Method of operating a medical imaging apparatus and medical imaging electronic apparatus

Abstract

The disclosure relates to an operating method of a medical image apparatus. The operating method of the medical image apparatus includes acquiring lesion information about at least one lesion detected from a medical image, determining shapes and positions of at least one contour corresponding to the at least one lesion based on the acquired lesion information, determining positions of at least one text region including text that displays the lesion information about the at least one lesion in the medical image, and displaying the at least one contour and the text included in the at least one text region in the medical image based on the determined shapes and positions of the at least one contour and the determined positions of the at least one text region.

Description

[0001] Technology Area

[0002] This disclosure relates to an apparatus and method for acquiring lesion information from medical images and displaying the lesion information in the medical images. Background Technology

[0003] With the development of technologies such as big data and artificial intelligence, the reliability of technologies that automatically detect lesions from medical images is gradually increasing. Therefore, medical devices can also detect multiple lesions from medical images. However, displaying all the information about the detected lesions in a single medical image could lead to an overabundance of information. Displaying too much information in a medical image not only obscures the original image, but also may require medical personnel to spend a considerable amount of time using the displayed lesion information for diagnosis. Furthermore, medical personnel may also miss some of the displayed lesion information.

[0004] Therefore, there is a need for technology that can effectively display lesions in images. Summary of the Invention

[0005] Technical problems to be solved

[0006] This disclosure provides a medical image processing method, a computer program stored in a recording medium, and a medical imaging device (system) for solving the above-mentioned problems.

[0007] means for solving problems

[0008] An operating method of a medical imaging device according to an embodiment of the present disclosure is characterized by comprising the following steps: acquiring lesion information about at least one lesion included in a medical image; generating at least one contour corresponding to the at least one lesion in the medical image based on the acquired lesion information; and outputting the at least one contour generated in the medical image.

[0009] The step of generating at least one contour in the operation method of a medical imaging device according to an embodiment of the present disclosure is characterized by including the following steps: generating a contour based on at least one of the following: information related to lesion regions repeated among multiple lesions included in a medical image or information related to the correlation between multiple lesions, based on acquired lesion information.

[0010] The step of generating at least one contour in the operation method of a medical imaging device according to an embodiment of the present disclosure is characterized by comprising the following steps: determining the size of the region of the first lesion and the region of the second lesion overlapping based on first lesion information and second lesion information included in a plurality of lesions; determining information related to the probability of the second lesion existing in the medical image based on the second lesion information; and generating at least one contour surrounding the first lesion when the size of the overlapping region is greater than a first threshold value and the information related to the probability of the second lesion existing in the medical image is less than a second threshold value.

[0011] The step of generating at least one contour in the operation method of a medical imaging device according to an embodiment of the present disclosure is characterized by including the following steps: determining whether there is pathological similarity between a first lesion and a second lesion; determining whether there is coexistence between the first lesion and the second lesion in the same region; when the existence of similarity indicates that the first lesion and the second lesion are similar, or the existence of coexistence indicates that the first lesion and the second lesion cannot coexist, generating at least one contour around the first lesion, and not generating at least one contour around the second lesion.

[0012] An operating method of a medical imaging device according to an embodiment of the present disclosure is characterized by further comprising a step of arranging multiple lesion information in order of high probability of existing in the medical image based on multiple lesion information, wherein the probability of the first lesion existing in the medical image is greater than that of the second lesion.

[0013] The step of outputting at least one contour according to an embodiment of the medical imaging device of the present disclosure is characterized by comprising the following steps: determining first candidate arrow information about a plurality of first candidate arrows, the plurality of first candidate arrows pointing to a first contour in at least one contour; determining an arrow-text region outside the first contour; in the arrow-text region, determining a contact point region where one side of a text box corresponding to the plurality of first candidate arrows and displaying lesion information about the first contour intersects with one end of the plurality of first candidate arrows included in the first candidate arrow information; generating at least one arrow set about the text box about the first contour and about the displayable position of the arrows based on the determined contact point region; obtaining a score for each at least one arrow set; selecting one arrow set from the at least one arrow set based on the obtained score; and outputting the arrows and the text in the text box together with the at least one contour based on the selected arrow set.

[0014] The step of determining first candidate arrow information in the operation method of a medical imaging device according to an embodiment of the present disclosure is characterized by including a step of obtaining modified first candidate arrow information by moving the start point or end point of the candidate arrow included in the first candidate arrow information so that the first text box does not overlap with the second text box or the second contour when the first text box about the first contour overlaps with the second text box or the second contour; the step of generating at least one arrow kit includes a step of generating at least one arrow kit based on the modified first candidate arrow information.

[0015] An operating method of a medical imaging device according to an embodiment of the present disclosure is characterized by further comprising: a step of determining second candidate arrow information regarding a plurality of second candidate arrows, the plurality of second candidate arrow information pointing to a second contour in at least one contour; a step of determining first candidate arrow information comprising: obtaining modified first candidate arrow information by moving the start point or end point of one of the plurality of first candidate arrows such that one of the plurality of first candidate arrows does not intersect with one of the plurality of second candidate arrows; and a step of generating at least one arrow kit comprising: generating at least one arrow kit based on the modified first candidate arrow information.

[0016] The step of determining first candidate arrow information in the operation method of a medical imaging device according to an embodiment of the present disclosure includes the following steps: obtaining the intersection point of a first contour and at least one second contour; obtaining a first contact point of one of a plurality of first candidate arrows that contacts the first contour; obtaining modified first candidate arrow information by modifying the position of the start point or end point of one of the plurality of first candidate arrows so that the first contact point and the intersection point are more than a critical value apart; the step of generating at least one arrow kit includes the step of generating at least one arrow kit based on the modified first candidate arrow information.

[0017] An arrow-text area of ​​an operation method of a medical imaging device according to an embodiment of the present disclosure is characterized in that it does not contact a first contour and is an annular area surrounding the first contour.

[0018] According to an embodiment of the present disclosure, the operation method of a medical imaging device is characterized in that the distance between at least one text box corresponding to at least one contour is greater and higher, the length of at least one arrow corresponding to at least one contour is shorter and higher, and the distance between the intersection of two contours included in at least one contour and the contact point of at least one contour and at least one arrow is greater and higher.

[0019] The step of generating at least one contour in the operation method of a medical imaging device according to an embodiment of the present disclosure is characterized by including: a step of determining the position and shape of at least one contour based on acquired lesion information.

[0020] The step of determining the position and shape of at least one contour in the operation method of a medical imaging device according to an embodiment of the present disclosure is characterized by including the steps of: obtaining the probability that each pixel in the medical image is included in the region of at least one lesion based on lesion information; and determining the thickness of at least one contour based on the probability of being included in the region of at least one lesion.

[0021] A medical imaging apparatus according to an embodiment of the present disclosure is characterized in that it includes: a processor and a memory, wherein the processor acquires lesion information about at least one lesion included in a medical image according to commands stored in the memory, and generates at least one contour corresponding to the at least one lesion in the medical image based on the acquired lesion information, and outputs at least one contour generated in the medical image.

[0022] A processor of a medical imaging apparatus according to an embodiment of the present disclosure is characterized in that, based on commands stored in a memory, it generates a contour based on acquired lesion information, on at least one of information related to lesion regions that repeat among a plurality of lesions included in a medical image, or on information related to the correlation between the plurality of lesions.

[0023] A processor of a medical imaging apparatus according to an embodiment of the present disclosure is characterized in that, according to commands stored in a memory, based on first lesion information and second lesion information included in a plurality of lesions, it determines the size of the region of the first lesion and the region of the second lesion that overlap, determines information related to the probability of the second lesion existing in the medical image based on the second lesion information, and generates at least one contour around the first lesion when the size of the overlapping region is greater than a first threshold value and the information related to the probability of the second lesion existing in the medical image is less than a second threshold value.

[0024] A processor of a medical imaging device according to an embodiment of the present disclosure is characterized in that, according to commands stored in a memory, it determines whether there is pathological similarity between a first lesion and a second lesion, determines whether the first lesion and the second lesion coexist in the same region, and when the existence of similarity indicates that the first lesion and the second lesion are similar, or the existence of coexistence indicates that the first lesion and the second lesion cannot coexist, it generates at least one contour around the first lesion, but does not generate at least one contour around the second lesion.

[0025] A processor of a medical imaging device according to an embodiment of the present disclosure is characterized in that, according to a command stored in a memory, it arranges multiple lesion information in order of high probability of existing in the medical image, and the probability of a first lesion existing in the medical image is greater than that of a second lesion.

[0026] A processor of a medical imaging device according to an embodiment of the present disclosure is characterized in that, according to commands stored in a memory, it determines first candidate arrow information about a plurality of first candidate arrows, the plurality of first candidate arrows pointing to a first contour in at least one contour; an arrow-text region is determined outside the first contour; in the arrow-text region, a contact point region is determined where a side of a text box corresponding to the plurality of first candidate arrows and displaying lesion information about the first contour intersects with one end of the plurality of first candidate arrows included in the first candidate arrow information; based on the determined contact point region, a text box about the first contour and at least one arrow set for the displayable position of the arrows are generated; a score is obtained for each at least one arrow set; based on the obtained score, one arrow set from the at least one arrow set is selected; and based on the selected arrow set, the arrows and the text in the text box are output together with at least one contour.

[0027] A processor of a medical imaging device according to an embodiment of the present disclosure is characterized in that, according to a command stored in a memory, when a first text box about a first contour overlaps with a second text box or a second contour about a second contour, the processor moves the start point or end point of a candidate arrow included in the first candidate arrow information so that the first text box does not overlap with the second text box or the second contour, thereby obtaining modified first candidate arrow information, and generating at least one arrow kit based on the modified first candidate arrow information.

[0028] A processor of a medical imaging apparatus according to an embodiment of the present disclosure is characterized in that, according to a command stored in a memory, it determines second candidate arrow information about a plurality of second candidate arrows, the plurality of second candidate arrows pointing to a second contour in at least one contour, and obtains modified first candidate arrow information by moving the start point or end point of one of the plurality of first candidate arrows so that one of the plurality of first candidate arrows does not intersect with one of the plurality of second candidate arrows, and generates at least one arrow kit based on the modified first candidate arrow information.

[0029] A processor of a medical imaging device according to an embodiment of the present disclosure is characterized in that, according to a command stored in a memory, it obtains the intersection point of a first contour and at least one second contour, obtains a first contact point of one of a plurality of first candidate arrows that contacts the first contour, modifies the position of the start point or end point of one of the plurality of first candidate arrows so that the first contact point and the intersection point are more than a critical value apart, thereby obtaining modified first candidate arrow information, and generates at least one arrow kit based on the modified first candidate arrow information.

[0030] An arrow-text area of ​​a medical imaging device according to an embodiment of the present disclosure is characterized in that it does not contact a first contour and is an annular area surrounding the first contour.

[0031] According to an embodiment of the medical imaging device of the present disclosure, the distance between at least one text box corresponding to at least one contour is greater and higher, the length of at least one arrow corresponding to at least one contour is shorter and higher, and the distance between the intersection of two contours included in at least one contour and the contact point of at least one contour and at least one arrow is greater and higher.

[0032] A processor of a medical imaging apparatus according to an embodiment of the present disclosure is characterized in that it determines the position and shape of at least one contour based on acquired lesion information according to commands stored in a memory.

[0033] A processor of a medical imaging apparatus according to an embodiment of the present disclosure is characterized in that, based on lesion information, it obtains the probability that each pixel in a medical image is included in the region of at least one lesion according to a command stored in a memory, and determines the thickness of at least one contour based on the probability that it is included in the region of at least one lesion.

[0034] An operating method of a medical imaging device according to an embodiment of the present disclosure is characterized by comprising the following steps: acquiring lesion information about at least one lesion detected from a medical image; determining the shape and position of at least one contour corresponding to the at least one lesion based on the acquired lesion information; determining the position of at least one text region including text displaying lesion information about the at least one lesion in the medical image; and displaying the at least one contour and the text included in the at least one text region in the medical image based on the determined shape and position of the at least one contour and the determined position of the at least one text region.

[0035] The step of determining the position of at least one text region according to an embodiment of the present disclosure includes the following steps: determining the position of at least one text region based on at least one of the distance between at least one contour and at least one text region or whether at least one contour and at least one text region overlap.

[0036] The acquisition steps according to an embodiment of this disclosure include the following steps: acquiring lesion information about a plurality of lesions detected from a medical image; determining the shape and position of at least one contour, including the following steps: identifying a portion of the lesions to be displayed in the medical image among the plurality of lesions; and determining the shape and position of at least one contour about the identified portion of the lesions; and determining the position of at least one text region, including the step of determining the position of at least one text region containing lesion information about the identified portion of the lesions.

[0037] The steps for determining a subset of lesions according to an embodiment of the present disclosure include the following steps: identifying lesions with overlapping lesion regions among a plurality of lesions; and identifying a subset of lesions among a plurality of lesions based on at least one of the following: the size of the overlapping regions among the overlapping lesions, the lesion probability of each overlapping lesion, the correlation between the overlapping lesions, or the probability that a subset of the overlapping lesions exists in a medical image.

[0038] The method according to an embodiment of the present disclosure further includes the step of generating at least one arrow pointing to at least one contour. The display step includes the step of displaying the generated at least one arrow in a medical image to connect at least one contour and at least one text region.

[0039] The acquisition step according to an embodiment of this disclosure includes acquiring lesion information about a plurality of lesions detected from a medical image. The step of generating arrows includes generating arrows respectively about the plurality of lesions. The step of displaying the generated arrows in the medical image includes displaying each arrow about the plurality of lesions in the medical image such that the arrows about each of the generated plurality of lesions do not intersect each other.

[0040] The acquisition step according to an embodiment of this disclosure includes acquiring lesion information about a plurality of lesions detected from a medical image. The step of generating arrows includes generating arrows for each of the plurality of lesions. The step of displaying the generated arrows in the medical image includes displaying the arrows for each of the plurality of lesions in the medical image such that the arrows for each generated plurality of lesions and the contours corresponding to each plurality of lesions do not intersect each other.

[0041] The steps of displaying a generated arrow in a medical image according to an embodiment of the present disclosure include the following steps: determining at least one contact point region where the generated arrow contacts at least one contour; and displaying at least one generated arrow so that it connects to at least one contact point region.

[0042] The step of determining at least one contact point region according to an embodiment of the present disclosure includes: determining at least one contact point region based on the distance between the plurality of contact point regions in contact with at least one contour.

[0043] According to an embodiment of the present disclosure, at least one text region includes a plurality of text regions. The step of determining the position of at least one text region includes: determining the position of each of the plurality of text regions based on the distance between the plurality of text regions.

[0044] An electronic device according to an embodiment of the present disclosure includes: a memory storing one or more instructions; and a processor configured to, by executing the stored one or more instructions, acquire lesion information about at least one lesion detected from a medical image, determine the shape and position of a contour corresponding to the at least one lesion based on the acquired lesion information, determine the position of at least one text region including text displaying lesion information about the at least one lesion in the medical image, and display the text including the at least one contour and the at least one text region in the medical image based on the determined shape and position of the at least one contour and the determined at least one text region.

[0045] The processor according to an embodiment of the present disclosure is further configured to determine the position of at least one text region based on at least one of the distance between at least one contour and at least one text region or whether at least one contour and at least one text region overlap.

[0046] The processor according to an embodiment of the present disclosure is further configured to acquire lesion information about a plurality of lesions detected from a medical image, determine a portion of the plurality of lesions to be displayed in the medical image, determine the shape and position of at least one contour of the determined portion of lesions, and determine the position of at least one text region including lesion information about the determined portion of lesions.

[0047] According to an embodiment of the present disclosure, the processor is further configured to identify lesions with overlapping lesion regions among a plurality of lesions, and to determine a portion of the lesions based on at least one of the following: the size of the overlapping regions among the overlapping lesions, the lesion probability of each overlapping lesion, the correlation between the overlapping lesions, or the probability that a portion of the overlapping lesions exists in a medical image.

[0048] The processor according to an embodiment of the present disclosure is further configured to generate at least one arrow pointing to at least one contour, and display the generated at least one arrow in a medical image to connect at least one contour and at least one text region.

[0049] The processor according to an embodiment of the present disclosure is further configured to acquire lesion information about a plurality of lesions detected from a medical image, generate arrows for each of the plurality of lesions, and display the arrows for each of the plurality of lesions in the medical image such that the generated arrows for each of the plurality of lesions do not intersect each other.

[0050] The processor according to an embodiment of the present disclosure is further configured to acquire lesion information about a plurality of lesions detected from a medical image, generate arrows about each of the plurality of lesions, and display the arrows about each of the plurality of lesions in the medical image such that the generated arrows about each of the plurality of lesions and the contours corresponding to each of the plurality of lesions do not intersect each other.

[0051] The processor according to an embodiment of the present disclosure is further configured to determine at least one contact point region where the generated arrow contacts at least one contour, and display the generated arrow so that it connects to at least one contact point region.

[0052] The processor according to an embodiment of the present disclosure is further configured to determine at least one contact point region based on the distance between the plurality of contact point regions in a plurality of contact point regions that are in contact with at least one contour.

[0053] At least one text region according to an embodiment of the present disclosure includes a plurality of text regions, and the processor is further configured to determine the position of each of the plurality of text regions based on the distance between the plurality of text regions.

[0054] Furthermore, the program for implementing the operating method of the medical imaging device as described above can be recorded in a computer-readable recording medium. Attached Figure Description

[0055] Figure 1 This is a diagram illustrating a medical imaging device according to an embodiment of the present disclosure.

[0056] Figure 2 This is a flowchart illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0057] Figure 3 This is a diagram illustrating a medical image according to an embodiment of the present disclosure.

[0058] Figure 4 Pseudocode is shown illustrating an operation method of a medical imaging device according to an embodiment of the present disclosure.

[0059] Figure 5 This is a diagram illustrating a medical image displayed by a medical imaging device according to an embodiment of the present disclosure.

[0060] Figure 6This is a diagram illustrating a medical image displayed by a medical imaging device according to an embodiment of the present disclosure.

[0061] Figure 7 This is a diagram illustrating a medical image displayed by a medical imaging device according to an embodiment of the present disclosure.

[0062] Figure 8 This is a diagram illustrating a medical image displayed by a medical imaging device according to an embodiment of the present disclosure.

[0063] Figure 9 This is a flowchart illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0064] Figure 10 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0065] Figure 11 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0066] Figure 12 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0067] Figure 13 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0068] Figure 14 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0069] Figure 15 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0070] Figure 16 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0071] Figure 17 This is a diagram illustrating a method for obtaining a score according to an embodiment of the present disclosure.

[0072] Figure 18 This is a diagram illustrating a method for obtaining a score according to an embodiment of the present disclosure.

[0073] Figure 19 A medical image illustrating an embodiment of this disclosure is shown.

[0074] Figure 20 A medical image illustrating an embodiment of this disclosure is shown.

[0075] Figure 21 This is a block diagram illustrating the internal structure of an electronic device according to an embodiment of the present disclosure.

[0076] Figure 22 This is a flowchart illustrating an operation method of a medical imaging device according to an embodiment of the present disclosure. Detailed Implementation

[0077] The advantages, features, and methods of implementation of the disclosed embodiments will become clear upon reference to the accompanying drawings and the following embodiments. However, this disclosure is not limited to the embodiments disclosed below, and can be implemented in various different forms. The purpose of providing these embodiments is solely to complete the disclosure and fully inform those skilled in the art of the scope of the invention.

[0078] The terminology used in this specification is briefly described, and the disclosed embodiments are described in detail.

[0079] The terminology used in this specification has been selected as widely used and common as possible, taking into account the functionality of this disclosure. However, these terms may be changed based on the intent of those skilled in the art, case law, or the emergence of new technologies. Furthermore, in certain cases, the applicant has arbitrarily selected certain terms; in such cases, the meanings of the selected terms will be described in detail in the descriptive section of this disclosure. Therefore, the terms used in this disclosure should be defined based on their inherent meanings and the overall content of this specification, and not merely on their names.

[0080] Unless explicitly defined as singular in the context, singular expressions in this specification include plural expressions. Furthermore, unless explicitly defined as plural in the context, plural expressions include singular expressions.

[0081] When a section of the specification "includes" a particular element, it may include other elements, rather than excluding them, unless there is a description to the contrary.

[0082] Furthermore, the term "part" as used in this specification refers to a software or hardware component, and a "part" performs certain functions. However, a "part" is not limited to software or hardware. A "part" can be configured to exist in addressable storage media or to reproduce one or more processors. Thus, as an example, a "part" includes: components such as software components, object-oriented software components, class components, and task components; procedures; functions; properties; procedures; subroutines; program code segments; drivers; firmware; microcode; circuits; data; databases; data structures; tables; arrays; and variables. The functionality provided by components and "parts" can be provided by combining them into fewer components and "parts," or by further separating them into more components and "parts."

[0083] According to one embodiment of this disclosure, a "part" may be implemented with a processor and memory. The term "processor" should be interpreted broadly to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some cases, "processor" may refer to application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), etc. The term "processor" may refer to a combination of processing devices, such as a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors coupled to a DSP core, or any other combination of such configurations.

[0084] The term "memory" should be broadly interpreted to include any electronic component capable of storing electronic information. The term "memory" can refer to various types of processor-readable media, such as Random Access Memory (RAM), Read-Only Memory (ROM), Non-Volatile Random Access Memory (NVRAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash Memory, magnetic or optical data storage devices, registers, etc. If the processor can read information from the memory and / or record information in the memory, the memory is said to be in electronic communication with the processor. Memory integrated into the processor is in electronic communication with the processor.

[0085] The embodiments will now be described in detail with reference to the accompanying drawings, so that those skilled in the art to which this disclosure pertains can readily implement it. Furthermore, for the sake of clarity, parts of the drawings unrelated to the description will be omitted.

[0086] Figure 1 This is a diagram illustrating a medical imaging device according to an embodiment of the present disclosure.

[0087] The medical imaging device 100 may include a control unit 110, a database 120, and an output unit 130. The control unit 110 may include a processor and a memory. The processor can execute instructions stored in the memory.

[0088] Database 120 can store various types of data. For example, database 120 can store at least one of the following: analysis results of medical images or medical personnel, and analysis results of medical analysis devices. Additionally, database 120 may include a medical image analysis model for analyzing medical images. The medical image analysis model can be a rule-based model or a machine learning model.

[0089] The output unit 130 may include at least one of an image output unit and an audio output unit. The output unit 130 may be controlled by the control unit 110. The output unit 130 may output at least one of medical images and analysis results.

[0090] The operation of the medical imaging device 100 will be further explained in detail below.

[0091] Figure 2This is a flowchart illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0092] The medical imaging device 100 can perform step 210 of acquiring lesion information about at least one lesion included in a medical image. The medical image can be an image of a part of a patient's body. The medical image can be an image captured by various medical imaging devices. For example, the medical image can be one of computed tomography (CT), magnetic resonance imaging (MRI), X-ray, mammography, or ultrasonography. Medical images can be received from a database 120. Furthermore, medical images can be received from external devices. For example, medical images can be received from an external medical imaging device that is a device other than the medical imaging device 100.

[0093] Lesion information can be information about lesions included in medical images. Lesion information can be information about lesions detected through automated analysis by medical image analysis equipment. However, it is not limited to this; lesion information can also be the result of analysis performed by medical personnel.

[0094] The medical imaging device 100 can receive lesion information from an external device or from its own database 120. Alternatively, the medical imaging device 100 can acquire lesion information by analyzing medical images using its own analysis tools. These analysis tools can be rule-based models or machine learning models for lesion detection. For example, its own analysis tools may include a medical image analysis model based on machine learning.

[0095] Lesion information may include at least one of the following: lesion type, lesion location, probability of lesion presence on medical imaging, lesion shape, lesion size, and lesion region.

[0096] Information about lesion types can include at least one of the lesion name or lesion classification information. This information can be derived from a diagnosis made by medical personnel or from a diagnosis based on the device's own analytical tools. As mentioned above, medical image analysis devices can extract information about lesion types from medical images based on rule bases or machine learning models.

[0097] The location information of a lesion can indicate at least one location on a medical image where the lesion has the highest probability of existence. The location information can be represented as at least one coordinate value. Specifically, it can be the pixel coordinates of the lesion's position within the medical image. When a lesion occupies a portion of the medical image, its location information can be represented as multiple coordinate values. Additionally, the location information can include the coordinates of a lesion location and the radius of that location. However, it is not limited to these methods; the location information can be represented in various ways.

[0098] The probability information of a lesion's presence in a medical image represents the probability, based on the medical image, that the lesion exists in a part of the patient's body corresponding to the medical image. Medical image analysis devices can detect lesions present in medical images using rule bases or machine learning models. Alternatively, the medical image analysis device can predict the probability of a lesion's presence in a medical image based on rule bases or machine learning models. The probability information of a lesion's presence in a medical image can include probability values ​​corresponding to each pixel included in the medical image. The probability information of a lesion's presence in a medical image can also include probability values ​​corresponding to a specific region of the medical image. This specific region, as a region included in the medical image, can be smaller than or equal to the area of ​​the medical image. The probability values ​​corresponding to specific regions of the medical image can be obtained through the medical image analysis device or received by medical personnel.

[0099] Furthermore, the medical imaging device 100 can determine a probability value corresponding to a specific region based on the probability values ​​corresponding to pixels included in that region. For example, the medical imaging device 100 can use the maximum, average, median, or minimum probability values ​​of the pixels included in the specific region to obtain a representative probability value corresponding to that specific region. Medical personnel can reduce the probability of misdiagnosis by making diagnoses based on probability information.

[0100] The shape information of a lesion can represent information related to the shape of the lesion. This information can be related to the shape of the lesion's outline. The shape of a lesion can be circular, elliptical, or atypical. The shape information of a lesion can be determined by medical personnel's diagnosis. Alternatively, medical image analysis devices can acquire lesion shape information based on rule bases or machine learning models.

[0101] The size information of a lesion refers to the extent of the lesion, which can be the number of pixels encompassed by the lesion region in a medical image. Additionally, the size information can be the horizontal or vertical length of the lesion in the medical image. Furthermore, the size information can be the area of ​​the lesion region in the medical image. The size information can also represent the number of pixels included within the lesion region. Additionally, the size information can represent the radius. That is, the lesion region can be represented by the inner region of a circle based on the lesion's center point and radius.

[0102] The lesion region information can represent an area in a medical image where the lesion has a high probability of being present. The medical imaging device 100 can receive lesion region information from medical personnel. Alternatively, the medical imaging device 100 can automatically acquire lesion region information based on a rule base or machine learning model. The medical imaging device 100 can calculate the probability of a lesion's presence for each pixel in the medical image. Alternatively, the medical imaging device 100 can calculate the probability of a lesion's presence for a group of pixels. For example, a group of pixels can include multiple pixels. A group of pixels can represent a certain area in the medical image. The medical imaging device 100 can calculate the probability of a lesion's presence for a group of pixels. When the probability of a lesion existing in a pixel is above a threshold value, the medical imaging device 100 can determine that the pixel is included in the lesion region. That is, the probability of a lesion existing in the pixels included in the lesion region can be above a threshold value. The threshold value can be preset information.

[0103] The medical imaging device 100 can perform step 220, based on the acquired lesion information, to generate at least one contour corresponding to at least one lesion in the medical image.

[0104] A contour can represent either the location or the shape of a lesion. Relative to a medical image, the medical imaging device 100 can represent at least one lesion. Multiple lesions can have different locations and shapes. The medical imaging device 100 can acquire the location and shape of at least one lesion based on lesion information. The medical imaging device 100 can generate a contour by reflecting the location and shape of each lesion. That is, the medical imaging device 100 can determine the location and shape of at least one contour based on the acquired lesion information. Specifically, the location of the contour can be determined based on the location of the lesion included in the lesion information of the medical imaging device 100. Furthermore, the medical imaging device 100 can determine the shape of the contour based on the shape of the lesion included in the lesion information.

[0105] The position of the contour can correspond to the position information of the lesion included in the lesion information. The medical imaging device 100 can determine the shape of the contour based on the lesion information. The medical imaging device 100 can determine the contour through the following process.

[0106] More specifically, the medical imaging device 100 can determine a contour based on the outline of the lesion region included in the lesion information. As described above, when the probability of a lesion existing in a pixel is above a critical value, the medical imaging device 100 can determine that the pixel is included in the lesion region. That is, the probability of a lesion existing in a pixel within the lesion region can be above a critical value. The medical imaging device 100 can determine the outline of the lesion region included in the lesion information as the contour. The contour can surround the lesion region.

[0107] Furthermore, the medical imaging device 100 can acquire a contour including the lesion by enlarging the contour line of the lesion region by a factor of A. A can be a real number greater than 1. That is, the contour can be greater than or equal to the lesion region. Enlarging the contour line of the lesion region by a factor of A may mean that the horizontal length of the lesion region becomes A times its vertical length. Therefore, the area inside the contour can be A times the area of ​​the lesion region. 2 times.

[0108] Furthermore, the medical imaging device 100 can define a polygon, ellipse, or circle that includes a lesion region, which is included in lesion information. According to this disclosure, medical personnel can focus on observing the area surrounding the contour, which is part of a medical image, and can ultimately easily determine whether a lesion exists within the contour.

[0109] The shape of the contour may also include the thickness of the contour lines. The medical imaging device 100 can obtain the thickness of the contour lines based on lesion information. For example, the medical imaging device 100 can obtain the probability that each pixel in the medical image is included in at least one lesion region based on the lesion information. Additionally, the medical imaging device 100 can determine the thickness of at least one contour, where the pixel is included within the contour, based on the probability that the pixel is included in at least one lesion region. For example, the thickness of the contour may increase as the probability increases.

[0110] The medical imaging device 100 can acquire the probability that each pixel in a medical image is included in a lesion. Furthermore, the medical imaging device 100 can define a contour as a combination of pixels whose probability of being included in a lesion equals a threshold value. Since the probability of being included in a lesion is discontinuous, there may not be a value identical to the threshold value. In this case, when one of two adjacent pixels has a probability greater than the threshold value and the other has a probability less than the threshold value, one of the two adjacent pixels can be included in the contour. The probability that pixels inside the contour are included in the lesion region may be greater than the threshold value. Here, the threshold value can be a preset value.

[0111] Furthermore, the medical imaging device 100 can define a contour as a combination of pixels whose probability of being included in a lesion falls within a critical range. The critical range is so narrow that the pixel group appears as a line. Pixels within the contour may have a probability greater than the minimum value of the critical range if they are included in the lesion region. Here, the critical range can be a preset range.

[0112] So far, the structure of the medical imaging device 100 that generates one contour for a single lesion has been described. When multiple lesions exist in a medical image, the medical imaging device 100 can generate multiple contours corresponding to the multiple lesions. This will be discussed in conjunction with... Figure 3 Please provide an explanation.

[0113] Figure 3 This is a diagram illustrating a medical image according to an embodiment of the present disclosure.

[0114] Additionally, the medical imaging device 100 can generate at least one contour for a lesion included in a medical image. The medical imaging device 100 can generate at least one contour, such as a contour line, for a lesion. The probability that pixels within a line are included in the lesion region can be greater than a threshold value, and the line is one of a plurality of lines included in the contour lines.

[0115] Reference Figure 3 The medical image may include a first contour line 311 and a second contour line 312 representing a lesion. The probability that pixels within the inner region of the first contour line 311 are included in the lesion region is greater than or equal to a first threshold. The probability that pixels within the inner region of the second contour line 312 are included in the lesion region is greater than or equal to a second threshold. The probability that pixels within the inner region of the second contour line 312 and the outer region of the first contour line 311 are included in the lesion region is less than the first threshold but greater than or equal to the second threshold. Here, the first and second thresholds can be preset values. The first threshold can be greater than the second threshold.

[0116] The higher the probability that pixels inside a contour line are included in a lesion area, the thicker the contour line generated by the medical imaging device 100 can be. For example, pixels included in the inner region of the first contour line 311 are likely to be included in a lesion area. However, pixels included between the first contour line 311 and the second contour line 312 are likely to be included in a lesion area relatively less likely. Therefore, the medical imaging device 100 can display the first contour line 311 as thicker than the second contour line 312.

[0117] The medical imaging device 100 can generate contour lines of different colors based on the probability that pixels within the contour lines are included in the lesion area. For example, pixels within the inner region of the first contour line 311 may have a high probability of being included in the lesion area. However, pixels between the first contour line 311 and the second contour line 312 may have a relatively low probability of being included in the lesion area. Therefore, the medical imaging device 100 can display the first contour line 311 in red and the second contour line 312 in orange.

[0118] The medical imaging device 100 can represent areas between contour lines with different colors based on the probability that pixels inside the contour lines are included in the lesion area. For example, pixels within the area of ​​the first contour line 311 may have a high probability of being included in the lesion area. However, pixels between the first contour line 311 and the second contour line 312 may have a relatively low probability of being included in the lesion area. Therefore, the medical imaging device 100 can fill the area inside the first contour line 311 with red and fill the area between the second contour line 312 and the first contour line 311 with orange. The medical imaging device 100 can adjust the transparency so that the original medical image is not covered by the fill color.

[0119] The probability that a pixel is included in a lesion area can fall within a specific critical range, where the pixel is included in one of a plurality of lines encompassed by the contour lines. This specific critical range can be a preset range. (See reference...) Figure 3 The probability that pixels included by the first contour line 311 are located within the lesion region can be included within a first critical range. Additionally, the probability that pixels included by the second contour line 312 are located within the lesion region can be included within a second critical range. The minimum value of the first critical range can be greater than the maximum value of the second critical range.

[0120] Furthermore, the medical imaging device 100 can generate multiple contours by enlarging the outline of the lesion area included in the lesion information. For example, the first contour line 311 can be the outline of the lesion area. The medical imaging device 100 can obtain a second contour line 312 by enlarging the first contour line 311. The thickness of the second contour line 312 can be thinner than that of the first contour line 311.

[0121] The medical imaging device 100 can perform step 230 of outputting at least one contour generated in the medical image. The output unit 130 can output the medical image and at least one contour.

[0122] The medical imaging device 100 can perform the following steps to generate at least one contour.

[0123] The medical imaging device 100 can perform the step of generating a contour based on at least one of the acquired lesion information, information related to lesion areas that repeat among multiple lesions included in the medical image, or information related to the correlation between multiple lesions.

[0124] Medical imaging can detect multiple lesions. Lesion information can be obtained separately for each lesion. As mentioned above, lesion information can include lesion region information.

[0125] The medical imaging device 100 can acquire information related to overlapping lesion areas among multiple lesions based on lesion information. Additionally, the medical imaging device 100 can acquire information related to the correlation between multiple lesions.

[0126] Information related to the correlation between multiple lesions indicates whether there is a medical correlation between them. For example, information related to correlation may include information about coexistence, where coexistence indicates whether multiple lesions can coexist in the same patient. For example, if the first lesion cannot coexist with the second lesion, there is no coexistence; if the first lesion can coexist with the second lesion, there is coexistence.

[0127] Additionally, information related to relevance may include information about similarity, where similarity indicates the high probability of multiple lesions presenting simultaneously. Multiple lesions may have different names but actually be similar. For example, similarity exists when a first lesion presents and a second lesion also presents. The fact that the second lesion presents when the first lesion presents may not mean that the first lesion will present when the second lesion presents. However, it is not limited to this; the fact that the second lesion presents when the first lesion presents may mean that the first lesion will present when the second lesion presents.

[0128] Furthermore, since the manifestations of the first lesion and the second lesion are independent, if the manifestations of the first lesion have no effect on the manifestations of the second lesion, then the first and second lesions are not similar.

[0129] The medical imaging device 100 can acquire relevant information based on a rule base or machine learning model. The medical imaging device 100 can also acquire relevant information based on a database 120. The medical imaging device 100 can acquire first lesion information about a first lesion. Furthermore, the medical imaging device 100 can acquire second lesion information about a second lesion. The medical imaging device 100 can acquire a first lesion identifier from the first lesion information, including at least one of the first lesion's code, name, and type. Additionally, the medical imaging device 100 can acquire a second lesion identifier from the second lesion information, including at least one of the second lesion's code, name, and type. The medical imaging device 100 can acquire relevant information about the first and second lesions from the database based on the first and second lesion identifiers. For example, the database can pre-store relevant information based on the first and second lesion identifiers. The medical imaging device 100 can derive relevant information from the database, corresponding to the first and second identifiers.

[0130] The medical imaging device 100 can obtain correlation-related information from sources other than the database 120. The medical imaging device 100 can obtain correlation-related information by applying first lesion information and second lesion information to a machine learning model. The machine learning model can be a model that performs machine learning on the correlation between the first lesion and the second lesion. The medical imaging device 100 can obtain correlation-related information from medical personnel. Furthermore, the medical imaging device 100 can obtain correlation-related information from lesion information.

[0131] The information about the first lesion related to the first lesion may include information about lesions that are similar to the first lesion and information about lesions that coexist with the first lesion. The medical imaging device 100 can determine whether a second lesion is similar to or coexists with the first lesion based on the information about the first lesion.

[0132] The medical imaging device 100 can acquire correlation-related information based on input signals from medical personnel. Additionally, the medical imaging device 100 can acquire correlation-related information from external devices.

[0133] In order to generate at least one contour, the medical imaging device 100 may perform the step of determining the size of the overlapping area of ​​the region of the first lesion and the region of the second lesion based on first lesion information and second lesion information included in a plurality of lesions.

[0134] As described above, the medical imaging device 100 can acquire first lesion information about a first lesion and second lesion information about a second lesion. The medical imaging device 100 can acquire region information of the first lesion in a medical image from the first lesion information and region information of the second lesion in a medical image from the second lesion information. Furthermore, the medical imaging device 100 can determine the size of the overlapping region between the first lesion region and the second lesion region. The size of the overlapping region can be represented by at least one of the following: the number of pixels in the overlapping region, the area of ​​the overlapping region, the horizontal length of the overlapping region, or the vertical length of the overlapping region.

[0135] Here, the regions of the first lesion and the regions of the second lesion can simply refer to the regions of the first lesion and the regions of the second lesion, but are not limited to this. The region of the first lesion can also mean the internal region of the first contour corresponding to the first lesion. In addition, the region of the second lesion can also mean the internal region of the second contour corresponding to the second lesion.

[0136] The medical imaging device 100 can perform a step of determining information related to the probability of a second lesion existing in a medical image based on second lesion information. As described above, the information related to the probability of a second lesion existing in the medical image can be a probability value corresponding to each pixel value included in the medical image or a probability value corresponding to a specific region included in the medical image. Here, the specific region may correspond to a generated contour.

[0137] Furthermore, when the size of the repetitive region is greater than a first threshold and the information related to the probability of a second lesion existing in the medical image is less than a second threshold, the medical imaging device 100 may perform the step of generating at least one contour around the first lesion. The first and second thresholds may be preset values. The second threshold may be information related to the probability of the first lesion existing in the medical image, but is not limited to this.

[0138] The contour may be greater than or equal to the area of ​​the first lesion. Since the method for generating at least one contour around the first lesion has already been described, repeated descriptions will be omitted.

[0139] When the size of the overlapping region is greater than a first threshold and the information related to the probability of a second lesion being present in the medical image is less than a second threshold, the medical imaging device 100 generates only at least one contour around the first lesion and may not generate at least one contour around the second lesion. This is because the size of the overlapping region is greater than the first threshold, so the first and second lesions overlap considerably, and the information related to the probability of the second lesion being present in the medical image is less than the second threshold, therefore the importance of the second lesion in the medical image may be relatively low.

[0140] To generate at least one contour, the medical imaging device 100 may perform the step of determining whether there is a pathological similarity between a first lesion and a second lesion. The existence of similarity may be included in information related to relevance. Since the information regarding the existence of similarity has already been described, repeated descriptions will be omitted. Furthermore, regarding the existence of similarity, the medical imaging device 100 may determine it based on a database via a rule base, or obtain it from a machine learning model, or receive it from medical personnel, or obtain it from lesion information. Since the process of obtaining information related to relevance has already been described, repeated descriptions will be omitted.

[0141] The medical imaging device 100 can perform the step of determining whether a first lesion and a second lesion coexist in the same area. Since information regarding coexistence has already been described, repeated descriptions will be omitted. Furthermore, regarding the existence of coexistence, the medical imaging device 100 can determine it based on a database using a rule base, or by obtaining it from a machine learning model, or from information received from medical personnel, or from lesion information. Since the process of obtaining information related to correlation has already been described, repeated descriptions will be omitted.

[0142] When the existence of similarity indicates that the first lesion and the second lesion are similar, or the existence of coexistence indicates that the first lesion and the second lesion cannot coexist, the medical imaging device 100 may perform the step of generating at least one contour around the first lesion, but not generating at least one contour around the second lesion.

[0143] When the presence of similarity indicates that the first lesion and the second lesion are similar, the medical imaging device 100 can generate at least one contour surrounding only the first lesion. This is because the presence of similarity implies that when the first lesion manifests, the second lesion may also manifest. When the presence of similarity indicates that the first lesion and the second lesion are dissimilar, the medical imaging device 100 can generate both at least one contour corresponding to the first lesion and at least one contour corresponding to the second lesion.

[0144] Furthermore, when coexistence is indicated by the inability of the first lesion and the second lesion to coexist, the medical imaging device 100 may generate at least one contour surrounding only one of the first or second lesions. The medical imaging device 100 may compare the probabilities of the first and second lesions existing in the medical image to determine which lesion's contour to generate. Additionally, when the probability of the first lesion existing in the medical image is greater than that of the second lesion, the medical imaging device 100 may generate at least one contour surrounding the first lesion. The medical imaging device 100 may not generate at least one contour surrounding the second lesion. Conversely, when the probability of the first lesion existing in the medical image is lower than that of the second lesion, the medical imaging device 100 may generate at least one contour surrounding the second lesion. The medical imaging device 100 may not generate at least one contour surrounding the first lesion.

[0145] The medical imaging device 100 can also perform the step of arranging multiple lesion information in order of their high probability of existence in a medical image. By arranging multiple lesion information in order of their high probability of existence in a medical image, the medical imaging device 100 can avoid outputting the contour corresponding to the lesion with a low probability of existence when there is no coexistence between two lesions.

[0146] In addition, when the existence of coexistence is expressed as the first lesion and the second lesion being able to coexist, the medical imaging device 100 can generate at least one contour corresponding to the first lesion and at least one contour corresponding to the second lesion.

[0147] Figure 4 Pseudocode illustrating an operation method of a medical imaging device according to an embodiment of this disclosure.

[0148] In online 410, C can represent the set of contours corresponding to multiple detected lesions. C can include a total of M elements. That is, it can be C = {c1, c2, ..., cM}.

[0149] The medical imaging device 100 can execute a for statement as the index i increases from 1 to M-1. In line 420, R(i) is a function that arranges the contour elements in set C in order of their probability of existence in the medical image. That is, R(1) can output at least one contour of the lesion with the highest probability of existence in the medical image. In addition, R(M-1) can output at least one contour of the lesion with the lowest probability of existence in the medical image. The medical imaging device 100 can assign the contour corresponding to the lesion with the i-th highest probability to cp using R(i). The medical imaging device 100 can assign the contour of the lesion with the lowest probability of existence in the medical image to cp using R(i).

[0150] In online 430, D(cp) is a function that outputs lesion information corresponding to the contour cp. The medical imaging device 100 can assign lesion information corresponding to cp to dp through D(cp).

[0151] The medical imaging device 100 can execute a for loop by incrementing index j from 2 to M. Figure 4 In this context, index j starts from 2 and increases, but is not limited to this. Index j can increase from i+1 to M.

[0152] In online 440, R(j) is a function that arranges the contour elements in set C in order of their highest probability of existence in the medical image. The medical imaging device 100 can use R(j) to assign the contour corresponding to the j-th highest probability lesion to cq.

[0153] In line 450, D(cq) is a function that outputs lesion information corresponding to contour cq. The medical imaging device 100 can assign lesion information corresponding to cq to dq via D(cq).

[0154] In the online 460, IoU(cp, cq) can represent the size of the overlapping region of contours cp and cq. Additionally, S(cq) can represent the probability that pixels within contour cq are included in the lesion region.

[0155] In line 460, when the size of the overlapping region of contours cp and cq is greater than the critical value MTdq, and the probability that the pixels inside contour cq are included in the lesion region is less than the critical value STdq, the medical imaging device 100 can execute line 470.

[0156] In online function 470, Sim(dp, dq) outputs information about whether there is similarity between lesion information dp and lesion information dq. When Sim(dp, dq) is 1, it indicates that there is similarity between lesion information dp and lesion information dq. Conversely, when Sim(dp, dq) is 0, it indicates that there is no similarity between lesion information dp and lesion information dq.

[0157] The `CoOcc(dp, dq)` function outputs information about whether lesion information `dp` and lesion information `dq` coexist. When `CoOcc(dp, dq)` is 1, it indicates that lesion information `dp` and lesion information `dq` coexist. Conversely, when `CoOcc(dp, dq)` is 0, it indicates that lesion information `dp` and lesion information `dq` do not coexist.

[0158] In line 470, when there is similarity between lesion information dp and lesion information dq, and there is no coexistence between lesion information dp and lesion information dq, the medical imaging device 100 can execute line 480.

[0159] When the above conditions are met, the medical imaging device 100 can remove the contour cq from set C. That is, when the size of the overlapping region of contours cp and cq is greater than the threshold value MTdq, the probability that the internal pixels of contour cq are included in the lesion region is less than the threshold value STdq, and there is similarity between lesion information dp and lesion information dq, but no coexistence between lesion information dp and lesion information dq, the medical imaging device 100 can remove the contour cq from set C. The medical imaging device 100 can output the contours included in set C to the output unit 130. That is, the medical imaging device 100 may not output the contour cq.

[0160] Figures 5 to 8 This is a diagram illustrating a medical image displayed by a medical imaging device according to an embodiment of the present disclosure.

[0161] The medical imaging device 100 can display arrows or text near the outline. The text may include content related to the outline. Figures 5 to 8 This is an example showing the configuration of arrows or text located near an outline. (See reference) Figures 5 to 8 The medical imaging device 100 can be configured with arrows and text so that users can clearly understand the meaning of the outline representation.

[0162] Reference Figure 5 The medical imaging device 100 can output medical images and outlines simultaneously. Additionally, the medical imaging device 100 can display arrows and text near the outlines. Arrows can connect the outlines and text. Furthermore, the text can describe lesions included within the outlines. The medical imaging device 100 can acquire text based on lesion information.

[0163] Medical image 510 shows an example of incorrect arrow and text display. Reference box 511 shows multiple texts displayed repeatedly. Additionally, reference box 511 shows at least a portion of multiple arrows intersecting. Therefore, medical personnel may have difficulty confirming the content of the text.

[0164] Medical image 520 shows a medical image normally displayed by the medical imaging device 100 according to the present disclosure. Referring to frame 521, the arrows included in medical image 520 do not intersect each other. Furthermore, the text is not repeated. Therefore, medical personnel can clearly understand the meaning represented by the outlines.

[0165] Reference Figure 6 Medical image 610 shows an example of incorrect arrow and text display. Referring to box 611, the arrow crosses a contour. When an arrow crosses a contour, the arrow may be long, and the distance between the contour the arrow points to and the text may be large. Therefore, medical personnel may have difficulty identifying which contour the text refers to.

[0166] Medical image 620 shows a medical image normally displayed by the medical imaging device 100 according to the present disclosure. Reference frame 621 shows that arrows included in medical image 620 do not cross the outline. Therefore, medical personnel can clearly understand the meaning represented by the outline.

[0167] Reference Figure 7 Medical image 710 shows an example of incorrect arrow and text display. Referring to box 711, the arrow and text are displayed above the outline. When the arrow and text are displayed above the outline, the text readability is reduced. Therefore, medical personnel may have difficulty confirming the content of the text.

[0168] Medical image 720 shows a medical image normally displayed by the medical imaging device 100 according to the present disclosure. Reference frame 721 shows that arrows and text included in medical image 720 are not displayed above the outlines. Therefore, medical personnel can clearly understand the meaning represented by the outlines.

[0169] Reference Figure 8 Medical image 810 shows an example of incorrect arrow and text display. Referring to box 811, the arrow is displayed above the intersection of two contours. When an arrow is displayed above the intersection of two contours, it can be difficult to determine which contour it points to. Therefore, medical personnel may have difficulty identifying the text corresponding to the contour.

[0170] Medical image 820 shows a medical image normally displayed by the medical imaging device 100 according to the present disclosure. Referring to frame 821, the arrow included in medical image 820 is not displayed at the intersection of two contours. Therefore, medical personnel can clearly understand the text corresponding to the contours.

[0171] Figure 9 This is a flowchart illustrating the operation of a medical imaging device according to an embodiment of the present disclosure. Additionally, Figures 10 to 13 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0172] In order to output at least one contour, the medical imaging device 100 may perform step 910 of determining first candidate arrow information about a plurality of first candidate arrows, the plurality of first candidate arrows pointing to a first contour in at least one contour.

[0173] Candidate arrow information may include at least one of the following: information about the position of the arrow's starting point, information about the position of the arrow's ending point, information about the arrow's direction, and information about the arrow's length.

[0174] Reference Figure 10In the upper left figure, the medical imaging device 100 can acquire a plurality of first candidate arrows 1021, 1022, 1023 pointing to a first contour 1010 in at least one contour. The plurality of first candidate arrows 1021, 1022, 1023 may be substantially perpendicular to the first contour 1010. The plurality of first candidate arrows 1021, 1022, 1023 may include a starting point and an ending point. In this disclosure, the starting point of an arrow may refer to the point on the arrow closest to the contour. In this disclosure, the ending point may refer to the other end of the arrow on the starting point. The starting point of an arrow may be the head of the arrow, but is not limited thereto; the ending point of an arrow may be the head of the arrow.

[0175] The starting points of multiple first candidate arrows 1021, 1022, and 1023 can be randomly determined on contour 1010. Furthermore, the number of first candidate arrows 1021, 1022, and 1023 can be a preset number. Figure 10 In this document, no reference numerals are assigned to all the multiple candidate arrows, but the number of candidate arrows 1021, 1022, and 1023 can be up to 10. The lengths of the candidate arrows 1021, 1022, and 1023 can be preset. Furthermore, the lengths of the candidate arrows 1021, 1022, and 1023 can be randomly determined within a preset range.

[0176] Reference Figure 11 The medical imaging device 100 can acquire a plurality of first candidate arrows 1121, 1122, and 1123 pointing to a first contour 1110 in at least one contour. Text boxes 1131, 1132, and 1133 can be located at the ends of the plurality of first candidate arrows 1121, 1122, and 1123. Text can be displayed in the text boxes 1131, 1132, and 1133. The plurality of first candidate arrows 1121, 1122, and 1123 and the text boxes 1131, 1132, and 1133 can correspond one-to-one.

[0177] The positions of multiple first candidate arrows 1121, 1122, 1123 and text boxes 1131, 1132, 1133 can be determined according to a preset method. The positions of the text boxes 1131, 1132, 1133 can be set based on the directions of the multiple first candidate arrows 1121, 1122, 1123. Furthermore, the medical imaging device 100 can set the positions of the text boxes so that one of the multiple first candidate arrows 1121, 1122, 1123 is located at a corner or side of the text box. For example, when the starting point of the first candidate arrow 1121 is located at the upper left of its end, the upper left vertex of the text box 1131 can be close to the end of the first candidate arrow 1121. Similarly, when the starting point of the first candidate arrow 1122 is located at the left side of its end, the left side of the text box 1132 can be close to the end of the first candidate arrow 1122. Since in Figure 11The relationship between the arrows and the text has been explained, so further explanation will be omitted.

[0178] Figure 11 The positional relationship between the candidate arrow and the text box shown is one example. In addition, there may be various other positional relationships between the candidate arrow and the text box.

[0179] The head of the candidate arrow 1160 can be located at the end. That is, the starting point of the candidate arrow 1160 can be close to or touch the outline 1150, and the end of the candidate arrow 1160 can be close to or touch the corner or edge of the text area 1170 (e.g., a box-shaped text area, etc.).

[0180] Refer again Figure 9 The medical imaging device 100 can perform step 920, which defines an arrow-text region 1030 outside the first contour 1010.

[0181] Reference Figure 10 In the upper right image, the arrow-text area 1030 can be an area that includes the end of the arrow and a portion of the text box. Within the arrow-text area 1030, the end of the arrow and the text box can be adjacent.

[0182] Reference Figure 12 The medical imaging device 100 can generate a contour 1210. The medical imaging device 100 can generate a first enlarged contour 1221 by enlarging the contour 1210. Additionally, the medical imaging device 100 can generate a second enlarged contour 1222 by enlarging the contour 1210. The second enlarged contour 1222 may include the first enlarged contour 1221. The medical imaging device 100 can use the contour 1210 at a preset multiple to obtain the first enlarged contour 1221 and the second enlarged contour 1222. The medical imaging device 100 can define an arrow-text region 1230 between the first enlarged contour 1221 and the second enlarged contour 1222. The arrow-text region 1230 may not contact the first contour 1210 and is a circle surrounding the first contour 1210.

[0183] When the ends of the plurality of first candidate arrows generated in step 910 are not included in the arrow-text area 1030, the medical imaging device 100 may adjust the start or end of the plurality of first candidate arrows so that the ends of the plurality of first candidate arrows are included in the arrow-text area 1030.

[0184] Refer again Figure 9The medical imaging device 100 can perform step 930 of determining a contact point region in an arrow-text area where one side of a text box intersects with one end of a plurality of first candidate arrows, wherein the text box corresponds to the plurality of first candidate arrows and displays lesion information about a first contour, the plurality of first candidate arrows being included in the first candidate arrow information. Here, "side" can refer to a corner or edge of the text box. Additionally, "one end" can be the starting point or ending point of a candidate arrow.

[0185] Reference Figure 10 As shown in the lower left figure, the medical imaging device 100 can determine the text to be placed in the text box based on lesion information. Additionally, the medical imaging device 100 can determine the size of the text box based on the font and content of the text. The medical imaging device 100 can arrange text boxes at the ends of multiple first candidate arrows 1041, 1042, and 1043.

[0186] The text content may include at least one of the following: information about the type of lesion, the probability of the lesion being present in the medical image, the shape of the lesion, the size of the lesion, and the probability of the lesion being present in a unit area of ​​the medical image.

[0187] The medical imaging device 100 can determine information about the text box. This information may include the text box's size, height, width, or position.

[0188] The medical imaging device 100 can determine the position of the text box based on information about the arrow. For example, the medical imaging device 100 can position a corner or side of the text box within a predetermined distance from the end of the arrow.

[0189] The medical imaging device 100 can determine whether text boxes corresponding to a plurality of first candidate arrows 1041, 1042, and 1043 can be located within a medical image. Additionally, the medical imaging device 100 can define a contact point region within the arrow-text region 1070 where the text box can be located within the medical image. For example, a portion of the text box corresponding to the first candidate arrow 1041 may be located outside the medical image 1050. The medical imaging device 100 can determine the contact point region by removing the area containing the first candidate arrow 1041 from the arrow-text region 1070.

[0190] Additionally, the medical imaging device 100 can determine whether the text boxes corresponding to the plurality of first candidate arrows 1041, 1042, and 1043 overlap with a target object. Furthermore, the medical imaging device 100 can define the area preventing the text boxes from overlapping with the target object as the contact point area. Here, the target object can include at least one of an outline, other text boxes, or other arrows. For example, a portion of the text box corresponding to the first candidate arrow 1042 may overlap with other outlines 1060. The medical imaging device 100 can determine the contact point area by removing the area where the first candidate arrow 1042 exists from the arrow-text area 1070.

[0191] When the text box corresponding to the first candidate arrow 1043 is located in the medical image and does not overlap with the target object, the medical imaging device 100 can obtain the contact point area by using the area including the end of the first candidate arrow 1040.

[0192] Reference Figure 10 As shown in the lower right figure, through the process described above, the medical imaging device 100 can acquire a portion of the arrow-text area 1070 as the contact point area 1080. The medical imaging device 100 can select multiple candidate arrows whose ends are included in the contact point area. Additionally, at least one arrow kit can be generated using the selected candidate arrows.

[0193] Refer again Figure 9 The medical imaging device 100 can perform step 940 of generating a text box about a first contour and at least one arrow kit about the displayable position of the arrow based on the determined contact point area.

[0194] Reference Figure 13 The medical image may include multiple contours 1310, 1320, and 1330. The medical imaging device 100 may, based on steps 910 to 930, determine contact point regions for each of the multiple contours 1310, 1320, and 1330. Additionally, the medical imaging device 100 may determine multiple candidate arrows for each of the multiple contours 1310, 1320, and 1330. The medical imaging device 100 may select multiple candidate arrows whose ends are included in the contact point regions. Furthermore, the medical imaging device 100 may remove candidate arrows whose ends are not included in the contact point regions.

[0195] The medical imaging device 100 can generate an arrow kit by selecting one candidate arrow from a plurality of candidate arrows, at least a portion of which is included in the contact point area, for each contour. That is, the medical imaging device 100 can select one from a plurality of candidate arrows corresponding to a contour to generate an arrow kit.

[0196] For example, refer to Figure 13In the first group (SET 1), the medical imaging device 100 can select arrow 1-1 1311 from a plurality of candidate arrows regarding the first contour 1310. Additionally, referring to the first group, the medical imaging device 100 can select arrow 2-1 1321 from a plurality of candidate arrows regarding the second contour 1320. Furthermore, referring to the first group, the medical imaging device 100 can select arrow 3-1 1331 from a plurality of candidate arrows regarding the third contour 1330. Arrows 1-1 1311, 2-1 1321, and 3-1 1331 can be included in the first group.

[0197] Reference Figure 13 In the second group, the medical imaging device 100 can select arrow 1-2 1312 from a plurality of candidate arrows regarding the first contour 1310. Additionally, referring to the second group, the medical imaging device 100 can select arrow 2-2 1322 from a plurality of candidate arrows regarding the second contour 1320. Furthermore, referring to the second group, the medical imaging device 100 can select arrow 3-2 1332 from a plurality of candidate arrows regarding the third contour 1330. Arrows 1-2 1312, 2-2 1322, and 3-2 1332 can be included in the second group.

[0198] The medical imaging device 100 can generate a preset number of kits. The medical imaging device 100 can randomly select arrows to be included in the kits from multiple candidate arrows. The medical imaging device 100 can position text boxes at the ends of the arrows according to a preset method. The medical imaging device 100 can include arrow information within the arrow kits. That is, the medical imaging device 100 can include and store arrow information corresponding to multiple contours in the arrow kits.

[0199] At least one arrow kit may include at least one of the following: arrow information or text box information. As mentioned above, the information about the text box may include the size, height, width, or position of the text box, etc.

[0200] Refer again Figure 9 The medical imaging device 100 can perform step 950 of obtaining scores for at least one arrow set. The score indicates the degree to which a medical professional can comfortably view at least one of the medical images, outlines, arrows, and text. A higher score indicates that the medical professional can comfortably view at least one of the medical images, outlines, arrows, and text. (The sentence about obtaining scores is incomplete and requires further context.) Figure 17 and 18 The steps for obtaining scores will be explained in more detail.

[0201] The medical imaging device 100 can perform step 960 of selecting an arrow kit from at least one arrow kit based on the acquired score. The medical imaging device 100 can select the arrow kit with the highest score. For example, in... Figure 13 In the process, when the score of the first group is the highest among the first and second groups, the medical imaging device 100 may select the first group. Additionally, even if it is the arrow kit with the highest score, the medical imaging device 100 may not select that arrow kit if the arrows in the arrow kit intersect each other.

[0202] When a first arrow corresponding to a first contour and a second arrow corresponding to a second contour intersect in an arrow kit, the medical imaging device 100 may not select that arrow kit. Alternatively, when a first arrow corresponding to a first contour and a second arrow corresponding to a second contour intersect in an arrow kit, the medical imaging device 100 may remove it from at least one arrow kit.

[0203] Refer again Figure 9 The medical imaging device 100 can perform step 950, based on a selected arrow kit, outputting arrows and text in a text box along with at least one outline. The medical imaging device 100 can output the arrows based on multiple arrow information included in the selected arrow kit. Additionally, the medical imaging device 100 can determine the content of the text based on lesion information. Furthermore, the medical imaging device 100 can arrange the text box adjacent to the arrows using a preset method. Additionally, the medical imaging device 100 can display text within the text box. The text box may not be displayed.

[0204] For example, in Figure 13 When the medical imaging device 100 selects the first group, the medical imaging device 100 can output medical images 1300, multiple outlines 1310, 1320, 1330, multiple arrows 1311, 1321, 1331 and text together with the first group.

[0205] Figure 14 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0206] The medical imaging device 100 can perform the following process to determine first candidate arrow information. The following steps can be compared with… Figure 9 One of steps 910 to 940 is executed together.

[0207] When a first text box about a first contour and a second text box or second contour about a second contour overlap, the medical imaging device 100 can perform the step of obtaining modified first candidate arrow information by moving the start point or end point of a candidate arrow included in the first candidate arrow information so that the first text box does not overlap with the second text box or second contour.

[0208] Referring to medical image 1410, medical imaging device 100 can determine that a first text box 1411 about a first contour overlaps with a second text box 1412 about a second contour. Medical imaging device 100 can obtain modified first candidate arrow information by moving the start or end point of a candidate arrow 1413 included in the first candidate arrow information so that the first text box 1411 does not overlap with the second text box 1412. For example, medical imaging device 100 can move the candidate arrow 1413 accordingly based on the degree of overlap between the first text box 1411 and the second text box 1412.

[0209] Medical image 1420 displays candidate arrow 1423 based on modified first candidate arrow information. Medical imaging device 100 can acquire a first text box 1421 modified based on candidate arrow 1423. The modified first text box 1421 may not overlap with a second text box 1422.

[0210] Referring to medical image 1430, medical imaging device 100 can determine that a first text box 1431 and a second contour 1432 overlap with the first contour. Medical imaging device 100 can obtain modified first candidate arrow information by moving the start or end of a candidate arrow 1433 included in the first candidate arrow information so that the first text box 1431 does not overlap with the second contour 1432.

[0211] Medical image 1440 displays candidate arrow 1443 based on modified first candidate arrow information. Medical imaging device 100 can acquire a first text box 1441 modified based on candidate arrow 1443. The modified first text box 1441 may not overlap with the second outline 1442.

[0212] The medical imaging device 100 can perform the step of generating at least one arrow kit based on modified first candidate arrow information. This step can be combined with... Figure 9 Step 940 is executed together.

[0213] Figure 15 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0214] The medical imaging device 100 can perform the following process to determine first candidate arrow information. The following steps can be compared with… Figure 9 One of steps 910 to 940 is executed together.

[0215] The medical imaging device 100 can perform a step of determining first candidate arrow information regarding a plurality of first candidate arrows, the plurality of first candidate arrows pointing to a first contour 1521 in at least one contour. The plurality of first candidate arrows may include a first candidate arrow 1522. Additionally, the medical imaging device 100 can perform a step of determining second candidate arrow information regarding a plurality of second candidate arrows, the plurality of second candidate arrows pointing to a second contour 1531 in at least one contour. The plurality of second candidate arrows may include a second candidate arrow 1532.

[0216] The medical imaging device 100 can determine whether a first candidate arrow 1522 among a plurality of first candidate arrows and a second candidate arrow 1532 among a plurality of second candidate arrows intersect. Additionally, as in medical imaging 1510, when the first candidate arrow 1522 and the second candidate arrow 1532 intersect, the medical imaging device 100 can perform a step of obtaining modified first candidate arrow information by moving the start or end point of the first candidate arrow 1522 so that the first candidate arrow 1522 among the plurality of first candidate arrows does not intersect with the second candidate arrow 1532 among the plurality of second candidate arrows.

[0217] For example, in medical imaging 1550, medical imaging device 100 can acquire a modified first candidate arrow 1562 by moving the start and end points of a first candidate arrow 1522 corresponding to a first contour 1561. Medical imaging device 100 can acquire first candidate arrow information modified based on the modified first candidate arrow 1562.

[0218] The medical imaging device 100 can perform the step of generating at least one arrow kit based on modified first candidate arrow information. This step can be combined with... Figure 9 Step 940 is executed together.

[0219] Figure 16 This is a diagram illustrating the operation of a medical imaging device according to an embodiment of the present disclosure.

[0220] The medical imaging device 100 can perform the following process to determine first candidate arrow information. The following steps are comparable to... Figure 9 One of steps 910 to 940 is executed together.

[0221] Referring to medical image 1610, medical imaging device 100 may perform the step of acquiring the intersection point 1640 of a first contour 1621 and a second contour 1631 of at least one contour. Medical imaging device 100 may also perform the step of acquiring the first contact point 1623 where a first candidate arrow 1622 of a plurality of first candidate arrows intersects with the first contour 1621.

[0222] The medical imaging device 100 can determine whether the distance between the first contact point 1623 and the intersection point 1640 is greater than or equal to a critical value. Here, the critical value can be a preset value. When the distance between the first contact point 1623 and the intersection point 1640 is less than the critical value, the medical imaging device 100 can modify the position of the start point or end point of the first candidate arrow 1622, which is one of a plurality of first candidate arrows, so that the first contact point 1623 is greater than or equal to the intersection point 1640. The medical imaging device 100 can perform the step of obtaining modified first candidate arrow information by modifying the position of the start point or end point of the first candidate arrow 1622. The medical imaging device 100 can move the start point of the first candidate arrow 1622 along a first contour so that the distance between the first contact point 1623 and the intersection point 1640 is greater than or equal to a critical value. Additionally, the medical imaging device 100 can move the end point of the first candidate arrow 1622 so that the arrow is perpendicular to the contour.

[0223] Medical image 1650 shows a modified first candidate arrow 1662. A second contact point can be the contact point between the modified first candidate arrow 1662 and the first contour 1661. Additionally, intersection 1680 can be the point where the first contour 1661 and the second contour 1671 intersect. A second contact point 1663 can be separated from intersection 1680 by a critical value.

[0224] The medical imaging device 100 can perform the step of generating at least one arrow kit based on modified first candidate arrow information. This step can be combined with... Figure 9 Step 940 is executed together.

[0225] Figure 17 and 18 A diagram illustrating a method for obtaining a score according to an embodiment of this disclosure.

[0226] like Figure 9 The medical imaging device 100 can perform step 950 of acquiring a score. The medical imaging device 100 can calculate the score according to a preset method. The medical imaging device 100 can calculate the score based on the distance between text boxes.

[0227] Reference Figure 17 The greater the distance between at least one text box 1711, 1721, 1731 corresponding to at least one outline 1710, 1720, 1730, the higher the score that the medical imaging device 100 can determine.

[0228] For example, the medical imaging device 100 can determine the shortest distance between text boxes. The medical imaging device 100 can determine a first distance 1741 between a first text box 1711 and a second text box 1721. The medical imaging device 100 can determine a second distance 1742 between a second text box 1721 and a third text box 1731. The medical imaging device 100 can determine a third distance 1743 between the first text box 1711 and the third text box 1731. The medical imaging device 100 can determine a score based on the first distance 1741, the second distance 1742, and the third distance 1743. The higher the sum of the first distance 1741, the second distance 1742, and the third distance 1743, the higher the score that the medical imaging device 100 can determine.

[0229] Furthermore, the shorter the length of the arrows 1712, 1722, and 1732 corresponding to at least one contour 1710, 1720, and 1730, the higher the score that the medical imaging device 100 can determine. The medical imaging device 100 can determine the length of the at least one arrow based on candidate arrow information corresponding to at least one contour, respectively. As described above, the candidate arrow information may include the position of the starting point, the position of the ending point, or the length of the arrow. The medical imaging device 100 can obtain the length of the arrow from the candidate arrow information.

[0230] More specifically, the medical imaging device 100 can obtain the lengths of the first arrow 1712, the second arrow 1722, and the third arrow 1732 based on the first candidate arrow information corresponding to the first contour 1710, the second candidate arrow information corresponding to the second contour 1720, and the third arrow information corresponding to the third contour 1730. The smaller the sum of the lengths of the first arrow 1712, the second arrow 1722, and the third arrow 1732, the higher the score that the medical imaging device 100 can determine.

[0231] Reference Figure 18 The medical imaging device 100 can determine a score based on the intersection points 1851 and 1852 of two contours 1810 and 1820 included in at least one contour 1810 and 1820, and the distances between the contact points 1812 and 1822 of at least one contour 1810 and 1820 and at least one arrow 1811 and 1821. More specifically, the greater the distance between the intersection points 1851 and 1852 of two contours 1810 and 1820 included in at least one contour 1810 and 1820, and the greater the distances between the contact points 1812 and 1822 of at least one contour 1810 and 1820 and at least one arrow 1811 and 1821, the higher the score that the medical imaging device 100 can determine.

[0232] The medical imaging device 100 can acquire a first arrow 1811 corresponding to a first contour 1810 included in at least one contour, based on arrow information. Additionally, the medical imaging device 100 can acquire a second arrow 1821 corresponding to a second contour 1820 included in at least one contour, based on arrow information.

[0233] The medical imaging device 100 can acquire the first intersection point 1851 and the second intersection point 1852 of the first contour 1810 and the second contour 1820.

[0234] Additionally, the medical imaging device 100 can define the first contour 1810 and the location closest to the first arrow 1811 as the first contact point 1812. The first contact point 1812 can be the starting point of the first arrow 1811. Alternatively, the first contact point 1812 can be the location within the first contour 1810 that is closest to the first arrow 1811.

[0235] Additionally, the medical imaging device 100 can define the second contour 1820 and the location closest to the first arrow 1821 as the second contact point 1822. The second contact point 1822 can be the starting point of the second arrow 1821. Alternatively, the second contact point 1822 can be the location within the second contour 1820 that is closest to the second arrow 1821.

[0236] The medical imaging device 100 can determine a score based on the distance 1831 between the first intersection point 1851 and the first contact point 1812, the distance 1841 between the first intersection point 1851 and the second contact point 1822, the distance 1832 between the second intersection point 1852 and the first contact point 1812, and the distance 1842 between the second intersection point 1852 and the second contact point 1822. The larger the sum of the distances 1831 between the first intersection point 1851 and the first contact point 1812, the larger the sum of the distances 1841 between the first intersection point 1851 and the second contact point 1822, the larger the score that the medical imaging device 100 can determine.

[0237] Figure 19 A medical image illustrating an embodiment of this disclosure is shown.

[0238] Similar to Figure 2 The medical imaging device 100 can perform step 210 of acquiring lesion information about at least one lesion included in the medical image 1900. Additionally, based on the acquired lesion information, the medical imaging device 100 can perform step 1920 of generating a heat map 1920 in the medical image corresponding to the at least one lesion.

[0239] Heatmap 1920 can be displayed on top of the lesion area included in the lesion information. Additionally, heatmap 1920 can be displayed larger than the lesion area included in the lesion information.

[0240] The medical imaging device 100 can generate a heatmap 1920 by changing the color and transparency based on the probability that pixels of the medical image 1900 are included in the lesion area. For example, a higher probability that a pixel is included in the lesion area can be represented by red tones, and a lower probability can be represented by blue tones. Furthermore, a higher probability that a pixel is included in the lesion area can be represented as opaque, and a lower probability can be represented as transparent.

[0241] The medical imaging device 100 can acquire the maximum probability that a pixel in the medical image 1900 is included in a lesion region. Furthermore, the medical imaging device 100 can determine whether the maximum probability is lower than a threshold value. Here, the threshold value can be a preset value. When the probability that a pixel is included in a lesion region is low, it may be difficult for medical personnel to confirm because the heatmap 1920 is represented by a highly transparent or inconspicuous color. For example, as... Figure 19 When the probability of a pixel being included in a lesion area is low (i.e., 27%), medical personnel may have difficulty confirming the thermal image. The medical imaging device 100 can determine whether it is convenient for medical personnel to view the thermal image 1920 by determining whether the maximum probability is below a threshold.

[0242] When the maximum probability is below a critical value, the medical imaging device 100 may perform the step of generating a contour 1910 surrounding at least a portion of the heatmap 1920. The contour 1910 may be less than or equal to the heatmap 1920. However, it is not limited to this; the contour 1910 may be larger than the heatmap 1920. The medical imaging device 100 may generate the contour when medical personnel have difficulty viewing the heatmap 1920. When medical personnel have difficulty viewing the heatmap 1920, the medical imaging device 100 may allow medical personnel to easily confirm lesion information displayed on the monitor by displaying only the contour or simultaneously displaying the contour and the heatmap.

[0243] The above describes the structure for obtaining the probability that each pixel in the medical image 1900 is included in a lesion region. However, it is not limited to this. For each unit region including at least one pixel, the medical imaging device 100 can obtain the probability that it is included in a lesion region. When the medical imaging device 100 uses a unit region, the same description as above can be performed, so repeated descriptions will be omitted.

[0244] Figure 20 A medical image illustrating an embodiment of this disclosure.

[0245] Similar to Figure 2 The medical imaging device 100 can perform step 210 of acquiring lesion information about at least one lesion included in the medical image 2000. Additionally, the medical imaging device 100 can perform step 220 of generating a contour of at least one lesion in the medical image corresponding to the at least one lesion based on the acquired lesion information. Furthermore, similar to... Figure 9 The medical imaging device 100 can generate arrows and text. However, in certain situations, the medical imaging device 100 may not generate arrows.

[0246] The medical imaging device 100 can determine whether the internal region of a lesion area or contour is larger than a threshold value. When the internal region of a lesion area or contour is larger than the threshold value, the medical imaging device 100 may not generate an arrow about the contour.

[0247] Alternatively, the medical imaging device 100 may determine whether the ratio of the inner region of a lesion area or contour in a medical image is greater than a threshold value. When the ratio of the inner region of a lesion area or contour in a medical image 2000 is greater than the threshold value, the medical imaging device 100 may not generate an arrow about the contour.

[0248] Additionally, when the lesion type included in the lesion information can only be displayed in a large size in the medical image, the medical imaging device 100 may not generate an arrow. Examples of such lesions include mediastinal widening (MW) or cardiomegaly (Cm).

[0249] When no arrow is generated, the medical imaging device 100 may display text related to lesion information in a portion of the medical image 2000. For example, text related to lesion information may be displayed below or in a corner of the medical image 2000.

[0250] Reference Figure 20 Since outline 2020 is a relatively small area, arrows and text can be displayed. However, since outline 2010 is a relatively large area, arrows can be omitted, and text 2011 can be displayed instead. The medical imaging device 100 can display text 2011 about outline 2010 in a portion of the medical image 2000 or at a specific location. For example, the medical imaging device 100 can display text 2011 about outline 2010 in a corner or below the medical image 2000.

[0251] The medical imaging device 100 can display the shape of the lines of the outline 2010 in front of the text 2011 to indicate that there is a correlation between the outline 2010 and the text 2011. In addition, the medical imaging device 100 can set the color of the outline 2010 and the color of the text 2011 to be the same.

[0252] Figure 21 This is a block diagram illustrating the internal structure of an electronic device 2100 according to an embodiment of the present disclosure. The electronic device 2100 may include a memory 2110, a processor 2120, a communication module 2130, and an input / output interface 2140. For example, the electronic device 2100 may include the aforementioned medical imaging device 100. Figure 21 As shown, electronic device 2100 can be configured to transmit information and / or data via a network using communication module 2130.

[0253] The memory 2110 may include any non-transitory computer-readable recording medium. According to one embodiment, the memory 2110 may include a non-volatile mass storage device such as random access memory (RAM), read-only memory (ROM), a disk drive, a solid-state disk (SSD), or flash memory. As another example, non-volatile mass storage devices such as ROM, SSD, flash memory, and disk drives may be included in the electronic device 2100 as a separate, permanent storage device distinct from the memory. Furthermore, the memory 2110 may contain an operating system and at least one program code (e.g., code installed and driven in the electronic device 2100 for acquiring lesion information, determining the shape and location of contours, determining the location of text regions, etc.).

[0254] These software components can be loaded from a computer-readable recording medium separate from memory 2110. These separate computer-readable recording media may include recording media that can be directly connected to these electronic devices 2100, such as computer-readable recording media of floppy disk drives, magnetic disks, magnetic tapes, DVD / CD-ROM drives, memory cards, etc. Alternatively, the software components can be loaded into memory 2110 via communication module 2130 instead of a computer-readable recording medium. For example, at least one program can be loaded into memory 2110 based on a computer program (e.g., a program for determining the shape and position of contours, determining the position of text areas, determining arrow generation, arrow position, etc.), and the computer program can be installed via a file distribution system that provides the installation files for the application through communication module 2130.

[0255] Processor 2120 can be configured to process commands of a computer program by performing basic arithmetic, logic, and input / output calculations. Commands can be provided to a user terminal (not shown) or other external systems via memory 2110 or communication module 2130. For example, processor 2120 can receive medical images and acquire lesion information about at least one lesion detected from the medical images. Furthermore, based on the acquired lesion information, processor 2120 can determine the shape and position of at least one contour corresponding to the at least one lesion, and determine the position of at least one text region including text displaying lesion information about the at least one lesion in the medical images. In this case, processor 2120 can provide the determined shape and position of the contour, the position of the text region, etc., to input / output interface 2140, user terminal (not shown), and / or other external systems.

[0256] The communication module 2130 provides the configuration or function for communication between the user terminal (not shown) and the electronic device 2100 via a network, and also provides the configuration or function for communication between the electronic device 2100 and external systems (for example, a standalone cloud system, etc.). For example, control signals, instructions, data, etc., provided by the processor 2120 of the electronic device 2100 can be transmitted to the user terminal and / or external system via the communication module 2130 and the network, or via the communication module of the user terminal and / or the external system. For example, the user terminal and / or the external system can receive medical images, the shape and position of contours, the content of text, the position of text areas, etc., received from the electronic device 2100.

[0257] Additionally, the input / output interface 2140 of the electronic device 2100 may be a means of connecting to the electronic device 2100 or an interface of a device (not shown) for input or output that the electronic device 2100 may include. For example, the input / output interface 2140 may include a means of interfacing with a display configured to display medical images. Figure 21 In this diagram, the input / output interface 2140 is shown as an element configured separately from the processor 2120, but is not limited thereto; the input / output interface 2140 may be configured to be included within the processor 2120. The electronic device 2100 may include... Figure 21 The constituent elements are more numerous. However, it is not necessary to explicitly illustrate most of the constituent elements of the prior art.

[0258] The processor 2120 of the electronic device 2100 can be configured to manage, process, and / or store information and / or data received from multiple user terminals and / or multiple external systems. According to one embodiment, the processor 2120 can acquire lesion information of at least one lesion detected from a medical image, and based on the acquired lesion information, determine the shape and position of at least one contour corresponding to the at least one lesion. Additionally, the processor 2120 can determine the position of at least one text region including text displaying lesion information about the at least one lesion in the medical image, and based on the determined shape and position of the at least one contour and the determined position of the at least one text region, display the text included in the at least one contour and the at least one text region in the medical image.

[0259] Figure 22 This is a flowchart illustrating an operation method 2200 of a medical imaging device according to an embodiment of the present disclosure. According to one embodiment, the operation method 2200 of the medical imaging device can be executed by a processor (e.g., a processor of at least one medical imaging device (electronic device)). As shown, the operation method 2200 of the medical imaging device can begin by the processor acquiring lesion information about at least one lesion detected from a medical image (S2210). Additionally or alternatively, the processor can acquire lesion information about multiple lesions detected from a medical image.

[0260] The processor can determine the shape and position of at least one contour corresponding to at least one lesion based on the acquired lesion information (S2220). For example, the processor can identify a portion of lesions to be displayed in a medical image among multiple lesions and determine the shape and position of at least one contour of the identified portion of the lesion. Additionally, the processor can determine the position of at least one text region including text displaying lesion information about at least one lesion in the medical image (S2230). For example, the processor can determine the position of at least one text region based on at least one of the distance between at least one contour and at least one text region, or whether at least one contour and at least one text region overlap. Furthermore, the processor can determine the position of at least one text including lesion information about the identified portion of the lesion. Additionally, at least one text region may include multiple text regions, in which case the processor can determine the position of each of the multiple text regions based on the distance between the multiple text regions.

[0261] The processor can display at least one contour and the text included in at least one text region in a medical image based on the shape and position of at least one determined contour and the position of at least one determined text region (S2240). Additionally, the processor can generate at least one arrow pointing to at least one contour, and display the at least one arrow generated to connect at least one contour and at least one text region in the medical image. At this time, the processor can acquire lesion information about multiple lesions detected from the medical image and generate an arrow for each of the multiple lesions. Then, the processor can display the arrows for each of the multiple lesions in the medical image such that each generated arrow for each of the multiple lesions does not intersect with each other. Alternatively or additionally, the processor can display each arrow for each of the multiple lesions in the medical image such that each generated arrow for each of the multiple lesions and the contour corresponding to each of the multiple lesions does not intersect with each other. Alternatively or additionally, at least one contact point region contacting at least one contour can be determined, and the generated at least one arrow can be displayed to connect to the at least one contact point region. For example, the at least one contact point region may include multiple contact point regions contacting at least one contour; in this case, the processor can determine the at least one contact point region based on the distance between the multiple contact point regions.

[0262] According to one embodiment, a processor can determine a portion of a lesion to be displayed in a medical image of multiple lesions. In this case, the processor can identify lesions that repeat in the lesion region among the multiple lesions and determine a portion of the lesion based on at least one of the following: the size of the repeating region between the repeating lesions, the lesion probability of each of the repeating lesions, the correlation between the repeating lesions, or the probability that a portion of the multiple repeating lesions is present in a single medical image. According to these embodiments, medical personnel can focus on observing the area around a contour that is part of a medical image and ultimately easily determine whether a lesion exists within the contour.

[0263] To date, various embodiments have been primarily studied. Those skilled in the art will understand that the invention can be implemented in modified forms without departing from its essential characteristics. Therefore, the disclosed embodiments should be considered descriptive rather than restrictive. The scope of the invention is defined by the scope of the claims, not by the foregoing description, and any differences within the equivalent scope should be interpreted as included within the invention.

[0264] Furthermore, the embodiments of the present invention described above can be programmed into a computer-executable program and implemented in a general-purpose digital computer operating the program using a computer-readable recording medium. The computer-readable recording medium includes storage media such as magnetic storage media (e.g., ROM, floppy disk, hard disk, etc.) and optically readable media (e.g., CD-ROM, DVD, etc.).

Claims

1. A method for operating a medical imaging device, wherein, Includes the following steps: Obtain lesion information about multiple lesions detected from medical images; Based on the acquired lesion information, determine the shape and position of at least one contour corresponding to at least a portion of the lesions; Determine the location of at least one text region containing text that displays lesion information about at least a portion of the lesion in the medical image; as well as Based on the shape and position of the determined at least one contour and the position of the determined at least one text region, the at least one contour and the text included in the at least one text region are displayed in the medical image. The step of determining the shape and position of the at least one contour includes: Identify lesions with overlapping lesion areas among the multiple lesions; Based on the repeated lesion regions among the repeated lesions, determine the shape and position of at least one contour corresponding to at least a portion of the lesions among the plurality of lesions; Based on at least one of the following: the size of the repeating region among the repeating lesions, the lesion probability of each repeating lesion, the correlation between the repeating lesions, or the probability that a portion of the repeating lesions is present in a medical image, the at least portion of lesions to be displayed in the medical image is determined from the plurality of lesions. The operation method further includes the step of generating at least one arrow pointing to the at least one contour. The display step further includes: The step of displaying at least one generated arrow in the medical image to connect the at least one contour and the at least one text region. The step of generating at least one arrow includes: The step of generating arrows about each of the at least a portion of the lesion. The step of displaying at least one generated arrow in the medical image includes: The step of displaying the generated arrows about each of the at least a portion of the lesion in the medical image such that the generated arrows about each of the at least a portion of the lesion do not intersect each other, and the generated arrows about each of the at least a portion of the lesion and the contours corresponding to each of the at least a portion of the lesion do not intersect each other.

2. The method of operating the medical imaging device according to claim 1, wherein, The step of determining the location of the at least one text region includes: The step of determining the position of the at least one text region based on at least one of the distance between the at least one contour and the at least one text region or whether the at least one contour and the at least one text region overlap.

3. The method of operating the medical imaging device according to claim 1, wherein, The step of determining the shape and position of at least one contour further includes: The step of determining the shape and location of at least one contour of at least a portion of the determined lesion; The step of determining the location of at least one text region includes determining the location of at least one text region, wherein the text includes lesion information about the determined at least a portion of the lesion.

4. The method of operating the medical imaging device according to claim 1, wherein, The step of displaying the generated arrow in the medical image includes the following steps: Determine at least one contact point region where the generated arrow contacts at least one contour; and Display the generated arrow and connect it to the at least one contact point area.

5. The method of operating the medical imaging device according to claim 4, wherein, The step of determining at least one contact point region includes: The step of determining the at least one contact point region based on the distance between the plurality of contact point regions in contact with the at least one contour.

6. The method of operating the medical imaging device according to claim 1, wherein, The at least one text region includes multiple text regions. The steps for determining the location of at least one text region include: The step of determining the position of each of the plurality of text regions based on the distance between them.

7. An electronic device, wherein, include: Memory, which stores one or more commands; as well as The processor is configured to execute one or more commands stored in the memory. To obtain lesion information about multiple lesions detected from medical images. Based on the acquired lesion information, the shape and position of the contour corresponding to at least a portion of the lesions are determined. Determine the location of at least one text region that includes text displaying lesion information about at least a portion of the lesion in the medical image. Based on the shape and position of the at least one defined contour and the at least one defined text region, the text included in the at least one contour and the at least one text region is displayed in the medical image. Identify lesions with overlapping lesion areas among the multiple lesions. Based on the recurring lesion regions among the recurring lesions, determine the shape and location of at least one contour corresponding to at least a portion of the lesions among the plurality of lesions. The processor is further configured to: determine, based on at least one of the following: the size of the repeating region between the repeating lesions, the lesion probability of each repeating lesion, the correlation between each repeating lesion, or the probability that a portion of the repeating lesions exists in a medical image, the at least portion of the lesions to be displayed in the medical image. The processor is further configured to generate at least one arrow pointing to the at least one contour, and to display the generated at least one arrow in the medical image to connect the at least one contour and the at least one text region. The processor is further configured to, Generate arrows about each of the at least a portion of the lesion. The generated arrows about each of the at least a portion of the lesion are displayed in the medical image such that the generated arrows about each of the at least a portion of the lesion do not intersect each other, and the generated arrows about each of the at least a portion of the lesion and the contours corresponding to each of the at least a portion of the lesion do not intersect each other.

8. The electronic device according to claim 7, wherein, The processor is further configured to, The position of the at least one text region is determined based on at least one of the following: the distance between the at least one contour and the at least one text region, or whether the at least one contour and the at least one text region overlap.

9. The electronic device according to claim 7, wherein, The processor is further configured to, Determine the shape and location of at least one contour relating to at least a portion of the determined lesion. Determine the location of at least one text region that includes lesion information about at least a portion of the determined lesion.

10. The electronic device according to claim 7, wherein, The processor is further configured to, Determine at least one contact point region where the generated arrow and the at least one contour are in contact. Display the generated arrow and connect it to the at least one contact point area.

11. The electronic device according to claim 10, wherein, The processor is further configured to, In a plurality of contact point regions that are in contact with the at least one contour, the at least one contact point region is determined based on the distance between the plurality of contact point regions.

12. The electronic device according to claim 7, wherein, The at least one text region includes multiple text regions. The processor is further configured to, The position of each of the multiple text regions is determined based on the distance between them.

Images