System and method for generating anatomy-specific information

Abstract

Embodiments of the disclosure describe a system (102) and method for generating anatomy- specific information is disclosed. The method (800) includes receiving a first abdomen surface image of a subject from a stereo view vision unit (106). The method includes determining a spatial pose of an ultrasound transducer (108) associated with an actuation unit (104) relative to at least a portion of an abdomen surface to obtain a plurality of ultrasound image frames based on the received first abdomen surface image. The method includes determining one or more fetus-specific hotspot regions using a virtual anatomical model, a plurality of landmarks associated with each of the plurality ultrasound image frames, and a spatial arrangement of the plurality of ultrasound image frames based on the obtained plurality of ultrasound image frames. The method includes generating the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions.

Description

SYSTEM AND METHOD FOR GENERATING ANATOMY-SPECIFIC INFORMATIONFIELD OF THE INVENTION

[0001] The present disclosure relates to the application of artificial intelligence (Al) in ultrasound imaging systems. Particularly, the present disclosure relates to a system and method for generating anatomy-specific information.BACKGROUND

[0002] The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.

[0003] Accurate fetal assessment is crucial to ensure the healthy development of a fetus and detect any anomalies of the fetus. During each trimester, different anatomical structures are examined using ultrasound imaging, with standardized planes that provide detailed insights into fetal growth and potential anomalies. However, there are significant challenges in ensuring consistent and accurate diagnoses due to inter- and intra-operator variability. Sonologists rely heavily on their expertise to acquire the correct planes during ultrasound imaging.

[0004] Through years of practice, expert sonologists develop the ability to identify the presenting fetal anatomy, anticipate the next anatomical structure or plane, and determine the proper probe orientation to capture precise images. This process requires the sonologist to interpret complex factors, including the alignment of fetal and maternal anatomy, detailed knowledge of anatomical structures, and an understanding of fetal presentation and lie. A vast amount of information and experience is required to perform accurate scans, which, if not assimilated, can create inconsistencies in imaging quality, often leading to diagnostic errors. Furthermore, the shortage of skilled sonologists presents agrowing problem, leading to delayed access contributing to poor patient outcome.

[0005] Therefore, there is a need for a system and method which eliminates the variability caused by operator dependence, ensuring that every scan is performed with the same level of precision and thoroughness, regardless of skill level of the operator.SUMMARY

[0006] This summary is provided to introduce a selection of concepts, in a simplified format, which is further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention nor is it intended for determining the scope of the invention.

[0007] In an embodiment of the present disclosure, a method for generating anatomy-specific information is disclosed. The method includes receiving a first abdomen surface image of a subject from a stereo view vision unit. The method includes determining a spatial pose of an ultrasound transducer associated with an actuation unit relative to at least a portion of an abdomen surface to obtain a plurality of ultrasound image frames based on the received first abdomen surface image. The method includes determining one or more fetus-specific hotspot regions using a virtual anatomical model, a plurality of landmarks associated with each of the plurality ultrasound image frames, and a spatial arrangement of the plurality of ultrasound image frames based on the obtained plurality of ultrasound image frames. The method includes generating the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions.

[0008] In yet another embodiment of the present disclosure, a system for generating anatomyspecific information is disclosed. The system includes a memory and at least one processor operatively coupled to the memory. The at least one processor is configured to receive, a first abdomen surface image of a subject from a stereo view vision unit. The at least one processor is configured to determine a spatial pose of an ultrasound transducer associated with an actuation unit relative to at least a portion of an abdomen surface to obtain a plurality of ultrasound image frames based on the received first abdomen surface image. The at least one processor is configured to determine one or more fetus-specific hotspot regions using a virtual anatomical model, a plurality of landmarks associated with each of the plurality ultrasound image frames, and a spatial arrangement of the plurality of ultrasound image frames based on the obtained plurality of ultrasound image frames. The at least one processor is configured to generate the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions.

[0009] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and thefollowing detailed description. For a better understanding of exemplary embodiments of the present disclosure, together with other and further features and advantages thereof, reference is made to the following description, taken in conjunction with the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS:

[0010] The embodiments of the disclosure itself, as well as a preferred mode of use, further objectives and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings. One or more embodiments are now described, by way of example only, with reference to the accompanying drawings in which:

[0011] Figure 1 illustrates an environment for establishing a system for generating anatomyspecific information of an abdomen surface, in accordance with an embodiment of the present disclosure;

[0012] Figure 2 illustrates a block diagram depicting the system for generating the anatomy¬ specific information, in accordance with an embodiment of the present disclosure;

[0013] Figure 3 illustrates a block diagram depicting the modules, in accordance with an embodiment of the present disclosure;

[0014] Figure 4 illustrates a flowchart depicting a method for receiving three-Dimensional (3D) digital coordinates at the system from a stereo view vision unit, in accordance with an embodiment of the present disclosure;

[0015] Figure 5 illustrates a flowchart depicting a method of performing a global scout scan by the stereo view vision unit, in accordance with an embodiment of the present disclosure;

[0016] Figure 6 illustrates a flowchart depicting a method of performing a global scout scan by the stereo view vision unit, in accordance with an embodiment of the present disclosure;

[0017] Figure 7 illustrates a schematic diagram depicting a feature-extraction pipeline, in accordance with an embodiment of the present disclosure; and

[0018] Figure 8 illustrates a flowchart depicting a method for generating the anatomy-specific information, in accordance with an embodiment of the present disclosure.

[0019] The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternativeembodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

[0020] It should be appreciated by those skilled in art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.DETAILED DESCRIPTION

[0021] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0022] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the spirit and the scope of the disclosure.

[0023] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a device or system or apparatus proceeded by “comprises... a” does not, without more constraints, preclude the existence of other elements or additional elements in the device or system or apparatus.

[0024] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changesmay be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0025] The term subject may refer to a pregnant women / expectant mother, the term anatomy may refer to heart, head, kidney, stomach, lower limbs, upper limbs, thorax, etc., the term standard plane may refer to clinically approved ultrasound image frames with specific, predefined views are used to assess the development and health of the fetus (Multiple standard planes may be identified within a single anatomical region to evaluate comprehensively) and the term anomaly / fetal anomaly may refer to any unusual or unexpected condition in a baby’s development during pregnancy (Structural / growth defects through ultrasound image) all over the specification.

[0026] Figure 1 illustrates an environment 100 for establishing a system 102 for generating anatomy-specific information of an abdomen surface, in accordance with an embodiment of the present disclosure. The environment 100 may include an actuation unit 104, a stereo view vision unit 106, and an ultrasound transducer 108. In an embodiment, the stereo view vision unit 104 may include a dual lens camera unit configured to reconstruct a surface of a subject. The actuation unit 104 may be an electromechanical unit which includes a series of electrically actuated motors placed in a combination of series and parallel connections. The series of electrically actuated motors may be rotatory' or prismatic.

[0027] A beam-forming component of the ultrasound transducer 108 may be connected to tire actuation unit 104 as an end effector for obtaining a plurality of ultrasound image frames (herein thereafter referred to as ultrasound image frames). Tire actuation unit 104 may be an electronic head mount device, which guides a user holding the beam-forming component of the ultrasound transducer 108 in an augmented reality (AR) space for obtaining the ultrasound image frames. The user may include, but is not limited to, a sonographer, a nurse, a technician, a patient, and the like. The actuation unit 104 may be configured to use an adaptive hybrid force and position controller methodology7to compensate respiratory motion of the subject.

[0028] In an embodiment, the system 102 may be implemented within the actuation unit 104. In another embodiment, the system 102 may be externally connected to the actuation unit 104. Yet, in another embodiment, some part of the system 102 may be implemented within the actuation unit 104 and remaining part of the system 102 may be externally connected to the actuation unit 104. The system 102 may be a central server or hub for information extracted from a first global scout scan model, a second global scout scan model, and a third global scoutscan model. The first global scout scan model may include a neural network-based featureextraction model. The third global scout scan model may include a virtual anatomical model.

[0029] In an embodiment, the user may login to access the system 102 with a face identity’, or use credential information such as username or password. Once the face identity is recognized, the system 102 creates a unique identity registered with a face based on a user input. Once the face identity’ matches with the previous database or history’, the system 102 creates a new event or visit under the ID and assigns the ID to the user.

[0030] Further, the subject registration (Name, Date of Birth (DOB), and Last Menstrual Period (LMP)), which may be performed by the user either manually or by using an interactive voice command interface. Maternal history' of the subject may further be entered manually or through the interactive voice command. The maternal history of the subject may include, but is not limited to, age, weight, height, blood group, and the like. For a new visit, previous history' may be loaded, and latest reports may’ be fed into the system 102. Alternatively, the latest reports may be scanned through an electronic device and directly transferred to the system 102. The electronic device may include, but is not limited to, a mobile phone, a user device, a laptop, a tablet, and the like. Furthermore, the subj ect may be positioned under field of view of the stereo view vision unit 106. A user interface may’ be shown to cover the complete abdomen region of the subject.

[0031] In an embodiment, the system 102 may be configured to receive a first abdomen surface image of the subject from the stereo view vision unit 106. The stereo view vision unit 106 may include an image sensor, a Light Detection and Ranging (LIDAR) sensor, and an Infrared (IR) sensor. The first abdomen surface image may include, but is not limited to, an abdomen surface image of the subject, a reconstructed abdomen surface image of the subject, and the like. Further, the system 102 may be configured to determine a movement of the subject based on the received first abdomen surface image. For example, the stereo view vision unit 106 is configured to continuously monitor movement of the subject using a plurality of visual clues and automatically adjust if considerable movement is detected. If the movement of the subject is not observed, then the stereo view vision unit 106 transmits the first abdomen surface image to the system 102. If the movement of the subject is observed, then the stereo view vision unit 106 adjusts the first abdomen surface image. In an embodiment, the adjusted abdomen surface image may be represented as a reconstructed abdomen surface image. Further, the system 102 may be configured to identify that the subject has fully moved out of the field of view. Upon identifying the subject fully moving out of the field of view, the system 102 may be configuredto receive a second abdomen surface image from the stereo view vision unit 106 . For example, the stereo view vision unit 106 initiates a digital surface reconstruction step if the subject has fully moved out of the field of view of the stereo view vision unit 106, followed by an update to a matrix ‘M’. If the movement of the subject is not observed, the actuation unit 104 may be enabled.

[0032] The system 102 may be configured to represent the first abdomen surface image and the second abdomen surface image in coordinates using an inherent coordinate transformation. The inherent coordinate transformation may be represented by the matrix ‘M’ with a dimension of 4x4. The system 102 may include a feature extractor and detection network, a spatial image stacking network, and a feedback-based reinforcement learning decision-making system.

[0033] The system 102 may include a computational logic configured to determine landmarks (3D positions and orientations), which are overlaid on the first abdomen surface image or the second abdomen surface image. The landmarks may be sequenced and spread over the first abdomen surface image or the second abdomen surface image. Further, the landmarks may be transformed to self-actuation coordinates using the matrix ‘M’. In an embodiment, the system 102 may be configured to segment an abdomen region of the subject using contour and image based methods. The contour and image based methods may include structure from motion and simultaneous location and mapping methods. The abdomen region of the subject may be a region of the interest and generate the segmented region of the interest as point cloud data and continuous smooth surface as mesh. Hie 3D digital coordinates may be transferred to the actuation unit 104 from the stereo view vision unit 106.

[0034] Further, the system 102 may be configured to determine a spatial pose of the ultrasound transducer 108 associated with the actuation unit 104 relative to at least a portion of an abdomen surface to obtain the ultrasound image frames based on the received first abdomen surface image or the second abdomen surface. The spatial pose may refer to a three-dimensional position and orientation of the ultrasound transducer 108. In an embodiment, the system 102 may be configured to determine anatomy-specific landmarks of the first abdomen surface image or the second abdomen surface image for the actuation unit 104. Further, the system 102 may be configured to determine the spatial pose of the ultrasound transducer 108 based on the determined anatomy-specific landmarks.

[0035] Furthermore, the system 102 may be configured to determine one or more fetus-specific hotspot regions using the virtual anatomical model based on the obtained plurality of ultrasound image frames. The one or more fetus-specific hotspot regions may include, but are not limitedto, one or more fetal head regions, one or more fetal hand regions, one or more fetal thorax regions, one or more fetal abdomen regions, one or more fetal leg regions, and the like. The system 102 may be configured to extract a sequence of multi -model information and estimate the one or more fetus-specific hotspot regions of fetal anatomies across digitally reconstructed abdominal surface. Based on aforementioned analysis, the system 102 may be configured to determine where specific anatomical structures such as the fetal head, hands, or abdomen are likely located within a global coordinate frame derived from the first abdomen surface image or second abdomen surface image. The system 102 may be configured to combine extracted visual features, spatially arranged ultrasound image frames, and the virtual anatomical model. For example, the system 102 interprets the positioning of the fetus. Using the positioning of the fetus, the sy stem 102 predicts the approximate anatomical regions of interest and uses that information to guide subsequent scanning actions carried out by the actuation unit 104.

[0036] The virtual anatomical model may be a computational 3D avatar of a fetus. The virtual anatomical model may serve as a central geometric and visual reference that links the ultrasound image frames. In addition, the system 102 may be configured to generate the anatomy-specific information based on the determined one or more fetus-specific hotspot regions. The system 102 has been further detailed with reference to Figure 2 to Figure 8.

[0037] Figure 2 illustrates a block diagram depicting the system 102 for generating the anatomy-specific information, in accordance with an embodiment of tire present disclosure. The system 102 may include an I / O interface 202, a processor 204, and a memory 206. The memory 206 may store data 208 organized within a database, which logs score calculations for auditability and model retraining purposes.

[0038] The processor 204 may be communicatively coupled to the memory 206 and the I / O interface 202. The processor 204 retrieves the data 208 from the memory 206 and executes instructions to generate the anatomy-specific information of the abdomen surface based on the data 209 stored in the memory 206. The processor 204 receives the first abdomen surface image or the second first abdomen surface image from the stereo view vision unit 106. The I / O interface 202 is communicatively coupled to the memory 206 and facilitates communication between the actuation unit 104 and the stereo view vision unit 106.

[0039] The processor 204 may comprise at least one data processor for executing program components for executing user or system-generated processes. The processor 204 may include specialized processing units such as, without limiting to, integrated system (bus) controllers,memory management control units, floating point units, graphics processing units, digital signal processing units, etc.

[0040] The processor 204 may be disposed in communication with one or more Input / Output (I / O) devices via I / O interface 202. The I / O interface 202 may employ communication protocol s / methods such as, without limitation, audio, analog, digital, stereo, serial bus, Universal Serial Bus (USB), infrared, Digital Visual Interface (DVI), High-Definition Multimedia Interface (HDMI), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), cellular (e.g., Code-Division Multiple Access (CDMA), High-Speed Packet Access (HSPA+), Global System For Mobile Communications (GSM), Uong-Term Evolution (UTE) or the like), and the like.

[0041] Using the I / O interface 202, the system 102 may communicate with one or more I / O devices. In some implementations, the processor 204 may be disposed in communication with a communication network via a network interface. The network interface may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), Transmission Control Protocol / Intemet Protocol (TCP / IP), token ring, IEEE 802.1 la / b / g / n / x, etc. The communication network can be implemented as one of the several types of networks, such as, without limiting to, intranet or any such wireless network interfaces. The communication network may either be a dedicated network or a shared network, which represents an association of several types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol / Intemet Protocol (TCP / IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the communication network may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc. In some embodiments, the processor 204 may be disposed in communication with a memory 206 e.g., RAM, and ROM, via a storage interface.

[0042] The memory 206 may store a collection of program or database components, including, without limitation, user / application, an operating system, a web browser, a mail client, a mail server, a user interface, and the like. In some embodiments, computer system may store user / application data, such as, without limiting to, the data, variables, records, etc. as described in this invention. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as, without limiting to, Oracle or Sybase.

[0043] The operating system may facilitate resource management and operation of the system 102. Examples of operating systems include, without limitation, Apple MacintoshTMOS X ™, UNIXTM, Unix-like system distributions (e.g., Berkeley Software Distribution (BSD), FreeBSDTM, Net BSD ™, Open BSDTM, etc.), Einux distributions (e.g., Red Hat™, Ubuntu ™, K-Ubuntu ™, etc.), Microsoft Windows ™ (XP ™, Vista / 6 / 8, etc.), Google Android ™, Blackberry™ Operating System (OS), or the like.

[0044] In an embodiment, the memory' 206 may be utilized in the system 102 for storing subject data. The subject data may include, but is not limited to, subject identity (ID), which may be a biometric ID or credential information such as username and password. The subject data may further include subject medical history’, allergic history’ and one or more ultrasound scan images. The memory' 206 may be a local memory' or a cloud storage.

[0045] Further, the system 102 may employ one or more processors 204 for implementing one or more features of the present disclosure. Additionally, as user interface may be used to be employed by the system 102 for displaying scans to an expert and for registering one or more user inputs. The system 102 may be the central server / hub for all information extracted from different models. In an embodiment, the memory' 206 may include modules 210. The modules 210 are further detailed with reference to Figure 3.

[0046] Figure 3 illustrates a block diagram depicting the modules 210, in accordance with an embodiment of the present disclosure. The modules 210 may be implemented using hardware, and / or software, or partly by hardware and partly by software or firmware. The operation of each of the modules 210 is explained herein.

[0047] The modules 210 may include abdomen surface image receiving module 302, a spatial pose determining module 304, a fetus-specific hotspot region determining module 306, an anatomy-specific information generating module 308, an anatomical landmark determining module 310, a traversal parameter modifying module 312, a standard plane identifying module 314, and an anomaly identifying module 316.

[0048] The abdomen surface image receiving module 302 may be configured to receive the first abdomen surface image of the subject from the stereo view vision unit 106. In an embodiment, the abdomen surface image receiving module 302 may be configured to receive any human anatomy-specific surface image. Furthermore, the abdomen surface image receiving module 302 may be configured to determine movement of the subject based on the received first abdomen surface image. The abdomen surface image receiving module 302 maybe configured to adjust the first abdomen surface image based on the determined movement of the subject. Further, the abdomen surface image receiving module 302 may be configured to identify the subject moving out of the field of view based on the adjusted first abdomen surface image. The abdomen surface image receiving module 302 may be configured to receive the second abdomen surface image from the stereo view vision unit 106 based on the identified subject moving out of the field of view of the stereo view vision unit 106.

[0049] Further, the spatial pose determining module 304 may be configured to determine the spatial pose of the ultrasound transducer 108 associated with the actuation unit 104 relative to at least a portion of the abdomen surface to obtain the ultrasound image frames based on the received first abdomen surface image. In an embodiment, the spatial pose determining module 304 maybe configured to determine the spatial pose of the ultrasound transducer 108 associated with the actuation unit 104 based on the adjusted first abdomen surface image. For example, the stereo view vision unit 106 continuously monitors the movement of the subject using the plurality of visual clues, and automatically adjust if considerable movement is detected. The system 102 may initiate the digital surface reconstruction step if the subject has fully moved out of the field of view of the stereo view vision unit 106, followed by an update to matrix ‘M’ throughout a workflow. If the movement of the subject is not observed, the actuation unit 104 may be enabled.

[0050] In an embodiment, the fetus-specific hotspot region determining module 306 may be configured to generate a spatial arrangement of the ultrasound image frames by stacking the ultrasound image frames together based on the received ultrasound image frames. Each of the ultrasound image frames may be stacked together and spatially arranged. Each of the ultrasound image frames may be stacked together and spatially arranged using a second global scout scan model. Time and frame rate synchronization of self-actuation and ultrasound transducer unit 102 may be performed to spatially arrange the ultrasound image frames. The ultrasound image frames may be sparsely arranged to co-locate the anatomy of the fetus.

[0051] Furthermore, the fetus-specific hotspot region determining module 306 may be configured to update the virtual anatomical model using the spatially arrangement of the ultrasound image frames and a plurality of features. The plurality of features may indicate fetal spatial orientation of the subject. Further, the fetus-specific hotspot region determining module 306 may be configured to determine the one or more fetus-specific hotspot regions using the virtual anatomical model based on the indicated fetal spatial orientation of the subject. The one or more fetus-specific hotspot regions may include, but are not limited to, the one or more fetalhead regions, the one or more fetal face regions, the one or more fetal thorax regions, one or more fetal abdomen regions, the one or more fetal lower limb regions, the one or more fetal upper limb regions, the one or more maternal regions, the one or more fetal hand regions, and the one or more fetal leg regions.

[0052] Furthermore, the anatomy-specific information generating module 308 may be configured to generate the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions. Further, the anatomy-specific information generating module 308 may be configured to identify anatomy-specific information from a gestation age of 6 weeks to 40 weeks or till labour.

[0053] The virtual anatomical model may be initialized to correlate the geometric arrangement of the fetus with respect to the subject and the actuation unit 104. The virtual anatomical model may be positioned and collocated in accordance with an actual fetus. Further, the virtual anatomical model may include a visualization software that shows orientation of the fetus relative to the subject and the actuation unit 104. As the actuation unit 104 traces more landmarks, the virtual anatomical model is also updated with the same. The aforementioned changes may be continuously updated to the visualization software to view the position and movements of the fetus.

[0054] In an embodiment, the anatomical landmark determining module 310 may be configured to determine a plurality of anatomical landmarks and a plurality of visual cues using the neural network-based feature-extraction model based on the received ultrasound image frames. For every ultrasound image frame, key anatomical landmarks and visual clues may be extracted using the neural network-based feature -extraction model.

[0055] The plurality of anatomical landmarks may include 3D positional and orientational coordinates on maternal abdomen or corresponding fetal anatomical regions. Further, the plurality of anatomical landmarks may refer to segmented masks or regions of key structures within standard planes. For example, key structures include CSP, midline, cerebellum, arrow sign. The key structures may be segmented as part of the standard planes of head anatomy. The plurality of anatomical landmarks may be obtained through the computational logic and overlaid on the first abdomen surface image or the second abdomen surface image. For example, each of the plurality of anatomical landmarks represents a point to be traced by the actuation unit 104 so the system 102 may deduce fetal presentation, lie, and anatomical arrangement. Further, the plurality of visual cues may include learned image features such ascontours, textures, organ boundaries that allow the system 102 to interpret real-time ultrasound data, recognize standard planes, detect anomalies, and ensure closed-loop actuation. The system 102 may be configured to use a path planner (for example, a 6DOF path planner) to derive the plurality of anatomical landmarks. Further, the system 102 may be configured to use a search model to find a closest point on the first abdomen surface image or the second abdomen surface image, and a smooth path may be formed by connecting points using a polynomial fit. The plurality of anatomical landmarks may be sequenced and spread over the first abdomen surface image or the second abdomen surface image, the system 102 may determine fetal presentation and lie using a computational approach. These plurality of anatomical landmarks may be transformed to self-actuation coordinates using a matrix ‘M.’

[0056] In an embodiment, the traversal parameter modifying module 312 may be configured to generate an anatomy specific trajectory for an anatomy of a fetus based on the determined spatial pose of the ultrasound transducer 108 associated with the actuation unit 104. Further, the traversal parameter modifying module 312 may be configured to determine one or more traversal parameters to receive the ultrasound image frames of the anatomy based on the generated anatomy specific trajectory. The one or more traversal parameters may refer to a set of motion control variables. The one or more traversal parameters may be system-defined motion variables (positions, orientations, velocities, forces, and continuous corrections) that dictate the actuation unit 104 moves along the anatomy-specific trajectory to receive sequences of ultrasound image frames.

[0057] In an embodiment, the standard plane identifying module 314 may be configured to generate a feature map for each of the ultrasound image frames using a plurality of weights and a plurality of parameters based on the received ultrasound image frames. The plurality of weights may include learnable numerical values in a deep neural network and the plurality of parameters may include internal variables a model learns from training data to make predictions.

[0058] Further, the feature map may indicate a plurality of contours relevant to a standard plane for the anatomy of the fetus. Furthermore, the standard plane identifying module 314 may be configured to determine that the generated feature map for each of the ultrasound image frames satisfies a predetermined template feature map. The predetermined template feature map may indicate a plurality of contour regions in an ultrasound image. The plurality of contour regions in the ultrasound image which are defined by clinical experts for the standard plane. Furthermore, the standard plane identifying module 314 may be configured to identify each ofthe image frames as a standard plane associated with the anatomy in the virtual anatomical model based on the determined feature map. For each anatomy, the standard plane identifying module 314 examines standard planes to understand growth patterns, structural integrity, and a plurality of anomalies. For example, the standard plane identifying module 314 evaluates clinically approved standard planes for each fetal anatomy, such as the transthalamic, transventricular, and transcerebellar planes for a head of the fetal.

[0059] The standard planes may be loaded into the virtual anatomical model corresponding to the anatomy. For example, when the user touches any particular anatomy on the virtual anatomical model, along with the spatially arranged ultrasound image frames, the standard plane may be also displayed.

[0060] Further, the anomaly identifying module 316 may be configured to identify a plurality of anomalies associated with the anatomy of the fetus based on the generated feature map for each of the plurality of ultrasound image frames and a spatial arrangement of the plurality of ultrasound image frames. The plurality of anomalies may refer to structural or growth-related irregularities in fetal anatomy, identified by comparing the generated feature maps of ultrasound image frames with expert-defined anatomical templates and by analyzing the spatially arranged 3D reconstruction of the anatomy. The anomaly identifying module 316 may be configured to detect the plurality of anomalies when deviations, discontinuities, or abnormal contour patterns are observed across the feature maps and the spatially arranged ultrasound volume.

[0061] Figure 4 illustrates a flowchart depicting a method 400 for receiving 3D digital coordinates at the system 102 from the stereo view vision unit 106, in accordance with an embodiment of the present disclosure.

[0062] The method 400 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract datatypes.

[0063] At step 402, the method 400 may include allowing the user to login to the system 102 through a face recognition module.

[0064] The user may login, to access the system 102 with the face identity, or use credential information such as username or password. Once a face is recognized, the system 102 creates a unique ID registered with the face based on the user input. Once the face ID matches with theprevious database or history, the system 102 creates a new event / visit under the ID and assigns the unique ID to the user.

[0065] At step 404, the method 400 may include registering the subject through a voice command associated with the system or manual registration.

[0066] At step 406, the method 400 may include allowing the subject to position under a field of view of the stereo view vision unit 106.

[0067] At step 408, the method 400 may include receiving the first abdomen surface image of the subject from the stereo view vision unit 106. For example, the stereo view vision unit 106 digitally reconstructs a scene using combination of an image sensor, the LIDAR, and the IR sensor.

[0068] The stereo view vision unit 106 may continuously monitor the movement of the subj ect using visual clues, and if considerable movement is detected, the system 100 may initiate the digital surface reconstruction step, followed by an update of matrix ‘M’ throughout the workflow. If patient movement is not observed, the actuation unit 104 may be enabled.

[0069] At step 410, the method 400 may include detecting the movement of the subject.

[0070] If the movement of the subject is not detected, at step 412, the method 400 may include receiving 3D digital coordinates from the stereo view vision unit 106. The digitally reconstructed surface is represented in the actuation unit 104 coordinates using an inherent coordinate transformation. If the movement of the subject is determined, at step 414, the method 400 may include adjusting the first abdomen surface image of the subject based on the detected movement of the subject. The first abdomen surface image is represented by the matrix ‘M’ which includes a dimension of 4X4.

[0071] At step 416, the method 400 may include identifying whether the subject has fully moved out of the field of view of the stereo view vision unit 106.

[0072] If the subject has not moved out of the field of view of the stereo view vision unit 106, then the method 400 may continue at step 412.

[0073] If the subject has moved out of the field of view of the stereo view vision unit 106, at step 418, the method 400 may include receiving a second abdomen surface image from the stereo view vision unit 106.

[0074] Figure 5 illustrates a flowchart depicting a method 500 of abdomen surface image performing a global scout scan by the stereo view vision unit 106, in accordance with an embodiment of the present disclosure.

[0075] The method 500 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract datatypes.

[0076] At step 502, the method 500 may include receiving the 3D digital coordinates from the stereo view vision unit 106.

[0077] At step 504, the method 500 may include determining 3D positions and orientations on the first abdomen surface image. The 3D positions and orientations may be overlaid on the first abdomen surface image .

[0078] At step 506, the method 500 may include determining the spatial pose of the ultrasound transducer associated with the actuation unit 104.

[0079] At step 508, the method 500 may include generating a spatial arrangement of the ultrasound image frames by stacking the ultrasound image frames together.

[0080] Similarly, At step 510, the method 500 may include determining anatomical landmarks from the ultrasound image frames.

[0081] At step 512, the method 500 may include initializing the virtual anatomical model.

[0082] At step 514, the method 500 may include determining the fetus-specific hotspot regions.

[0083] At step 516, the method 500 may include generating the anatomy-specific information of the abdomen surface.

[0084] Figure 6 illustrates a flowchart depicting a method 600 of performing a global scout scan by the stereo view vision unit 106, in accordance with an embodiment of the present disclosure.

[0085] The method 600 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract datatypes.

[0086] At step 602, the method 600 may include determining the spatial pose of the ultrasound transducer 108 associated with the actuation unit 104 relative to at least the portion of the abdomen surface to obtain the ultrasound image frames based on the received first abdomen surface image or the second abdomen surface image.

[0087] At step 604, the method 600 may include generating the anatomy specific trajectory for the anatomy of the fetus based on the determined spatial pose of the ultrasound transducer associated with the actuation unit 104.

[0088] At step 606, the method 600 may include determining the one or more traversal parameters to receive the ultrasound image frames of the anatomy based on the generated anatomy specific trajectory.

[0089] At step 608, the method 600 may include modifying the one or more traversal parameters based on one or more respiratory-related motion signals and the determined one or more traversal parameters.

[0090] At step 610, the method 600 may include manoeuvring the actuation unit 104 along the anatomy specific trajectory on the anatomy of the subject.

[0091] At step 612, the method 600 may include loading the ultrasound image frames and the first abdomen surface image or the second abdomen surface image into the system 102.

[0092] Under connector A, at step 614, the method 600 may include generating the spatial arrangement of the ultrasound image frames by stacking the ultrasound image frames together.

[0093] At step 616, the method 600 may include generating the feature map for each of the ultrasound image frames using the plurality of weights and the plurality of parameters.

[0094] At step 618, the method 600 may include optimizing the ultrasound transducer 108 for force and fetus movement.

[0095] At step 620, the method 600 may include optimizing the virtual anatomical model for geometric arrangement.

[0096] At step 622, the method 600 may include determining whether an ultrasound image matches a template feature map. Further, at step 624, the method 600 may include determining the ultrasound image is found in finer spatial arrangement of that anatomy? Furthermore, at step 626, the method 600 may include determining geometric position of the ultrasound image matches the virtual anatomical model?

[0097] If the ultrasound image does not march the template feature map, at step 628, the method 600 may include predicting a next real-time trajectory for the actuation unit 104. Thereafter, at step 630, the method 600 may include performing global scout scan by the actuation unit 104. Thereafter, the method 600 may be continued at connector B.

[0098] Similarly, if the ultrasound image does not march the template feature map, the method 600 may be continued at connector E. At step 632, the method 600 may include terminating the process of the actuation unit 104 due to fetal presentation and lie.

[0099] Further, if the ultrasound image does not found in the finer spatial arrangement of that anatomy, the method 600 may be continued at connector F.

[0100] Furthermore, if the geometric position of the ultrasound image does not match the virtual anatomical model, the method 600 may be continued at connector C and connector G.

[0101] If the ultrasound image matches the template feature map, the method 600 may be continued at connector D. At step 634, the method 600 may include declaring current ultrasound image as the standard plane for that particular anatomy. Similarly, if the ultrasound image is found in the finer spatial arrangement of that anatomy, the method 600 may continue at step 634. Further, if the geometric position of the ultrasound image matches the virtual anatomical model, the method 600 may be continued at step 634.

[0102] At step 636, the method 600 may include loading the standard plane along with spatial arrangement information into the virtual anatomical model.

[0103] Figure 7 illustrates a schematic diagram depicting a feature-extraction pipeline 700, in accordance with an embodiment of the present disclosure. The system 102 may use the feature-extraction pipeline 700 to derive the landmarks and the visual cues from each ultrasound image frame. The feature -extraction pipeline 700 may correspond to the first global scout scan model. The feature-extraction pipeline 700 may include an ultrasound image 702, convolutional layers 704, pooling layers 706, full connected layers 708, a feature vector 710, and extracted features 712.

[0104] The feature-extraction pipeline 700 may begin with an ultrasound image 702 captured during the global scout scan. The ultrasound image 702 may be a two dimensional (2D) greyscale frame that includes fetal anatomical structures. The ultrasound image 702 may be obtained while the actuation unit 104 may trace predefined landmarks across the maternal abdomen.

[0105] The system 102 may pass the ultrasound image 702 into multiple convolutional layers 704, which perform localized filtering operations to highlight important visual anatomy patterns. The multiple convolutional layers 704 may extract structural components such as tissue boundaries, organ contours, and characteristic echogenic patterns.

[0106] Further, the pooling layers 706 may progressively reduce spatial dimensions. Pooling helps the system 102 to retain only the most essential anatomical information, remove noise, and improve robustness against fetal motion and image variability.

[0107] The output of the pooling layers 706 is then passed into the fully connected neural layers 708. The fully connected neural layers 708 may combine all extracted spatial features to form a higher-level understanding of the fetal anatomy in the ultrasound image. Further, a final numerical output of the fully connected layers 708 may be the feature vector 710. The feature vector 710 may be a compact representation encoding anatomical contours, texture-based cues, geometric relationships, and fetal structure indicators. Furthermore, the extracted features 712 may be delivered to the system 102. The extracted features may form part of the multi-model information used during the global scout scan to determine fetal presentation and lie, initialize the virtual anatomical model, guide spatial arrangement of frames, and support prediction of hotspot regions of fetal anatomy.

[0108] For every frame of the ultrasound image 702, the computational model along with the plurality of weights and the plurality of parameters may be used to map the feature map of the standard plane. The plurality of weights and the plurality of parameters may be derived using retrospective clinical images or videos collected from a diverse dataset. The feature map may indicate multiple contours of structures relevant to the standard plane for any particular anatomy. The multiple contours may be derived from clinical experts.

[0109] Figure 8 illustrates a flowchart depicting a method 800 for generating the anatomy-specific information, in accordance with an embodiment of the present disclosure.

[0110] The method 800 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract datatypes.

[0111] At step 802, the method 800 may include receiving the first abdomen surface image or the second abdomen surface image of the subject from the stereo view vision unit 106.

[0112] At step 804, the method 800 may include determining the spatial pose of the ultrasound transducer 108 associated with the actuation unit 104 relative to the portion of the abdomen surface to obtain the ultrasound image frames based on the received first abdomen surface image or the second abdomen surface image.

[0113] At step 806, the method 800 may include determining the one or more fetusspecific hotspot regions using the virtual anatomical model, the plurality of landmarks associated with each of the ultrasound image frames, and the spatial arrangement of the ultrasound image frames based on the obtained ultrasound image frames.

[0114] At step 808, the method 800 may include generating the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions.

[0115] For determining the spatial pose of the ultrasound transducer 108 associated with the actuation unit 104, the method 800 may include detecting movement of the subject based on the received first abdomen surface image. Further, the method 800 may include adjusting the first abdomen surface image based on the detected movement of the subject. Furthermore, the method 800 may include determining the spatial pose of the ultrasound transducer associated with the actuation unit based on the adjusted first abdomen surface image.

[0116] The method 800 may include identifying the subject moving out of a field of view of the stereo view vision unit 106 based on the adjusted first abdomen surface image. Further, the method 800 may include receiving the second abdomen surface image from the stereo view vision unit (106) based on the identified subject moving out of the field of view of the stereo view vision unit (106).

[0117] The method 800 may include determining, for each of the ultrasound image frames, the plurality of anatomical landmarks and a plurality of visual cues using a featureextraction model based on the received plurality of ultrasound image frames.

[0118] Further, the method 800 may include generating the spatial arrangement of the ultrasound image frames by stacking the ultrasound image frames together based on the received ultrasound image frames. The method 800 may include updating the virtual anatomical model using the spatially arrangement of the ultrasound image frames and the plurality of features to indicate fetal spatial orientation of the subject. Furthermore, the method 800 may include determining the one or more fetus-specific hotspot regions using the virtual anatomical model based on the indicated fetal spatial orientation of the subject.

[0119] The method 800 may include generating the anatomy specific trajectory for the anatomy of the fetus based on the determined spatial pose of the ultrasound transducer associated with the actuation unit 104. Further, the method 800 may include determining the one or more traversal parameters of the actuation unit to receive the ultrasound image frames of the anatomy based on the generated anatomy specific trajectory. Furthermore, the method 800 may include modifying, using an adaptive control model, the one or more traversal parameters based on one or more respiratory-related motion signals and the determined one or more traversal parameters. The adaptive control model may include hybrid position and force controller model.

[0120] The method 800 may include generating the feature map for each of the ultrasound image frames using the plurality of weights and the plurality of parameters based on the received ultrasound image frames. The feature map may indicate a plurality of contours relevant to the standard plane for an anatomy of the fetus. The method 800 may include determining that the generated feature map for each of the plurality of ultrasound image frames satisfies a predetermined template feature map. The predetermined template feature map indicates the plurality of contour regions in an ultrasound image. The method 800 may include identifying each of the plurality of ultrasound image frames as the standard plane associated with the anatomy in the virtual anatomical model based on the determined feature map. The method 800 may include identifying the plurality of anomalies associated with an anatomy of a fetus based on the generated feature map for each of the plurality of ultrasound image frames and a spatial arrangement of the plurality of ultrasound image frames.

[0121] The embodiments of the present invention would help bridge the gap in sonologist shortages and reduce subjective diagnostic errors, ultimately improving fetal assessment and prenatal care outcomes. By employing the method of scanning as per the present invention, the need for highly specialized personnel is reduced and the operational costs are lowered. Fetal sonography may be made more affordable and accessible to a broader population.

[0122] The embodiments of the present invention provide various advantages such as any time scan based on system availability, reduced scan time, consistent diagnosis without sonologist skill dependence, continuous learning through patient data, non-requirement of a sonologist as the scan can be performed by any technician or nurse, audit by sonologist through cloud storage and larger accessibility of scans. The present invention performs continuousultrasound scans by adjusting probe position, force, and deriving volumetric data, facilitated by the system.

[0123] The present invention leverages a learning-based process to understand ultrasound imaging, fetal anatomy and fetal positioning, the system consistently acquires the correct planes. The present invention computationally derives volumetric data to provide clearer, more detailed views of fetal anatomy, to enhance the diagnostic information. The present invention provides real-time feedback, confirming whether the correct anatomical planes have been captured, improving the quality and completeness of the scan. The present invention extracts anatomy-specific information and optimizes the anatomy-specific information combinedly from different models to declare standard planes or anomalies. The present invention for visualization and repeating the anatomy-specific scan until all the anatomies of the fetus are examined. The present invention expedites the output for expert auditing and an automatic report is generated. The present invention generalizes to full fetal anatomy with autonomous robotic scanning and multi -model fetus control.

[0124] The present invention uniquely combines automated scanning hardware with multi-model decision control to autonomously acquire, verify, and map standard planes and anomalies onto a fetus avatar. The present invention fuses multiple models (feature maps, spatial arrangement, fetus avatar, control) into a unified decision engine The present invention enables full-fetus autonomous scanning and standardized, anatomy-wise assessment. The present invention integrates stereo-vision, self-actuation, multi-model fusion, and Fetus-iMODs to plan trajectories autonomously, acquire standard planes, and detect anomalies across all anatomies without operator-driven probe navigation. The present invention examines all fetal anatomies and generate reports systematically.

[0125] The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

[0126] The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise.

[0127] The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise.

[0128] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

[0129] When a single device or article is described herein, it will be readily apparent that more than one device / article (whether or not they cooperate) may be used in place of a single device / article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device / article may be used in place of the more than one device or article, or a different number of devices / articles may be used instead of the shown number of devices or programs. The functionality and / or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality / features. Thus, other embodiments of the invention need not include the device itself.

[0130] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art.

Claims

We claim:

1. A method (800) for generating anatomy-specific information, the method (800) comprising:receiving a first abdomen surface image of a subject from a stereo view vision unit (106);determining a spatial pose of an ultrasound transducer (108) associated with an actuation unit (104) relative to at least a portion of an abdomen surface to obtain a plurality of ultrasound image frames based on the received first abdomen surface image;determining one or more fetus-specific hotspot regions using a virtual anatomical model, a plurality of landmarks associated with each of the plurality ultrasound image frames, and a spatial arrangement of the plurality of ultrasound image frames based on the obtained plurality of ultrasound image frames; and generating the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions.

2. The method (800) as claimed in claim 1, wherein determining the spatial pose of the ultrasound transducer (108) associated with the actuation unit (104) comprises:detecting movement of the subject based on the received first abdomen surface image;adjusting the first abdomen surface image based on the detected movement of the subject; anddetermining the spatial pose of the ultrasound transducer (108) associated with the actuation unit (104) based on the first abdomen surface image.

3. The method (800) as claimed in claim 2, further comprising:identifying the subject moving out of a field of view of the stereo view vision unit (106) based on the adjusted first abdomen surface image; andreceiving a second abdomen surface image from the stereo view vision unit (106) based on the identified subject moving out of the field of view of the stereo view vision unit (106).

4. The method (800) as claimed in claim 1, further comprising:determining, for each of the plurality of ultrasound image frames, a plurality of anatomical landmarks and a plurality of visual cues using a feature-extraction model based on the received plurality of ultrasound image frames.

5. The method (800) as claimed in claim 1 , wherein determining the one or more fetus-specific hotspot regions comprises:generating the spatial arrangement of the plurality of ultrasound image frames by stacking the plurality of ultrasound image frames together based on the received plurality of ultrasound image frames;updating the virtual anatomical model using the spatially arrangement of the plurality of ultrasound image frames and a plurality of features to indicate fetal spatial orientation of the subject; anddetermining the one or more fetus-specific hotspot regions using the virtual anatomical model based on the indicated fetal spatial orientation of the subject, wherein the one or more fetus-specific hotspot regions comprise one or more fetal head regions, one or more fetal face regions, one or more fetal thorax regions, one or more fetal abdomen regions, one or more fetal lower limb regions, one or more fetal upper limb regions, one or more maternal regions, one or more fetal hand regions, and one or more fetal leg regions.

6. The method (800) as claimed in claim 1, further comprising:generating an anatomy specific trajectory for an anatomy of a fetus based on the determined spatial pose of the ultrasound transducer (108) associated with the actuation unit (104);determining one or more traversal parameters of the actuation unit (104) to receive the plurality of ultrasound image frames of the anatomy based on the generated anatomy specific trajectory; andmodifying, using an adaptive control model, the one or more traversal parameters based on one or more respiratory-related motion signals and the determined one or more traversal parameters.

7. The method (800) as claimed in claim 1, further comprising:generating a feature map for each of the plurality of ultrasound image frames using a plurality of weights and a plurality of parameters based on the received pluralityof ultrasound image frames, wherein the feature map indicates a plurality of contours relevant to a standard plane for an anatomy of a fetus;determining that the generated feature map for each of the plurality of ultrasound image frames satisfies a predetermined template feature map, wherein the predetermined template feature map indicates a plurality of contour regions in an ultrasound image; andidentifying each of the plurality of ultrasound image frames as the standard plane associated with the anatomy in the virtual anatomical model based on the determined feature map.

8. The method (800) as claimed in claim 7, further comprising:identifying a plurality of anomalies associated with an anatomy of a fetus based on the generated feature map for each of the plurality of ultrasound image frames and a spatial arrangement of the plurality of ultrasound image frames.

9. A system (102) for generating anatomy-specific information, the system (102) comprising:a memory (206);at least one processor (204) operatively coupled to the memory (206), wherein the at least one processor (204) is configured to:receive, a first abdomen surface image of a subject from a stereo view vision unit 106;determine a spatial pose of an ultrasound transducer (108) associated with an actuation unit (104) relative to at least a portion of an abdomen surface to obtain a plurality of ultrasound image frames based on the received first abdomen surface image;determine one or more fetus-specific hotspot regions using a virtual anatomical model, a plurality of landmarks associated with each of the plurality ultrasound image frames, and a spatial arrangement of the plurality of ultrasound image frames based on the obtained plurality of ultrasound image frames; andgenerate the anatomy-specific information of the abdomen surface based on the determined one or more fetus-specific hotspot regions.

10. The system (102) as claimed in claim 9, wherein to determine the spatial pose of the ultrasound transducer (108) associated with the actuation unit (104), the at least one processor (204) is configured to:detect movement of the subject based on the received first abdomen surface image;adjust the first abdomen surface image based on the detected movement of the subject; anddetermine the spatial pose of the ultrasound transducer (108) associated with the actuation unit (104) based on the adjusted first abdomen surface image.

11. The system (102) as claimed in claim 10, wherein the at least one processor (204) is configured to:identify the subject moving out of a field of view of the stereo view vision unit (106) based on the adjusted first abdomen surface image; andreceive a second abdomen surface image from the stereo view vision unit (106) based on the identified subject moving out of the field of view of the stereo view vision unit (106).

12. The system (102) as claimed in claim 9, wherein the at least one processor (204) is configured to:determine, for each of the plurality of ultrasound image frames, a plurality of anatomical landmarks and a plurality of visual cues using a feature-extraction model based on the received plurality of ultrasound image frames.

13. The system ( 102) as claimed in claim 9, wherein to determine the one or more fetus-specific hotspot regions, the at least one processor (204) is configured to:generate the spatial arrangement of the plurality of ultrasound image frames by stacking the plurality of ultrasound image frames together based on the received plurality of ultrasound image frames;update the virtual anatomical model using the spatially arrangement of the plurality of ultrasound image frames and a plurality of features to indicate fetal spatial orientation of the subject; anddetermine the one or more fetus -specific hotspot regions using the virtual anatomical model based on the indicated fetal spatial orientation of the subject, whereinthe one or more fetus-specific hotspot regions comprise one or more fetal head regions, one or more fetal face regions, one or more fetal thorax regions, one or more fetal abdomen regions, one or more fetal lower limb regions, one or more fetal upper limb regions, one or more maternal regions, one or more fetal hand regions, and one or more fetal leg regions.

14. The system (102) as claimed in claim 9, wherein the at least one processor (204) is configured to:generate an anatomy specific trajectory for an anatomy of a fetus based on the determined spatial pose of the ultrasound transducer (108) associated with the actuation unit (104);determine one or more traversal parameters to receive the plurality of ultrasound image frames of the anatomy based on the generated anatomy specific trajectory; and modify, using an adaptive control model, the one or more traversal parameters based on one or more respiratory-related motion signals and the determined one or more traversal parameters.

15. The system (102) as claimed in claim 9, wherein the at least one processor (204) is configured to:generate a feature map for each of the plurality of ultrasound image frames using a plurality of weights and a plurality of parameters based on the received plurality of ultrasound image frames, wherein the feature map indicates a plurality of contours relevant to a standard plane for an anatomy of a fetus;determine that the generated feature map for each of the plurality of ultrasound image frames satisfies a predetermined template feature map, wherein the predetermined template feature map indicates a plurality of contour regions in an ultrasound image; andidentify each of the plurality of ultrasound image frames as the standard plane associated with the anatomy in the virtual anatomical model based on the determined feature map.

16. The system (102) as claimed in claim 15, wherein the at least one processor (204) is configured to:5 identifying a plurality of anomalies associated with an anatomy of a fetus based on the generated feature map for each of the plurality of ultrasound image frames and a spatial arrangement of the plurality of ultrasound image frames.

Images