Edge detection brush

Abstract

A method for processing a medical image of a subject is provided. The method includes presenting a slice of the medical image of the subject on a display. The medical image includes voxels. The method further includes performing automatic edge detection on a first slice of the medical image and obtaining segmented slices. Automatic edge detection is based on user-selected voxels in the slice of the medical image. Automatic edge detection is based on a user-controllable edge detection brush. Not all voxels selected by the edge detection brush are designated as edges.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims priority to U.S. Provisional Application No. 63 / 609,246, filed December 12, 2023; U.S. Provisional Application No. 63 / 524,470, filed June 30, 2023; and U.S. Provisional Application No. 63 / 524,387, filed June 30, 2023, the contents of each of which are hereby incorporated by reference in their entirety. This application is related to U.S. Patent Application No. 18 / 750,582, filed June 21, 2024, and U.S. Patent Application No. 18 / 750,190, filed June 21, 2024, the contents of each of which are hereby incorporated by reference in their entirety.

Background Art

[0002] Tumor treating fields (TT fields) are low - intensity alternating electric fields within an intermediate frequency range (e.g., 50 kHz to 1 MHz) and can be used in the treatment of tumors as described in U.S. Patent No. 7,565,205. In current commercial systems, a TT field is non - invasively induced in a region of interest by applying an alternating current (AC) voltage between an electrode assembly (e.g., an array of capacitive coupling electrodes, also referred to as an electrode array, a transducer array, or simply a "transducer") disposed on a patient's body. Conventionally, a first pair of transducers and a second pair of transducers are disposed on a subject's body. An AC voltage is applied between the first pair of transducers for a first time interval to generate an electric field with electric field lines running generally in the anterior - posterior direction. Next, an AC voltage is applied between the second pair of transducers at the same frequency for a second time interval to generate an electric field with electric field lines running generally in the left - right direction. The system repeats this two - step sequence over the course of treatment.

Brief Description of the Drawings

[0003] [Figure 1]This flowchart shows an example of a computer implementation method for processing a medical image of a subject to generate a transducer layout for applying a tumor treatment field to the subject, according to one embodiment. [Figure 2] This flowchart shows an example of a computer implementation method for automatic edge detection in medical images of a subject, according to one embodiment. [Figure 3] This flowchart shows an example of a computer implementation method for generating a transducer layout for applying a tumor treatment field to a subject, according to one embodiment. [Figure 4] This is an example of an application interface for automatic edge detection according to one embodiment. [Figure 5] This is an example of an application interface that generates at least one transducer layout for delivering a TT field to a subject, according to one embodiment. [Figure 6] This is an example of an application interface that generates at least one transducer layout for delivering a TT field to a subject, according to one embodiment. [Figure 7] An exemplary system for applying an alternating electric field to a subject is shown. [Figure 8] An example of a transducer placed on the subject's head is shown. [Figure 9] This specification shows an exemplary computer device according to one or more embodiments described herein.

[0004] Various embodiments will be described in detail below with reference to the attached drawings. In the drawings, similar reference numerals represent similar elements. [Modes for carrying out the invention]

[0005] Medical images of a subject are often used when generating transducer layouts for applying a tumor treatment field (TT field) to that subject. Examples of such medical images include magnetic resonance imaging (MRI) scans, computed tomography (CT) images, positron emission tomography (PET) images, and / or combinations thereof. Segmentation is often performed on medical images, dividing the image into two or more segments. Each segment represents a different object of interest. Medical images are often segmented to extract or separate objects of interest (e.g., abnormal tissue) from other structures (e.g., normal tissue). For example, segmenting a medical image can separate a tumor from normal tissue. Segmentation can be performed manually, semi-automatically, and / or automatically.

[0006] As the inventors have discovered, performing medical image segmentation is difficult when generating transducer layouts for applying the TT field to a subject, and this is a technical problem. For example, separating tissue associated with tumors or other similar objects (e.g., abnormal tissue) from non-tumor tissue (e.g., normal tissue) is difficult due to the irregular shape of the tissue, the resolution of the medical image, noise in the medical image, and other similar factors. Furthermore, segmentation is performed for each slice of the medical image. When done manually, segmentation is a time-consuming process because it is necessary to perform segmentation for each slice of the medical image in order to separate abnormal tissue from normal tissue. As the inventors have discovered, partially and / or fully automating the segmentation of medical images can save time and improve the segmentation results, thereby improving the transducer layout for applying the TT field.

[0007] One or more embodiments described herein provide a technical solution to address the technical problem of performing pre-segmentation on medical images used to generate transducer layouts for applying a TT field to a subject. One or more embodiments described herein provide a computer implementation method for processing medical images of a subject to generate transducer layouts for applying a TT field to the subject. One or more embodiments described herein provide a computer implementation method for automated edge detection in medical images of a subject. One or more embodiments described herein provide a computer implementation method for generating transducer layouts for applying a TT field to a subject. Due to the amount of data and computational complexity, the technical solutions are not feasible with human intelligence and must instead be performed by the computer-based methods described herein.

[0008] In some embodiments, upon receiving a medical image, a first slice of the medical image can be presented to the user. The user selects voxels from the first slice of the medical image. The selected voxels are used to automatically detect edges within the first slice using a user-controllable edge detection brush. That is, the user defines an edge detection brush and uses it to indicate objects of interest (e.g., tumors) on the slice. Automatic edge detection designates some (but not all) of the voxels selected by the edge detection brush as edges of the object of interest (e.g., tumors). This generates a first segmented slice. Next, a second slice of the medical image is displayed, with one or more intermediate slices between the first and second slices. Automatic edge detection is then performed on the second slice of the medical image to generate a second segmented slice. Next, automatic segmentation of the intermediate slice(s) is performed using the first and second segmented slices to obtain segmented slices. Subsequently, a transducer layout for applying a TT field to a subject is generated based on the segmented medical image.

[0009] One or more embodiments described herein provide users with practical applications for generating transducer layouts based on medical images. By using medical images such as MRI, CT, and / or PET, the tissue conductivity of the subject is taken into consideration when generating transducer layouts for treating the subject with a TT field. Automating the segmentation process allows for more effective use of medical images, enabling more efficient image review and processing for generating transducer layouts for applying a TT field to the subject. For example, these tools help pinpoint the areas of the subject to be treated (e.g., where to concentrate the AC electric field on the subject). These and other technical improvements may be realized using one or more embodiments described herein.

[0010] Figure 1 is a flowchart illustrating an example of a computer implementation method 100 for processing a medical image of a subject to generate a transducer layout for applying a tumor treatment field to the subject. Certain steps of method 100 are described as computer implementation steps. The computer may be any device including, for example, one or more processors and memory accessible by one or more processors, the memory storing instructions that, when executed by one or more processors, cause the computer to perform the relevant steps of method 100. Method 100 may be carried out by any suitable system or apparatus, such as the apparatus in Figure 9. Although the sequence of operations is shown in Figure 1 for illustrative purposes, the timing and sequence of such operations may be modified where appropriate without prejudice to the objectives and advantages of the embodiments described in detail herein.

[0011] Referring to Figure 1, in step 102, method 100 includes presenting a first slice of a medical image of the subject on a display. The medical image includes voxels, which are three-dimensional representations of points on the image. For example, the medical image may include an MRI image, a CT image, a PET image, and / or a combination thereof and / or a combination thereof. According to one or more embodiments described herein, the medical image may include the torso of the subject, the head of the subject, and / or other appropriate body parts of the subject.

[0012] In step 104, method 100 includes performing automatic edge detection on a first slice of a medical image and obtaining a first segmented slice. For example, when a user draws on a medical image using an edge detection brush, edges are detected from the medical image based on the user's drawing. More specifically, edge detection is based on, for example, user-selected voxels (voxels selected by the user using the edge detection brush) in the first slice of the medical image. Automatic edge detection is based on a user-controllable edge detection brush. It should be noted that not all voxels selected by the edge detection brush are designated as edges. For example, the user selects the edge detection brush using the interface of the automatic edge detection application.

[0013] Figure 4 shows an example of an interface 400 for such an application for automatic edge detection. In this example, interface 400 includes a brush option 402, a brush radius option 404, an edge detection option 406, and a gray level selection option 408. The user can select from options 402, 404, 406, and 408, and automatic edge detection is performed based on the user's selection. The brush option 402 includes brush types such as freedraw brushes, lasso brushes, and polygon brushes, as well as / or combinations and / or multiple forms thereof. The brush radius option 404 defines the brush radius (e.g., 3 millimeters (mm)), and the user can set the brush radius by entering a numerical value as shown in the figure or by manipulating arrows and / or sliders. The edge detection option 406 defines the amount of pixels defined as edges, as a percentage of selected pixels.

[0014] In other words, according to one or more embodiments described herein, performing automatic edge detection includes determining the radius of the edge detection brush to be used for automatic edge detection and determining the edge threshold of the edge detection brush. The image values ​​of voxels selected by the edge detection brush are designated as edges based on the edge threshold. For example, if a user draws on a slice using the brush, the edge detection option 406 defines the percentage of user-selected (e.g., drawn) pixels that are designated as edges.

[0015] Consider the following example. An exception occurs when edge detection option 406 is set to 100%, so a more reasonable range for edge detection option 406 is 0% to 90%. Selecting 30% for edge detection option 406 means detecting 70% of 90% (e.g., 63%). The length of the range is determined by the width of the window settings (e.g., contrast and brightness) sampled by the user (e.g., the user clicks with a brush and samples the median intensity at the center of the brush and a certain number (e.g., 8) voxels around the center of the brush). Therefore, selecting 0% means that all voxels within the range are detected as edges. Selecting 30% means that 70% of 100% are detected (e.g., 70% of 90% = 63%). Thus, the range is [minimum, maximum] = related range = width × (1 - tolerance × 0.9). For example, if the median is 100 and the tolerance is 70%, then if the width (range length) is 1000, the relevant range will be 1000 × (1 - (0.7 × 0.9)) = 370. For details on automatic edge detection, please refer to Figure 2 and see the explanation below.

[0016] Continuing to refer to Figure 1, in step 106, method 100 includes displaying a second slice through the medical image of the subject on a display. In this example, the first and second slices are in the same direction and are divided by multiple slices of the medical image.

[0017] In step 108, method 100 includes performing automatic edge detection in the second slice of the medical image based on user-selected voxels in the second slice of the medical image to obtain a second segmented slice.

[0018] In step 110, method 100 includes performing automated segmentation on a plurality of slices between the first and second segmented slices based on a first segmented slice and a second segmented slice to obtain a segmented slice, the segmented medical image includes the first segmented slice, the second segmented slice, and the segmented slice of the medical image. According to one or more embodiments described herein, the plurality of slices are automatically segmented by interpolating between the segmentation in the first segmented slice and the segmentation in the second segmented slice. According to one or more embodiments described herein, the segmented slice includes at least one of a resection cavity or edema of a subject having an edge detected by automated edge detection. A resection cavity may refer to a cavity resulting from the removal of tissue, structure, or organ. Edema may refer to swelling caused by fluid accumulation. As an example, the number of plurality of automated segmented slices between a pair of segmented slices is between 2 and 20. As another example, the number of plurality of automated segmented slices between a pair of segmented slices is between 2 and 5. Other numbers of automated segmented slices are also possible.

[0019] In step 112, method 100 includes generating multiple transducer layouts for applying tumor treatment fields to a subject based on segmented medical images.

[0020] According to one or more embodiments described herein, Method 100 may include one or more additional steps. For example, Method 100 may include determining the position of a transducer for a TT field. A detailed description of determining the transducer position in a TT field is given below with reference to Figure 3.

[0021] FIG. 2 is a flowchart showing an example of a computer-implemented method 200 for automatic edge detection in a medical image of a subject. According to one or more embodiments described herein, step 104 of FIG. 1 may be implemented using method 200. Certain steps of method 200 are described as computer-implemented steps. The computer can be any device including, for example, one or more processors and a memory accessible by the one or more processors, and the memory stores instructions that, when executed by the one or more processors, cause the computer to perform the relevant steps of method 200. Method 200 can be implemented by any suitable system or device, such as the apparatus of FIG. 9. Although the order of operations is shown in FIG. 2 for illustrative purposes, such timing and order of operations can be changed where appropriate without negating the objectives and advantages of the embodiments described in detail herein.

[0022] Referring to FIG. 1, at step 202, method 200 includes identifying a user-selected voxel within a slice of a medical image. The user-selected voxel may be at the center of the position selected by the user within the slice of the medical image.

[0023] In step 204, method 200 includes determining an edge detection image value based on a user-selected voxel within a slice of a medical image. According to one or more embodiments described herein, determining an edge detection image value based on a user-selected voxel in a slice of a medical image includes determining a central image value as the image value of the user-selected voxel at the center of the user-selected position in the slice of the medical image, determining adjacent image values as the image values of voxels adjacent to the user-selected voxel, calculating an average image value based on the central image value and the adjacent image values, and assigning the edge detection image value as the average image value. According to one or more embodiments described herein, the voxels adjacent to the user-selected voxel include eight voxels surrounding the user-selected voxel. According to one or more embodiments described herein, the voxels adjacent to the user-selected voxel may include any number of voxels surrounding the user-selected voxel, such as two, three, four, five, six, seven, eight, nine, ten or more voxels, such as 24 or more voxels. According to one or more embodiments described herein, the voxels adjacent to the user-selected voxel may be user-defined, pre-defined, or a combination thereof. According to one or more embodiments described herein, determining an edge detection image value based on a user-selected voxel in a slice of a medical image includes determining the image value of the user-selected voxel at the center of the user-selected position in the slice of the medical image as the central image value, and assigning the edge detection image value as the average image value.

[0024] In step 206, method 200 includes determining the size of the edge detection brush to be used for automatic edge detection. According to one or more embodiments described herein, the size of the edge detection brush may be determined by the shape of the edge detection brush, for example, a freedraw brush, a lasso brush, a polygon brush, and / or a combination thereof. According to one or more embodiments described herein, the type of edge detection brush may be user-defined, predefined, or a combination thereof. As an example, in Figure 4, brush option 402 provides a default predefined edge detection brush and a user-selectable icon for changing the predefined edge detection brush. According to one or more embodiments described herein, the size of the edge detection brush is the radius of the edge detection brush, such as a circular edge detection brush. According to one or more embodiments described herein, the size of the edge detection brush may be user-defined, predefined, or a combination thereof. As an example, in Figure 4, edge radius option 404 provides a default predefined value (e.g., 3 mm) for changing the predefined value of the edge detection brush size, a user-selectable icon, and a user-adjustable data field.

[0025] In step 208, method 200 includes determining the edge threshold of the edge detection brush. According to one or more embodiments described herein, the user-selected edge threshold of the edge detection brush is defined as a percentage and / or image value. According to one or more embodiments described herein, the edge threshold of the edge detection brush may be user-defined, predefined, or a combination thereof. As an example, in Figure 4, the edge detection option 404 provides a default predefined value (e.g., 30%) for changing the predefined value of the edge threshold of the edge detection brush, a user-selectable icon, and a user-adjustable data field.

[0026] In step 210, method 200 includes determining a range of image values ​​to be designated as an edge based on the edge detection image values ​​and the edge threshold.

[0027] According to one or more embodiments described herein, the range of image values ​​designated as an edge includes the number of image values ​​within the range M, the upper limit of the range UL, and the lower limit of the range LL. The number of image values ​​M is M = N × (1 - P), where the range of image values ​​in a medical image has a maximum value N and the user selection for the edge threshold is a percentage P. The upper limit of the range UL is UL = IV + 0.5 × M, where the image value IV is the edge detection image value. The lower limit of the range LL is LL = IV - 0.5 × M. For example, if N = 1000, P = 0.7, and M = 300, then IV = 600, UL = 750, and LL = 450.

[0028] According to one or more embodiments described herein, the range of image values ​​designated as an edge includes the number of image values ​​M within the range, the upper limit of the range UL, and the lower limit of the range LL. The number of image values ​​M is in the range M = N × (1 - (P × RL)), where the range of image values ​​in a medical image has a maximum number of image values ​​N, the user selection for the edge threshold is a percentage P, and the range limiter is a percentage RL. The upper limit of the range UL is UL = IV + 0.5 × M, where the image value IV is the edge detection image value. The lower limit of the range LL is LL = IV - 0.5 × M. For example, if N = 1000, P = 0.7, RL = 0.9, and M = 370, then IV = 600, UL = 785, and LL = 415.

[0029] According to one or more embodiments described herein, the edge threshold is an image value. The upper limit of the range of image values ​​is the sum of the edge detection image value and the edge threshold, and the lower limit of the range of image values ​​is the difference between the edge detection image value and the edge threshold.

[0030] In step 212, method 200 includes receiving user-selected voxels in the slice based on the interaction between the edge detection brush and the voxels in the slice, and the size of the edge detection brush.

[0031] In step 214, method 200 includes designating user-selected voxels in a slice as edge voxels of the slice based on a range of image values ​​to be designated as edges. According to one or more embodiments described herein, designating user-selected voxels in a slice as edge voxels of the slice includes comparing the image value of the user-selected voxel with a range of image values. According to one or more embodiments described herein, designating user-selected voxels in a slice as edge voxels of the slice includes, for each user-selected voxel in the slice, designating the user-selected voxel as an edge if the image value of the user-selected voxel is within the range of image values, and designating the user-selected voxel as not an edge if the image value of the user-selected voxel is outside the range of image values. According to one or more embodiments described herein, the image value of a voxel in a slice includes an integer indicating the intensity of the voxel. According to one or more embodiments described herein, the image value of a voxel in a slice includes a gray level value.

[0032] According to one or more embodiments described herein, multiple transducer layouts for applying a tumor treatment field to a subject are generated based on segmented slices of a medical image.

[0033] Figure 3 is a flowchart illustrating an example of a computer implementation method 300 for generating a transducer layout for applying a tumor treatment field to a subject. According to one or more embodiments described herein, step 112 in Figure 1 may be performed using method 300. Certain steps of method 300 are described as computer implementation steps. The computer may be any device including, for example, one or more processors and memory accessible by one or more processors, the memory storing instructions that, when executed by one or more processors, cause the computer to perform the relevant steps of method 300. Method 300 may be performed by any suitable system or apparatus, such as the apparatus in Figure 9. Although the sequence of operations is shown in Figure 3 for illustrative purposes, the timing and sequence of such operations may be modified where appropriate without prejudice to the objectives and advantages of the embodiments described in detail herein.

[0034] Referring to Figure 3, in step 302, method 300 includes defining a region of interest (ROI) in a medical image or segmented medical image for applying a tumor treating field to a subject. The ROI defines the location where the TT electric field is concentrated. According to one or more embodiments described herein, a volume can be assigned to the region of interest, for example, by using the approach described in "Correlation of Tumor Treating Fields Dosimetry to Survival Outcomes in Newly Diagnosed Glioblastoma: A Large-Scale Numerical Simulation-Based Analysis of Data from the Phase 3 EF-14 Randomized Trial" by Ballo MT et al., Int J Radiat Oncol Biol Phys. 2019;104(5):1106-1113.

[0035] In step 304, method 300 includes creating a three-dimensional model of the subject based on segmented medical images (e.g., segmented medical images determined from steps 102-110 in Figure 1), where the three-dimensional model of the subject includes a region of interest. According to one or more embodiments described herein, the region of interest in a medical image is part of the 3D model. According to one or more embodiments described herein, a three-dimensional conductivity map is part of the 3D model. The three-dimensional conductivity map may show the electrical conductivity of body tissues. Creating the 3D model may include performing calculations to determine the conductivity of the subject's tissues based on anchor medical images, medical images, and tissue types within the medical images. For example, creating the 3D model may include assigning tissue types and associated conductivity to voxels in the subject's 3D model. According to one or more embodiments described herein, creating a 3D model of the subject may include automatically segmenting normal tissue within medical images.

[0036] In step 306, method 300 includes generating a plurality of transducer layouts for applying a tumor treatment field to a subject based on a three-dimensional model of the subject. The transducer layout defines relative positions to the subject for positioning the transducer arrays. According to one or more embodiments described herein, the plurality of transducer layouts include four positions on the subject for positioning each of the four transducer arrays, such as the subject's head or torso. According to one or more embodiments described herein, each of the transducer arrays includes one or more electrode elements. The electrode elements can be of any suitable type or material. For example, at least one electrode element may include a ceramic dielectric layer, a polymer film, and / or a combination thereof and / or a combination thereof. The generation of the plurality of transducer layouts can be performed after receiving a selection by the user from a user interface to initiate the generation. According to one or more embodiments described herein, the generation of multiple transducer layouts in step 306 can be carried out using the technology of U.S. Patent Application Publication No. 2021 / 0201572, entitled “METHODS, SYSTEMS, AND APPARATUSES FOR IMAGE SEGMENTATION,” which is owned by the same party and is incorporated herein by reference in whole.

[0037] In step 308, method 300 includes selecting at least two of the transducer layouts as recommended transducer layouts. According to one or more embodiments described herein, at least one of the recommended transducer layouts has a tumor treatment field with the highest dose delivered to an ROI, a tumor progression area, and / or a combination thereof and / or a combination thereof to similar elements. According to one or more embodiments described herein, at least one of the recommended transducer layouts is a transducer layout that is moved or rotated compared to the transducer layout with the highest dose of tumor treatment field delivered to an ROI. According to one or more embodiments described herein, at least three of the recommended transducer layouts have three tumor treatment fields with the highest dose delivered to an ROI.

[0038] In step 310, method 300 includes presenting recommended transducer layouts. For example, method 300 may include presenting one (or at least two, or at least three, or at least four) recommended transducer layouts, but other embodiments may present more or fewer transducer layouts. According to one or more embodiments described herein, presenting recommended transducer layouts includes presenting information about the recommended transducer layouts via a user interface. The information may include one or more of the following: the dose of the tumor treatment site delivered to the ROI for each of the recommended transducer layouts; medical image slices with the dose of the tumor treatment site superimposed for at least one recommended transducer layout; a two-dimensional graph comparing the percentage volume of the ROI with the percentage dose of the tumor treatment site for at least one recommended transducer layout; images of subjects depicting the positions of electrode elements for at least one recommended transducer layout; a two-dimensional graph depicting the cumulative dose of the tumor treatment site across the ROI for at least one recommended transducer layout; a two-dimensional graph depicting the dose of the tumor treatment site across the ROI for at least one recommended transducer layout; the percentage of overlap between the electrode elements of two recommended transducer layouts; the percentage of overlap between the bonding portions of two recommended transducer layouts; and / or similar elements including combinations thereof and / or multiples thereof.

[0039] In step 312, method 300 includes receiving a user selection of at least one recommended transducer layout. According to one or more embodiments described herein, the user can select a primary transducer layout and an alternative transducer arrangement. To make a selection, the user can approve the primary layout as the first layout, and then, after reviewing and evaluating the alternative layouts, select the alternative layout as the second layout. For example, the user selects one transducer layout (e.g., primary) to be used for a certain period. The user can then select another (e.g., alternative) transducer layout for use for another period after a certain period has elapsed. According to one or more embodiments described herein, the transducer layout can be approved by entering a username and password. Having two or more transducer layouts allows the subject to switch between transducer layouts, which can improve, for example, the subject's comfort.

[0040] In step 314, method 300 includes providing a report of at least one selected recommended transducer layout. According to one or more embodiments described herein, the report may show the positions of the transducer array of the selected recommended transducer layout on the subject in multiple views. According to one or more embodiments described herein, the report may provide doses of the tumor treatment field. It should be understood that different reports may be provided, for example, depending on the expected target of the report (e.g., a first report type for the subject, a second report type for inclusion in the subject's medical record). According to one embodiment, comments may be added using text boxes on the interface, a 3D head rendering may be shown and rotated as needed, and the report may be created using a report creation button on the interface. According to one or more embodiments described herein, the report may be edited via the interface. In this example, users can edit reports using the edit button on the interface, download or print reports using the download / print button on the interface, anonymize reports using the anonymize button on the interface, generate different report types (e.g., full reports, patient reports, and / or combinations thereof and / or multiples thereof) using the type dropdown on the interface, review different versions of reports using the version dropdown on the interface, return to patient management using the patient management button on the interface, and return to the welcome screen using the back button on the interface.

[0041] Figures 5 and 6 will be described below. Figure 5 is an example of an application interface for generating at least one transducer layout for delivering a TT electric field to a subject. The interface in Figure 5 supports, for example, the segmentation of an abnormal tissue region 501. The abnormal tissue region 501 is shown as shown in Figure 5. To segment abnormal tissue, such as the abnormal tissue region 501, the user can select the tools tab 502 to begin outlining the structure. The user can then select an active structure 504 to outline. In another embodiment, it may also be possible to select an active structure from the structure tab 505. The user can then select a brush 506 (or any other suitable tool) to perform the segmentation. According to one or more embodiments described herein, the brush 506 may be an edge detection brush that performs the automatic edge detection described with respect to Figure 1. According to one or more embodiments described herein, the brush 506 may be selected using the interface shown in Figure 4. According to one or more embodiments described herein, segmentation can be expedited using an interpolation tool 508. For example, a structure can be segmented in a first slice of a medical image (e.g., as in steps 102 and 104 of Figure 1), one or more subsequent slices of the medical image can be skipped, and then the structure can be segmented again on the next slice following the skipped slice (e.g., as in steps 106 and 108 of Figure 1). The interpolation tool 508 is then used to apply segmentation to the skipped slice, and this interpolation segmentation is performed based on segmentation performed on slices adjacent to the skipped slice (e.g., as in step 110 of Figure 1). According to one or more embodiments described herein, segmentation of abnormal tissue in a medical image is performed based on user input identifying abnormal tissue in the medical image, for example, the segmentation described with respect to Figure 1.

[0042] Referring to Figure 6, a dropdown menu displays multiple user-selectable options 602 (e.g., user-selectable icons) for manually segmenting a slice. Examples of user-selectable options 602 include, for example, a user-selectable icon for automatically filling an area (e.g., a polybrush option), a user-selectable icon for selecting an area without automatic filling (e.g., a paintbrush option), a user-selectable icon for erasing a segmentation (e.g., an erase option), a user-selectable icon for assigning a tissue type (e.g., an assignment option), a user-selectable icon for extending the boundary of an area (e.g., an expand and margin option), and / or combinations thereof and / or multiples thereof. According to one or more embodiments described herein, the user-selectable options 602 provide the user with a set of selectable tools without switching to the user tools tab 502. The tools can be used to segment abnormal tissue. For example, a polybrush or paintbrush can be used to draw the outline of an abnormal tissue area, such as an abnormal tissue area 501. Abnormal tissue can be any undesirable type of tissue, such as tumors, necrotic tissue, previous surgical sites (e.g., excision cavities), and / or combinations thereof and / or similar elements including multiples thereof.

[0043] The interface in Figure 6 may also include a cleanup option 604. This option allows for the automatic cleanup of segmented slices (either automatically segmented or manually segmented) through medical images, resulting in a cleaned segmented slice. For example, a segmented slice is automatically cleaned by dividing the segmented region of the segmented slice into a first and second part based on grayscale values. The first part is identified as normal tissue, and the second part as abnormal tissue. Abnormal tissue can include tumors, necrotic tissue, previous surgical sites, and / or combinations thereof and / or a combination thereof, including similar elements. As an example, the segmented region is divided based on a threshold adjusted by a user-selectable slider of grayscale values. According to one or more embodiments described herein, a segmented slice can be automatically cleaned by smoothing one or more edges of the segmented region of the segmented slice, removing one or more discontinuous segmented regions outside a larger segmented region of the segmented slice, removing one or more unsegmented regions inside the segmented region of the segmented slice, and / or a combination thereof and / or a combination thereof, including similar actions.

[0044] Figure 7 shows an exemplary apparatus 700 for applying an alternating current electric field (e.g., a TT electric field) to a subject's body. This system can be used to treat a target area of ​​a subject's body with the alternating current electric field. For example, the target area may be in the subject's brain, and the alternating current electric field may be delivered to the subject's body via two pairs of transducer arrays (e.g., four transducers 800 in Figure 8) positioned above the subject's head. In another example, the target area may be in the subject's torso, and the alternating current electric field is delivered to the subject's body via two pairs of transducer arrays positioned in at least one of the subject's chest, abdomen, or one or both thighs. Other arrangements of transducer arrays on the subject's body are also possible.

[0045] Exemplary apparatus 700 illustrates an exemplary system having four transducers (or “transducer arrays”) 700A–D. Each transducer 700A–D may include substantially flat electrode elements 704A–D positioned on substrates 702A–D and electrically and physically connected (e.g., through conductive wiring 706A–D). The substrates 704A–D may include, for example, cloth, foam, flexible plastic, and / or conductive medical gel. Two transducers (e.g., 700A and 200D) may be a first pair of transducers configured to apply an alternating electric field to a target area of ​​the subject's body. The other two transducers (e.g., 700B and 700C) may be a second pair of transducers similarly configured to apply an alternating electric field to a target area.

[0046] Transducers 700A-D may be coupled to an AC voltage generator 720, and the system may further include a controller 710 communicatively coupled to the AC voltage generator 720. The controller 710 may include a computer including one or more processors 724 and a memory 726 accessible by one or more processors 724. The memory 726 may store instructions, when executed by one or more processors, that cause the computer to control the AC voltage generator 720 to induce an alternating electric field between the pair of transducers 700A-D according to one or more voltage waveforms, and / or one or more methods disclosed herein. The controller 710 may monitor the operation performed by the AC voltage generator 720 (e.g., via a processor 724). One or more sensors 728 may be coupled to the controller 710 to provide the controller 710 with measurements or other information.

[0047] In some embodiments, the voltage generating component may supply the transducers 700A to D with an electrical signal having an AC waveform suitable for delivering TT field therapy to the subject's body at a frequency in the range of about 50 kHz to about 1 MHz.

[0048] Electrode elements 702A-D can be capacitively coupled. In one example, electrode elements 702A-D are ceramic electrode elements coupled to each other via conductive wiring 706A-D. The ceramic electrode elements may be circular or non-circular when viewed from a direction perpendicular to their surface. In other embodiments, the array of electrode elements is not capacitively coupled, and there is no dielectric material (such as a ceramic or high-dielectric polymer layer) associated with the electrode elements.

[0049] The structure of transducers 700A-D can take various forms. The transducer may be attached to the subject's body, or attached to or incorporated into clothing covering the subject's body. The transducer may include suitable materials for attaching it to the subject's body. For example, suitable materials may include cloth, foam, flexible plastic, and / or conductive medical gel. The transducer may be conductive or non-conductive.

[0050] A transducer may include any desired number of electrode elements (e.g., one or more electrode elements). For example, a transducer may include one, two, three, four, five, six, seven, eight, nine, ten, or more electrode elements (e.g., twenty electrode elements). Electrode elements may be of various shapes, sizes, and materials. Any structure for implementing a transducer (or electric field generator) used in conjunction with embodiments of the present invention may be used, insofar as they are capable of (a) delivering an AC electric field to the subject's body and (b) being positioned at locations specified herein. Transducers may be conductive or nonconductive. In some embodiments, an AC signal may be capacitively coupled to the subject's body. In some embodiments, at least one electrode element of the first, second, third, or fourth transducer may include at least one ceramic disk adapted to generate an AC electric field. In some embodiments, at least one electrode element of the first, second, third, or fourth transducer may include a polymer film adapted to generate an alternating electric field.

[0051] Figure 9 shows an example of a computer device 900 (also referred to as "device 900") for use in embodiments of the present invention. For example, device 900 may be a computer for implementing certain inventive techniques disclosed herein, such as processing a medical image of a subject to generate a transducer layout for delivering a TT electric field to the subject. For example, method 300 in Figure 3 may be performed by a computer such as device 900. For example, method 100 in Figure 1 may be performed by a computer such as device 900, and device 900 may be the same computer or a different computer used to perform method 200 in Figure 2 and / or method 300 in Figure 3. For example, steps 102-112 in Figure 1, steps 202-214 in Figure 2, and / or steps 302-314 in Figure 3 may be performed by a computer such as device 900. In some embodiments, a controller 710 shown in Figure 7 may be implemented together with device 900. In some embodiments, a controller 710 that applies an alternating electric field (e.g., a TT field) to a subject may be implemented using a device 900. The device 900 may include one or more processors 902, a memory 903, one or more input devices (not shown), and one or more output devices 905.

[0052] In some embodiments, based on input 901, one or more processors 902 may generate control signals to control a voltage generator to implement one or more embodiments described herein. For example, input 901 is a user input. For example, input 901 may be an input from another computer communicating with the device 900. Input 901 may be received in conjunction with one or more input devices (not shown) of the device 900.

[0053] Memory 903 may be accessible by one or more processors 902 (e.g., via link 904) so ​​that one or more processors 902 can read information to and write information to memory 903. Memory 903 may store instructions that, when executed by one or more processors 902, implement one or more embodiments described herein. Memory 903 may be a non-temporary computer-readable medium (or non-temporary processor-readable medium) containing a set of instructions for selecting at least one transducer layout for processing a medical image of a subject and delivering a tumor treatment field to the subject, and when the instructions are executed by a processor (such as one or more processors 902), the processor is caused to execute one or more methods described herein, such as methods 100, 200, and / or 300 shown in Figures 1 to 3, respectively.

[0054] One or more output devices 405 may provide information about the operation of the present invention, such as the selection of the transducer array, the voltage generated, and other operational information. Output devices 405 may provide visualization data according to some embodiments described herein.

[0055] The apparatus 900 may be an apparatus that processes medical images of a subject to generate a transducer layout for applying a TT field to the subject, and the apparatus may include one or more processors (such as one or more processors 902) and memory accessible by one or more processors 902 (such as memory 903), the memory 903 storing instructions that, when executed by one or more processors 902, cause the apparatus 900 to execute one or more methods described herein, such as methods 100, 200, and / or 300 shown in Figures 1-3. Exemplary Embodiments

[0056] The present invention includes other exemplary embodiments ("Embodiments") as follows:

[0057] (Embodiment 1) A computer implementation method for processing a medical image of a subject, the method comprising presenting a slice of the medical image of the subject, including voxels, on a display, and performing automatic edge detection on the slice of the medical image to obtain a segmented slice, wherein the automatic edge detection is based on user-selected voxels in the slice of the medical image, and the automatic edge detection is based on a user-controllable edge detection brush, not all of the voxels selected by the edge detection brush are designated as edges.

[0058] (Embodiment 2) The method according to Embodiment 1, wherein the execution of automatic edge detection includes determining the radius of the edge detection brush used for the automatic edge detection and determining the edge threshold of the edge detection brush, and the image values ​​of voxels selected by the edge detection brush are designated as edges based on the edge threshold.

[0059] (Embodiment 3) The method according to Embodiment 1, wherein performing automatic edge detection includes determining the user-selected voxel in the slice of the medical image, determining an edge detection image value based on the user-selected voxel in the slice of the medical image, determining the size of the edge detection brush to be used for automatic edge detection, determining an edge threshold for the edge detection brush, determining a range of image values ​​to be designated as an edge based on the edge detection image value and the edge threshold, receiving the user-selected voxel in the slice based on the interaction between the edge detection brush and the voxel in the slice, and the size of the edge detection brush, and designating the user-selected voxel in the slice as an edge voxel of the slice based on the range of image values ​​to be designated as an edge.

[0060] (Embodiment 4) The method according to Embodiment 3, wherein determining the edge detection image value based on the user-selected voxel in the slice of the medical image includes determining a central image value as the image value of the user-selected voxel at the center of the user-selected position in the slice of the medical image, determining adjacent image values ​​as the image values ​​of voxels adjacent to the user-selected voxel, calculating an average image value based on the central image value and the adjacent image value, and assigning the edge detection image value as the average image value.

[0061] (Embodiment 4A) The method according to Embodiment 4, wherein the voxel adjacent to the user-selected voxel includes eight voxels surrounding the user-selected voxel.

[0062] (Embodiment 5) The method according to Embodiment 3, wherein determining the edge detection image value based on the user-selected voxel in the slice of the medical image includes determining a center image value as the image value of the user-selected voxel at the center of the user-selected position in the slice of the medical image, and assigning the edge detection image value as the average image value.

[0063] (Embodiment 6) The method according to Embodiment 3, wherein the size of the edge detection brush is the radius of the circular edge detection brush.

[0064] (Embodiment 7) The method according to Embodiment 3, wherein the user selection of the edge threshold of the edge detection brush includes a percentage.

[0065] (Embodiment 7A) The method according to Embodiment 3, wherein the user selection of the edge threshold of the edge detection brush includes an image value.

[0066] (Embodiment 8) The method according to Embodiment 3, wherein the range of image values ​​to be designated as an edge includes the number of image values ​​M within the range, the upper limit UL of the range, and the lower limit LL of the range, the number of image values ​​M within the range is M = N × (1 - P), the range of image values ​​of the medical image has a maximum value N, the user selection for the edge threshold is a percentage P, the upper limit UL of the range is UL = IV + 0.5 × M, the image value IV is the edge detection image value, and the lower limit LL of the range is LL = IV - 0.5 × M.

[0067] (Embodiment 9) The method according to Embodiment 3, wherein the range of image values ​​to be designated as an edge includes the number of image values ​​M within the range, the upper limit UL of the range, and the lower limit LL of the range, the number of image values ​​M within the range is M = N × (1 - (P × RL)), the range of image values ​​of the medical image has a maximum value N, the user selection for the edge threshold is a percentage P, the range limiter is a percentage RL, the upper limit UL of the range is UL = IV + 0.5 × M, the image value IV is the edge detection image value, and the lower limit LL of the range is LL = IV - 0.5 × M.

[0068] (Embodiment 10) The method according to Embodiment 3, wherein the edge threshold is an image value, the upper limit of the range of the image value is the sum of the edge detection image value and the edge threshold, and the lower limit of the range of the image value is the difference between the edge detection image value and the edge threshold.

[0069] (Embodiment 11) The method according to Embodiment 3, wherein designating a user-selected voxel in the slice as an edge voxel of the slice includes comparing the image value of the user-selected voxel with the range of image values.

[0070] (Embodiment 12) The method according to Embodiment 3, wherein specifying a user-selected voxel in the slice as an edge voxel in the slice includes, for each user-selected voxel in the slice, specifying the user-selected voxel as an edge if the image value of the user-selected voxel is within the range of image values, and specifying the user-selected voxel as not an edge if the image value of the user-selected voxel is outside the range of image values.

[0071] (Embodiment 12A) The method according to Embodiment 3, wherein the image values ​​of the voxels of the slice include an integer indicating the intensity of the voxels.

[0072] (Embodiment 12B) The method according to Embodiment 3, wherein the image values ​​of the voxels of the slice include gray level values.

[0073] (Embodiment 13) The method according to Embodiment 1, further comprising performing automatic segmentation on a plurality of slices of the medical image based on the segmented slices to obtain automatically segmented slices of the medical image.

[0074] (Embodiment 14) The method according to Embodiment 13, wherein the automatically segmented slice is automatically segmented by interpolation between the segmented slice and the second segmented slice.

[0075] (Embodiment 14A) The method according to Embodiment 13, wherein the automatically segmented slice of the medical image is located between the first segmented slice and the second segmented slice, the automatically segmented slice is in the same direction as the first segmented slice and the second segmented slice, and the automatically segmented slice is automatically segmented based on the first segmented slice and the second segmented slice.

[0076] (Embodiment 14B) The method according to Embodiment 14A, wherein the number of automatically segmented slices between the segmented slice and the second segmented slice is 2 to 20.

[0077] (Embodiment 14C) The method according to Embodiment 14A, wherein the number of automatically segmented slices between the segmented slice and the second segmented slice is 2 to 5.

[0078] (Embodiment 15) The method according to Embodiment 1, further comprising generating a plurality of transducer layouts for applying tumor treatment fields to the subject based on the segmented slices of the medical image.

[0079] (Embodiment 16) The method according to Embodiment 1, wherein the segmented slice includes at least one of the resection cavity or edema of the subject having an edge detected by the automatic edge detection.

[0080] (Embodiment 16A) The method according to Embodiment 1, wherein the medical image includes the torso of the subject.

[0081] (Embodiment 16B) The method according to Embodiment 1, wherein the medical image includes the head of the subject.

[0082] (Embodiment 16C) The method according to Embodiment 1, wherein the medical image includes computed tomography (CT) medical images, magnetic resonance imaging (MRI) medical images, or positron emission tomography (PET) medical images.

[0083] (Embodiment 16D) A non-temporary processor-readable medium comprising a set of instructions for processing a medical image of a subject, wherein when the instructions are executed by the processor, the processor causes the processor to perform a method comprising presenting a slice of the medical image of the subject, comprising voxels, on a display, and performing automatic edge detection on the slice of the medical image to obtain a segmented slice, wherein the automatic edge detection is based on user-selected voxels in the slice of the medical image, and the automatic edge detection is based on a user-controllable edge detection brush, not all of the voxels selected by the edge detection brush are designated as edges.

[0084] (Embodiment 16E) An apparatus for processing medical images of a subject, the apparatus comprising one or more processors and a memory accessible by the one or more processors, the memory storing instructions that, when executed by the one or more processors, cause the apparatus to perform a method including presenting a slice of the medical image of the subject, including voxels, on a display, and performing automatic edge detection on the slice of the medical image to obtain segmented slices, wherein the automatic edge detection is based on user-selected voxels in the slice of the medical image, and the automatic edge detection is based on a user-controllable edge detection brush, not all of the voxels selected by the edge detection brush are designated as edges.

[0085] (Embodiment 17) A computer implementation method for processing a medical image of a subject, the method comprising: presenting a first slice of the medical image of the subject, including voxels, on a display; performing automatic edge detection on the first slice of the medical image based on user-selected voxels in the first slice of the medical image to obtain a first segmented slice; presenting a second slice of the medical image of the subject on the display, wherein the first and second slices are in the same direction and separated by a plurality of slices of the medical image; performing automatic edge detection on the second slice of the medical image based on user-selected voxels in the second slice of the medical image to obtain a second segmented slice; and performing automatic segmentation on a plurality of slices between the first and second slices based on the first segmented slice and the second segmented slice to obtain a segmented slice, wherein the segmented medical image comprises the first segmented slice, the second segmented slice, and the segmented slice of the medical image.

[0086] (Embodiment 17A) The method according to Embodiment 17, wherein the plurality of slices are automatically segmented by interpolating between the first slice and the second slice.

[0087] (Embodiment 18) Further comprising generating a plurality of transducer layouts for applying a tumor treatment field to the subject based on the segmented medical image, The method according to embodiment 17, further comprising generating a plurality of transducer layouts for applying tumor treatment fields to the subject based on the segmented medical images.

[0088] (Embodiment 19) The method of Embodiment 17, further comprising: defining a region of interest (ROI) in the medical image or the segmented medical image in order to apply a tumor treatment field to the subject; creating a three-dimensional model of the subject including the region of interest based on the segmented medical image; generating a plurality of transducer layouts for applying a tumor treatment field to the subject based on the three-dimensional model of the subject; selecting at least two of the transducer layouts as recommended transducer layouts; presenting the recommended transducer layouts; receiving a user selection of at least one recommended transducer layout; and providing a report relating to the at least one selected recommended transducer layout.

[0089] (Embodiment 19A) A non-temporary processor-readable medium comprising a series of instructions for processing a medical image of a subject, wherein when the instructions are executed by the processor, the processor is caused to perform a method comprising: presenting a first slice of the medical image of the subject, including voxels, on a display; performing automatic edge detection on the first slice of the medical image based on user-selected voxels in the first slice of the medical image to obtain a first segmented slice; presenting a second slice of the medical image of the subject on the display, wherein the first and second slices are in the same direction and separated by a plurality of slices of the medical image; performing automatic edge detection on the second slice of the medical image based on user-selected voxels in the second slice of the medical image to obtain a second segmented slice; and performing automatic segmentation on a plurality of slices between the first and second slices based on the first segmented slice and the second segmented slice to obtain a segmented slice, wherein the segmented medical image comprises the first segmented slice, the second segmented slice, and the segmented slice of the medical image.

[0090] (Embodiment 19B) Apparatus for processing medical images of a subject, the apparatus comprising one or more processors and a memory accessible by the one or more processors, the memory, when executed by the one or more processors, presents a first slice of the medical image of the subject, including voxels, on a display; performs automatic edge detection in the first slice of the medical image based on user-selected voxels in the first slice of the medical image to obtain a first segmented slice; and a second slice of the medical image of the subject, wherein the first and second slices are in the same direction and separated by a plurality of slices of the medical image, The apparatus is configured to perform a method comprising: presenting a second slice on the display; performing automatic edge detection on the second slice of the medical image based on a user-selected voxel in the second slice of the medical image to obtain a second segmented slice; and performing automatic segmentation on a plurality of slices between the first slice and the second slice based on the first segmented slice and the second segmented slice to obtain a segmented slice, wherein the segmented medical image includes the first segmented slice, the second segmented slice, and the segmented slice of the medical image.

[0091] (Embodiment 20) A computer implementation method for processing a medical image of a subject, the method comprising: presenting a slice of the medical image of the subject, including voxels, on a display; performing automatic edge detection on the slice of the medical image using a user-controllable edge detection brush to obtain a segmented slice, wherein not all of the voxels selected by the edge detection brush are designated as edges; performing automatic segmentation on a plurality of slices of the medical image based on the segmented slice to obtain an automatically segmented slice and a segmented medical image of the medical image; and generating a plurality of transducer layouts for applying a tumor treatment field to the subject based on the segmented medical image.

[0092] (Embodiment 20A) A non-temporary processor-readable medium comprising a set of instructions for processing a medical image of a subject, wherein when the instructions are executed by the processor, the processor is instructed to perform a method comprising: presenting slices of the medical image of the subject, including voxels, on a display; performing automatic edge detection on the slices of the medical image using a user-controllable edge detection brush to obtain segmented slices, wherein not all of the voxels selected by the edge detection brush are designated as edges; performing automatic segmentation on a plurality of slices of the medical image based on the segmented slices to obtain automatically segmented slices and segmented medical images of the medical image; and generating a plurality of transducer layouts for applying a tumor treatment field to the subject based on the segmented medical images.

[0093] (Embodiment 20B) Apparatus for processing medical images of a subject, the apparatus comprising one or more processors and a memory accessible by the one or more processors, wherein the memory, when executed by the one or more processors, causes the apparatus to perform a method including: presenting slices of the medical image of the subject, including voxels, on a display; performing automatic edge detection on the slices of the medical image using a user-controllable edge detection brush to obtain segmented slices, wherein not all of the voxels selected by the edge detection brush are designated as edges; performing automatic segmentation on a plurality of slices of the medical image based on the segmented slices to obtain automatically segmented slices and segmented medical images of the medical image; and generating a plurality of transducer layouts for applying tumor treatment fields to the subject based on the segmented medical images.

[0094] (Embodiment 20C) A computer implementation method for processing a medical image of a subject, the method comprising presenting one or more user-selectable icons on a display for presenting slices of the medical image of the subject, each containing voxels, and presenting user-selectable icons on a display for performing automatic edge detection on the slices of the medical image to obtain segmented slices, wherein the automatic edge detection is based on user-selected voxels in the slices of the medical image, and the automatic edge detection is based on a user-controllable edge detection brush, where not all voxels selected by the edge detection brush are designated as edges.

[0095] (Embodiment 20D) The method according to Embodiment 20C, comprising presenting a user-selectable icon on the display for determining the radius of the edge detection brush used for automatic edge detection, and presenting a user-selectable icon on the display for determining the edge threshold of the edge detection brush, wherein the image value of the voxel selected by the edge detection brush is designated as an edge based on the edge threshold.

[0096] (Embodiment 20E) The method according to Embodiment 20C, further comprising presenting user-selectable icons on a display for performing automatic segmentation on a plurality of slices of the medical image based on the segmented slices, and obtaining the automatically segmented slices of the medical image.

[0097] (Embodiment 20F) The method according to Embodiment 20C, further comprising presenting user-selectable icons on a display for generating a plurality of transducer layouts for applying tumor treatment fields to the subject based on the automatically segmented slices of the medical image.

[0098] (Embodiment 21) A method, machine, product, and / or system substantially identical to those illustrated and described.

[0099] Optionally, in each embodiment described herein, the voltage generating component supplies the transducer with an AC waveform suitable for delivering TT field therapy to the subject's body at a frequency in the range of about 50 kHz to about 1 MHz.

[0100] Embodiments described in any heading or portion of this disclosure may be combined with embodiments described in the same heading or other portions of this disclosure, unless otherwise stated herein or unless the context clearly contradicts the description. For example, an embodiment described in dependent claim form to a given embodiment (e.g., a given embodiment described in independent claim form) may be combined with other embodiments (described in independent or dependent claim form).

[0101] Numerous modifications, alterations, and changes are possible to the embodiments described without departing from the scope of the invention as defined in the claims. The invention is not limited to the embodiments described and is intended to encompass the entire scope as defined by the following claims and their equivalents.

Claims

1. A computer implementation method for processing medical images of a subject, wherein the method is Presenting a slice of the medical image of the subject, including voxels, on a display, A method comprising: performing automatic edge detection on the slice of the medical image to obtain segmented slices, wherein the automatic edge detection is based on user-selected voxels in the slice of the medical image, and the automatic edge detection is based on a user-controllable edge detection brush, and not all of the voxels selected by the edge detection brush are designated as edges.

2. Performing automatic edge detection means Determining the radius of the edge detection brush used for the automatic edge detection, The method according to claim 1, comprising determining an edge threshold for the edge detection brush, wherein the image values ​​of voxels selected by the edge detection brush are designated as edges based on the edge threshold.

3. Performing automatic edge detection means Determining the user-selected voxel in the slice of the medical image, The edge detection image values ​​are determined based on the user-selected voxels in the slice of the medical image, Determining the size of the edge detection brush used for the automatic edge detection, Determining the edge threshold of the edge detection brush, Based on the edge detection image values ​​and the edge threshold, the range of image values ​​to be designated as edges is determined, Based on the interaction between the edge detection brush and the voxels in the slice, and the size of the edge detection brush, the system receives user-selected voxels in the slice. The method according to claim 1, comprising designating a user-selected voxel within the slice as an edge voxel of the slice based on the range of image values ​​to be designated as an edge.

4. Determining the edge detection image value based on the user-selected voxel in the slice of the medical image means that The central image value is determined as the image value of the user-selected voxel at the center of the user-selected position in the slice of the medical image, The adjacent image value is determined as the image value of the voxel adjacent to the user-selected voxel, The average image value is calculated based on the aforementioned central image value and the aforementioned adjacent image values, The method according to claim 3, comprising assigning the edge detection image value as the average image value.

5. Determining the edge detection image value based on the user-selected voxel in the slice of the medical image means that The method according to claim 3, comprising determining a central image value as the image value of the user-selected voxel at the center of the user-selected position in the slice of the medical image.

6. The range of image values ​​designated as edges includes the number of image values ​​M within the range, the upper limit UL of the range, and the lower limit LL of the range. The number M of the image values ​​within the aforementioned range is M = N × (1 - P), The range of image values ​​for the medical image has a maximum value N, and the user selection for the edge threshold is a percentage P. The upper limit UL of the range is UL = IV + 0.5 × M, Image value IV is the edge detection image value, The lower limit LL of the range is The method according to claim 3, wherein LL = IV - 0.5 × M.

7. The range of image values ​​designated as edges includes the number of image values ​​M within the range, the upper limit UL of the range, and the lower limit LL of the range. The number M of the image values ​​within the aforementioned range is M = N × (1 - (P × RL)), The range of image values ​​in the medical image has a maximum value N, the user selection for the edge threshold is a percentage P, and the range limiter is a percentage RL. The upper limit UL of the range is UL = IV + 0.5 × M, Image value IV is the edge detection image value, The lower limit LL of the range is The method according to claim 3, wherein LL = IV - 0.5 × M.

8. Designating a user-selected voxel within the slice as an edge voxel of the slice means that for each user-selected voxel within the slice, If the image value of the user-selected voxel falls within the range of image values, the user-selected voxel is designated as an edge. The method according to claim 3, further comprising specifying that the user-selected voxel is not an edge if the image value of the user-selected voxel is outside the range of image values.

9. The method according to claim 1, further comprising performing automatic segmentation on a plurality of slices of the medical image based on the segmented slices to obtain automatically segmented slices of the medical image.

10. The method according to claim 9, wherein the automatically segmented slice is automatically segmented by interpolating between the segmented slice and the second segmented slice.

11. The method according to claim 1, further comprising generating a plurality of transducer layouts for applying a tumor treatment field to the subject based on the segmented slices of the medical image.

12. The method according to claim 1, wherein the segmented slice includes at least one of the resection cavity or edema of the subject having an edge detected by the automatic edge detection.

13. A computer implementation method for processing medical images of a subject, wherein the method is Presenting a first slice of the medical image of the subject, including voxels, on a display, Based on the user-selected voxels in the first slice of the medical image, automatic edge detection is performed in the first slice of the medical image to obtain a first segmented slice. The second slice of the medical image of the subject, wherein the first slice and the second slice are in the same direction and are separated by a plurality of slices of the medical image, is presented on the display. Based on the user-selected voxels in the second slice of the medical image, automatic edge detection is performed in the second slice of the medical image to obtain a second segmented slice. A method comprising: performing automatic segmentation on a plurality of slices between the first slice and the second slice based on the first segmented slice and the second segmented slice to obtain a segmented slice, wherein the segmented medical image comprises the first segmented slice, the second segmented slice, and the segmented slice of the medical image.

14. In order to apply a tumor treatment field to the subject, define a region of interest (ROI) within the medical image or the segmented medical image, Based on the segmented medical images, a three-dimensional model of the subject including the region of interest is created. Based on the three-dimensional model of the subject, a plurality of transducer layouts for applying a tumor treatment field to the subject are generated, Select at least two of the aforementioned transducer layouts as recommended transducer layouts, The recommended transducer layout is presented, To receive a user selection of at least one recommended transducer layout, The method of claim 13, further comprising providing a report relating to at least one selected recommended transducer layout.

15. A computer implementation method for processing medical images of a subject, wherein the method is Presenting a slice of the medical image of the subject, including voxels, on a display, In the slice of the medical image, automatic edge detection is performed using a user-controllable edge detection brush to obtain a segmented slice in which not all of the voxels selected by the edge detection brush are designated as edges. Based on the segmented slices, automatic segmentation is performed on multiple slices of the medical image to obtain automatically segmented slices and segmented medical images of the medical image. A method comprising generating a plurality of transducer layouts for applying a tumor treatment field to the subject based on the segmented medical image.

Images