes the images using a pre-trained model that identifies and segments key fetal structures such as the frontal bone, nasal skin, nasal bone, midbrain, and NT (nuchal translucency). This module also identifies the midsagittal plane (MSP) by locating critical markers—nasal bone, nasal skin, and nasal tip—enabling automatic measurement of fetal markers in this plane. Key markers analyzed include the Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, midbrain position, and NT thickness, among others. These measurements are essential for detecting craniofacial, neurological, and chromosomal anomalies.
The nomogram-based risk assessment module (140) calculates a risk score for fetal anomalies by integrating the fetal markers, gestational age, and clinical data such as maternal age and pregnancy history. This module relies on a nomogram to compare fetal markers against normative population data, providing an individualized risk assessment. Finally, the reporting module (150) compiles a comprehensive report, which includes the risk score, visual representations of the fetal measurements, and any highlighted areas of concern. The report may also suggest clinical recommendations for follow-up and can be integrated into electronic health record (EHR) systems.
Additional embodiments of the system support enhanced functionalities such as real-time image analysis, iterative alignment refinement for the best MSP, and continuous learning for the AI model. Some embodiments include telemedicine capabilities, enabling remote consultation by streaming ultrasound images and AI-based analysis to specialists. The modular design also allows for selection of specific fetal markers to tailor the assessment for particular clinical needs. Through this comprehensive design, the system offers a robust solution for early detection and risk assessment of fetal anomalies in various clinical and telehealth settings.
Figures 2A and 2B illustrate a flowchart that includes the steps involved in a method (200) for early trimester fetal ultrasound analysis, in accordance with an embodiment of the present disclosure. The order in which the method (200) is described is not intended to be construed as a limitation, and any number of the described method (200) steps may be combined in any order to implement the method (200), or an alternative method. Furthermore, the method (200) may be implemented by processing resource or electronic device(s) through any suitable hardware, non-transitory machine-readable medium/instructions, or a combination thereof. The method (200) comprises the following steps:
At step (202), the method (200) includes acquiring, by an ultrasound imaging device (110), a sequence of ultrasound images of a fetal in various orientations.
At step (204), the method (200) includes preprocessing, by a pre-processing unit (120), the acquired ultrasound images by applying preprocessing techniques including noise reduction, contrast enhancement, and normalization, to enhance quality and standardize format of the ultrasound images for generating pre-processed images.
At step (206), the method (200) includes identifying and segmenting, by an artificial intelligence (AI) based analysis module (130), key fetal structures in the pre-processed images, comprising the frontal bone, nasal skin, nasal bone, midbrain, tip of the nose, maxilla, mandible, brainstem, fourth ventricle, cisterna magna, and nuchal translucency (NT).
At step (208), the method (200) includes identifying, by the AI based analysis module (130), midsagittal plane (MSP) based on the positions and orientations of the key fetal structures by locating at least the nasal bone, nasal skin, and tip of the nose in a single image frame.
At step (210), the method (200) includes automatically measuring key fetal markers in the mid-sagittal plane (MSP) for anomaly detection, the key fetal markers including Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Naseon line, midbrain position, maxilla continuity, NT thickness, and visibility of the brainstem, fourth ventricle, and cisterna magna.
At step (212), the method (200) includes calculating, by a nomogram-based risk assessment module (140), a risk score for fetal anomalies based on a nomogram that integrates the fetal markers, gestational age, and other relevant clinical data.
At step (214), the method (200) includes generating, by a reporting module (150), a comprehensive report including the risk score, visual representation of fetal measurements, highlighted areas of potential concern, and recommendations for further action.
In an embodiment, the method (200) further comprises real-time analysis of ultrasound images during the scan to provide feedback for optimal image capture and orientation adjustments, thereby enhancing the accuracy of MSP identification.
In an embodiment, the method (200) includes performing, by the AI based analysis module (130), an iterative analysis of multiple images to identify the best mid-sagittal plane based on an optimal alignment of the nasal bone, the nasal skin, and the nasal tip.
In an embodiment, the method (200) includes the nomogram and integrates the other relevant clinical data, including maternal age, prior pregnancy history, and genetic testing data, to refine the risk assessment score.
In an embodiment, the method (200) further comprises exporting the generated report containing fetal marker measurements and anomaly risk scores from the nomogram-based risk assessment module (140) to an electronic health record (EHR) system through a user interface (160).
In an embodiment, the method (200) further comprises the step of validating the fetal marker measurements by comparing them with normative values stored in a memory unit (135) to detect potential deviations that indicate anomalies.
In an embodiment, the method (200) further comprises the step of adapting the method (200) for remote operation by transmitting ultrasound image data and analysis results over a telemedicine platform for specialist consultation.
Figure 3 shows an ultrasound image illustrates several key fetal markers used for assessment, including the Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Nasion line (MNM Angle), midbrain position, maxilla continuity, brainstem, 4th ventricle, cisterna magna, and Nuchal Translucency (NT). These markers help in evaluating craniofacial structure, brain development, and potential anomalies. The FMF and FMA angles are drawn over the profile of the fetal face, while the Nasion line is shown extending from the nasal region. The positions of the midbrain, brainstem, and 4th ventricle are marked to assess neurological and structural integrity. The NT thickness is highlighted below the fetal neck, as it is an important marker for chromosomal abnormalities.
Figure 4 shows a schematic view of critical fetal head structures as observed on a midsagittal ultrasound scan. The labels identify the frontal bone, nasal skin, nasal bone, maxilla/palate, mandible, midbrain position, diencephalon, brainstem, 4th ventricle, cisterna magna, and Nuchal Translucency (NT). These labels correspond to anatomical features typically assessed in early pregnancy. Each structure is indicated in a standardized position, helping clinicians understand the spatial relationships between these markers during the evaluation of fetal development.
Figure 5 shows an outline of the fetal profile that highlights specific facial and craniofacial markers: nasal skin, tip of the nose, nasal bone, maxilla/palate, mandible, and Nuchal Translucency (NT). This schematic serves as a basic reference for identifying essential facial markers in the midsagittal plane. These markers are commonly measured to assess craniofacial development and detect structural anomalies, such as cleft lip and palate.
Figure 6 shows a series of images that categorize fetal ultrasound scans as optimal, sub-optimal, or non-midsagittal. The optimal image shows clear visualization of essential fetal markers with correct alignment, ensuring accuracy in measurements. The sub-optimal image displays a slightly misaligned fetal profile, leading to less reliable readings, while the non-midsagittal image lacks alignment altogether, making it unsuitable for accurate assessment. This classification helps clinicians select the best-quality images for fetal analysis.
Figure 7 shows a schematic illustration of the Frontomaxillary Facial (FMF) angle, which is measured between the frontal bone and the maxilla. This angle helps assess the relationship between the forehead and upper jaw, providing insight into craniofacial development. Anomalies in this angle may indicate potential developmental issues or structural anomalies in the facial profile.
Figure 8 shows a demonstration of the Facial Maxillary Angle (FMA), an important angle between the face and the maxilla. It is used to evaluate the positioning and development of the upper jaw relative to other facial structures. Variations in the FMA can help in the early identification of anomalies related to facial and jaw development.
Figure 9 shows the Profile Line (PL) distance shown in this diagram represents the linear measurement from the top of the forehead to the chin along the fetal profile. This line provides a reference for assessing cranial projection and facial structure. Measuring the PL distance helps clinicians detect irregularities in craniofacial growth, which could indicate potential anomalies.
Figure 10 shows the Nasion line (MNM Angle) is illustrated as a line extending from the nasion (bridge of the nose) toward the mandible. This angle provides information on the positioning of the chin and jaw about the nasal region, helping to detect anomalies like micrognathia. The MNM angle is an essential measurement in assessing facial symmetry and alignment.
Figure 11 shows integrates several markers, including the Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line, and Nasion line within the fetal head. The markers are displayed to illustrate their interrelation, providing a comprehensive view of craniofacial angles and distances critical for structural assessment. The blue and purple lines outline the head shape, helping guide the alignment of each angle for accurate measurements.
Figure 12 shows schematic highlights of Maxilla continuity, indicated by the arrows showing the alignment and integrity of the maxilla (upper jaw) structure. The continuity of the maxilla is crucial for assessing conditions like cleft lip and palate (CLCP). In this view, the maxilla is shown as an intact structure, which is a sign of normal development in the fetal face.
Figure 13 shows the Nuchal Translucency (NT) thickness in the fetal neck area. NT thickness is the measurement of the fluid-filled space at the back of the fetal neck, which is an important marker in early pregnancy screenings. An abnormal NT measurement can indicate an increased risk of chromosomal abnormalities, such as Down syndrome. This marker is commonly assessed during the first trimester to provide early insights into fetal health.
Figure 14 shows highlights of the brainstem, 4th ventricle, and cisterna magna within the fetal brain. These structures are vital components of the fetal central nervous system and are visible in a properly aligned midsagittal view. The brainstem connects the brain to the spinal cord and is essential for regulating vital functions, while the 4th ventricle is a fluid-filled space that supports brain circulation. The cisterna magna is a cerebrospinal fluid-filled space near the back of the brain. Abnormalities in these structures may indicate neural tube defects or other developmental issues, making their visibility and integrity critical markers in fetal assessment.
In one embodiment, the system is adapted to integrate data from other imaging modalities, such as three-dimensional (3D) ultrasound and Doppler ultrasound, alongside standard two-dimensional (2D) ultrasound. The processing unit in this configuration can automatically process and align data from multiple imaging formats, allowing for a more comprehensive view of fetal anatomy and cardiovascular function. This multimodal integration enables a more complete diagnostic tool for assessing fetal development and can provide clinicians with a layered, more nuanced dataset that informs both anatomical and functional assessments in early pregnancy.
In an embodiment, the system is miniaturized and adapted for use in a portable or mobile device, such as a tablet or smartphone. This setup enables field or resource-limited setting use, where traditional full-scale ultrasound machines are impractical. In this portable version, the processing unit, nomogram-based risk assessment module, and AI techniques are optimized for mobile hardware capabilities. The display interface can be a tablet or mobile screen, allowing clinicians to perform fetal ultrasound analysis and risk assessment directly from a handheld device. This setup would be especially valuable in rural healthcare or telemedicine applications where remote diagnosis is needed.
In another embodiment, the system is modified as a training and simulation platform configured specifically for educating sonographers and clinicians in fetal ultrasound techniques. The AI-driven modules are configured to simulate real-time analysis of various fetal markers in stored ultrasound images or videos, providing trainees with guided practice in identifying the midsagittal plane (MSP) and specific fetal markers. The display interface includes interactive feedback on measurements and scoring, along with suggestions for optimal image acquisition techniques. The simulation platform thus serves as a tool to standardize sonographer training and improve skill levels before clinical practice.
In an embodiment, the system expands beyond ultrasound analysis by integrating additional clinical data sources, such as genetic testing and biochemical markers. The nomogram-based risk assessment module is configured to accept data inputs from genetic and biochemical screening tests, along with ultrasound measurements, allowing for a comprehensive and multifactorial risk assessment. This combined approach offers an in-depth risk score that incorporates structural, genetic, and biochemical risk factors, providing clinicians with a holistic view of fetal health and potential anomalies. Such integration could be especially valuable in cases where structural anomalies detected via ultrasound have known genetic or biochemical correlations.
In one more embodiment, the system leverages telemedicine capabilities by enabling real-time data sharing and remote expert consultations. In this setup, the system’s interface allows ultrasound images and AI-generated analysis to be streamed to specialists in other locations, who can then provide consultation in real-time. The processing unit can also transmit real-time data on fetal markers and risk assessment scores to the remote consultant, who may be able to annotate images or adjust settings for optimized image quality. This setup is configured for clinical settings that lack specialized fetal imaging expertise and would benefit from direct access to remote specialists.
In another embodiment, the AI techniques used for identifying the MSP and measuring fetal markers are configured to continuously learn and adapt based on feedback from clinicians. The system includes a feedback interface that allows clinicians to input their evaluations on the AI-generated measurements, enabling the system to refine its techniques based on real-world data. Additionally, the system includes customization features for region-specific adaptations, such as adjusting thresholds in the nomogram-based risk assessment based on demographic data or clinical standards specific to different regions or populations.
In one embodiment, the system is configured to operate as a cloud-based diagnostic tool, where image data, fetal measurements, and risk assessments are processed and stored on a remote server. Clinicians upload ultrasound data to the cloud, where it is analyzed using advanced AI techniques housed on the cloud infrastructure. This approach not only enables greater processing power for large-scale data analysis but also allows for the aggregation of data across multiple institutions. This data can then be used in large-scale research studies on fetal development and population-level studies, contributing to new insights into prenatal health.
In one embodiment, the system includes additional AI modules specifically for Doppler ultrasound analysis to assess fetal cardiovascular health. The processing unit is configured to measure blood flow in the fetal heart and major vessels, generating additional markers related to cardiovascular function. These Doppler-based measurements are incorporated into the risk assessment module, allowing the system to flag potential cardiovascular issues in early pregnancy. This configuration expands the utility of the system beyond anatomical assessments to include functional cardiovascular assessments.
In another embodiment envisions the system’s integration with wearable ultrasound devices that allow for continuous or intermittent monitoring of fetal development. The processing unit and AI techniques are adapted to process real-time data from a wearable ultrasound device, which could be applied to the abdomen to capture ongoing fetal imaging. In this setup, the nomogram-based risk assessment module could perform periodic analyses based on updated image data, enabling clinicians to monitor fetal health over extended periods and respond to any detected anomalies in real time.
In one more embodiment, the system is configured to be modular, allowing clinicians to select specific fetal markers relevant to their diagnostic needs. The processing unit and risk assessment module are configured to operate with a customizable set of markers, rather than a fixed set. For example, clinicians may opt to analyze only craniofacial markers or include additional markers based on specific clinical indications. This modular approach is useful for tailoring the system to specialized clinical cases or when focused assessments are required.
The functions described herein may be implemented in hardware, executed by a processor, firmware, or any combination thereof. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. The present disclosure can be implemented by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but, are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS
The present disclosure described hereinabove has several technical advantages including, but not limited to, a system and method for early trimester fetal ultrasound analysis, which;
• enhances the accuracy and consistency of fetal anatomical marker identification during early trimester ultrasound imaging;
• facilitates automatic detection of specific fetal structures and markers, minimizing variability in interpretation;
• offers real-time guidance and feedback to clinicians during ultrasound exams, thereby improving the quality of fetal imaging and reducing the potential for missed observations;
• enables a standardized, evidence-based approach to early fetal anomaly assessment that can be seamlessly integrated into existing clinical workflows and electronic health record systems;
• supports remote consultations and telemedicine applications for fetal ultrasound analysis, allowing healthcare providers to access expert insights regardless of geographic location; and
• provides a scalable and adaptive system that learns from ongoing data and clinician feedback, continuously improving its assessment accuracy over time.
The foregoing disclosure has been described with reference to the accompanying embodiments which do not limit the scope and ambit of the disclosure. The description provided is purely by way of example and illustration.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
Any discussion of devices, articles or the like that has been included in this specification is solely for the purpose of providing a context for the disclosure. It is not to be taken as an admission that any or all of these matters form a part of the prior art base or were common general knowledge in the field relevant to the disclosure as it existed anywhere before the priority date of this application.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation. , Claims:WE CLAIM:
1. A system (100) for detecting fetal anomalies in first trimester ultrasound imaging, said system (100) comprising:
• an ultrasound imaging device (110) configured to capture a sequence of ultrasound images of a fetal in various orientations;
• a pre-processing unit (120) configured to receive said ultrasound images and preprocesses said ultrasound images by applying preprocessing techniques including noise reduction, contrast enhancement, and normalization, to enhance quality and standardize format of said ultrasound images for generating preprocessed images;
• an artificial intelligence (AI) based analysis module (130) configured to analyse the preprocessed images with a pre-trained AI model which is configured to:
- identify and segment key fetal structures in the preprocessed images, comprising the frontal bone, nasal skin, nasal bone, midbrain, tip of the nose, maxilla, mandible, brainstem, fourth ventricle, cisterna magna, and nuchal translucency (NT);
- identify midsagittal plane (MSP) based on the positions and orientations of said key fetal structures by locating at least the nasal bone, nasal skin, and tip of the nose in a single image frame; and
- automatically measure key fetal markers in the mid-sagittal plane (MSP) for anomaly detection, said key fetal markers including Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Naseon line, midbrain position, maxilla continuity, NT thickness, and visibility of the brainstem, fourth ventricle, and cisterna magna;
• a nomogram-based risk assessment module (140) configured to calculate a risk score for fetal anomalies based on a nomogram that integrates said fetal markers, gestational age, and other relevant clinical data; and
• a reporting module (150) configured to generate a comprehensive report including the risk score, visual representation of fetal measurements, highlighted areas of potential concern, and recommendations for further action.
2. The system (100) as claimed in claim 1, wherein said ultrasound imaging device (110) is further configured to perform real-time analysis of ultrasound images during the scan to provide feedback for optimal image capture and orientation adjustments, thereby enhancing the accuracy of MSP identification.
3. The system (100) as claimed in claim 1, wherein said AI based analysis module (130) is configured to perform an iterative analysis of multiple images to identify the best mid-sagittal plane (MSP) based on an optimal alignment of the nasal bone, the nasal skin, and the nasal tip.
4. The system (100) as claimed in claim 1, wherein the nomogram integrates the other relevant clinical data, including maternal age, prior pregnancy history, and genetic testing data, to refine the risk assessment score.
5. The system (100) as claimed in claim 1, wherein said AI based analysis module (130) includes a machine learning component that continuously improves segmentation and marker identification based on feedback from subsequent scans and clinician input
6. The system (100) as claimed in claim 1, wherein said AI model is a deep learning model trained on a dataset of diverse fetal ultrasound images dataset, to enhance the detection of fetal markers even in low-quality or ambiguous images.
7. The system (100) as claimed in claim 1, further comprises a user interface (160) configured to integrate the system (100) with hospital information systems (HIS) or electronic health records (EHR) to automate the storage and retrieval of ultrasound measurements and diagnostic reports.
8. The system (100) as claimed in claim 1, wherein the AI model provides a confidence score for each identified fetal marker to guide the sonographer in image acquisition quality.
9. The system (100) as claimed in claim 1, wherein the risk score generated by the nomogram includes a breakdown of individual anomaly risks, comprising Down syndrome, cleft lip, and neural tube defects, based on the measurements and presence of associated markers.
10. The system (100) as claimed in claim 1, wherein the nomogram incorporates population-based fetal development data to benchmark the measurements against normative values for the corresponding gestational age.
11. The system (100) as claimed in claim 1, further comprises a user interface (160) configured to display real-time risk assessments, measurement guides, and suggestions for optimal imaging based on live ultrasound feed.
12. The system (100) as claimed in claim 1, further comprises an alert module (170) configured to indicate suboptimal imaging when said AI based analysis module (130) detects an inadequate view of critical anatomical markers, prompting a sonographer to adjust the image capture angle.
13. The system (100) as claimed in claim 1, further comprises a mobile application associated with the reporting module (150) so as to receive remote access to fetal health assessments and risk scores for telemedicine applications.
14. A method (200) for detecting fetal anomalies in first trimester ultrasound imaging, comprising:
• acquiring, by an ultrasound imaging device (110), a sequence of ultrasound images of a fetal in various orientations;
• preprocessing, by a pre-processing unit (120), the acquired ultrasound images by applying preprocessing techniques including noise reduction, contrast enhancement, and normalization, to enhance quality and standardize format of said ultrasound images for generating preprocessed images;
• identifying and segmenting, by an artificial intelligence (AI) based analysis module (130 ), key fetal structures in the preprocessed images, comprising the frontal bone, nasal skin, nasal bone, midbrain, tip of the nose, maxilla, mandible, brainstem, fourth ventricle, cisterna magna, and nuchal translucency (NT);
• identifying, by the AI based analysis module (130), midsagittal plane (MSP) based on the positions and orientations of said key fetal structures by locating at least the nasal bone, nasal skin, and tip of the nose in a single image frame;
• automatically measuring key fetal markers in the mid-sagittal plane (MSP) for anomaly detection, said key fetal markers including Frontomaxillary Facial (FMF) angle, Facial Maxillary Angle (FMA), Profile Line (PL) distance, Naseon line, midbrain position, maxilla continuity, NT thickness, and visibility of the brainstem, fourth ventricle, and cisterna magna;
• calculating, by a nomogram-based risk assessment module (140), a risk score for fetal anomalies based on a nomogram that integrates said fetal markers, gestational age, and other relevant clinical data; and
• generating, by a reporting module (150), a comprehensive report including the risk score, visual representation of fetal measurements, highlighted areas of potential concern, and recommendations for further action.
15. The method (200) as claimed in claim 14, further comprises further comprising real-time analysis of ultrasound images during the scan to provide feedback for optimal image capture and orientation adjustments, thereby enhancing the accuracy of MSP identification.
16. The method (200) as claimed in claim 14, wherein performing, by the AI based analysis module (130), an iterative analysis of multiple images to identify the best mid-sagittal plane based on an optimal alignment of the nasal bone, the nasal skin, and the nasal tip.
17. The method (200) as claimed in claim 14, wherein the nomogram integrates the other relevant clinical data, including maternal age, prior pregnancy history, and genetic testing data, to refine the risk assessment score.
18. The method (200) as claimed in claim 14, further comprises exporting the generated report containing fetal marker measurements and anomaly risk scores from said nomogram-based risk assessment module (140) to an electronic health record (EHR) system through a user interface (160).
19. The method (200) as claimed in claim 14, further comprises the step of validating the fetal marker measurements by comparing them with normative values stored in a memory unit (135) to detect potential deviations that indicate anomalies.
20. The method (200) as claimed in claim 14, further comprises the step of adapting said method (200) for remote operation by transmitting ultrasound image data and analysis results over a telemedicine platform for specialist consultation.
Dated this 18th Day of December 2024

_______________________________
MOHAN RAJKUMAR DEWAN, IN/PA – 25
OF R. K. DEWAN & CO.
AUTHORIZED AGENT OF APPLICANT