Method of generating procedure plan information for procedure using focused ultrasound

Abstract

Disclosed is a method of generating procedure plan information for a procedure utilizing focused ultrasound (FU), the method being performed by a computing device according to one embodiment of the present disclosure. The method may comprise the steps of: acquiring an image of a body part to be treated; identifying one or more layers in the body part to be treated; generating procedure plan information for a procedure using focused ultrasound for the one or more layers on the basis of the type of the identified layers; displaying the generated procedure plan information on the acquired image; and generating, on the basis of the generated procedure plan information, an actuator control signal for automatically moving a device generating the focused ultrasound to a target treatment site.

Description

Method for generating procedure planning information for procedures utilizing focused ultrasound

[0001] The present invention relates to a method for generating procedure planning information for a procedure utilizing focused ultrasound, and more specifically, to a technology for generating procedure planning information by analyzing ultrasound scanning images using artificial intelligence and performing a procedure utilizing focused ultrasound.

[0002] Focused Ultrasound (FU) is a technology that utilizes High-Intensity Focused Ultrasound (HIFU) to non-invasively treat human tissues or apply them to cosmetic procedures, and is utilized in various medical and cosmetic fields such as improving skin elasticity, fat breakdown, and tumor treatment. However, conventional High-Intensity Focused Ultrasound (HIFU) procedures often rely on the operator's experience and skill, and there are difficulties in accurately identifying target tissues (e.g., fat layer, fascia layer, etc.) and optimizing energy delivery.

[0003] The practice of establishing a treatment plan using ultrasound images followed by HIFU therapy is currently used only in the medical field for treating diseases, such as oncology, and has not been introduced in the cosmetic field. Furthermore, in conventional procedures utilizing ultrasound images, it is common for medical staff to manually analyze the images to identify the target tissue, establish a treatment plan, and then adjust the focal position and energy of the High-Intensity Focused Ultrasound (HIFU) device. However, this method can lead to problems such as a lack of objective standards, high dependence on the operator, time consumption, and reduced accuracy. Additionally, there are limitations in responding to real-time changes in ultrasound images and in consistently reproducing the same treatment results.

[0004] Korean Patent Publication No. 10-2014-0113172 (September 24, 2014) discloses a method and apparatus for establishing an ultrasonic irradiation plan and an ultrasonic irradiation method.

[0005]

[0006] The present disclosure aims to provide a method for automatically segmenting soft tissue through AI-based ultrasound image analysis and automatically establishing a procedure plan for high-intensity focused ultrasound based on this.

[0007] In addition, the present disclosure aims to provide an integrated automated HIFU treatment system that automatically moves the focal point of focused ultrasound (FU) to a target point through motor control and adjusts the energy in real time according to tissue characteristics.

[0008] Meanwhile, the technical problem that the present disclosure aims to solve is not limited to the technical problem mentioned above, and various technical problems may be included within the scope obvious to a person skilled in the art from the contents described below.

[0009]

[0010] According to one embodiment of the present disclosure for realizing the aforementioned objectives, a method for generating procedure planning information for a procedure utilizing focused ultrasound (FU) performed by a computing device is disclosed. The method may include the steps of: acquiring an image of a body part to be treated; identifying one or more layers in the body part to be treated; generating procedure planning information for a procedure utilizing focused ultrasound for the one or more layers based on the type of the identified layers; displaying the generated procedure planning information on the acquired image; and generating an actuator control signal to automatically move a device generating the focused ultrasound to a target procedure site based on the generated procedure planning information.

[0011] In one embodiment, the step of identifying one or more layers includes the step of identifying a plurality of different layers in the body part to be treated, and the step of generating treatment plan information includes the step of generating treatment plan information for a treatment utilizing focused ultrasound on the plurality of different layers based on the types of the identified plurality of different layers, and the generated treatment plan information may be displayed in different ways on the identified different layers.

[0012] In one embodiment, the actuator control signal may include control signals in the direction of two or more mutually orthogonal axes.

[0013] In one embodiment, based on the generated procedure plan information, the method may further include the step of generating an energy control signal to automatically adjust the energy of the focused ultrasound in conjunction with movement by the actuator.

[0014] In one embodiment, the body part to be treated includes skin, and the types of the plurality of different layers may include at least two of the dermis layer, fat layer, or fascia layer of the skin.

[0015] In one embodiment, the step of identifying a plurality of different layers in the body part to be treated may include at least two of the steps of: setting a first boundary line for the dermis layer; setting a second boundary line for the fat layer; or setting a third boundary line for the fascia layer.

[0016] In one embodiment, the step of generating treatment planning information utilizing focused ultrasound for the plurality of different layers based on the identified types of the plurality of different layers may include at least two of the following steps: setting a treatment exclusion location for the dermis layer; setting a first type of treatment location for the fat layer; or setting a second type of treatment location for the fascia layer.

[0017] In one embodiment, the step of setting a first type of treatment location for the fat layer includes the step of setting a treatment location utilizing a first energy focused ultrasound for the fat layer, and the step of setting a second type of treatment location for the fascia layer may include the step of setting a treatment location utilizing a second energy focused ultrasound different from the first energy for the fascia layer.

[0018] In one embodiment, the step of setting a first type of treatment location for the fat layer includes the step of setting a treatment interval utilizing a first energy focused ultrasound in consideration of the characteristics of the fat layer, and the step of setting a second type of treatment location for the fascia layer may include the step of setting a treatment interval utilizing a second energy focused ultrasound different from the first energy in consideration of the characteristics of the fascia layer.

[0019] In one embodiment, the step of displaying the generated procedure plan information on the acquired image may include: a step of displaying a first type of procedure location for the fat layer; and a step of displaying a second type of procedure location for the fascia layer by utilizing a display method different from the method of displaying the first type of procedure location.

[0020] In one embodiment, the step of displaying the generated procedure plan information on the acquired image may include: a step of displaying first type path information connecting a plurality of first type locations on the fat layer; and a step of displaying second type path information connecting a plurality of second type locations on the fascia layer.

[0021] In one embodiment, the step of acquiring an image of the body part to be treated includes the step of acquiring an image of the body part to be treated using an ultrasound scanner, and the ultrasound scanner may utilize a separate ultrasound different from the focused ultrasound.

[0022] A computer program stored on a computer-readable storage medium is disclosed in accordance with one embodiment of the present disclosure for realizing the aforementioned objectives. When the computer program is executed on one or more processors, the one or more processors are configured to perform the following operations to generate focused ultrasound (FU) procedure planning information, wherein the operations may include: acquiring an image of a body part to be treated; identifying one or more layers in the body part to be treated; generating procedure planning information for a procedure utilizing the focused ultrasound on the one or more layers based on the type of the identified layers; displaying the generated procedure planning information on the acquired image; and generating an actuator control signal to automatically move a device generating the focused ultrasound to a target procedure site based on the generated procedure planning information.

[0023] In one embodiment, the operation of identifying one or more layers includes the operation of identifying a plurality of different layers in the body part to be treated, and the operation of generating treatment plan information includes the operation of generating treatment plan information for a treatment utilizing focused ultrasound on the plurality of different layers based on the types of the identified plurality of different layers, and the generated treatment plan information may be displayed in different ways on the identified different layers.

[0024] In one embodiment, the body part to be treated includes skin, and the types of the plurality of different layers may include at least two of the dermis layer, fat layer, or fascia layer of the skin.

[0025] In one embodiment, the operation of generating treatment plan information utilizing focused ultrasound for the plurality of different layers based on the identified types of the plurality of different layers may include at least two of the following: an operation of setting a treatment exclusion location for the dermis layer; an operation of setting a first type of treatment location for the fat layer; or an operation of setting a second type of treatment location for the fascia layer.

[0026] In one embodiment, the operation of displaying the generated procedure plan information on the acquired image may include: an operation of displaying a first type of procedure location for the fat layer; and an operation of displaying a second type of procedure location for the fascia layer by utilizing a display method different from the method of displaying the first type of procedure location.

[0027] In one embodiment, the operation of displaying the generated procedure plan information on the acquired image may include: the operation of displaying first type path information connecting a plurality of first type locations on the fat layer; and the operation of displaying second type path information connecting a plurality of second type locations on the fascia layer.

[0028] In one embodiment, the operation of acquiring an image of the body part to be treated includes the operation of acquiring an image of the body part to be treated using an ultrasound scanner, and the ultrasound scanner may utilize a separate ultrasound different from the focused ultrasound.

[0029] A computing device according to one embodiment of the present disclosure for realizing the aforementioned objectives is disclosed. The device comprises at least one processor; and memory, wherein the at least one processor may be configured to acquire an image of a body part to be treated; identify one or more layers in the body part to be treated; generate treatment plan information for a treatment utilizing the one or more layers based on the type of the identified layers; display the generated treatment plan information on the acquired image; and generate an actuator control signal for automatically moving a device that generates the focused ultrasound to a target treatment site based on the generated treatment plan information.

[0030] In one embodiment, the at least one processor is configured to identify a plurality of different layers in the body part to be treated and, based on the types of the identified plurality of different layers, to generate treatment plan information for a treatment utilizing the focused ultrasound on the plurality of different layers, and the generated treatment plan information may be displayed in different ways on the identified different layers.

[0031] In one embodiment, the body part to be treated includes skin, and the types of the plurality of different layers may include at least two of the dermis layer, fat layer, or fascia layer of the skin.

[0032] In one embodiment, the at least one processor may include at least two of the following operations: setting a procedure exclusion location for the dermis layer; setting a first type of procedure location for the fat layer; or setting a second type of procedure location for the fascia layer.

[0033] In one embodiment, the at least one processor may be configured to indicate a first type of procedure location for the fat layer; and to indicate a second type of procedure location for the fascia layer by utilizing a display method different from the method of indicating the first type of procedure location.

[0034] In one embodiment, the at least one processor may be configured to display first type path information connecting a plurality of first type locations for the fat layer; and second type path information connecting a plurality of second type locations for the fascia layer.

[0035] In one embodiment, the at least one processor includes the step of acquiring an image of the body part to be treated using an ultrasound scanner, and the ultrasound scanner may use a separate ultrasound different from the focused ultrasound.

[0036]

[0037] The present disclosure analyzes ultrasound images using artificial intelligence (AI) to automatically segment the body parts to be treated (dermis layer, fat layer, fascia layer, etc.), thereby enabling precise identification of the treatment area and making more accurate and consistent treatment possible.

[0038] In addition, the present disclosure automatically establishes a high-intensity focused ultrasound (HIFU) procedure plan based on segmented tissue information, thereby calculating the optimal focal point location and procedure path, allowing the procedure to be performed based on objective criteria without relying on the operator's experience.

[0039] In addition, the present disclosure allows the focused ultrasound to be accurately delivered to a set target location by automatically controlling a motor mounted on a high-intensity focused ultrasound (HIFU) to move the focus point, thereby increasing the precision of the procedure and minimizing unnecessary tissue damage.

[0040] In addition, the present disclosure automatically adjusts the frequency and energy of high-intensity focused ultrasound (HIFU) according to the characteristics of each tissue layer, thereby enabling the delivery of energy optimized for each tissue, which can maximize the effectiveness of the procedure while reducing side effects.

[0041] In addition, the present disclosure allows the operator to immediately check the status of the procedure and make adjustments if necessary by visually displaying the procedure plan in real time on an ultrasound image that changes in real time, thereby enabling a more intuitive and safe procedure.

[0042] Meanwhile, the effects of the present disclosure are not limited to those mentioned above, and various effects may be included within the scope obvious to a person skilled in the art from the contents described below.

[0043]

[0044] FIG. 1 is a block diagram of a computing device for generating planning information for a procedure utilizing focused ultrasound (FU) according to one embodiment of the present disclosure.

[0045] FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure.

[0046] FIG. 3 is a flowchart illustrating a method for generating planning information for a procedure utilizing focused ultrasound (FU) according to one embodiment of the present disclosure.

[0047] FIG. 4 is a drawing of an image of a body part to be treated according to one embodiment of the present disclosure.

[0048] FIG. 5 is a schematic diagram showing the results of identifying a plurality of different layers in a body part subject to treatment according to one embodiment of the present disclosure.

[0049] FIG. 6 is a diagram schematically illustrating procedure planning information utilizing focused ultrasound in one embodiment of the present disclosure.

[0050] FIG. 7 is a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0051]

[0052] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to provide an understanding of the present disclosure. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0053] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0054] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0055] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0056] And, the term "at least one of A or B" should be interpreted to mean "a case including only A," "a case including only B," or "a combination of A and B."

[0057] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be construed as going beyond the scope of this disclosure.

[0058]

[0059] FIG. 1 is a block diagram of a computing device for generating planning information for a procedure utilizing focused ultrasound (FU) according to one embodiment of the present disclosure.

[0060] The configuration of the computing device (100) illustrated in FIG. 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing the computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

[0061] The computing device (100) may include a processor (110), memory (130), and a network unit (150).

[0062] The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in memory (130) and perform data processing for machine learning according to one embodiment of the present disclosure. According to one embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process the learning of a network function. For example, a CPU and a GPGPU can work together to process the learning of a network function and data classification using the network function. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices can be used together to process the learning of a network function and data classification using the network function. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0063] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (150).

[0064] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may operate in conjunction with web storage that performs the storage function of the memory (130) on the internet. The description of the memory described above is merely an example and the present disclosure is not limited thereto.

[0065] Alternatively, the processor (110) may include internal memory and may utilize said memory when performing operations for data processing and machine learning. Additionally, the computing device (100) or the processor (110) may be implemented as a System on a Chip (SoC) structure in which a central processing unit (CPU), a graphics processing unit (GPU), a tensor processing unit (TPU), and memory are integrated on a single chip. The computing device (100) or the processor (110) may perform operations independently by utilizing internally embedded memory or operate in combination with external memory.

[0066] A network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0067] In addition, the network unit (150) presented in this specification may use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0068] In the present disclosure, the network unit (150) can be configured regardless of the communication mode, such as wired and wireless, and can be configured as various communication networks such as a Local Area Network (LAN), a Personal Area Network (PAN), and a Wide Area Network (WAN). In addition, the network may be a known World Wide Web (WWW) and may utilize wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

[0069] The technologies described in this specification can be used not only in the networks mentioned above but also in other networks.

[0070]

[0071] FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure.

[0072] Throughout this specification, artificial intelligence model, artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably.

[0073] A neural network can be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node. The nodes (or neurons) constituting neural networks may be interconnected by one or more links.

[0074] In a neural network, one or more nodes connected via links can form relative input and output node relationships. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As described above, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0075] In a relationship between an input node and an output node connected through a single link, the value of the output node's data can be determined based on the data input to the input node. Here, the link interconnecting the input node and the output node may have a weight. The weight can be variable and can be varied by the user or an algorithm to enable the neural network to perform the desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node's value can be determined based on the values ​​input to the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0076] As described above, a neural network consists of one or more nodes interconnected through one or more links, forming input-output node relationships within the network. The characteristics of a neural network can be determined by the number of nodes and links within the network, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two neural networks exist with the same number of nodes and links but different weight values ​​for the links, the two neural networks may be recognized as different from each other.

[0077] A neural network can be composed of a set of one or more nodes. A subset of nodes constituting a neural network can form a layer. Some of the nodes constituting a neural network can form a layer based on their distances from an initial input node. For example, a set of nodes with a distance of n from an initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links that must be traversed to reach that node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a way different from that described above. For example, a layer of nodes may be defined by its distance from a final output node.

[0078] In one embodiment of the present disclosure, a set of neurons or nodes may be defined by the expression a layer.

[0079] Initial input nodes may refer to one or more nodes within a neural network to which data is directly input without passing through links in their relationships with other nodes. Alternatively, in terms of link-based relationships between nodes within the neural network, they may refer to nodes that do not have other input nodes connected by links. Similarly, final output nodes may refer to one or more nodes within a neural network that do not have output nodes in their relationships with other nodes. Furthermore, hidden nodes may refer to nodes constituting the neural network that are neither initial input nodes nor final output nodes.

[0080] A neural network according to one embodiment of the present disclosure may have the number of nodes in the input layer equal to the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. Additionally, a neural network according to another embodiment of the present disclosure may have the number of nodes in the input layer less than the number of nodes in the output layer, and may be a neural network in which the number of nodes increases as it progresses from the input layer to the hidden layer. Additionally, a neural network according to yet another embodiment of the present disclosure may have the number of nodes in the input layer greater than the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases as it progresses from the input layer to the hidden layer. A neural network according to yet another embodiment of the present disclosure may be a neural network in which the above-described neural networks are combined.

[0081] An artificial intelligence-based model according to one embodiment of the present disclosure may include a deep neural network (DNN). A deep neural network may refer to a neural network that includes a plurality of hidden layers in addition to an input layer and an output layer. By using a deep neural network, latent structures of data can be identified. That is, latent structures of photos, text, video, voice, protein sequence structures, gene sequence structures, peptide sequence structures, music (e.g., what objects are in the photo, what is the content and emotion of the text, what is the content and emotion of the voice, etc.), and / or binding affinity between peptides and MHCs can be identified. Deep neural networks may include convolutional neural networks (CNN), recurrent neural networks (RNN), autoencoders, restricted Boltzmann machines (RBM), deep belief networks (DBN), Q networks, U networks, Siamese networks, Generative Adversarial Networks (GAN), Transformers, etc. The description of deep neural networks described above is merely illustrative and the present disclosure is not limited thereto.

[0082] The artificial intelligence-based model of the present disclosure may be represented by a network structure of any structure described above, including an input layer, a hidden layer, and an output layer.

[0083] A neural network that can be used in an artificial intelligence-based model of the present disclosure may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, transfer learning, active learning, or reinforcement learning. Training of a neural network may be a process of applying knowledge to the neural network to perform a specific operation.

[0084] Neural networks can be trained to minimize the error in their output. The training process involves repeatedly inputting training data into the network, calculating the error between the network's output and the target for the training data, and updating the weights of each node by backpropagating the error from the output layer to the input layer in a direction that reduces the error. In supervised learning, training data is used where the correct answer is labeled for each data point (i.e., labeled training data), whereas in unsupervised learning, the correct answer may not be labeled for each training data point. For instance, in the case of supervised learning for data classification, the training data may consist of data where each training point is labeled with a category. Labeled training data is input into the neural network, and the error can be calculated by comparing the network's output (category) with the labels of the training data. As another example, in the case of unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network's output. The calculated error is backpropagated in the neural network (i.e., from the output layer to the input layer), and through backpropagation, the connection weights of each node in each layer of the neural network can be updated. The amount of change in the connection weights of each node being updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of training to quickly achieve a certain level of performance and increase efficiency, while a low learning rate can be used in the later stages to improve accuracy.

[0085] In the training of neural networks, the training data is generally a subset of the real-world data (i.e., the data intended to be processed using the trained neural network). Consequently, a training cycle may exist where errors decrease on the training data but increase on the real-world data. Overfitting is a phenomenon where the network learns excessively on the training data, leading to increased errors on the real-world data. For example, a neural network trained on yellow cats might fail to recognize cats when seeing anything other than yellow, which can be considered a type of overfitting. Overfitting can act as a cause for increased errors in machine learning algorithms. Various optimization methods can be used to prevent this overfitting. To prevent overfitting, methods such as increasing the training data, regularization, dropout (which disables some nodes in the network during training), and the use of batch normalization layers can be applied.

[0086]

[0087] According to one embodiment of the present disclosure, the focused ultrasound (FU) mentioned below may be high-intensity focused ultrasound (HIFU). For reference, focused ultrasound (FU) is an ultrasound technology that operates by concentrating energy on a specific tissue. It induces a therapeutic or procedural effect by gathering multiple ultrasound beams at a single focus and delivering high energy to the corresponding area. In particular, high-intensity focused ultrasound (HIFU) is a technology that uses thermal energy to non-invasively treat a target area and can be utilized for skin aesthetics, tumor treatment, fat removal, etc. For example, focused ultrasound can be used to increase skin elasticity by promoting collagen regeneration (e.g., Ulthera, Shurink, Doublo, etc.). Additionally, focused ultrasound can be used for non-invasive lipolysis treatment that targets subcutaneous fat and destroys fat cells.

[0088]

[0089] FIG. 3 is a flowchart illustrating a method for generating planning information for a procedure utilizing focused ultrasound (FU) according to one embodiment of the present disclosure. For reference, the method for generating planning information for a procedure utilizing focused ultrasound (FU) can be performed by a computing device (100).

[0090] Referring to FIG. 3 according to one embodiment of the present disclosure, a method for generating procedure planning information for a procedure utilizing focused ultrasound (FU) may include the steps of: acquiring an image of a body part to be treated (S110); identifying one or more layers in the body part to be treated (S120); generating procedure planning information utilizing the focused ultrasound for the one or more layers based on the type of the identified layers (S130); displaying the generated procedure planning information on the acquired image (S140); and generating an actuator control signal to automatically move a device generating the focused ultrasound to a target procedure site based on the generated procedure planning information (S150).

[0091]

[0092] FIG. 4 is a drawing of an image of a body part to be treated according to one embodiment of the present disclosure. For reference, the image of the body part to be treated shown in FIG. 4 may be an ultrasound image obtained using an ultrasound scanner.

[0093] According to one embodiment of the present disclosure, a computing device (100) can acquire an image of a body part to be treated (S110). For example, the computing device (100) can acquire an image of the body part to be treated by utilizing an ultrasound scanner. For example, the ultrasound scanner can utilize a separate ultrasound different from focused ultrasound. For example, the ultrasound scanner can transmit an ultrasound signal of a specific frequency to the body part to be treated. The ultrasound scanner can acquire an image of the body part to be treated by generating ultrasound using a range of frequencies from low to high frequencies. The ultrasound scanner can generate an image by irradiating ultrasound onto the body part to be treated using a transducer and receiving the reflected signal. A user can place the transducer of the ultrasound scanner in close contact with the body part to be treated (e.g., face, abdomen, thigh, etc.), and the ultrasound scanner can generate an image by irradiating ultrasound onto the body part to be treated and receiving the reflected signal. For example, the probe may be configured as a line array or a curved array, and an appropriate array may be selected depending on the shape of the treatment site. The ultrasound scanner can acquire continuous 2D images (ultrasound B-mode images) by utilizing ultrasound irradiated while moving at a constant speed. Additionally, the ultrasound scanner can acquire the images by utilizing ultrasound signals of different frequencies and intensities than focused ultrasound (FU). For example, referring to FIG. 4, a computing device (100) can receive ultrasound images acquired from the ultrasound scanner in real time. Additionally, the computing device (100) can process the received ultrasound data in real time and convert it into an image format. Additionally, the computing device (100) can display the converted ultrasound images on a display device in real time.Additionally, the computing device (100) can transmit ultrasound images in real time in a remote medical environment via a network. Additionally, the computing device (100) can support real-time viewing of the transmitted ultrasound images in a remote monitoring system. Furthermore, the computing device (100) may apply image compression and transmission techniques that minimize delay while maintaining the quality of the ultrasound images.

[0094] Alternatively, the ultrasound device may include a main body module comprising an ultrasound scanner for acquiring ultrasound images. Additionally, the ultrasound device may include a mounting module mounted on the main body module and configured to generate high-intensity focused ultrasound in a target area. For example, the main body module and the mounting module may be combined such that at least a portion of the ultrasound generated by the ultrasound scanner of the main body module passes through the interior of the mounting module and is irradiated to the target area. For instance, the main body module may be a handpiece module. Additionally, the mounting module may be a cartridge module. For instance, the handpiece module and the cartridge module may be combined such that at least a portion of the beamforming geometry of the ultrasound generated by the ultrasound scanner of the handpiece passes through the interior of the cartridge module. Alternatively, the ultrasound scanner and focused ultrasound included in the ultrasound device may be applied separately, or, in some cases, integrated or coupled to be utilized as a single unit. Meanwhile, a method in which the ultrasound scanner is embedded within the main body module and the focused ultrasound is designed to be replaceable in the form of a cartridge may be advantageous in terms of maintenance and practicality.

[0095]

[0096] FIG. 5 is a schematic diagram showing the results of identifying a plurality of different layers in a body part subject to treatment according to one embodiment of the present disclosure.

[0097] According to one embodiment of the present disclosure, a computing device (100) can identify one or more layers in a body part to be treated (S120). For example, the computing device (100) can identify a plurality of different layers in a body part to be treated. For example, the body part to be treated may include skin. In addition, the types of the plurality of different layers may include at least two of the dermis, fat layer, or fascia layer of the skin. However, this is not limited thereto, and the types of the plurality of different layers may be further subdivided according to the purpose of the treatment. For example, the dermis is located below the epidermis and may be a tissue with a relatively high density. In addition, the subcutaneous fat is located between the dermis and the fascia layer and appears as a relatively low-echo region in ultrasound imaging. In addition, the SMAS / Fascia is located below the fat layer and exhibits a continuous linear structure showing a relatively high echo. The computing device (100) can divide multiple different layers in a body part to be treated by considering the characteristics of multiple different layers. For example, the computing device (100) can identify multiple different layers in a body part to be treated by performing preprocessing, semantic segmentation, binarization, post-processing, and boundary detection on an image (ultrasound image) of a body part to be treated. According to one embodiment, the computing device (100) can analyze medical image data using artificial intelligence (AI) models such as U-Net, V-Net, SegNet, DeepLab v3+, Mask R-CNN, and TransUNet, and can identify multiple different layers, including a fat layer and a fascia layer, in real time in a body part to be treated.These AI-based segmentation techniques utilize deep learning to precisely distinguish tissue boundaries in ultrasound images and identify layered anatomical structures, thereby contributing to the determination of the optimal treatment site. In particular, U-Net and V-Net series models perform precise segmentation at the pixel level, while TransUNet and Attention U-Net enhance accuracy by strengthening focus on specific tissue regions. This enables the establishment of customized treatment plans during HIFU procedures that reflect the anatomical characteristics of the fat and fascia layers.

[0098] For example, the computing device (100) may perform image preprocessing to identify multiple distinct layers in the body part to be treated. The computing device (100) may apply filtering techniques (e.g., Gaussian Filter, Median Filter) to remove noise from the acquired image. Additionally, image enhancement may be performed to clarify the layer structure through contrast stretching and histogram equalization. Furthermore, the computing device (100) may use techniques such as histogram equalization to enhance the contrast of the image. Additionally, the computing device (100) may normalize the size and resolution of the image and convert it into input data for a model. Additionally, the computing device (100) may set a Region of Interest (ROI) by performing image cropping with the area to be treated as the focus. However, the foregoing is merely an example and the present disclosure is not limited thereto.

[0099] For example, the computing device (100) can utilize an artificial intelligence model to segment multiple distinct layers of a body part to be treated in a preprocessed image. The computing device (100) can utilize a deep learning model to segment multiple distinct layers in an image at the pixel level (Semantic Segmentation). For example, the computing device (100) can utilize various Semantic Segmentation models to analyze an ultrasound image and segment layers such as the dermis, fat layer, and fascia / SMAS layer. For example, the computing device (100) can utilize at least one of models based on FCN (Fully Convolutional Networks), U-Net, DeepLab v3+, PSPNet (Pyramid Scene Parsing Network), SegNet, and Vision Transformers (ViT) to segment multiple distinct layers in a body part to be treated. For example, Fully Convolutional Networks (FCN) models can classify and segment layers by classifying each pixel of an ultrasound image through the removal of fully connected layers and the configuration of all layers as convolutional layers. U-Net effectively segments layers of ultrasound images by utilizing an encoder-decoder structure and skip connections, demonstrating powerful performance, particularly in medical imaging. DeepLab v3+ can precisely segment the boundaries of ultrasound images by applying Atrous Convolution and Spatial Pyramid Pooling to learn features at various scales. Pyramid Scene Parsing Network (PSPNet) can segment layer boundaries even more accurately by combining multi-scale feature maps and utilizing a wide range of contextual information.SegNet can reuse pooling indices in an encoder-decoder structure to more precisely reconstruct the structure of layers and perform segmentation of ultrasound images. Vision Transformers (ViT) based models can utilize Transformer-based long-range dependency learning to precisely analyze relationships between pixels and segment layers in ultrasound images. A computing device (100) can classify multiple distinct layers classified by pixel into different colors. For example, the computing device (100) can classify the dermis layer by displaying it in red, the fat layer in blue, the fascia layer in green, etc. Additionally, the computing device (100) can apply Otsu's Thresholding or Adaptive Thresholding to more clearly distinguish the segmented layers. Furthermore, it can extract layer boundaries using Canny Edge Detection, Sobel Filter, etc., and remove unnecessary noise and refine the boundaries more precisely through morphological operations.

[0100] Referring to FIG. 5 for an example, the computing device (100) can use a deep learning-based semantic segmentation model to divide multiple distinct layers of the body part to be treated in an ultrasound image and then set a boundary line (e.g., a bounding box, etc.) for each layer. The computing device (100) can set a curved or polygonal boundary line along the boundary in the post-processed image. The computing device (100) can recognize the upper boundary of the skin layer in the image and set a first boundary line (10). The first boundary line (10) may be a boundary line for distinguishing between the skin and the dermis layer. Additionally, the computing device (100) can identify the upper and lower boundaries of the fat layer and set a second boundary line (20). The second boundary line (20) may distinguish the beginning and end of the fat layer. Additionally, the computing device (100) can identify the boundary of the fascia layer and set a third boundary line (30). The set boundary lines (bounding boxes) accurately define the location of each layer and can serve as an important criterion when establishing a procedure plan. Additionally, the computing device (100) can set the energy adjustment, procedure depth, and procedure accuracy required for each layer through the boundary lines. Furthermore, the computing device (100) can display the set boundary lines by overlaying them onto the image in different colors. Alternatively, the user can predict procedure plan information for each layer through the displayed boundary lines and establish a customized procedure strategy based on this.

[0101]

[0102] FIG. 6 is a diagram schematically illustrating procedure planning information utilizing focused ultrasound in one embodiment of the present disclosure.

[0103] According to one embodiment of the present disclosure, a computing device (100) can generate procedure planning information utilizing focused ultrasound for one or more layers based on the type of identified layer (S130). For example, based on the types of identified multiple different layers, procedure planning information for a procedure utilizing focused ultrasound for multiple different layers can be generated. For example, the computing device (100) can generate the procedure planning information using an artificial intelligence model or logic coding. For example, the procedure planning information may include information on the location of the procedure utilizing focused ultrasound, information on the movement of the focused ultrasound, or information on the amount of energy of the focused ultrasound for multiple different layers. For reference, focused ultrasound can focus ultrasound on a fat layer to deliver thermal energy to fat cells, thereby destroying the fat cell membrane and inducing the dissolution of fat cells. Additionally, by performing Shrinking, a procedure that uses focused ultrasound to concentrate thermal energy on the fascia layer to coagulate and contract the tissue, skin lifting and skin elasticity can be improved.

[0104] According to one embodiment, the computing device (100) can set a procedure exclusion location for the dermis layer. Since the dermis layer serves to protect the skin, the computing device (100) can exclude the dermis layer from the procedure. The computing device (100) can set an internal area included in the first boundary line (10) as a procedure exclusion location.

[0105] Additionally, the computing device (100) can set a first type of treatment location (21) for the fat layer. For example, the computing device (100) can set a treatment location for the fat layer to utilize a first energy focused ultrasound. For instance, the computing device (100) can set a treatment location to apply the first energy focused ultrasound by analyzing the thickness and characteristics of the fat layer based on multiple different layers identified using an artificial intelligence model. For example, the computing device (100) can set a second type of treatment location (21) to utilize the first energy focused ultrasound in the area inside the second boundary line (20). Additionally, the computing device (100) can set a treatment interval to utilize the first energy focused ultrasound by considering the characteristics of the fat layer. For example, the blue dots shown in FIG. 6 represent treatment locations for the fat layer, and the interval between the dots represents the treatment interval. Since the fat layer is a relatively uniform tissue, focused ultrasound can be applied at regular intervals. For example, the fat-dissolving effect can be maximized by placing treatment points at preset intervals. Additionally, in areas where the fat layer is thick, a higher density of treatment intervals can be set to maximize the fat reduction effect. For example, the computing device (100) can utilize an artificial intelligence model to analyze the thickness and characteristics of the fat layer and, based on this, evenly distribute the first type of treatment locations (21). The computing device (100) can utilize a first boundary line (bounding box) that defines the boundary of the fat layer. The bounding box is formed based on the outermost boundary of the identified fat layer and can be used to distribute treatment locations at even intervals along this boundary. Additionally, a method utilizing a centroid line can also be applied.If the shape of the fat layer is irregular or the thickness is not uniform, the computing device (100) can divide the identified fat layer into upper, middle, and lower regions, calculate the centerline of each region, and place the treatment location accordingly. For example, a method of aligning the high-intensity focused ultrasound (HIFU) focal points along the center coordinates of each region can be applied, thereby enabling more uniform energy delivery and effective treatment. As a result, through this approach, the effect of HIFU can be maximized by evenly distributing the treatment location while taking into account the various anatomical characteristics of the fat layer.

[0106] Additionally, the computing device (100) can set a second type of treatment location (22) for the fascial layer. For example, the computing device (100) can set a treatment location for the fascial layer to utilize a second energy focused ultrasound. For instance, the computing device (100) can set a treatment location to apply a second energy focused ultrasound by analyzing the characteristics of the fascial layer (SMAS / Fascia) based on multiple different layers identified using an artificial intelligence model. For example, the computing device (100) can set a second type of treatment location (22) to utilize a second energy focused ultrasound in the area inside the third boundary line (30). Additionally, the computing device (100) can set a treatment interval to utilize a second energy focused ultrasound, which is different from the first energy, by considering the characteristics of the fascial layer. For example, the red dots shown in FIG. 6 represent treatment locations for the fascial layer, and the distance between the dots represents the treatment interval. Since the fascia layer is a crucial layer determining skin elasticity and lifting effects, higher energy can be applied than to the fat layer. Because the fascia layer possesses high elasticity and a complex structure, energy can be dispersed at an appropriate intensity by setting wider spacing than in the fat layer. Higher energy can be applied to specific areas (e.g., the cheeks), while energy can be adjusted in sensitive areas (e.g., the jawline).

[0107] Alternatively, the computing device (100) can set the first energy delivered to the fat layer to be higher than the second energy. For example, the computing device (100) can set the first energy delivered to the fat layer to a high intensity for fat breakdown. On the other hand, the computing device (100) can set the second energy delivered to the fascia layer to be higher than the first energy for tissue contraction and collagen remodeling. The computing device (100) can selectively adjust the intensity of the first energy and the second energy according to the purpose of the procedure and the target tissue. In summary, the computing device (100) can set the procedure location, procedure interval, energy of focused ultrasound, etc., for each of the multiple layers identified according to the procedure plan.

[0108] For example, the computing device (100) can utilize an artificial intelligence model to analyze the thickness and characteristics of the fascial layer and, based on this, evenly distribute the second type of treatment locations (22). The computing device (100) can utilize a second boundary line (bounding box) that defines the boundary of the fascial layer. The bounding box is formed based on the outermost boundary of the identified fascial layer and can be utilized to distribute treatment locations at even intervals along this boundary. Additionally, if the thickness of the fascial layer is not uniform or forms a curve, the treatment locations may not be optimized if only the second boundary line is considered. Accordingly, the computing device (100) can utilize the second boundary line to calculate the centroid line of the fascial layer and apply a method of placing treatment locations along it. This method can help to effectively deliver the energy of High-Intensity Focused Ultrasound (HIFU) while reflecting the anatomical characteristics of the fascial layer more precisely.

[0109] Alternatively, the computing device (100) may utilize an artificial intelligence model to analyze the thickness of the fat layer (20) and the fascia layer (30) and determine the optimal treatment location based on this. For example, the computing device (100) may analyze an image to identify multiple distinct layers in the body part to be treated and measure the thickness of the fat layer. Subsequently, the computing device (100) may divide the fat layer into three regions—upper, middle, and lower—based on the measured thickness information, and place HIFU (High-Intensity Focused Ultrasound) irradiation points along the centroid of the boundary line (20) of the fat layer so that ultrasound energy is evenly distributed throughout the fat layer. At this time, depending on the thickness information, it may be divided into two or four regions, etc. For example, since the fascia layer is relatively thin and has a clear boundary, the optimal treatment path can be set based on the thickness information analyzed by the artificial intelligence model, and HIFU targets can be placed in a single line to prevent unnecessary energy dispersion. This enables a precise procedure that delivers ultrasonic energy intensively along a specific structure of the fascial layer. That is, the computing device (100) can use artificial intelligence to analyze the thickness of the fat layer and the fascial layer, and based on this, automatically optimize the placement of three lines of focus points in the fat layer and one line in the fascial layer to enable effective procedure. For example, for a more precise procedure, a method that considers the first boundary line (fat layer) and the second boundary line (fascial layer) together can also be applied. For example, it is possible to place the procedure location within the fat layer based on the first boundary line, and then align the procedure location with the centerline of the fascial layer based on the second boundary line. Through this, it is possible to set up an effective procedure by delivering ultrasonic energy to the optimal location while considering the structural difference between the fascial layer and the fat layer.

[0110] Alternatively, the computing device (100) may set a third type of treatment location between the dermis layer and the fat layer. For example, the computing device (100) may set a third type of treatment location in an area corresponding to a preset distance (e.g., 2 mm to 4 mm) below the dermis layer. For example, the computing device (100) may set a treatment location utilizing a third energy focused ultrasound between the dermis layer and the fat layer. For example, the third energy focused ultrasound may be a relatively weaker energy compared to the second energy for the fascia layer. The computing device (100) may use an artificial intelligence model to analyze the inter-layer region between the dermis layer and the fat layer and set a third type of treatment location for this region. For example, the artificial intelligence model may detect the lower boundary of the dermis layer (first boundary line) and the upper boundary of the fat layer (second boundary line) and extract a third type of treatment location corresponding to the area between them. The artificial intelligence model can analyze the applicability of focused ultrasound of the third energy (medium intensity) by considering tissue density and ultrasound absorption rate. Additionally, the artificial intelligence model can automatically detect the area requiring the third type of procedure by analyzing changes in tissue density near the boundary between the dermis and the fat layer. By setting the location for the third type of procedure to utilize focused ultrasound of the third energy, the computing device (100) can generate customized procedure plan information that simultaneously considers the lifting effect of the dermis and the reduction effect of the fat layer.

[0111]

[0112] According to one embodiment of the present disclosure, a computing device (100) can display generated procedure plan information on an acquired image (S140). Here, the computing device (100) can display the generated procedure plan information in different ways on identified different layers. For example, the computing device (100) can display each procedure location by applying different colors to each layer. In addition, the computing device (100) can display procedure location and path information using points and lines to visually represent the procedure plan information. In addition, the computing device (100) can adjust the size of the points according to the procedure intensity. In summary, each point (●) represents a location where ultrasound energy is focused, and the spacing between the points serves as a factor for adjusting the procedure intensity and frequency. The lines connecting the points serve to visually highlight the path along which the procedure will proceed and to define the procedure pattern for each layer. All procedure points can be arranged to maintain a constant spacing along the path. Through this, the computing device (100) can more effectively display procedure planning information and provide real-time visual feedback to support medical staff in performing more precise procedures. For example, the computing device (100) can display procedure planning information overlaid with images acquired for the body part to be treated in real time. By displaying procedure planning information overlaid with images acquired in real time, the computing device (100) can support medical staff in immediately recognizing and adjusting the treatment area. For reference, the procedure planning information may be changed based on images acquired in real time.

[0113] According to one embodiment, the computing device (100) may display a first type of procedure location (21) for the fat layer. For example, the computing device (100) may display first type path information connecting a plurality of first type locations for the fat layer. For example, the computing device (100) may display the first type of procedure location for the fat layer as a point and the first type path connecting a plurality of first type locations as a line to visually represent procedure planning information, thereby displaying procedure location and path information. The computing device (100) may represent a specific procedure point for the fat layer as an individual point (●) so that medical staff can intuitively recognize the procedure location. The computing device (100) may represent the point for displaying the first type of procedure location (21) for the fat layer as a first type point. For example, the first type of dots may include a first color (e.g., blue) and a first size (e.g., a size smaller than that of the second type of dots). For example, the spacing of the dots in the fat layer is set considering the tissue characteristics of the fat layer and may be arranged at a spacing different from or the same as the spacing between the dots in the fascia layer.

[0114] According to one embodiment, the computing device (100) may display a second type of procedure location for the fascial layer by utilizing a display method different from the method of displaying a first type of procedure location. For example, the computing device (200) may display second type path information connecting a plurality of second type locations for the fascial layer. For example, the computing device (200) may display the second type of procedure location for the fascial layer as a point and the second type path connecting a plurality of second type locations as a line to visually represent procedure planning information, thereby displaying procedure location and path information. The computing device (200) may represent a specific procedure point for the fascial layer as an individual point (●) so that medical personnel can intuitively recognize the procedure location. The computing device (200) may represent a point for displaying the second type of procedure location (22) for the fascial layer as a second type point. For example, the second type of dots may include a second color (e.g., red) and a second size (e.g., a size larger than the second type of dots). For example, the spacing of the dots in the fascial layer is set considering the tissue characteristics of the fascial layer and may be arranged at a spacing different from or the same as the spacing between the dots in the fat layer.

[0115] Alternatively, the path information of the first type connecting the first type of procedure location and multiple first type locations is represented as a straight line (1-dimensional), but depending on the embodiment, it may be represented in 2-dimensional. For example, referring to FIG. 6, it can be seen that the first type of procedure location moves only along the X-axis (procedure direction) and points and lines are arranged while maintaining a constant spacing. This is a method of displaying the procedure location as if following a single path, with points connected in only one direction (left and right or a constant straight line direction). In the 2-dimensional representation, the points are not simply arranged in the X-axis direction (horizontal direction), but may include an arrangement that also considers the Y-axis direction (depth direction). For example, the procedure location may be extended like a grid or a surface rather than a simple line shape. In the same way, the path information of the second type connecting the second type of procedure location and multiple second type locations may be represented in 2-dimensionally.

[0116]

[0117] According to one embodiment of the present disclosure, a computing device (100) can generate an actuator control signal to automatically move a device generating focused ultrasound to a target treatment site based on generated treatment plan information (S150). For example, the computing device (100) can generate a control signal for an actuator mounted on the focused ultrasound based on the generated treatment plan information. For example, the actuator may include an electric motor, a linear actuator, etc. For instance, the computing device (100) can calculate the position coordinates of the site for generating focused ultrasound based on the generated treatment plan information. For example, the actuator control signal may include control signals in the direction of two or more mutually orthogonal axes. For example, the x-axis may be the treatment direction and the y-axis may be the skin depth direction. Alternatively, a z-axis may be included to enable three-dimensional 3D movement. Additionally, by adding rotation and tilt adjustment functions, the optimal irradiation angle for a specific treatment site may be maintained. The computing device (100) can control the actuator based on the treatment plan to automatically move the focused ultrasound device and perform ultrasound irradiation at a set target location. For example, the actuator control signal may include a control signal that can move in at least one of linear movement if moving in only one direction (X-axis or Y-axis), plane movement if moving in two directions (X-axis + Y-axis), or space movement if moving in three directions (X-axis + Y-axis + Z-axis). The actuator control signal may include a control signal that moves not only in one direction but also in multiple directions to move the focus point of the ultrasound to a desired location within a line, plane, or 3D space.

[0118] According to one embodiment, the computing device (100) can generate an energy control signal to automatically adjust the energy of the focused ultrasound in conjunction with movement by an actuator, based on the generated procedure plan information. For example, the energy control signal to automatically adjust the energy of the focused ultrasound may include the energy intensity (amount), ultrasound irradiation time, irradiation frequency, irradiation pattern (focusing mode, continuous mode, etc.), and irradiation depth control. Additionally, the computing device (100) can update the generated procedure plan information based on an image acquired in real time and regenerate an energy control signal to automatically adjust the energy of the focused ultrasound in conjunction with movement by an actuator.

[0119] Alternatively, the computing device (100) displays procedure plan information generated by artificial intelligence on a display, and the user can view and modify the generated procedure plan information. Taking this into consideration, the computing device (100) may also regenerate an energy control signal to automatically adjust the energy of the focused ultrasound in conjunction with movement by an actuator, based on the modified procedure plan information.

[0120]

[0121] According to one embodiment of the present disclosure, a computing device (100) can transmit and monitor an image (ultrasound image data) in real time, and based on this, utilize a deep learning model to automatically identify and segment a target area (anatomical structure of fascia and fat) and provide the analyzed information to medical staff in real time. In addition, it supports monitoring by visually overlaying procedure planning information (e.g., HIFU target point and path) on the image (ultrasound image) in real time, thereby enabling medical staff to verify the exact procedure location in real time and plan and adjust the optimal ultrasound irradiation path. In particular, this real-time image monitoring and analysis function can be designed to be linked with automatic actuator control to dynamically adjust the target location according to anatomical changes in the procedure site and automatically adjust the HIFU energy to an optimal intensity.

[0122]

[0123] The steps mentioned in the foregoing description may be further subdivided into additional steps or combined into fewer steps, depending on the embodiment of the present disclosure. Additionally, some steps may be omitted as necessary, and the order of the steps may be changed.

[0124]

[0125] Meanwhile, a computer-readable medium storing a data structure is disclosed according to an embodiment of the present disclosure.

[0126] A computer-readable medium storing a data structure according to one embodiment of the present disclosure is disclosed. The aforementioned data structure may be stored in memory as described in the present disclosure, executed by a processor, and transmitted and received by a network unit.

[0127] A data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure can refer to the organization of data for solving specific problems (e.g., data analysis, data retrieval, data storage, data modification). A data structure may also be defined by physical or logical relationships between data elements designed to support specific data processing functions. Logical relationships between data elements may include connections between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (e.g., a permanent storage device). Specifically, a data structure may include sets of data, relationships between data, and functions or instructions applicable to the data. Through an effectively designed data structure, a computing device can perform operations while minimizing the use of the device's resources. Specifically, through an effectively designed data structure, a computing device can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and retrieval.

[0128] Data structures can be classified into linear and non-linear data structures based on their form. A linear data structure is one where only one piece of data is connected to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a set of data that maintains an internal order. Lists can include linked lists. A linked list is a data structure where data is connected in a line, with each piece of data possessing a pointer. In a linked list, the pointer can contain information regarding the connection to the next or previous data. Depending on its form, a linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list. A stack is a data arrangement structure that allows for restricted access to data. A stack can be a linear data structure where data can be processed (e.g., insertion or deletion) only at one end. Data stored in a stack can be a Last-In, First-Out (LIFO) data structure, meaning that the later an item is entered, the sooner it is retrieved. A queue is a data sequence structure that allows for limited access to data; unlike a stack, it can be a FIFO (First in First Out) data structure where data stored later is retrieved later. A deque is a data structure that can process data at both ends.

[0129] Non-linear data structures can be structures where multiple data are connected after a single piece of data. Non-linear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge may include a line connecting two different vertices. Graph data structures may include tree data structures. A tree data structure may be a data structure where there is only one path connecting two different vertices among the multiple vertices included in the tree. In other words, it may be a data structure that does not form loops in a graph data structure.

[0130] Throughout this specification, the terms artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, they will be described uniformly as neural network. A data structure may include a neural network. Furthermore, a data structure including a neural network may be stored on a computer-readable medium. A data structure including a neural network may also include data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. A data structure including a neural network may include any of the components disclosed above. That is, a data structure including a neural network may be configured to include all or any combination thereof, such as data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for learning the neural network. In addition to the configurations described above, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated during the computational process of the neural network, and is not limited to the foregoing. A computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0131] A data structure may include data input to a neural network. A data structure including data input to a neural network may be stored on a computer-readable medium. Data input to a neural network may include training data input during the neural network learning process and / or input data input to a neural network after training is complete. Data input to a neural network may include pre-processed data and / or data subject to pre-processing. Pre-processing may include a data processing process for inputting data into a neural network. Accordingly, a data structure may include data subject to pre-processing and data generated by pre-processing. The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0132] The data structure may include weights of the neural network. (In this specification, weights and parameters may be used interchangeably.) The data structure including the weights of the neural network may be stored on a computer-readable medium. The neural network may include multiple weights. The weights may be variable and may be varied by a user or an algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node may determine the data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set on the links corresponding to each input node. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0133] As an example rather than a limitation, weights may include weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Weights that vary during the neural network learning process may include weights at the start of the learning cycle and / or weights that vary during the learning cycle. Weights for which neural network learning is completed may include weights for which the learning cycle is completed. Accordingly, a data structure containing the weights of a neural network may include a data structure containing weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Therefore, the weights and / or combinations of each weight described above are included in the data structure containing the weights of a neural network. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0134] Data structures containing the weights of a neural network may be stored on a computer-readable storage medium (e.g., memory, hard disk) after undergoing a serialization process. Serialization may be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed for use. A computing device may serialize the data structure to transmit and receive data over a network. A serialized data structure containing the weights of a neural network may be reconstructed on the same or different computing devices through deserialization. Data structures containing the weights of a neural network are not limited to serialization. Furthermore, data structures containing the weights of a neural network may include data structures designed to increase computational efficiency while minimizing the use of computing device resources (e.g., B-Tree, R-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree in non-linear data structures). The foregoing is merely an example and the present disclosure is not limited thereto.

[0135] The data structure may include hyperparameters of the neural network. The data structure including the neural network hyperparameters may be stored on a computer-readable medium. The hyperparameters may be variables that are varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weight values ​​subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0136]

[0137] FIG. 7 is a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0138] Although the present disclosure has been described as generally being implementable by a computing device, a person skilled in the art will be well aware that the present disclosure may be implemented in combination with computer-executable instructions and / or other program modules that can be executed on one or more computers and / or as a combination of hardware and software.

[0139] Generally, a program module includes routines, programs, components, data structures, etc., that perform a specific task or implement a specific abstract data type. Furthermore, a person skilled in the art will be well aware that the method of the present disclosure can be implemented in other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. (each of which may be connected to and operated with one or more associated devices).

[0140] The embodiments described in this disclosure may also be implemented in a distributed computing environment in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0141] Computers typically include various computer-readable media. Any medium accessible by a computer may be a computer-readable medium, and such computer-readable media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media. By example, but not limiting, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and used to store desired information.

[0142] Computer-readable transmission media typically include all information transmission media that implement computer-readable instructions, data structures, program modules, or other data, etc., on a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or modified to encode information within the signal. By example, not limiting, computer-readable transmission media include wired media, such as wired networks or direct-wired connections, and wireless media, such as acoustic, RF, infrared, and other wireless media. Any combination of the media described above is also considered to be within the scope of computer-readable transmission media.

[0143] An exemplary environment for implementing various aspects of the present disclosure, including a computer (1102), is shown, wherein the computer (1102) includes a processing unit (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including system memory (1106) (but not limited thereto), to the processing unit (1104). The processing unit (1104) may be any processor among various commercial processors. Dual processor and other multiprocessor architectures may also be used as the processing unit (1104).

[0144] The system bus (1108) may be any of several types of bus structures that can be additionally interconnected to a local bus using any of the memory bus, peripheral bus, and various commercial bus architectures. System memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that help transfer information between components within the computer (1102) at times such as during startup. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0145] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA)—this internal hard disk drive (1114) may also be configured for external use within a suitable chassis (not shown)—a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from a CD-ROM disk (1122) or reading from or writing to other high-capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may each be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128). The interface (1124) for implementing an external drive includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0146] These drives and associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of a computer (1102), the drives and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, a person skilled in the art will know that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., may also be used in exemplary operating environments and that any of these media may contain computer-executable instructions for performing the methods of the present disclosure.

[0147] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or part of the operating system, application, module and / or data may also be cached in RAM (1112). It will be well known that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0148] The user can input commands and information into the computer (1102) through one or more wired / wireless input devices, such as a pointing device like a keyboard (1138) and a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, etc. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) connected to the system bus (1108), but may also be connected via other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, etc.

[0149] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface such as a video adapter (1146). In addition to the monitor (1144), the computer generally includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0150] The computer (1102) may operate in a networked environment using a logical connection to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communication. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), but for brevity, only the memory storage device (1150) is illustrated. The illustrated logical connection includes a wired / wireless connection to a local area network (LAN) (1152) and / or a larger network, e.g., a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a global computer network, e.g., the Internet.

[0151] When used in a LAN networking environment, the computer (1102) is connected to a local network (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communication to the LAN (1152), and the LAN (1152) may also include a wireless access point installed therein to communicate with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communication computing device on the WAN (1154), or have other means to establish communication through the WAN (1154), such as through the Internet. The modem (1158), which may be an internal or external and a wired or wireless device, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, the program modules described for the computer (1102) or parts thereof may be stored in a remote memory / storage device (1150). It will be well known that the illustrated network connection is exemplary and that other means of establishing a communication link between computers may be used.

[0152] The computer (1102) operates to communicate with any wireless device or object that is deployed and operated via wireless communication, for example, a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or place associated with a wireless detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or simply ad hoc communication between at least two devices.

[0153] Wi-Fi (Wireless Fidelity) enables connectivity to the Internet and other sources without wires. Wi-Fi is a wireless technology, similar to a cell phone, that allows devices, such as computers, to transmit and receive data indoors and outdoors—that is, anywhere within the coverage area of ​​a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band).

[0154] Those skilled in the art of the present disclosure will understand that information and signals may be represented using any various different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0155] Those skilled in the art will understand that the various exemplary logical blocks, configurations, modules, logics, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented by electronic hardware, various forms of computer programs or design code (referred to herein as software for convenience), or a combination of all such. To clearly illustrate this interoperability between hardware and software, the various exemplary logical blocks, configurations, modules, logics, processors, means, circuits, and steps have been generally described above in relation to their functions. Whether such functions are implemented in hardware or software depends on the design constraints imposed on the specific application and the overall system. Those skilled in the art may implement the functions described in this disclosure in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of this disclosure.

[0156] The various embodiments presented herein may be implemented as methods, devices, or articles manufactured using standard programming and / or engineering techniques. The term "article manufactured" includes a computer program, a carrier, or a medium accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical discs (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0157] It should be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but do not imply being limited to the specific order or hierarchy presented.

[0158] Description of the presented embodiments is provided so that a person skilled in the art may use or practice the present disclosure. Various modifications to these embodiments will be apparent to a person skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0159]

[0160] As described above, the relevant details have been described in the best mode for carrying out the invention.

Claims

1. A method for generating procedure planning information for a procedure utilizing focused ultrasound (FU) performed by a computing device, wherein A step of acquiring an image of the body part to be treated; A step of identifying one or more layers in the body part to be treated above; A step of generating procedure planning information for a procedure utilizing focused ultrasound for one or more layers based on the type of the identified layer; A step of displaying the generated procedure plan information on the acquired image; and A step of generating an actuator control signal to automatically move the device generating the focused ultrasound to the target treatment site based on the above-mentioned generated treatment plan information. including, method.

2. In Paragraph 1, The step of identifying one or more of the above layers is, The method includes the step of identifying a plurality of different layers in the body part to be treated, and The step of generating the above procedure plan information is, Based on the types of the plurality of different layers identified above, the method includes the step of generating procedure planning information for a procedure utilizing the focused ultrasound on the plurality of different layers. The above-mentioned generated procedure plan information is displayed in different ways in the above-mentioned identified different layers, method.

3. In Paragraph 2, The actuator control signal includes control signals in the direction of two or more mutually orthogonal axes. method.

4. In Paragraph 2, A step of generating an energy control signal to automatically adjust the energy of the focused ultrasound in conjunction with movement by the actuator based on the procedure plan information generated above. including, method.

5. In Paragraph 2, The body part subject to the above procedure includes skin, and The types of the plurality of different layers include at least two of the dermis layer, fat layer, or fascia layer of the skin. method.

6. In Paragraph 5, The step of identifying a plurality of different layers in the body part subject to the procedure described above is, A step of establishing a first boundary line for the dermal layer; A step of setting a second boundary line for the above fat layer; or Step of establishing a third boundary line for the above fascia layer; including at least two of method.

7. In Paragraph 5, Based on the types of the plurality of different layers identified above, the step of generating treatment planning information utilizing the focused ultrasound for the plurality of different layers is: A step of setting a procedure exclusion location for the above dermal layer; A step of setting a first type of procedure location on the above-mentioned fat layer; or Step of setting a second type of procedure location for the above fascia layer including at least two of method.

8. In Paragraph 6, The step of setting a first type of procedure location for the above-mentioned fat layer is, The above-mentioned fat layer includes the step of setting a treatment location to utilize focused ultrasound of the first energy, and The step of setting a second type of procedure location for the above fascia layer is, A step of setting a treatment location to utilize focused ultrasound of a second energy different from the first energy for the above fascia layer. including, method.

9. In Paragraph 6, The step of setting a first type of procedure location for the above-mentioned fat layer is, It includes a step of setting a treatment interval to utilize focused ultrasound of the first energy, taking into account the characteristics of the above-mentioned fat layer, and The step of setting a second type of procedure location for the above fascia layer is, Step of setting a treatment interval to utilize focused ultrasound of a second energy different from the first energy, taking into account the characteristics of the fascial layer. including, method.

10. In Paragraph 7, The step of displaying the generated procedure plan information on the acquired image is: A step of marking a first type of procedure location on the above-mentioned fat layer; and A step of indicating a second type of procedure location on the fascia layer by utilizing a marking method different from the method of indicating the first type of procedure location above. including, method.

11. In Paragraph 10, The step of displaying the generated procedure plan information on the acquired image is: A step of displaying first type path information connecting a plurality of first type locations on the above fat layer; and A step of displaying second type path information connecting a plurality of second type locations on the fascia layer. including, method.

12. In Paragraph 1, The step of acquiring an image of the body part to be treated above is, It includes the step of acquiring an image of the body part to be treated using an ultrasound scanner, and The above ultrasound scanner utilizes a separate ultrasound different from the above focused ultrasound, method.

13. A computer program stored on a computer-readable storage medium, wherein, when the computer program is executed on one or more processors, the one or more processors are configured to perform the following operations to generate procedure planning information for a procedure utilizing focused ultrasound (FU), and said operations are: Action of acquiring an image of the body part to be treated; An action of identifying one or more layers in the body part subject to the procedure; An operation to generate procedure planning information for a procedure utilizing focused ultrasound for one or more layers based on the type of the identified layer; The operation of displaying the generated procedure plan information on the acquired image; and Operation of generating an actuator control signal to automatically move the device generating the focused ultrasound to the target treatment site based on the above-generated treatment plan information. including, A computer program stored on a computer-readable storage medium.

14. As a computing device, At least one processor; and Memory; Includes, The above at least one processor is, Acquire an image of the body part to be treated; Identify one or more layers in the body part subject to the procedure; Based on the type of the identified layer, generate procedure planning information for a procedure utilizing focused ultrasound on one or more layers; Display the generated procedure plan information on the above-mentioned acquired image; and Based on the above-mentioned generated procedure plan information, configured to generate an actuator control signal to automatically move the device generating the focused ultrasound to the target procedure site, device.

Images