Three-dimensional model generation for tumor therapy field transducer layout

Abstract

A computer-implemented method for generating a three-dimensional (3D) composite model of a region of a subject, the method comprising: generating a 3D clinical model of the region of the subject based on one or more images of the region of the subject; obtaining a 3D generic model of the region of the generic subject; combining the 3D clinical model and the 3D generic model using an affine transformation, a bend transformation, and a squeeze transformation of the 3D generic model to obtain the 3D composite model of the subject; and displaying the composite 3D model on a display.

Description

[0001] Cross - reference to related applications

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 411,375, filed Sep. 29, 2022, and U.S. Patent Application No. 18 / 373,102, filed Sep. 26, 2023, the entire contents of both of which are incorporated herein by reference. Background Art

[0003] Tumor treating fields (TTFields) are low - intensity alternating electric fields in the intermediate frequency range (e.g., 50 kHz to 1 MHz), which can be used to treat tumors, as described in U.S. Patent No. 7,565,205. TTFields are non - invasively induced into the region of interest by transducers placed directly on the subject's body and applying an alternating current (AC) voltage between these transducers. Conventionally, a first pair of transducers and a second pair of transducers are placed on the subject's body. An AC voltage is applied between the first pair of transducers during a first time interval to generate an electric field having field lines extending generally in the anterior - posterior direction. Then, an AC voltage is applied between the second pair of transducers at the same frequency during a second time interval to generate an electric field having field lines extending generally in the left - right direction. Then, the system repeats this two - step sequence throughout the treatment. Brief Description of the Drawings

[0004] Figure 1 is a flowchart depicting an example of a three - dimensional (3D) composite model of a region of a subject.

[0005] Figure 2 is a flowchart depicting an example of an affine transformation.

[0006] Figures 3A to 3C is an example of a 3D clinical model, a 3D general model, and a 3D composite model generated according to an embodiment of the disclosed subject matter.

[0007] Figure 4A is an example of showing transducer array placement on a 3D clinical model of a subject and 4B is an example of showing transducer array placement on a 3D composite model of a subject.

[0008] Figure 5 depicts an example computer device for use with embodiments herein.

[0009] Various embodiments are described in detail below with reference to the accompanying drawings, in which like reference numerals represent like elements. Detailed Description

[0010] To provide effective TTField therapy to a subject, it is necessary to generate precise locations on the subject's body where transducers are to be placed, and these precise locations are based on, for example, the type of cancer, the size of the cancer, and the location of the cancer in the subject's body. Visualizing the locations on a three-dimensional (3D) model where the transducers are to be placed helps assist a user (e.g., a doctor, nurse, assistant, staff, physicist, dosimetrist, etc.) in precisely placing the transducers on the subject's body, thereby optimizing tumor treatment. However, there are certain problems in generating a 3D model of the subject for use in visualizing the transducer locations. For example, the scan of the subject may be noisy, resulting in a distorted 3D model of the subject, and some subjects may feel discomfort when viewing a distorted version of their body. As another example, even if the 3D model is an accurate representation of the subject, some subjects may still feel discomfort when seeing their own body (e.g., the subject's face or the subject's torso) on a display. As another example, to save cost and / or processing time, only a part of the subject's body may be scanned (e.g., a partial scan of the subject's head), resulting in a partial 3D model of the subject's body, and some subjects may feel discomfort when seeing such a partial version of their body. The inventors recognized these problems and found a way to generate a 3D composite model of the subject by combining a 3D clinical model of the subject and a 3D generic model that can represent the size, shape, and / or characteristics of an individual subject.

[0011] Figure 1 is a flowchart depicting an example of generating a three-dimensional (3D) composite model of a region of a subject. Certain steps of method 100 are described as computer-implemented steps. The computer can be any device that includes one or more processors and a memory that is accessible by the one or more processors and stores instructions that, when executed by the one or more processors, cause the computer to perform the relevant steps of method 100. Although the order of operations is indicated in Figure 1 for illustrative purposes, the timing and sequencing of such operations can vary, as appropriate, without negating the purpose and advantages of the examples elaborated in the present disclosure.

[0012] Refer to Figure 1, at step 102, method 100 includes: generating a 3D clinical model of the region of the subject based on one or more images of the region of the subject. In some embodiments, the one or more images are medical images. The medical images can include, for example, magnetic resonance imaging (MRI) images, computed tomography (CT) images, X-ray images, ultrasound images, nuclear medicine images, positron emission tomography (PET) images, arthrogram images, myelogram images, or any image of the subject's body that provides an internal view of the subject's body. Each medical image can include the external shape of a portion of the subject's body and a region corresponding to a region of interest (e.g., a tumor) within the subject's body. As an example, the medical image can be a 3D MRI image.

[0013] In some embodiments, the images are not limited to medical images and can be any type of image. In one example, the one or more images are two-dimensional (2D) images that can be captured by one or more user devices. As an example, the one or more user devices can be a mobile phone or a camera. In some embodiments, the one or more images include one or more medical images and one or more 2D images captured by one or more user devices.

[0014] In some embodiments, the region of the subject includes a region of interest, such as a tumor within the subject's body. As an example, the region of the subject is the subject's head. As an example, the region of the subject is the subject's torso.

[0015] In some embodiments, the 3D clinical model includes a coordinate system. As an example, if the region of the subject includes the subject's head, method 100 further includes: identifying the center of the 3D clinical model, where the center is equidistant between a left ear reference position and a right ear reference position of the 3D clinical model; identifying the X-axis of the 3D clinical model, where the X-axis passes through the center of the 3D clinical model and is located between the left ear reference position and the right ear reference position of the 3D clinical model; identifying the Y-axis of the 3D clinical model, where the Y-axis passes through the center of the 3D clinical model, is orthogonal to the X-axis, and is located between the front and back of the 3D clinical model; and identifying the Z-axis of the 3D clinical model, where the Z-axis passes through the center of the 3D clinical model, is orthogonal to the X-axis and the Y-axis, and is located between the top and bottom of the 3D clinical model. In some embodiments, the surface of the 3D clinical model includes a plurality of meshes.

[0016] At step 104, method 100 includes: obtaining a 3D general model of the region of a general subject. In some embodiments, the surface of the 3D general model includes a plurality of meshes. As an example, both the 3D clinical model and the 3D general model include a coordinate system. As an example, if the region of the subject includes the subject's head, the 3D clinical model and the 3D general model may each include: a center; an X-axis that intersects the left ear reference position, the right ear reference position, and the center; a Y-axis that is orthogonal to the X-axis, intersects the center, and is located between the front and back of the head; and a Z-axis that is orthogonal to the X-axis and the Y-axis and intersects the center.

[0017] At step 106, method 100 includes: combining the 3D clinical model and the 3D general model. In some embodiments, the combination of the 3D clinical model and the 3D general model can be accomplished by using affine transformation, bending transformation, and squeezing transformation of the 3D general model. As an example, combining the 3D clinical model and the 3D general model includes: deforming the mesh of the 3D general model according to the mesh of the 3D clinical model. In some embodiments, method 100 includes: transforming the 3D general model using the transformation and the 3D clinical model, where the transformation includes affine transformation, bending transformation, and squeezing transformation. The following further describes an example of affine transformation. Figure 2 Further describe an example of affine transformation.

[0018] Regarding the bending transformation, in some embodiments, if the region of the subject includes the subject's head, the bending transformation may include: transforming the eye part of the 3D general model to match the eye part of the 3D clinical model without moving the ear positions of the 3D general model. As an example, transforming the eye part of the 3D general model to match the eye part of the 3D clinical model may include: transforming the equidistant point between the left eye reference position and the right eye reference position of the 3D general model to align with the equidistant point between the left eye reference position and the right eye reference position of the 3D clinical model. In some embodiments, the bending transformation of the 3D general model may include: bending the 3D general model at the X-axis according to the 3D clinical model, where after bending the 3D general model, the front position of the 3D general model is located on the Y-axis, where the front position of the 3D general model is the position equidistant between the left eye reference position and the right eye reference position of the 3D general model. In some embodiments, the bending transformation is a second-order transformation.

[0019] Regarding the squeezing transformation, in some embodiments, the squeezing transformation may include: transforming the 3D general model to match the 3D clinical model. In some embodiments, the squeezing transformation of the 3D general model includes: squeezing the 3D general model at the X-axis according to the 3D clinical model. In some embodiments, the squeezing transformation is a second-order transformation.

[0020] At step 108, method 100 includes: generating a 3D composite model of the subject based on combining the 3D clinical model and the 3D generic model at step 106. As an example, method 100 may further include: performing a surface fitting on the 3D composite model, wherein the surface fitting process includes at least one of interpolation or extrapolation.

[0021] At step 110, the method includes: displaying the 3D composite model on a display. In some embodiments, the display is located on a user interface. As an example, a user may select to display the 3D clinical model and the 3D composite model on the display for comparison.

[0022] At step 112, method 100 includes: generating one or more recommended transducer array positions of one or more transducer arrays on the 3D clinical model to apply a tumor treatment field. In some embodiments, the one or more recommended transducer placement positions are generated based on, for example, the region of interest of the subject's body corresponding to the tumor. As an example, the one or more recommended transducer placement positions may be aimed at optimizing the tumor treatment dose delivered to the region of interest of the subject's body. In some embodiments, the one or more recommended transducer placement positions may be generated based on the 3D composite model.

[0023] At step 114, the method includes: displaying at least one recommended transducer placement position on the 3D composite model on the display. Figure 4A and Figure 4B illustrates an example of generating and displaying one or more recommended transducer placement positions, which will be discussed further below.

[0024] Figure 2 is a flowchart depicting an example of an affine transformation. Certain steps of method 200 are described as computer-implemented steps. The computer can be any device that includes one or more processors and a memory that is accessible by the one or more processors and stores instructions that, when executed by the one or more processors, cause the computer to perform the relevant steps of method 200. Although the order of operations is indicated in Figure 2 for illustrative purposes, the timing and sequencing of such operations may vary, as appropriate, without negating the purpose and advantages of the examples elaborated in the present disclosure.

[0025] At step 202, method 200 includes: translating the 3D general model to the 3D clinical model. In some embodiments, translating the 3D general model to the 3D clinical model includes: identifying the center of the 3D clinical model (as an example, if the region of the subject includes the subject's head, the center may be equidistant between the left ear reference position and the right ear reference position of the 3D clinical model); identifying the center of the 3D general model (as an example, if the region of the subject includes the subject's head, the center may be equidistant between the left ear reference position and the right ear reference position of the 3D general model); and translating the 3D general model such that the center of the 3D general model overlaps with the center of the 3D clinical model.

[0026] At step 204, method 200 includes: rotating the 3D general model to align with the 3D clinical model. In some embodiments, rotating the 3D general model to align with the 3D clinical model may include: identifying a first part of the 3D clinical model; identifying a first part of the 3D general model, where the first part of the 3D general model corresponds to the first part of the 3D clinical model; and rotating the 3D general model such that the first part of the 3D general model overlaps with the first part of the 3D clinical model. In some embodiments, if the region of the subject includes the subject's head, rotating the 3D general model to align with the 3D clinical model may include: identifying the eye part of the 3D clinical model; identifying the eye part of the 3D general model; and rotating the 3D general model such that the eye part of the 3D general model overlaps with the eye part of the 3D clinical model. As an example, the eye part of the 3D clinical model may be equidistant between the left eye reference position and the right eye reference position of the 3D clinical model, and the eye part of the 3D general model may be equidistant between the left eye reference position and the right eye reference position of the 3D general model.

[0027] In some embodiments, as Figure 1 discussed, both the 3D clinical model and the 3D general model include a coordinate system. In some embodiments, rotating the 3D general model to align with the 3D clinical model may include: rotating the 3D general model about the X axis to align the first part of the 3D general model with the corresponding first part of the 3D clinical model in the same x-y plane. As an example, if the region of the subject includes the subject's head, rotating the 3D general model to align with the 3D clinical model may include: rotating the 3D general model about the X axis to align the eye part of the 3D general model with the eye part of the 3D clinical model in the same x-y plane.

[0028] At step 206, method 200 includes: scaling the 3D general model to align with the 3D clinical model. In some embodiments, scaling the 3D general model to align with the 3D clinical model may include: scaling the 3D general model such that a first region of the 3D general model aligns with a corresponding first region of the 3D clinical model (e.g., if the region of the subject includes the subject's head, aligning the ear region of the 3D general model with the ear region of the 3D clinical model); and scaling the 3D general model such that a second region of the 3D general model aligns with a corresponding second region of the 3D clinical model (e.g., if the region of the subject includes the subject's head, aligning the eye region of the 3D general model with the eye region of the 3D clinical model). As an example, the distance between the left ear reference position and the right ear reference position of the 3D general model may be scaled to match the distance between the left ear reference position and the right ear reference position of the 3D clinical model, and the distance between the left eye reference position and the right eye reference position of the 3D general model may be scaled to match the distance between the left eye reference position and the right eye reference position of the 3D clinical model.

[0029] In some embodiments, as discussed above, both the 3D clinical model and the 3D general model include a coordinate system. In some embodiments, scaling the 3D general model to align with the 3D clinical model may include: scaling the X-axis of the 3D general model such that the distance between two parts on the 3D general model is the same as the distance between two corresponding parts on the 3D clinical model (e.g., if the region of the subject includes the subject's head, making the distance between the ears on the 3D general model the same as the distance between the ears on the 3D clinical model); and scaling the Y-axis of the 3D general model such that the distance between a first part of the 3D general model and the center is the same as the distance between a corresponding first part of the 3D clinical model and the center (e.g., if the region of the subject includes the subject's head, making the distance between the eye part and the center on the 3D general model the same as the distance between the eye part and the center on the 3D clinical model). As an example, the distance between the ears on the 3D clinical model may be the distance between the left ear reference position and the right ear reference position of the 3D clinical model, and the distance between the eye part and the center on the 3D clinical model may be the distance between the left eye reference position and the right eye reference position of the 3D clinical model.

[0030] In some embodiments, scaling the 3D general model to align with the 3D clinical model may include: scaling the 3D general model along the X-axis, the Y-axis, and the Z-axis according to the 3D clinical model. As an example, scaling the X-axis of the 3D general model may include: setting the distance between the left and right positions of the 3D general model to be the same as the distance between the corresponding left and right positions of the clinical 3D model (e.g., if the region of the subject includes the subject's head, setting the distance between the reference positions of the left ear and the right ear of the 3D general model to be the same as the distance between the reference positions of the left ear and the right ear of the clinical 3D head model); scaling the Y-axis of the 3D general model may include: setting the distance between the front position and the center of the 3D general model to be the same as the distance between the front position and the center of the 3D clinical model; and scaling the Z-axis of the 3D general model may include: scaling the Z-axis at the same scale as the X-axis. As an example, the front position of the 3D general model may be the position equidistant between the reference positions of the left eye and the right eye of the 3D general model, and the front position of the 3D clinical model may be the position equidistant between the reference positions of the left eye and the right eye of the 3D clinical model.

[0031] Figures 3A to 3C is an example of a 3D clinical model, a 3D general model, and a 3D composite model generated according to an exemplary embodiment. In Figure 3A In the example depicted, a 3D clinical model of a region of a subject (e.g., the subject's head) is generated based on one or more images of the region of the subject. As Figure 3A shown, the 3D clinical model represents the shape, size, features, etc. of the subject's head. However, the 3D clinical model has noise, e.g., the eyes and ears of the model are not clearly shown. Additionally, the 3D clinical model is a partial version of the subject's head. Figure 3B is an example of a 3D general model of a region (e.g., the head). Figure 3C is a 3D composite model of a subject based on the combination of the 3D clinical model in Figure 3A and the 3D general model in Figure 3B . As Figure 3C shown, the 3D composite model represents the shape, size, features, etc. of the subject's head, has very little noise (e.g., the eyes and ears of the model are clearly shown), and is a complete version of the subject's body part (e.g., the subject's head), rather than a partial version.

[0032] Figure 4A is an example of transducer array placement shown on a 3D clinical model of a subject. As an example, the transducer array placement is for application in Figure 1One of the recommended transducer array positions for the tumor treatment fields generated at step 112 of Figure 4B is an example of transducer array placement shown on a 3D composite model of a subject. Although Figure 4A and Figure 4B illustrate a transducer array having circular electrode elements, the electrode elements can have various shapes.

[0033] Figure 5 Depicts an example computer device for use with the embodiments herein. By way of example, device 500 can be a computer implementing certain inventive techniques disclosed herein. For example, Figure 1 and Figure 2 The methods of can be performed by a computer device such as device 500. Device 500 can include one or more processors 502, a memory 503, one or more input devices, and one or more output devices 505.

[0034] In one example, based on input 501, one or more processors generate a 3D composite model according to the embodiments herein. In one example, input 501 is a user input. In another example, input 501 is one or more images of a region of a subject. In another example, input 501 can be from another computer in communication with device 500. Input 501 can be received in conjunction with one or more input devices (not shown) of device 500.

[0035] Memory 503 can be accessible by one or more processors 502 (e.g., via link 504) such that one or more processors 502 can read information from and write information to the memory. Memory 503 can store instructions that, when executed by one or more processors 502, implement one or more of the embodiments described herein. Memory 503 can be a non-transitory computer-readable medium (or non-transitory processor-readable medium) having a set of instructions thereon for generating a 3D composite model of a region of a subject, where when executed by a processor (such as one or more processors 502), the instructions cause the processor to perform one or more of the methods disclosed herein.

[0036] One or more output devices 505 can provide the status of the computer-implemented techniques herein. One or more output devices 505 can provide visualization data according to certain embodiments of the present invention, such as medical images, 3D clinical models, 3D general models, 3D composite models, and / or transducer placement on a 3D composite model. One or more output devices 505 can include one or more displays, e.g., monitors, liquid crystal displays, organic light emitting diode displays, active matrix organic light emitting diode displays, stereoscopic displays, etc.

[0037] Apparatus 500 may be an apparatus for generating a 3D composite model of a region of a subject, the apparatus including: one or more processors (such as one or more processors 502); and a memory (such as memory 503), the memory being accessible by the one or more processors and storing instructions which, when executed by the one or more processors, cause the apparatus to perform one or more of the methods disclosed herein.

[0038] Exemplary embodiment

[0039] The present invention includes other exemplary embodiments such as those shown below.

[0040] Exemplary embodiment 1 A computer-implemented method for generating a three-dimensional (3D) composite model of a region of a subject, the method including: generating a 3D clinical model of the region of the subject based on one or more images of the region of the subject; obtaining a 3D general model of the region of a general subject; using affine transformation, bending transformation, and squeezing transformation of the 3D general model to combine the 3D clinical model and the 3D general model to obtain the 3D composite model of the subject; and displaying the composite 3D model on a display.

[0041] Exemplary embodiment 2 The computer-implemented method according to exemplary embodiment 1, wherein the affine transformation includes: translating the 3D general model to the 3D clinical model; rotating the 3D general model to align with the 3D clinical model; and scaling the 3D general model to align with the 3D clinical model.

[0042] Exemplary embodiment 3 The computer-implemented method according to exemplary embodiment 2, wherein translating the 3D general model to the 3D clinical model includes: identifying the center of the 3D general model; identifying the center of the 3D general model; and translating the 3D general model such that the center of the 3D general model overlaps with the center of the 3D clinical model.

[0043] Exemplary embodiment 4 The computer-implemented method according to exemplary embodiment 3, wherein the center of the 3D clinical model is equidistant between a left ear reference position and a right ear reference position of the 3D clinical model.

[0044] Exemplary embodiment 5 The computer-implemented method according to exemplary embodiment 2, wherein rotating the 3D general model to align with the 3D clinical model includes: identifying the eye region of the 3D clinical model; identifying the eye region of the 3D general model; and rotating the 3D general model such that the eye region of the 3D general model overlaps with the eye region of the 3D clinical model.

[0045] Exemplary Embodiment 6 The computer-implemented method according to Exemplary Embodiment 5, wherein the eye portion of the 3D clinical model is equidistant between the left-eye reference position and the right-eye reference position of the 3D clinical model.

[0046] Exemplary Embodiment 7 The computer-implemented method according to Exemplary Embodiment 2, wherein scaling the 3D general model to align with the 3D clinical model includes: scaling the 3D general model such that the ear region of the 3D general model aligns with the ear region of the 3D clinical model; and scaling the 3D general model such that the eye region of the 3D general model overlaps with the eye region of the 3D clinical model.

[0047] Exemplary Embodiment 8 The computer-implemented method according to Exemplary Embodiment 7, wherein the distance between the left-ear reference position and the right-ear reference position of the 3D general model is scaled to match the distance between the left-ear reference position and the right-ear reference position of the 3D clinical model, and wherein the distance between the left-eye reference position and the right-eye reference position of the 3D general model is scaled to match the distance between the left-eye reference position and the right-eye reference position of the 3D clinical model.

[0048] Exemplary Embodiment 9 The computer-implemented method according to Exemplary Embodiment 1, wherein the bending transformation includes: transforming the eye portion of the 3D general model to match the eye portion of the 3D clinical model without moving the ear position of the 3D general model.

[0049] Exemplary Embodiment 10 The computer-implemented method according to Exemplary Embodiment 9, wherein the equidistant point between the left-eye reference position and the right-eye reference position of the 3D general model is transformed to align with the equidistant point between the left-eye reference position and the right-eye reference position of the 3D clinical model.

[0050] Exemplary Embodiment 11 The computer-implemented method according to Exemplary Embodiment 9, wherein the bending transformation is a second-order transformation.

[0051] Exemplary Embodiment 12 The computer-implemented method according to Exemplary Embodiment 1, wherein the squeezing transformation includes: transforming the 3D general model to match the 3D clinical model.

[0052] Exemplary Embodiment 13 The computer-implemented method according to Exemplary Embodiment 12, wherein the squeezing transformation is a second-order transformation.

[0053] Exemplary Embodiment 14 The computer-implemented method according to Exemplary Embodiment 1, the method further comprising: performing surface fitting on the 3D composite model, wherein the surface fitting process includes at least one of interpolation or extrapolation.

[0054] Exemplary Embodiment 15 The computer-implemented method according to Exemplary Embodiment 1, the method further comprising: generating one or more recommended transducer array positions of one or more transducer arrays on the 3D clinical model to apply a tumor treatment field; and displaying at least one of the recommended transducer array positions on the 3D composite model on the display.

[0055] Exemplary Embodiment 16 The computer-implemented method according to Exemplary Embodiment 1, wherein the region of the subject is the head of the subject.

[0056] Exemplary Embodiment 17 The computer-implemented method according to Exemplary Embodiment 1, wherein the region of the subject is the torso of the subject.

[0057] Exemplary Embodiment 18 The computer-implemented method according to Exemplary Embodiment 1, the method further comprising: identifying the center of the 3D clinical model, wherein the center is equidistant between the left ear reference position and the right ear reference position of the 3D clinical model; identifying the X-axis of the 3D clinical model, wherein the X-axis passes through the center of the 3D clinical model and is located between the left ear reference position and the right ear reference position of the 3D clinical model; identifying the Y-axis of the 3D clinical model, wherein the Y-axis passes through the center of the 3D clinical model, is orthogonal to the X-axis, and is located between the front and back of the 3D clinical model; and identifying the Z-axis of the 3D clinical model, wherein the Z-axis passes through the center of the 3D clinical model, is orthogonal to the X-axis and the Y-axis, and is located between the top and bottom of the 3D clinical model.

[0058] Exemplary Embodiment 19 The computer-implemented method according to Exemplary Embodiment 18, wherein the affine transformation includes: rotating the 3D general model around the X-axis to align the eye part of the 3D general model with the eye part of the 3D clinical model on the same x-y plane.

[0059] Exemplary Embodiment 20 The computer-implemented method according to Exemplary Embodiment 19, wherein the eye part of the 3D clinical model is equidistant between the left eye reference position and the right eye reference position of the 3D clinical model.

[0060] Exemplary Embodiment 21 The computer-implemented method according to Exemplary Embodiment 18, wherein the affine transformation includes: scaling the X-axis of the 3D general model such that the distance between the ears on the 3D general model is the same as the distance between the ears on the 3D clinical model; and scaling the Y-axis of the 3D general model such that the distance between the eye part of the 3D general model and the center is the same as the distance between the eye part of the 3D clinical model and the center.

[0061] Exemplary Embodiment 22 The computer-implemented method according to Exemplary Embodiment 21, wherein the distance between the ears on the 3D clinical model is the distance between the left ear reference position and the right ear reference position of the 3D clinical model, and wherein the distance between the eye part of the 3D clinical model and the center is the distance between the left eye reference position and the right eye reference position of the 3D clinical model.

[0062] Exemplary Embodiment 23 An apparatus for generating a three-dimensional (3D) composite model of a subject's head, the apparatus comprising: one or more processors; and a memory accessible by the one or more processors and storing instructions that, when executed by the one or more processors, cause the apparatus to perform the following operations: generating a 3D clinical model of the subject's head based on one or more images of the subject's head; obtaining a 3D general model of the head of a general subject; transforming the 3D general model using a transformation and the 3D clinical model, wherein the transformation includes an affine transformation, a bending transformation, and a squeezing transformation; generating the 3D composite model based on the transformed 3D general model and the 3D clinical model; and displaying the 3D composite model on a display.

[0063] Exemplary Embodiment 24 The apparatus according to Exemplary Embodiment 23, wherein each of the 3D clinical model and the 3D general model includes: a center; an X-axis that intersects with the left ear reference position, the right ear reference position, and the center; a Y-axis that is orthogonal to the X-axis, intersects with the center, and is located between the front and back of the head; and a Z-axis that is orthogonal to the X-axis and the Y-axis and intersects with the center.

[0064] Exemplary Embodiment 25 The apparatus according to Exemplary Embodiment 24, wherein the affine transformation of the 3D general model includes: overlapping the center of the 3D general model with the center of the 3D clinical model; and rotating the 3D general model about the X-axis to place the position equidistant between the left eye reference position and the right eye reference position of the 3D general model on the x-y plane.

[0065] Exemplary Embodiment 26 The apparatus according to Exemplary Embodiment 24, wherein the affine transformation of the 3D general model includes: scaling the 3D general model at the X-axis, the Y-axis, and the Z-axis according to the 3D clinical model, wherein scaling the 3D general model at the X-axis includes: setting the distance between the left ear reference position and the right ear reference position of the 3D general model to be the same as the distance between the left ear reference position and the right ear reference position of the clinical 3D head model, wherein scaling the 3D general model at the Y-axis includes: setting the distance between the front position and the center of the 3D general model to be the same as the distance between the front position and the center of the 3D clinical model, wherein the front position of the 3D general model is the position equidistant between the left eye reference position and the right eye reference position of the 3D general model, and wherein the front position of the 3D clinical model is the position equidistant between the left eye reference position and the right eye reference position of the 3D clinical model; and wherein scaling the 3D general model at the Z-axis includes: scaling the Z-axis at the same scaling ratio as the X-axis.

[0066] Exemplary Embodiment 27 The apparatus according to Exemplary Embodiment 24, wherein the bending transformation of the 3D general model includes: bending the 3D general model at the X-axis according to the 3D clinical model, wherein after bending the 3D general model, the front position of the 3D general model is located on the Y-axis, and wherein the front position of the 3D general model is the position equidistant between the left eye reference position and the right eye reference position of the 3D general model.

[0067] Exemplary Embodiment 28 The apparatus according to Exemplary Embodiment 24, wherein the squeezing transformation of the 3D general model includes: squeezing the 3D general model at the X-axis according to the 3D clinical model.

[0068] Exemplary Embodiment 29 A non-transitory computer-readable medium, the non-transitory computer-readable medium including instructions for generating one or more recommended transducer placement positions on a subject, the instructions causing the computer to perform a method when executed by the computer, the method including: generating a 3D clinical model of the subject based on one or more images of the subject; obtaining a 3D general model of a general subject; using the affine transformation, bending transformation, and squeezing transformation of the 3D general model to combine the 3D clinical model and the 3D general model to obtain a 3D composite model of the subject; and generating one or more recommended transducer array positions of one or more transducer arrays on the 3D clinical model to apply a tumor treatment field; displaying at least one recommended transducer placement position on the 3D composite model on a display.

[0069] Exemplary embodiment 30 The non-transitory computer-readable medium according to exemplary embodiment 29, wherein the surface of the 3D clinical model includes a plurality of meshes, wherein the surface of the 3D general model includes a plurality of meshes, and wherein combining the 3D clinical model and the 3D general model includes: deforming the meshes of the 3D general model according to the meshes of the 3D clinical model.

[0070] Exemplary embodiment 31 The non-transitory computer-readable medium according to exemplary embodiment 29, wherein combining the 3D clinical model and the 3D general model includes: using affine transformation, bending transformation, and extrusion transformation of the 3D general model.

Claims

1. A computer-implemented method for generating a three-dimensional (3D) composite model of a region of a subject, the method comprises: generating a 3D clinical model of the region of the subject based on one or more images of the region of the subject; obtaining a 3D general model of the region of a general subject; combining the 3D clinical model and the 3D general model using an affine transformation, a bending transformation, and a squeezing transformation of the 3D general model to obtain the 3D composite model of the subject; and displaying the composite 3D model on a display.

2. The computer-implemented method according to claim 1, wherein the affine transformation comprises: translating the 3D general model to the 3D clinical model; rotating the 3D general model to align with the 3D clinical model; and scaling the 3D general model to align with the 3D clinical model.

3. The computer-implemented method according to claim 2, wherein translating the 3D general model to the 3D clinical model comprises: identifying the center of the 3D clinical model; identifying the center of the 3D general model; and translating the 3D general model such that the center of the 3D general model overlaps with the center of the 3D clinical model.

4. The computer-implemented method according to claim 2, wherein rotating the 3D general model to align with the 3D clinical model comprises: identifying the eye region of the 3D clinical model; identifying the eye region of the 3D general model; and rotating the 3D general model such that the eye region of the 3D general model overlaps with the eye region of the 3D clinical model.

5. The computer-implemented method according to claim 2, wherein scaling the 3D general model to align with the 3D clinical model comprises: scaling the 3D general model such that the ear region of the 3D general model aligns with the ear region of the 3D clinical model; and scaling the 3D general model such that the eye region of the 3D general model overlaps with the eye region of the 3D clinical model.

6. The computer-implemented method according to claim 1, wherein the bending transformation comprises: transforming the eye region of the 3D general model to match the eye region of the 3D clinical model without moving the ear position of the 3D general model.

7. The computer-implemented method according to claim 1, wherein the squeezing transformation comprises: transforming the 3D general model to match the 3D clinical model.

8. The computer-implemented method according to claim 1, the method further comprises: generating one or more recommended transducer array positions of one or more transducer arrays on the 3D clinical model to apply a tumor treatment field; and displaying at least one of the recommended transducer array positions on the 3D composite model on the display.

9. An apparatus for generating a three-dimensional (3D) composite model of a head of a subject, the apparatus comprises: one or more processors; and a memory that is accessible by the one or more processors and stores instructions that, when executed by the one or more processors, cause the device to perform the following operations: Generate a 3D clinical model of the subject's head based on one or more images of the subject's head; Obtain a 3D general model of the head of a general subject; Transform the 3D general model using a transformation and the 3D clinical model, where the transformation includes an affine transformation, a bending transformation, and a squeezing transformation; Generate the 3D composite model based on the transformed 3D general model and the 3D clinical model; and Display the 3D composite model on a display.

10. The apparatus according to claim 9, wherein each of the 3D clinical model and the 3D general model comprises: a center; an X-axis that intersects with a left ear reference position, a right ear reference position, and the center; a Y-axis that is orthogonal to the X-axis, intersects with the center, and is located between the front and back of the head; and a Z-axis that is orthogonal to the X-axis and the Y-axis and intersects with the center.

11. The apparatus according to claim 10, wherein the affine transformation of the 3D general model comprises: Overlap the center of the 3D general model with the center of the 3D clinical model; and Rotate the 3D general model about the X-axis to place a position equidistant between the left eye reference position and the right eye reference position of the 3D general model on the x-y plane.

12. The apparatus according to claim 10, wherein the bending transformation of the 3D general model comprises: Bend the 3D general model according to the 3D clinical model at the X-axis, where after bending the 3D general model, the front position of the 3D general model is located on the Y-axis, where the front position of the 3D general model is a position equidistant between the left eye reference position and the right eye reference position of the 3D general model.

13. The apparatus according to claim 10, wherein the squeezing transformation of the 3D general model comprises: Squeeze the 3D general model according to the 3D clinical model at the X-axis.

14. A non-transitory computer-readable medium that includes instructions for generating one or more recommended transducer placement positions on a subject, the instructions that, when executed by a computer, cause the computer to perform a method that comprises: Generate a 3D clinical model of the subject based on one or more images of the subject; Obtain a 3D general model of a general subject; Use an affine transformation, a bending transformation, and a squeezing transformation of the 3D general model to combine the 3D clinical model and the 3D general model to obtain a 3D composite model of the subject; and Generate one or more recommended transducer array positions of one or more transducer arrays on the 3D clinical model to apply a tumor treatment field; Display at least one recommended transducer placement position on the 3D composite model on a display.

15. The non-transitory computer-readable medium according to claim 14, wherein combining the 3D clinical model and the 3D general model comprises: using the affine transformation, bending transformation, and extrusion transformation of the 3D general model.

Images