Method for editing a perceived anatomical profile and system for implementing said method

Abstract

A method of perceptual anatomy contour editing includes receiving an image, wherein the image characterizes an anatomically identifiable structure; identifying a first image segment that characterizes a portion of the anatomically identifiable structure; labeling the first image segment to generate a label for the portion; drawing a contour along a boundary of the portion; receiving a first input from a user device that indicates a contour failure region, wherein the contour failure region includes a portion of the contour that needs to be edited; editing the contour based on the first input and anatomical information to generate an edited contour; and updating another contour for another portion of the anatomically identifiable structure based on the edited contour, wherein the another portion is anatomically related to the aforementioned portion.

Description

Technical Field

[0001] The aspects of the disclosed embodiments generally relate to the field of image processing, and more specifically to perceptual anatomical contour editing. Background Technology

[0002] Conventionally, magnetic resonance imaging (MRI) uses a magnetic resonance (MR) scanner to capture time-series images of a biological body using strong magnetic fields, radio waves, and computers. In this paper, time-series images comprise a collection of images captured sequentially over time; for example, the number of images in this collection could be one hundred. Physicians use these time-series images to monitor bodily functions, such as the state of the heart at any given moment. This is used to further detect diseases associated with impaired bodily function. The time-series images are further segmented to monitor different parts within organs, such as the left and right ventricles of the heart and the papillary muscles. When segmenting different parts within an organ, contours are drawn along the boundaries of the organ's parts to extract useful information from the time-series images. This facilitates future research in a detailed manner related to the function of the organ's parts. However, the drawn contours are not always accurate in nature and may require editing.

[0003] First, two-dimensional (2D) contour editing methods are used to edit the contours and make them accurate. However, 2D contour editing is typically performed manually, where the user manually labels the segmented organ parts and then verifies the correctness of the contours. This is a time-consuming process. Alternatively, 2D contour editing can be performed automatically, where the segmentation of organ parts is performed automatically. However, for anatomical accuracy, the contours still need to be manually verified and edited. Therefore, the user must manually perform segmentation, labeling, and drawing of organ parts contours for each image in the image set. Thus, on average, the user must verify contours in nearly one hundred images. This is time-consuming, inefficient, and inaccurate.

[0004] Secondly, the conventional method for editing a given contour employs user interface (UI)-based interactive tools. These tools edit a portion of a given contour by dynamically selecting control points. These control points are used to adjust the neighborhood of the given contour by adding or removing parts of the organ. Typically, a regular function (such as a Bezier function) can be used to smooth the given contour. Additionally, curve interpolation techniques are applied to further smooth the given contour. In some cases, control points are predefined on the polygon containing the organ, and the given contour is edited only between two consecutive control points. When editing a contour in this way, the user needs to continuously interact with the contour and make fine adjustments to accurately edit the given contour. This is error-prone and inherently time-consuming.

[0005] Other limitations and disadvantages of conventional and traditional methods will become apparent to those skilled in the art by comparing such a system with some aspects of this disclosure as set forth with reference to the accompanying drawings in the remainder of this application. Summary of the Invention

[0006] Methods, systems, and / or computer program products for implementing the perceptual anatomical contour editing method are provided, as generally shown and / or described in conjunction with at least one accompanying drawing and set forth more fully in the claims.

[0007] According to a first embodiment, aspects of the disclosed embodiments relate to a method for editing perceptual anatomical contours. In one embodiment, the method includes: receiving at least one image by at least one processor, wherein the at least one image represents at least one organ. The method further includes: identifying a first image segment representing at least one portion of the at least one organ by the at least one processor, and labeling the first image segment by the at least one processor to generate a label for the at least one portion. The method further includes: drawing at least one contour by the at least one processor along the boundary of the at least one portion. The method further includes: receiving a first input indicating a contour failure region by the at least one processor, wherein the contour failure region includes a portion of the contour that needs to be edited. The method further includes: editing the contour by the at least one processor based on the first input and anatomical information to generate an edited contour. The method further includes: updating another contour of another portion of the at least one organ by the at least one processor based on the edited contour, wherein the other portion is anatomically related to the at least one portion.

[0008] According to a second possible embodiment, aspects of the disclosed embodiments relate to a system for implementing a perceptual anatomical contour editing method. In one embodiment, the system includes a user device and at least one processor. The at least one processor is configured to receive at least one image, wherein the at least one image represents at least one anatomically identifiable structure. The at least one processor is further configured to identify a first image segment representing at least one portion of the at least one anatomically identifiable structure and to label the first image segment to generate a label for the at least one portion. The at least one processor is further configured to draw at least one contour along the boundary of the at least one portion. The at least one processor is further configured to receive a first input indicating a contour failure region, wherein the contour failure region includes a portion of the contour that needs to be edited. The at least one processor is further configured to edit the contour based on the first input and anatomical information to generate an edited contour. The at least one processor is further configured to update another contour of another portion of the at least one anatomically identifiable structure based on the edited contour, wherein the other portion is anatomically related to the at least one portion.

[0009] According to a third possible embodiment, aspects of the disclosed embodiments relate to a computer program product for implementing a perceptual anatomical contour editing method. In an embodiment, the computer program product includes non-transitory computer-readable program instructions that, when executed by the hardware processor of a computing device, are configured to cause the computing device to implement the perceptual anatomical contour editing method according to a first possible embodiment.

[0010] These and other advantages, aspects and novel features of the present disclosure, as well as the details of the illustrative embodiments thereof, will be more fully understood from the following description and accompanying drawings. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating the steps of a perceptual anatomical contour editing method according to an embodiment of the present disclosure;

[0012] Figure 2 This is a block diagram illustrating a system for implementing a perceptual anatomical contour editing method according to an embodiment of the present disclosure;

[0013] Figure 3A and Figure 3B These are exemplary images of at least one anatomically identifiable structure according to embodiments of the present disclosure;

[0014] Figure 4 It is an exemplary image of at least one anatomically identifiable structure, wherein the contour is edited according to embodiments of the present disclosure to generate an edited contour;

[0015] Figure 5 This is an exemplary image illustrating the control radius of a circular control region according to an embodiment of the present disclosure;

[0016] Figure 6 These are exemplary images illustrating another outline of an updated portion according to an embodiment of this disclosure; and

[0017] Figure 7 An exemplary computing device configured to implement aspects of the disclosed embodiments is illustrated. Detailed Implementation

[0018] The disclosed embodiments provide methods, systems, and computer program products that correspond to solutions for efficiently editing and verifying contours using workflows. Conventional techniques for editing contours include manual annotation and verification. However, such techniques are time-consuming and tedious. Furthermore, automated mechanisms can be used to segment anatomically identifiable structures. However, manual verification and correction of improperly drawn contours are still required. In contrast, the perceptual anatomical contour editing method of the disclosed embodiments provides an improved workflow for editing contours using user input and anatomical information associated with a user device. Therefore, the method enables efficient interactive editing, verification, and correction of contours.

[0019] refer to Figure 1 The disclosed embodiments generally relate to a method for editing perceptual anatomical contours. In one embodiment, the method includes: receiving at least one image. The at least one image represents at least one anatomically identifiable structure. Identifying a first image segment representing at least one portion of the at least one anatomically identifiable structure. Labeling the first image segment to generate a label for the at least one portion. Drawing at least one contour along the boundary of the at least one portion. Receiving a first input indicating a contour failure region, the first input being provided using a user device. The contour failure region includes a portion of the contour that needs to be edited. Editing the contour based on the first input and anatomical information. Updating the contour of another portion of the at least one anatomically identifiable structure based on the edited contour. The other portion is anatomically related to the at least one portion.

[0020] The perceptual anatomical contour editing method 100 introduces an efficient way to edit contours to generate edited contours, and then update another contour based on the edited contours. The perceptual anatomical contour editing method 100 is described in detail in the following steps.

[0021] In step 102, the perceptual anatomical contour editing method 100 includes: receiving at least one image by at least one processor, wherein the at least one image represents at least one anatomically identifiable structure. In this document, the at least one image is a detailed three-dimensional (3D) anatomical image received using magnetic resonance imaging (MRI), wherein MRI is performed by subdividing a portion of a patient's body. It will be understood that the term "at least one image" in some embodiments refers to "a single image" and in other embodiments refers to "multiple images." A single image is captured at a single moment from a specific orientation of a medical imaging device used to perform MRI. Multiple images are captured in a time sequence. Furthermore, multiple images are captured along different standard orientations of the camera, which helps to obtain a better view of at least one anatomically identifiable structure within the patient's body. In this document, the term "anatomically identifiable structure" refers to an anatomically correct and identifiable structure. In this document, an anatomically identifiable structure is a group of different kinds of tissues located at a specific location within an organism, arranged to perform a specific function relevant to the patient or organism. Examples of anatomically identifiable structures may include, but are not limited to, organs, tissues, lesions, etc.

[0022] It should be understood that a given image is a visual representation of at least one anatomically recognizable structure of an organism. The term "visual representation" includes color information represented in a given image, and optionally additionally includes other attributes associated with the given image (e.g., density information, movement-related information, tissue information, etc.). A given image consists of multiple pixels. Examples of grayscale with color information include, but are not limited to, pixel colors ranging from white to black, including several levels of gray.

[0023] Optionally, the given image is at least one of a radiographic image, an acoustic image, or a positron emission tomography (PET) scan. A radiographic image characterizes at least one anatomically identifiable structure in grayscale and is captured using X-ray energy (i.e., an electromagnetic energy packet). The radiographic image is used to assess the presence or absence of at least one of disease, foreign body, structural abnormality, or injury to at least one anatomically identifiable structure. An acoustic image uses high-frequency sound waves from an ultrasound device to capture and observe at least one anatomically identifiable structure. Furthermore, by capturing acoustic images in real-time or near real-time, acoustic images can depict the movement of internal organs and blood flow through the body's blood vessels. A PET scan is used to assess the metabolic and biochemical functions of tissues and at least one anatomically identifiable structure. A PET scan uses a small amount of radioactive material (i.e., a radiotracer) that is intravenously injected and travels through the bloodstream and is collected in organs and tissues, thereby further visualizing said organs and tissues. For example, a parasternal short-axis scan can characterize the heart of a given organism.

[0024] Optionally, at least one image captured using any one of computed tomography (CT), fluoroscopy, radiography, ultrasound, MRI, PET scans, etc., is received in real-time or near real-time (without any delay / latency) by at least one processor. The term "processor" refers to a computational element operable to respond to and process instructions. At least one processor implements the perceptual anatomical contour editing method in operation. Furthermore, the term "processor" can refer to one or more individual processors, processing devices, and various elements associated with the processing device that can be shared by other processing devices. Such processors, processing devices, and elements can be arranged in various architectures to respond to and execute steps of the method.

[0025] Optionally, at least one image can be received from a data storage library using at least one processor, wherein the data storage library is communicatively coupled to at least one processor. Throughout this disclosure, the term "processor" refers to a computing element operable to respond to and process instructions. At least one processor implements the steps of the perceptual anatomical contour editing method in operation. Furthermore, the term "processor" can refer to one or more individual processors, processing devices, and various elements associated with the processing devices that can be shared by other processing devices. Such processors, processing devices, and elements can be arranged in various architectures to respond to and execute the steps of the perceptual anatomical contour editing method.

[0026] In step 104, the perceptual anatomical contour editing method 100 includes: identifying a first image segment representing at least one portion of at least one anatomically identifiable structure by at least one processor. Throughout this disclosure, the term "image segment" for a given image refers to a portion (i.e., a segment) of a given image representing at least one portion of at least one anatomically identifiable structure. The first image segment can be of any shape, such as a circle, ellipse, polygon, freeform, etc. The foregoing method also includes, optionally, cropping the first image segment from the given image, wherein the first image segment represents at least one portion of at least one anatomically identifiable structure. The first image segment provides a virtual anatomy of at least one anatomically identifiable structure to reveal at least one real portion of at least one anatomically identifiable structure. It should be understood that individual pixel representations in a given image can be identified as given portions of a class, and that given portion is explicitly identifiable. The given image consists of points rendered as pixels, and the individual pixels of the given image are identified from a predefined set of classes (such as right ventricle, left ventricular myocardium, at least one papillary muscle). The first image fragment can be identified by at least one of the following operations: classifying a single pixel representing at least one part, classifying multiple pixels representing at least one part, classifying individual pixels based on their neighboring pixels. The first image fragment can be identified manually by visually inspecting a given image, automatically using a computer-based algorithm, and / or by a combination of both. The technical effect of identifying the first image fragment is to accurately diagnose a problem area in at least one part of at least one anatomically identifiable structure, and to recommend a treatment plan if the organism is ill.

[0027] For example, a given image may represent the heart, wherein the given image may consist of 1000 pixels. At least one part of the heart may be at least one of the right ventricle, left ventricular myocardium, left ventricular epicardium, left ventricular endocardium, and left ventricular papillary muscle. Subsequently, image segments are identified, wherein 250 pixels can be assigned to the right ventricle, 350 pixels to the left ventricular myocardium, 150 pixels to the left ventricular epicardium, 150 pixels to the left ventricular endocardium, and 100 pixels to the left ventricular papillary muscle.

[0028] In step 106, the perceptual anatomical contour editing method 100 includes: labeling a first image segment by at least one processor to generate labels for at least one part. The first image segment is labeled to record the first image segment. Herein, labeling is performed to mark or classify the first image segment using text or drawing, or both, to indicate features that can be used to identify consecutive image segments when at least one image is a collection of images captured consecutively over a period of time. Labeling can be performed manually by a person or by using a computer, wherein labeling can be performed automatically by a computer or semi-automatically using a combination of computer and manual input from a person. Subsequently, labels for at least one part are generated, wherein the labels provide an indication of at least one part. Referring to and continuing with the first example, the image segment represents at least one of the following: the right ventricle may be labeled as representing "RV", the left ventricular myocardium may be labeled as representing "LV myocardium", the left ventricular endocardium may be labeled as representing "LV endocardium", and the left ventricular papillary muscle may be labeled as representing "LV papillary muscle". Herein, "RV", "LV myocardium", "LV endocardium", and "LV papillary muscle" can be labels generated when labeling the image segment.

[0029] In step 108, the perceptual anatomical contour editing method 100 includes: drawing at least one contour along the boundary of at least one portion by at least one processor. Drawing at least one contour along the boundary (or edge) is to extract the boundary of at least one portion in a first image segment. Advantageously, the at least one contour is used to evaluate the function of at least one portion of at least one anatomically identifiable structure. The term "contour" refers to a line that connects all consecutive points (consecutive points traversing the first image segment with the same color and intensity) along the boundary of at least one portion, thereby forming a closed curve. The at least one contour can be drawn manually, automatically, or by a combination of both. Drawing at least one contour is to visually separate at least one portion of at least one anatomically identifiable structure and precisely define the features of at least one portion. The at least one contour is drawn using techniques known in the art. Drawing at least one contour overcomes the problem of weak or blurred boundaries of at least one portion of at least one anatomically identifiable structure, thereby accurately extracting the boundary of at least one anatomically identifiable structure. Advantageously, the at least one contour can be used to analyze the shape of at least one portion, determine the size of at least one portion, and detect abnormalities in at least one portion. Furthermore, the size and shape of at least one outline drawn along the boundary of at least one part helps to identify any potential diseases within the organism.

[0030] In step 110, the perceptual anatomical contour editing method 100 includes: receiving, by at least one processor, a first input indicating a contour failure region, the first input being provided using a user device, and wherein the contour failure region comprises a portion of the contour to be edited. Throughout this disclosure, the phrase "contour failure region" refers to a portion of a contour that is incorrectly drawn such that it does not correctly include at least one portion. This occurs when at least one contour is not aligned along the boundary of at least one portion, for example, when at least one portion of at least one anatomically identifiable structure is displaced from a given location to another given location. The contour failure region can become apparent when the position of at least one portion changes or the condition (i.e., state) of at least one anatomically identifiable structure changes. The contour failure region is received as the first input in real-time or near real-time and can be edited using computer-aided tools. For example, a medical imaging device can capture multiple images of the beating state of the heart. Thus, any one of the multiple images can characterize the heart when it is at least partially constricted (i.e., contracted), and another of the multiple images can characterize the heart when it is at least partially relaxed (i.e., diastolic).

[0031] In step 112, the perceptual anatomical contour editing method 100 includes: editing a contour by at least one processor based on a first input and anatomical information to generate an edited contour. Hereinafter, the term "edited contour" refers to a contour that correctly identifies at least one portion of at least one anatomically identifiable structure and correctly draws its boundaries along at least one portion. Upon receiving the first input, inappropriately drawn portions of the contour are identified. The portion of the contour to be edited is manipulated by actions performed on the portion of the contour. Examples of such actions may include, but are not limited to, deleting, cropping, pasting, and copying portions of the contour. The edited contour can be generated using computer vision techniques known in the art. Editing can be performed interactively, wherein ineffective regions of the contour are automatically edited based on input received from a user device. Ineffective regions of the contour can be edited manually, automatically, or by a combination of both. Additionally, editing can be performed by at least one of explicit selection and implicit selection of the contour of at least one portion. Explicit selection of the contour is performed using a selection tool provided by the editing tool. Examples of such selection tools may include, but are not limited to, rotating, translating, adding, deleting, and deforming the contour. Hereinafter, the term "editing tool" refers to a utility or program used for editing contours. Implicit selection of a contour is performed by the user, associated with the user device, directly interacting with the contour to edit it.

[0032] According to an embodiment, anatomical information is accessed from a data store storing anatomical information. The data store can be used to digitally pre-store at least one image for later use. The term "data store" refers to hardware, software, firmware, or a combination thereof used to store at least one image. It will be understood that the data store can be implemented as a cloud-based storage, the storage of at least one server, the storage of a computing device, the local storage of a user device, a removable storage device, etc. Optionally, at least one image can be received from a medical imaging device, wherein the medical imaging device includes at least one camera for capturing at least one image of at least one anatomically recognizable structure. In this document, the at least one camera can be in a fixed orientation or different orientations. Optionally, the at least one image captured by the medical imaging device is stored in the data store and retrieved from the data store whenever needed.

[0033] According to another embodiment, the anatomical information includes at least one of the following: dimensions, thickness values, boundaries, relative sizes, predefined size thresholds, arrangements, and anatomical relationships between any one of a given portion and another portion and the other of a given portion and another portion. Throughout this disclosure, the term "anatomical information" refers to prior known information about at least one portion and at least one of a given anatomically identifiable structure. The anatomical information is used to characterize at least one portion of at least one anatomically identifiable structure and at least one organ. Hereinafter, anatomical information is the identification and description of at least one portion of at least one anatomically identifiable structure. The term "size" refers to a measurable range of a given portion, such as length, width, depth, or height. The term "thickness value" refers to a distance value through at least one portion and / or at least one anatomically identifiable structure. The term "relative size" refers to the size of a given portion of a given anatomically identifiable structure, at least one of a given anatomically identifiable structure, compared to another given portion of another given anatomically identifiable structure, at least one of another given anatomically identifiable structure. The term "predefined size threshold" refers to a known value for the size of at least one portion of at least one anatomically identifiable structure. The term "arrangement" refers to biological tissue comprising at least one portion of at least one anatomically identifiable structure within an organism. The term "anatomical relationship" refers to the association or relationship between any one of a given part and another part and the other of the given part and another part.

[0034] In addition, the anatomical information includes at least one of the following: the appearance and pose of at least one anatomically identifiable structure; the appearance and pose of at least one part of at least one anatomically identifiable structure; the material constituting at least one part and / or at least one anatomically identifiable structure; the ontological relationship between any one of the at least one part and at least one anatomically identifiable structure and the other of the at least one part and at least one anatomically identifiable structure; the function of at least one part and at least one anatomically identifiable structure; the chemical processes involved; and the interconnection between any one of the at least one part and at least one anatomically identifiable structure and the other of the at least one part and at least one anatomically identifiable structure. Optionally, the anatomical information also includes information on the anatomical structure of at least one other anatomically identifiable structure that is not represented in at least one image.

[0035] Subsequently, anatomical information is used to edit the contour, ensuring that the edited contour is anatomically accurate. Specifically, the edited contour follows the basic rules of biological anatomy, such that at least one part is represented in the first image fragment as corresponding to the biological pose of said part in the body. Therefore, the edited contour generated based on the first input and anatomical information is a smooth structure.

[0036] According to an embodiment, the step of editing the outline to generate an edited outline includes:

[0037] A second input indicating a control point is received by at least one processor, the second input being provided using a user device, and wherein the control point is located outside or inside the profile;

[0038] The processor receives a third input indicating the control radius of a circular control region centered on a control point, the third input being provided using a user device, and wherein the circular control region includes at least a portion of a contour failure region;

[0039] A fourth input indicating the two furthest points on the contour from the control point is received by at least one processor. The fourth input is provided using a user device, and the two furthest points are located within a portion of the contour failure area.

[0040] A spline is drawn from one of the two farthest points to the other of the two farthest points by at least one processor, passing through control points.

[0041] The spline is replaced by at least one processor with uniformly sampled spline points; and

[0042] The edited contour is generated by at least one processor by adjusting the contour to include uniformly sampled spline points.

[0043] In this document, the second, third, and fourth inputs are provided by the user device. The term "control point" refers to a fixed keypoint selected based on the first input, which helps to directly adjust the size and edit the contour. A control point is a point in a set of points along a contour, which can be used to at least determine the shape of the contour. The technical advantage of using control points is that contour editing can be performed in a precise manner and is highly controllable and efficient compared to conventional techniques used for contour editing. Control points are needed when a contour is inappropriately drawn for a given portion of a given anatomically identifiable structure, where some parts of the given portion (i.e., at least a portion of the contour failure area) are not included in the contour. Control points are selected to include or remove contour failure areas in an anatomically accurate manner.

[0044] Additionally, a second input is received regarding the portion of the given area within the contour failure region that needs editing. In one case, when a portion of the given area within the contour failure region is to be included, the control point is located outside the contour. In another case, when a portion of the given area within the contour failure region is to be deleted, the control point is located inside the contour. Subsequently, the area of ​​the portion of the given area to be included or deleted can be manipulated by changing the control radius of the circular control area centered on the control point. This is received as a third input. The control radius in the third input is selected to generate an edited contour based on the portion of the given area to be included or deleted. Subsequently, a fourth input is used to ensure a smooth curve for the contour. The fourth input indicates two farthest points, which are selected to include or delete portions of the given area within the contour failure region. The two farthest points are located on the contour and serve as boundaries, where the smaller area of ​​the contour within the boundaries is edited.

[0045] Subsequently, a spline is drawn from one of the two farthest points to the other. In this paper, the term "spline" refers to a smooth curve that passes through or near a given set of points, where the given set of points determines the shape of the spline. The given set of points includes control points and at least one of the two farthest points. The spline is drawn using algorithms well-known in the art. The spline is drawn to ensure that contour failure areas are properly identified, portions of a given section are included or removed, and the contour is adjusted accordingly.

[0046] Subsequently, the spline is replaced with uniformly sampled spline points. These uniformly sampled points become the fixed keypoints of the edited contour. In this paper, the uniformly sampled spline points are linear and positioned at uniform distances from each other. The technical benefit of replacing the spline with uniformly sampled spline points is that it ensures a smoother consistency in the edited contour. Therefore, the above steps are repeated to precisely adjust the contour, thereby generating the edited contour. The edited contour will include uniformly sampled spline points located between the two furthest points, as well as the contour of at least one previously drawn portion.

[0047] According to an embodiment, the control point simulates a magnet, and the control radius indicates the strength of the magnet's external magnetic field. The control radius can be increased or decreased, similar to the magnet's magnification factor (such as 0.1X, 0.2X, 0.5X, 1X, 2X, 3X, 4X..., NX). In one case, when the magnet's magnification factor is high, the strength of the magnet's external magnetic field is high. Therefore, the control radius is high. In another case, when the magnet's magnification factor is low, the strength of the magnet's external magnetic field is low. Therefore, the control radius is low. The control radius can be adjusted by a user associated with a user device to perform actions; for example, a mouse can be used to increase or decrease the control radius by scrolling up or down. The contour located within the two furthest points is attracted to the control point, much like iron filings are attracted to a magnet. Advantageously, the control radius ensures that the contour is smoothly drawn along the desired area of ​​a given portion in the contour failure region.

[0048] According to an embodiment, a user device is used to provide a given input, which is at least one of touch input, click input, click and drag input, and text input. The given input includes at least one of a first input, a second input, a third input, and a fourth input. Herein, the term "user device" refers to an electronic device capable of providing at least a given input. The user device is associated with (or used by) a user and enables the user to perform a specific task associated with the method. Furthermore, the term "user device" is intended to be broadly interpreted to include any electronic device that can be used to facilitate the provision of a given input to a user. Examples of user devices include, but are not limited to, a mouse, touchpad, keyboard, keypad, joystick, etc.

[0049] In step 114, the perceptual anatomical contour editing method 100 includes: updating another contour of another part of at least one anatomically identifiable structure based on an edited contour by at least one processor, wherein the other part is anatomically related to at least one part. The contour is adjusted to include uniformly sampled spline points within the edited contour. This necessitates altering the other contour because it is anatomically related to the edited contour. Therefore, updating the other contour of the other part based on the edited contour ensures that the edited contour and the other contour of the other part are consistent with each other and anatomically accurate.

[0050] According to an embodiment, at least one anatomically identifiable structure is the heart, and another part of the heart is at least one of the epicardium and endocardium. In this respect, the epicardium is the outer protective layer, and the endocardium is the innermost layer lining the multiple chambers of the heart. The epicardium is an important source of signals that maintain continuous growth and distinguish the different parts of the heart during its development. The endocardium ensures that the blood flowing through the heart is separated from the other parts of the heart or the myocardium.

[0051] According to another embodiment, updating another outline of another part includes:

[0052] A first profile along the boundary of the epicardium and a second profile along the boundary of the endocardium are identified by at least one processor;

[0053] The first and second contours are compared with anatomical information by at least one processor; and

[0054] When the relative arrangement of the first profile and the second profile is determined to be mismatched with the reference relative arrangement of the epicardium and endocardium based on comparison, at least one of the first profile and the second profile is adjusted by at least one processor to match the reference relative arrangement.

[0055] In this paper, a first contour along the boundary of the epicardium includes a second contour along the boundary of the endocardium, and no overlap is observed. The first and second contours can be compared manually, automatically, or by a combination of both. The first and second contours are compared to determine whether the first contour is incorrectly drawn relative to the second contour such that the first contour intrudes into the second contour, or vice versa. The relative arrangement is the current pose of the epicardium and endocardium, and a reference relative arrangement of the epicardium and endocardium is obtained from anatomical information. When the first contour intrudes into the second contour, this implies that the epicardium is inside the endocardium, which is anatomically incorrect. Therefore, the first and second contours are adjusted based on the corresponding reference relative arrangement of the epicardium and endocardium such that at least one image accurately represents the relative arrangement of the epicardium and endocardium.

[0056] According to another embodiment, another part of the heart is at least one papillary muscle, and wherein the step of updating another contour of the other part includes:

[0057] The third contour polygon of a given papillary muscle is identified by at least one processor; and

[0058] The size of the third contour polygon is adjusted by at least one processor based on a predefined size threshold algorithm.

[0059] In this paper, at least one papillary muscle is a small muscular structure located in the corresponding ventricle of the heart. The third contour polygon is in the form of an island. Image segmentation is used to locate at least one papillary muscle and its boundaries (e.g., lines, curves, etc.) in at least one image. Subsequently, a label is assigned to each pixel in at least one image such that pixels with the same label are identified as third contour polygons. These pixels share certain features. The size of the third contour polygon is then adjusted based on a predefined size thresholding algorithm (such as the Otsu method). The Otsu method is used to automatically determine the size of the third contour polygon. In this paper, the predefined size thresholding algorithm searches for a threshold obtained by minimizing the intra-class strength variance or equivalently by maximizing the inter-class variance.

[0060] According to another embodiment, at least one anatomically identifiable structure is the heart, and another part of the heart is at least one of the right ventricular epicardium and the left ventricular epicardium. In this text, the right ventricular epicardium is the outer protective layer of the right ventricle, wherein the right ventricle is located in the lower right portion of the heart opposite the left ventricle. Similarly, the left ventricular epicardium is the outer protective layer of the left ventricle, wherein the left ventricle is located in the lower left portion of the heart opposite the right ventricle.

[0061] According to another embodiment, updating another outline of another part includes:

[0062] A first contour polygon of the right ventricular epicardium and a second contour polygon of the left ventricular epicardium are identified by at least one processor, wherein one of the first contour polygon and the second contour polygon overlaps with the other of the first contour polygon and the second contour polygon.

[0063] A first pair of points is determined by at least one processor, the first pair of points including a first point in a first contour polygon and a first point in a second contour polygon, the first points being closest to each other;

[0064] A second pair of points is determined by at least one processor by traversing along a first contour polygon or a second contour polygon, wherein the second pair of points includes a second point in the first contour polygon and a second point in the second contour polygon, the second points being closest to each other; and

[0065] Edited first contour polygons and edited second contour polygons are generated by at least one processor by adjusting the first contour polygon and the second contour polygon based on the first point pair, the second point pair, and anatomical information.

[0066] In this paper, the right ventricle attached to the epicardium of the left ventricle of the heart is used as a reference. The term "contour polygon" refers to a completely closed and continuous contour that mimics the shape of a polygon. In this respect, the polygon can have straight edges, curved edges, free-form edges, etc. A first contour polygon and a second contour polygon are identified in at least one image of the heart. In some cases, the first contour polygon and the second contour polygon will not overlap each other. In other cases, one of the first contour polygon and the second contour polygon may at least partially overlap with the other of the first contour polygon and the second contour polygon. In this paper, at least partial overlap of the first contour polygon and the second contour polygon can be determined manually, automatically, or by a combination of both. A first point pair is used as a starting point, from which a traversal is made to a second point pair, wherein the second point pair is at the point where the traversal ends. The first point pair and the second point pair are determined only if one of the first contour polygon and the second contour polygon overlaps with the other of the first contour polygon and the second contour polygon. The first point pair and the second point pair are determined when the first contour polygon and the second contour polygon are closest to each other. A given pair of points can be in the form of coordinates, such as a given first pair of points being (RV1, LV1) and a given second pair of points being (RV2, LV2). Then, the common area between the first and second pair of points is determined, wherein any overlap is checked. This common area is continuously updated as the first and second contour polygons are adjusted to make them anatomically accurate, thereby generating edited first and second contour polygons.

[0067] According to an embodiment, at least one image is a time-series image, and the method further includes: updating at least one subsequent image of the at least one image based on at least one of an edited contour and another updated contour, wherein the step of updating at least one subsequent image includes:

[0068] At least one processor determines, based on at least one of the edited contour and at least one of the updated contours, the affected key points near the contour failure region, and at least one of the affected contours; and

[0069] The affected keypoint and at least one of the affected contours are moved by at least one processor in at least one subsequent image by a time-based distance, wherein the time-based distance depends on the time interval between at least one image and at least one subsequent image.

[0070] In this context, the term "time-series image" refers to a set of images captured sequentially over consecutive time by a medical imaging device in the same pose. The contours of at least one image are edited based on a first input and anatomical information. However, the contours are edited only for the first image among the at least one images. Therefore, at the current time, necessary adjustments are made in at least one subsequent image based on the edited contour and at least one of the updated contours to ensure that a given contour drawn along the boundary of at least one portion in the at least one subsequent image is consistent with the corresponding contour in the first image among the at least one images. In this context, affected keypoints are determined, wherein the affected keypoints are in the neighborhood of at least one of the edited contours and at least one of the updated contours. Hereinafter, the term "affected keypoint" refers to a keypoint on a contour that requires editing for anatomical accuracy based on at least one of the edited contours and at least one of the updated contours. The affected keypoints do not need to be anatomically related to at least one of the edited contours and at least one of the updated contours. Similarly, affected contours are determined, wherein the affected contours are in the neighborhood of at least one of the edited contours and at least one of the updated contours. In this paper, the term "affected contour" refers to a portion of the contour of at least one part or another part that requires editing for anatomical accuracy based on at least one of the edited contour or the updated contour. Subsequently, the affected keypoints or at least one of the affected contours are moved over time. The time-based distance can be determined using at least one mathematical formula or function, which facilitates moving the affected keypoints or at least one of the affected contours by knowing the precise location of at least one part over time. Furthermore, the time interval between at least one image and at least one subsequent image can be inherently fixed or dynamic. For example, time-series images of the heart's beating state. The affected keypoints and affected contours can be manipulated by the user device to verify whether small or large regions are affected by at least one of the edited contour or the updated contour.

[0071] According to an embodiment, the step of updating at least one subsequent image of at least one image further includes copying at least one of the edited contours and the other updated contours from at least one image to at least one subsequent image by at least one processor. This is done to consistently adjust another contour in the at least one subsequent image based on anatomical information, using at least one of the edited contours and the other updated contours from at least one image. The technical benefit of copying at least one of the edited contours and the other updated contours from at least one image to at least one subsequent image is the precise marking of the contours in the at least one subsequent image, such that another contour is drawn along the boundary of at least one portion in the at least one subsequent image, as drawn in the at least one image. This ensures that at least one portion in the at least one subsequent image is not misidentified.

[0072] Figure 2 This is a block diagram illustrating a system for implementing a perceptual anatomical contour editing method according to an embodiment of the present disclosure. (See reference) Figure 2 A block diagram illustrating a system 200 for implementing a perceptual anatomical contour editing method is shown. The system 200 includes at least one processor (depicted as processor 202) and a user device 204. The at least one processor 202 is communicatively coupled to the user device 204.

[0073] Figure 3A and Figure 3B This is an exemplary image of at least one anatomically identifiable structure according to embodiments of the present disclosure. Reference Figure 3A and Figure 3B The image 300 shows at least one anatomically identifiable structure, wherein the at least one anatomically identifiable structure is the heart. Figure 3A In this process, a first image segment is identified, wherein the first image segment represents at least one part of the heart. In this document, at least one part of the heart is at least one of the right ventricle 302, left ventricular myocardium 304, left ventricular endocardium 306, and at least one papillary muscle (depicted as papillary muscle 308). Figure 3B In the process, at least one outline (depicted as outlines 310, 312, 314) is drawn along the boundary of at least one part of the heart. Outline 310 is drawn along the boundary of the left ventricular myocardium 304, outline 312 is drawn along the boundary of the left ventricular endocardium 306, and outline 314 is drawn along the boundary of at least one papillary muscle 308.

[0074] Figure 4 It is an exemplary image of at least one anatomically identifiable structure, wherein the contour is edited according to embodiments of this disclosure to generate an edited contour. Reference Figure 4 Image 400 is shown with control point C0. Control point C0 is located outside a given contour 402 or inside another given contour 404. A third input indicating a control radius (not shown) is then determined. Image 400 then shows the two furthest points C1 and C2 on the given contour 402 and the other given contour 404 from control point C0. A spline (not shown) is drawn from one of the two furthest points C1 and C2 to the other through control point C0. The spline is then replaced with uniformly sampled spline points (as shown in surrounding region 406). Thus, edited contour 408 and another edited contour 410 are generated by adjusting the given contour 402 and the other given contour 404 to include uniformly sampled spline points 406.

[0075] According to an embodiment, when editing contours 402, 404 to generate edited contours 408, 410, at least one processor is configured to implement a perceptual anatomical contour editing method. First, a second input indicating a control point C0 is received, wherein the control point C0 is located outside or inside contours 402, 404. Second, a third input indicating the control radius of a circular control region centered on control point C0 is received, wherein the circular control region includes at least a portion of the contour failure region. Third, a fourth input indicating the two farthest points C1, C2 on contours 402, 404 from control point C0 is received, wherein the two farthest points C1, C2 are located within a portion of the contour failure region. Fourth, a spline is drawn from one of the two farthest points C1, C2 to the other of the two farthest points C1, C2 through control point C0. Fifth, the spline is replaced with uniformly sampled spline points 406. Finally, the edited contour is generated by adjusting the contour to include the uniformly sampled spline points 406.

[0076] Figure 5 This is an exemplary image illustrating the control radius of a circular control region according to an embodiment of the present disclosure. Reference Figure 5 Image 500 shows the control radii of circular control areas 502 and 504. The control radii of circular control areas 502 and 504 can be manipulated by a user associated with a user device (not shown). In one case, scrolling the mouse upwards increases the control radius of circular control area 502. In another case, scrolling the mouse downwards decreases the control radius of circular control area 504.

[0077] Figure 6 This is an exemplary image illustrating another outline of an updated portion according to an embodiment of this disclosure. Reference Figure 6 Image 600 represents the heart, and another part of the heart is at least one of the right ventricular endocardium 602 and the left ventricular epicardium 604. A first contour polygon 606 of the right ventricular endocardium 602 and a second contour polygon 608 of the left ventricular epicardium 604 are identified. In this document, one of the first contour polygon 606 and the second contour polygon 608 overlaps with the other of the first contour polygon 606 and the second contour polygon 608. A first point pair (RV1, LV1) and a second point pair (RV2, LV2) are determined. Subsequently, edited first contour polygons and edited second contour polygons are generated by adjusting the first contour polygons 606 and the second contour polygons 608 based on the first point pair (RV1, LV1), the second point pair (RV2, LV2), and anatomical information.

[0078] As used herein, the term "exemplary" means used as a non-limiting example, instance, or illustration. As used herein, the term "for example" refers to a list of one or more non-limiting examples, instances, or illustrations. As used herein, a circuit is "operable" to perform a function, regardless of whether the execution of the function is disabled or not enabled by some user-configurable setting, as long as the circuit includes the hardware and / or code necessary to perform the function (if required).

[0079] The disclosed embodiments also relate to the system as described above. The various embodiments and variations disclosed above are applicable to the system with necessary modifications.

[0080] According to an embodiment, when editing a contour to generate an edited contour, at least one processor is configured to:

[0081] Receive a second input indicating a control point, wherein the control point is located outside or inside the contour;

[0082] Receive a third input indicating the control radius of a circular control area centered on a control point, wherein the circular control area includes at least a portion of the contour failure area;

[0083] Receive a fourth input indicating the two farthest points on the profile from the control point, wherein the two farthest points are located within a portion of the profile failure area;

[0084] Draw a spline from one of the two farthest points to the other of the two farthest points through control points;

[0085] Replace the spline with uniformly sampled spline points; and

[0086] Edited contours are generated by adjusting the contours to include uniformly sampled spline points.

[0087] According to another embodiment, at least one anatomically identifiable structure is the heart, and another portion of the heart is at least one of the epicardium and endocardium, and at least one processor is further configured to update another contour of the other portion by:

[0088] Identify the first profile along the boundary of the epicardium and the second profile along the boundary of the endocardium;

[0089] Compare the first and second contours with anatomical information; and

[0090] When the relative arrangement of the first profile and the second profile is determined to be mismatched with the reference relative arrangement of the epicardium and endocardium based on comparison, at least one of the first profile and the second profile is adjusted to match the reference relative arrangement.

[0091] According to yet another embodiment, at least one anatomically identifiable structure is the heart, and another portion of the heart is at least one of the right ventricular epicardium and the left ventricular epicardium, and at least one processor is configured to update another contour of the other portion by:

[0092] Identify a first contour polygon of the right ventricular epicardium and a second contour polygon of the left ventricular epicardium, wherein one of the first contour polygon and the second contour polygon overlaps with the other of the first contour polygon and the second contour polygon;

[0093] Determine a first pair of points, which includes a first point in a first contour polygon and a first point in a second contour polygon, wherein the first points are closest to each other.

[0094] The second point pair is determined by traversing along either the first or second contour polygon, wherein the second point pair includes a second point in the first contour polygon and a second point in the second contour polygon, the second points being closest to each other; and

[0095] Edited first contour polygons and edited second contour polygons are generated by adjusting the first contour polygon and the second contour polygon based on the first point pair, the second point pair, and anatomical information.

[0096] According to an embodiment, at least one image is a time-series image, and at least one processor is further configured to update at least one subsequent image of the at least one image based on at least one of an edited contour and another updated contour, wherein, when updating at least one subsequent image, the at least one processor is configured to:

[0097] Based on at least one of the edited contour and the updated contour, identify at least one affected key point near the contour failure region, and at least one affected contour; and

[0098] In at least one subsequent image, the affected keypoint or at least one of the affected contours is moved by a time-based distance, wherein the time-based distance depends on the time interval between at least one image and at least one subsequent image.

[0099] According to another embodiment, when updating at least one subsequent image of at least one image, at least one processor is further configured to copy at least one of the edited contours, or another updated contour, from at least one image to at least one subsequent image.

[0100] The disclosed embodiments also relate to computer program products as described above. The various embodiments and variations disclosed above are applicable to computer program products with necessary modifications.

[0101] refer to Figure 7 Furthermore, many embodiments are described based on sequences of actions performed, for example, by elements of a computing device or apparatus 700. Figure 7 As shown in the example, computing device 700 may include one or more of processor 702, memory 704, and graphical user interface 706, or any combination thereof. Although not shown, computing device 700 may be communicatively coupled to a network or network interface to enable communication with components and devices of computing device 700.

[0102] Processor 702 will typically include a hardware processor. While only one processor 702 is typically described herein, aspects of the disclosed embodiments are not limited thereto. In alternative embodiments, computing device 700 may include any suitable number of processors 702. Examples of processor 702 may include, but are not limited to, microprocessors, microcontrollers, complex instruction set computing (CISC) microprocessors, reduced instruction set computing (RISC) microprocessors, very long instruction word (VLIW) microprocessors, or any other type of processing circuitry.

[0103] exist Figure 7 In the example, computing device 700 also includes or is communicatively coupled to memory 704. Memory 704 may include appropriate logic, circuitry, interfaces, and / or code, which may be configured to store instructions executable by processor 702. Memory 704 is also configured to store sensor information, status information, and predictions. Memory 704 may also be configured to store the operating system of processor 702 and associated applications. Examples of implementations of memory 704 may include, but are not limited to, random access memory (RAM), read-only memory (ROM), hard disk drive (HDD), flash memory, and / or secure digital storage (SD) cards. Computer-readable storage media for providing non-transitory memory for computer program products may include, but are not limited to, electronic storage devices, magnetic storage devices, visual storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof.

[0104] It should be understood that the various actions described herein can be performed by specific circuitry (e.g., an application-specific integrated circuit (ASIC)), program instructions executed by one or more processors, or a combination of both. Furthermore, these sequences of actions described herein can be considered fully embodied in any non-transitory form of computer-readable storage medium storing a corresponding set of computer instructions that, when executed, will cause the associated processor to perform the functions described herein. Thus, various aspects of this disclosure can be embodied in a variety of different forms, all of which are considered to be within the scope of the claimed subject matter. Additionally, for the various embodiments described herein, any corresponding form of such an embodiment may be described herein as, for example, "logic configured to perform the actions."

[0105] Another embodiment of this disclosure may provide a non-transitory machine and / or computer-readable storage and / or medium having machine code and / or a computer program stored thereon, the computer program having at least one code segment executable by a machine and / or computer, thereby enabling the machine and / or computer to perform the steps described herein to implement the perceptual anatomical contour editing method.

[0106] Aspects of the disclosed embodiments may also be embedded in a computer program product that includes all features enabling the implementation of the methods described herein and, when loaded into a computer system, is capable of executing those methods. In this context, a computer program means any expression of a set of instructions, statically or dynamically defined in any language, code, or notation, intended to cause a system with information processing capabilities to directly perform a particular function, or to perform a particular function after one or both of the following: a) being translated into another language, code, or notation; or b) being reproduced in a different material form.

[0107] Furthermore, those skilled in the art will understand that the various illustrative logic blocks, modules, circuits, algorithms, and / or steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, firmware, or a combination thereof. To clearly illustrate this hardware-software interchangeability, various illustrative components, blocks, modules, circuits, and steps have been described above in general terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art may implement the described functionality in different ways for various specific applications, but such implementation decisions should not be construed as departing from the scope of this disclosure.

[0108] The methods, sequences, and / or algorithms described in conjunction with the embodiments disclosed herein can be directly implemented in firmware, hardware, software modules executed by a processor, or combinations thereof. Software modules may reside in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disks, physical and / or virtual disks, removable disks, CD-ROMs, virtualization systems or devices such as virtual servers or containers, or any other form of storage medium known in the art. Exemplary storage media are communicatively coupled to a processor (including logic / code executed in the processor) such that the processor can read information from and write information to the storage medium. Alternatively, the storage medium may be integrated with the processor.

[0109] Although this disclosure has been described with reference to certain embodiments, it should be noted that, for example, those skilled in the art will understand that various changes and modifications can be made and equivalents can be substituted without departing from the scope of this disclosure, such as that defined in the appended claims. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of this invention without departing from the scope of this disclosure. The functions, steps, and / or actions of the method claims according to embodiments of this disclosure described herein need not be performed in any particular order. Moreover, although elements of this disclosure may be described or claimed in the singular, the plural forms are also covered unless expressly stated to be limited to the singular. Therefore, it is contemplated that this disclosure is not limited to the specific embodiments disclosed, but rather that this disclosure will include all embodiments falling within the scope of the appended claims.

[0110] Modifications to the embodiments of the present disclosure described above are possible without departing from the scope of the disclosure as defined by the appended claims. Expressions such as “comprising,” “including,” “incorporated,” “having,” and “are” used to describe and claim this disclosure are intended to be interpreted in a non-exclusive manner, allowing for the presence of additional items, parts, or elements not explicitly described. Singular references are also interpreted to refer to the plural. The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment described as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments and / or to exclude the incorporation of features from other embodiments. The word “optionally” is used herein to mean “provided in some embodiments and not in others.” It should be understood that certain features of the present disclosure described in the context of a single embodiment for clarity may also be provided in combination in a single embodiment. Conversely, various features of the present disclosure described in the context of a single embodiment for brevity may also be provided individually or in any suitable combination or as suitably as in any other embodiment described in this disclosure.

Claims

1. A method for editing perceptual anatomical contours, comprising: Receive at least one image, wherein the at least one image represents at least one anatomically recognizable structure; Identify a first image fragment that characterizes at least one part of the at least one anatomically identifiable structure; The first image segment is labeled to generate a label for at least one of the parts; Draw at least one outline along the boundary of at least one portion; Receive a first input indicating a contour failure area, the first input being provided using a user device, and wherein the contour failure area includes a portion of a contour that needs to be edited; The contour is edited based on the first input and anatomical information to generate an edited contour; wherein a second input indicating control points located outside or inside the contour is received; a third input indicating the control radius of a circular control region centered on the control points is received, the circular control region including at least a portion of the contour failure region; a fourth input indicating the two farthest points on the contour from the control points, the two farthest points located within the contour failure region; a spline is drawn from one of the two farthest points to the other via the control points; the spline is replaced with uniformly sampled spline points, and the edited contour is generated by adjusting the contour to include the uniformly sampled spline points; and Update another contour of another part of the at least one anatomically identifiable structure based on the edited contour, wherein the other part is anatomically related to the at least one part.

2. In the perceptual anatomical contour editing method according to claim 1, the second input, the third input, and the fourth input are all provided using a user device.

3. The perceptual anatomical contour editing method according to claim 2, wherein, The at least one anatomically identifiable structure is the heart, and the other portion of the heart is at least one of the epicardium and endocardium, wherein updating the other contour of the other portion includes: Identify a first profile along the boundary of the epicardium and a second profile along the boundary of the endocardium; Compare the first and second contours with the anatomical information; and When it is determined based on the comparison that the relative arrangement of the first profile and the second profile does not match the reference relative arrangement of the epicardium and the endocardium, at least one of the first profile and the second profile is adjusted to match the reference relative arrangement.

4. The perceptual anatomical contour editing method according to claim 2, wherein, The at least one anatomically identifiable structure is the heart, and the other portion of the heart is at least one of the right ventricular epicardium and the left ventricular epicardium, wherein updating the other contour of the other portion includes: Identify a first contour polygon of the right ventricular epicardium and a second contour polygon of the left ventricular epicardium, wherein one of the first contour polygon and the second contour polygon overlaps with the other of the first contour polygon and the second contour polygon; Determine a first pair of points, which includes a first point in the first contour polygon and a first point in the second contour polygon, wherein the first points are closest to each other; A second pair of points is determined by traversing along either the first or the second contour polygon, wherein the second pair of points comprises a second point in the first contour polygon and a second point in the second contour polygon, the second points being closest to each other; and Edited first contour polygons and edited second contour polygons are generated by adjusting the first contour polygon and the second contour polygon based on the first point pair, the second point pair and the anatomical information.

5. The perceptual anatomical contour editing method according to claim 3, wherein, The other part of the heart is at least one papillary muscle, and wherein the step of updating the other contour of the other part includes: Identify the third contour polygon of a given papillary muscle; and The size of the third contour polygon is adjusted based on a predefined size threshold algorithm.

6. The perceptual anatomical contour editing method according to claim 1, wherein, The at least one image is a time-series image, and the method further includes: updating at least one subsequent image of the at least one image based on at least one of the edited contour and another updated contour, wherein the step of updating the at least one subsequent image includes: Based on the edited contour and at least one of the updated contours, determine the affected key points near the contour failure region, and at least one of the affected contours; and In the at least one subsequent image, at least one of the affected key points and the affected contours is moved by a time-based distance, wherein the time-based distance depends on the time interval between the at least one image and the at least one subsequent image.

7. The perceptual anatomical contour editing method according to claim 6, wherein, The step of updating the at least one image of the at least one subsequent image further includes copying at least one of the edited contour and the other updated contour from the at least one image to the at least one subsequent image.

8. The perceptual anatomical contour editing method according to claim 1, wherein, A user device is used to provide a given input, which is at least one of touch input, click input, click and drag input, and text input.

9. The perceptual anatomical contour editing method according to claim 1 further includes: Access the anatomical information from a data store in which the anatomical information is stored, wherein the anatomical information includes at least one of the following: the size, thickness value, boundary, relative size, predefined size threshold, arrangement, and anatomical relationship between a given portion and the at least one portion of the at least one anatomically identifiable structure.

10. A computer program product comprising non-transitory computer-readable program instructions, which, when executed by a hardware processor of a computing device, are configured to cause the computing device to perform the method as described in any one of claims 1-9.

Images