Enhanced medical imaging

Abstract

A computer implementation method for enhancing medical images includes: acquiring a first medical image of a subject, wherein the first medical image has a plurality of voxels and the first medical image has missing voxels in a portion of the region of interest; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels and the second medical image has voxels in a portion of the region of interest; and generating a combined medical image based on the first and second medical images, wherein the combined medical image does not have missing voxels in a portion of the region of interest.

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims priority to U.S. Patent Application No. 18 / 744,991, filed on June 17, 2024, and U.S. Provisional Application No. 63 / 524,574, filed on June 30, 2023, the entireties of which are incorporated herein by reference.

Background Art

[0002] Tumor treatment 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. TT fields are placed on a patient's body and are non - invasively induced within the region of interest by transducers that apply an alternating current (AC) voltage between the transducers. Conventionally, transducers used to generate TT fields include a plurality of electrode elements including ceramic disks. One side of each ceramic disk is placed in contact with the patient's skin, and the other side of each disk has a conductive backing. Electrical signals are applied to this conductive backing, and these signals are capacitively coupled into the patient's body through the ceramic disks. Conventional transducer designs include an array of ceramic disks attached to the subject's body through a conductive skin - contact layer such as a hydrogel. At time intervals, an AC voltage is applied between a pair of transducers, generating an electric field with electric field lines running generally in the anterior - posterior direction. Next, an AC voltage is applied at a different time interval at the same frequency between at least one other pair of transducers, generating 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.

Summary of the Invention

Means for Solving the Problems

[0003] One aspect of the present disclosure provides a computer - implemented method for enhancing medical images. The method includes The method involves obtaining a first medical image of a subject, wherein the first medical image has multiple voxels, and the first medical image has missing voxels within a portion of the region of interest. The method involves obtaining a second medical image of the subject, wherein the second medical image has multiple voxels, and the second medical image has voxels within a portion of the region of interest. The method includes generating a combined medical image based on a first medical image and a second medical image, wherein the combined medical image is generated in which no voxels are missing within a portion of the region of interest.

[0004] Another aspect of this disclosure provides a computer implementation method for enhancing medical images. This method is The method involves obtaining a first medical image of a subject, wherein the first medical image has multiple voxels, and the first medical image has a missing slice within a portion of the region of interest. The method involves obtaining a second medical image of the subject, wherein the second medical image has multiple voxels, and the second medical image has voxels within a portion of the region of interest where slices are missing in the first medical image. Perform histogram matching on the first medical image to obtain the first histogram image, Perform histogram matching on the second medical image to obtain a second histogram image, The method includes generating a combined medical image based on a resampled first medical image, an aligned second medical image, a first histogram image, and a second histogram image, wherein the combined medical image is generated such that no slices are missing in any part of the region of interest.

[0005] Another aspect of this disclosure provides a computer implementation method for enhancing medical images. This method is The first medical image of the subject is to be obtained, and the first medical image is to be obtained having multiple voxels. The method involves acquiring a second medical image of a subject, wherein the second medical image has multiple voxels, and the first medical image has a lower resolution than the second medical image in a first direction. For the first medical image, a first weighted map is generated that has values ​​representing the distance between a voxel in the first medical image and the same voxel in the resampled first medical image. For the second medical image, a second weighting map is generated that has a value representing the distance between a voxel in the first medical image and the same voxel in the resampled second medical image, The method includes generating a combined medical image based on a first medical image, a second medical image, a first weighting map, and a second weighting map, wherein the combined medical image has a lower resolution in a first direction. [Brief explanation of the drawing]

[0006] [Figure 1] An exemplary method for generating composite medical images is shown. [Figure 2] This section provides an exemplary method for performing image matching based on histograms. [Figure 3] This demonstrates an exemplary method for performing image matching based on a checkerboard image. [Figure 4] This demonstrates an exemplary method for performing image matching based on a checkerboard image. [Figure 5] Figures 1-4 show an exemplary flowchart for implementing the exemplary method. [Figure 6] This shows an exemplary apparatus for applying an alternating electric field to a subject's body. [Figure 7A] A schematic diagram of an example of a transducer design for applying an alternating current electric field is shown. [Figure 7B] A schematic diagram of an example of a transducer design for applying an alternating current electric field is shown. [Figure 8] An example of a transducer placed on the subject's head is shown. [Figure 9] An example of a computer device is shown. [Modes for carrying out the invention]

[0007] This application describes exemplary techniques of computer algorithms used to supplement medical images that have lost information due to missing slices, sections, low resolution, etc.

[0008] When administering TT to a subject, one or more medical images are read and analyzed to determine the treatment plan for the subject. Traditionally, obtaining a complete set of full-resolution medical images of a subject can take about an hour, but with rapidly acquired images, it may only take a few minutes. However, rapidly acquired medical images may have low resolution or missing slices, and therefore may not contain complete information, and may not provide the most accurate judgment.

[0009] The inventors recognized that in the medical image reading process for determining TT field treatment, there is a need to supplement and enhance medical images that are missing or of low quality based on existing medical images that contain complete or better information about the same subject.

[0010] The methods and systems described herein provide practical applications for complementing and / or enhancing medical images where voxels are missing. By complementing and / or enhancing such medical images, more information about the subject can be obtained, leading to a more comprehensive view. Using medical images with a greater amount of subject information allows for a more accurate 3D computational model of the subject. Using a more accurate 3D computational model of the subject makes it possible to more precisely determine where the transducer array should be positioned within the subject to deliver the TT field.

[0011] In particular, the inventors have discovered computational techniques for complementing and / or enhancing medical images where voxels are missing. Exemplary methods and systems provide a method for complementing missing portions of a first medical image based on a second medical image having voxels corresponding to the missing portions, thereby generating a combined medical image. In some embodiments, the computer algorithm technique may generate the combined medical image using histogram matching of the first and second medical images. In some embodiments, the computer algorithm technique may use a checkerboard algorithm that generates first and second weighting maps based on first and second checkerboard images, and combines the weighted first and second medical images to generate a combined medical image.

[0012] Figure 1 shows an example of a computer implementation method 100 for generating a combined medical image based on a first medical image and a second medical image of a subject. Method 100 may be implemented by a computer, which includes one or more processors and memory accessible by one or more processors. When executed by one or more processors, the memory stores instructions that cause the computer to perform the steps of Method 100. Modifications, additions, or omissions may be made to Method 100 and other methods described herein. In Figure 1 and other methods described herein, the order of operations is shown for illustrative purposes, but the timing and order of such operations may be changed where appropriate without prejudice to the purpose and merits of the examples in this disclosure.

[0013] Method 100 may include, in step 102, acquiring a first medical image of the subject. The first medical image may have multiple voxels, and voxels may be missing within a portion of the region of interest. The image data may be, for example, an X-ray image, a magnetic resonance imaging (MRI) image, a computed tomography (CT) image, an ultrasound image, or any image that provides an internal view of the subject's body. For example, in some embodiments, the first medical image may have missing slices in a portion of the region of interest. In some embodiments, the first medical image may be truncated in a portion of the region of interest. For example, in a head scan of a subject, the top of the subject's head may be missing in the first medical image. In some embodiments, the first medical image may have low resolution in a portion of the region of interest. For example, in the case of low resolution, the first medical image may use a resolution of 512 × 512 with a plane spacing of approximately 3 mm to approximately 5 mm. A high-resolution medical image may use a resolution of 512 × 512 with a plane spacing of approximately 1 mm. Medical images with moderate resolution may use a 512×512 resolution with a plane spacing of approximately 2mm to 9mm. Ultra-high resolution medical images may use a 512×512 resolution with a plane spacing of less than approximately 1mm. The orientation of voxels in a medical image may be determined by the direction used when scanning the subject and / or the subject's orientation relative to the scanning system. In some embodiments, the first medical image has a specific MRI modality with a particular acquisition direction, resulting in high resolution in one direction and low resolution in the other.

[0014] In step 104, method 100 may include obtaining a second medical image of the subject. The second medical image may have a plurality of voxels, including the voxels of the portion of the region of interest where voxels are missing in the first medical image. In particular, although the first and second medical images reflect information of the same subject, the first medical image has less information or incomplete information than the second medical image. For example, in some embodiments, in the first medical image, voxels are missing within a part of the region of interest, and in the second medical image, voxels are present in the portion of the region of interest where voxels are missing in the first medical image. In some embodiments, in the first medical image, slices are missing within a part of the region of interest, and in the second medical image, slices are present in the portion of the region of interest where slices are missing in the first medical image. In some embodiments, the first medical image is cropped in a part of the region of interest, and the second medical image has voxels in the portion of the region of interest that are missing due to the cropping of the first medical image. In some embodiments, the first medical image has a low resolution in a part of the region of interest, and the second medical image has a high resolution in the said part of the region of interest. For example, in the first medical image, a resolution of 512×512 with an interval between planes of about 3 mm to about 5 mm, or about 2 mm to about 9 mm, may be used, and in the second medical image, a resolution of 512×512 with an interval between planes of about 1 mm or less may be used. For example, the first medical image may be an MRI image obtained quickly of the subject, which is faster but has a lower resolution than the second full-resolution MRI medical image of the subject. For example, the first medical image may be an MRI image for a quicker examination, and the second medical image may be an initial detailed MRI image of the subject that can be used for the diagnosis of the subject. In some embodiments, the first medical image and the second medical image have the same magnetic resonance imaging (MRI) modality, and the first medical image and the second medical image have different acquisition directions. Therefore, the first medical image has missing voxels compared to the second medical image.

[0015] In some embodiments, the first medical image and the second medical image may be preprocessed. In some embodiments, voxels having outliers may be removed. For example, for each of the first medical image and the second medical image, outlier voxels having significantly high or low gray level values that may affect the combined result of the two images may be removed. Such outlier voxels may be removed by restricting the gray level of the image to a certain percentile. In some embodiments, bias correction may be performed. For example, as a problem of MRI images, bias of the magnetic field signal at the time of acquisition may be mentioned. Bias correction may be used to reduce its influence.

[0016] In step 106, method 100 may include padding the first medical image to obtain a padded first medical image in order to pad voxels missing within a portion of the region of interest.

[0017] In step 108, method 100 may include padding the second medical image to obtain a padded second medical image in order to pad any voxels missing within a portion of the region of interest.

[0018] In step 110, method 100 may include resampling the padded first medical image and the padded second medical image at the same interval size to obtain a resampled first medical image and a resampled second medical image.

[0019] In step 112, method 100 may include aligning a resampled second medical image with a resampled first medical image to obtain an aligned second medical image. Aligning the two medical images allows both images to have the same orientation and size for a subject. In some embodiments, aligning a resampled second medical image may include registering the resampled second medical image with the resampled first medical image using a rigid body transformation. Various methods may be used to register the two medical images, such as applying landmarks or a Gaussian mixture model. In some embodiments, the rigid body transformation may be an affine transformation. In other embodiments, registration may use a non-rigid body transformation (e.g., warp). In some embodiments, as a result of the alignment, the resampled second medical image and the resampled first medical image may have the same coordinate system and the same voxel size.

[0020] In step 114, method 100 may also include performing the same image processing on the resampled first medical image and the aligned second medical image to obtain the processed first medical image and the processed second medical image. Further details regarding step 114 are shown in the description of Figures 2-4.

[0021] In step 116, method 100 may include generating a combined medical image based on the processed first medical image and the processed second medical image, wherein the combined medical image does not have any missing voxels or slices in the portion of the region of interest. Further details regarding step 116 are shown in the description of Figures 2-4.

[0022] In some embodiments, Method 100 may include introducing a third medical image if the combined medical image is missing voxels in a second portion (not shown) of the region of interest. More specifically, Method 100 may include obtaining a third medical image of a subject, the third medical image having a number of voxels, particularly in the second portion of the region of interest. Furthermore, Method 100 may include generating a second combined medical image based on the combined medical image and the third medical image, where the second combined medical image is not missing voxels in the second portion of the region of interest. In particular, the generation of the second combined medical image may employ a procedure similar to those described in steps 102-116.

[0023] In step 118, method 100 may include generating at least one transducer position for delivering the TT field to the subject based on the combined medical image. The combined medical image provides more complete visual information of the subject. This is because voxels that were missing in the first medical image are padded with voxels that contain information about the subject. Because the combined medical image contains more information about the subject, a more accurate 3D computational model of the subject can be obtained. Using a more accurate 3D computational model of the subject makes it possible to more accurately determine where the transducer array should be positioned on the subject to deliver the TT field.

[0024] In some embodiments, generating at least one transducer location for delivering a TT field to a subject based on a combined medical image may include processing the combined medical image to determine the location of a tumor in the subject; assigning conductivity to the subject's tissue type based on the combined medical image; generating a three-dimensional model of the subject based on the combined medical image, the conductivity of the subject's tissue type, and the location of the tumor; simulating the application of a TT field at a number of transducer locations on the subject using the three-dimensional model of the subject; calculating the TT field dose for each simulated transducer location; and selecting at least one transducer location for delivering the TT field to the subject.

[0025] Referring to Figure 2, Figure 2 illustrates an exemplary method of performing steps 114 and 116 of Figure 1 based on a histogram. Steps 202 and 204 are examples of implementing step 114, and steps 206-212 are examples of implementing step 116.

[0026] In step 202, the method of performing the same image processing on the resampled first medical image as described in step 114 of Figure 1 may include performing histogram matching on the resampled first medical image to obtain a first histogram image as the processed first medical image. Histogram matching may be performed, for example, according to any known technique for doing so. In some embodiments, if slices are missing in a portion of the region of interest of the first medical image, the first histogram image may be obtained by performing histogram matching on the first medical image.

[0027] In step 204, the method of performing the same image processing on the aligned second medical image, as described in step 114 of Figure 1, may include performing histogram matching on the aligned second medical image to obtain a second histogram image as the processed second medical image. In some embodiments, if slices are missing in part of the region of interest of the first medical image, the second histogram image may be obtained by performing histogram matching on the second medical image.

[0028] In some embodiments, both medical images are of the same type (e.g., T1MRI) in order to perform histogram matching in steps 202 and 203.

[0029] In step 206, the method may include iteratively performing steps 208 to 212, described below, for each voxel in the combined medical image in order to generate a combined medical image as shown in step 116 of Figure 1.

[0030] In step 208, the method for generating a combined medical image as described in step 116 of Figure 1 may include comparing the first value of a voxel in a first histogram image with the second value of a voxel in a second histogram image to determine which histogram image has the lowest gray level value.

[0031] In some embodiments, the method for generating a combined medical image, as described in step 116 of Figure 1, may include comparing the voxel values ​​in a first histogram image with the voxel values ​​in a second histogram image to determine which histogram image has the lowest gray level value.

[0032] In step 210, if the first histogram image contains a value with the lowest gray level, the corresponding voxel from the resampled first medical image may be copied to the combined medical image. In some embodiments, when comparing the voxel values ​​in the first histogram image with the voxel values ​​in the second histogram image, if the first histogram image has the lowest gray level, the corresponding voxel from the resampled first medical image is copied to the combined medical image.

[0033] In step 212, if the first histogram image contains a value with the lowest gray level, the corresponding voxel from the aligned second medical image can be copied to the combined medical image. In some embodiments, when comparing the voxel values ​​in the first histogram image with the voxel values ​​in the second histogram image, if the second histogram image has the lowest gray level, the corresponding voxel from the aligned second medical image is copied to the combined medical image.

[0034] Once the loop processing of steps 206-212 is complete, a combined medical image is obtained, similar to step 116 in Figure 1. Therefore, returning to Figure 1, in step 116, in some embodiments, a combined medical image may be generated based on a resampled first medical image, an aligned second medical image, a first histogram image, and a second histogram image, the combined medical image containing the voxels missing in the first medical image.

[0035] Referring to Figure 3, Figure 3 shows an exemplary way of performing steps 114 and 116 of Figure 1 based on a checkerboard image. Steps 302 and 304 are examples of implementing step 114, and steps 306 and 308 are examples of implementing step 116.

[0036] In step 302, the method of performing the same image processing on the resampled first medical image as described in step 114 of Figure 1 may include generating a first weighting map for the resampled first medical image. The first weighting map may have values, each representing the distance between a voxel in the first medical image and the same voxel in the resampled first medical image.

[0037] In step 304, the method of performing the same image processing on the aligned second medical image, as described in step 114 of Figure 1, may further include generating a second weighting map for the aligned second medical image. The second weighting map may have values ​​representing the distance between voxels in the second medical image and the same voxels in the aligned second medical image.

[0038] In some embodiments, the first weighting map and the second weighting map may be normalized individually or across the entire range of values ​​in both maps.

[0039] In step 306, the method may include iteratively performing step 308 for each voxel in the combined medical image in order to generate a combined medical image as shown in step 116 of Figure 1.

[0040] In step 308, the method for generating the combined medical image described in step 116 of Figure 1 may include summing, for each voxel in the combined medical image, the product of a first weighting map and the resampled first medical image, and the product of a second weighting map and the aligned second medical image. In some embodiments, the generation in step 308 may include summing a first weighting value for a voxel in the resampled first medical image and a second weighting value for a voxel in the aligned second medical image. The first weighting value may be based on a first weighting map having values ​​representing the distance between a voxel in the first medical image and the same voxel in the resampled first medical image, and the second weighting value may be based on a second weighting map having values ​​representing the distance between a voxel in the first medical image and the same voxel in the aligned second medical image.

[0041] In some embodiments, the generation in step 308 may include, for each voxel in the combined medical image, summing a first combination of the corresponding voxel in the processed first medical image and the corresponding voxel in the resampled first medical image, and a second combination of the corresponding voxel in the processed second medical image and the corresponding voxel in the aligned second medical image.

[0042] Once the loop processing in steps 306-308 is complete, a combined medical image may be obtained, similar to step 116 in Figure 1. Therefore, returning to Figure 1, in step 116, in some embodiments, a combined medical image may be generated based on the first medical image, the second medical image, the first weighting map, and the second weighting map, and this combined medical image includes the voxels missing in the first medical image.

[0043] Referring to Figure 4, Figure 4 further shows an exemplary method for carrying out steps 302 and 304 of Figure 3.

[0044] In step 402, the method for generating the first and second weighting maps may include generating a first checkerboard image and a second checkerboard image for the first and second medical images, respectively. In some embodiments, each checkerboard image may alternate between values ​​of -1 and 1. In some embodiments, the generation method in step 402 may further include assigning each voxel in the first checkerboard image a value calculated by dividing the value of that voxel in the first checkerboard image by the sum of the values ​​of the voxels in the first and second checkerboard images, and assigning each voxel in the second checkerboard image a negative value of the value of that voxel in the first checkerboard image.

[0045] In step 404, the method for generating the first and second weighting maps may include padding, resampling, and alignment of the first and second checkerboard images. The techniques of steps 106, 108, 110, and 112 described above may be used to perform step 404 on the first and second checkerboard images.

[0046] In step 406, the method for generating the first weighting map and the second weighting map may include assigning a value to each voxel in the first checkerboard image, calculated by dividing the value of that voxel in the first checkerboard image by the sum of the values ​​of the voxels in the first and second checkerboard images.

[0047] In step 408, the method for generating the first and second weighted maps may include assigning a negative value of the value of the voxel in the first checkerboard image to each voxel in the second checkerboard image.

[0048] In step 410, the method for generating the first and second weight maps may include generating the first and second weight maps based on the first and second checkerboard images. In some embodiments, the first and second weight maps may be the first and second checkerboard images, respectively.

[0049] In some embodiments, both the histogram matching technique shown in Figure 2 and the checkerboard image usage technique shown in Figures 3 and 4 may be performed in step 114 of Figure 1.

[0050] Figure 5 shows an exemplary flowchart for carrying out the methods of the embodiments shown in Figures 1-4. Similar to step 102, a primary image 502 may be obtained, and similar to step 104, a secondary image 504 may be obtained. In this example, the primary image 502 has lower resolution in the first direction compared to the secondary image 504, and therefore the primary image 502 is missing voxels in the first direction. Similar to steps 106 and 108, a resampled primary image 506 may be obtained by padding and resampling the primary image 502. Similar to steps 106, 108, and 110, an aligned secondary image 508 may be obtained by padding, resampling, and aligning the secondary image 504 with the primary image. As part of preprocessing, bias correction (e.g., N4 bias correction) may be applied to the resampled primary image 506 and the aligned secondary image 508 to obtain a corrected primary image 510 and a corrected secondary image 512. As shown in Figure 2, histogram matching may be further performed on the corrected primary image 510 and the corrected secondary image 512. Similar to step 402, a primary checkerboard image 514 and a secondary checkerboard image 516 may be generated. Similar to block 404, the primary checkerboard image 514 is padded and resampled to obtain a primary checkerboard image 518. Similar to block 404, the secondary checkerboard image 514 may be padded, resampled, and aligned using the same parameters used when aligning the secondary image 504 to the primary image 502 to obtain a secondary checkerboard image 520. Similar to blocks 302, 304, 408, and 410, a primary weighting map 522 and a secondary weighting map 524 may be generated. Similar to block 308, a super-resolution image 526 may be generated as a combined medical image using the corrected primary image 510, the corrected secondary image 512, the primary weighting map 522, and the secondary weighting map 524.

[0051] Exemplary systems and devices Figure 6 shows an exemplary apparatus 600 for applying an alternating current field (e.g., a TT field) to a subject's body. This system may be used to treat a target area of ​​the subject's body with the alternating current field. For example, the target area may be in the subject's brain, and the alternating current 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 field is delivered to the subject's body via two pairs of transducer arrays positioned on 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.

[0052] Exemplary apparatus 600 illustrates a system example having four transducers (or "transducer arrays") 600A-D. Each transducer 600A-D may include substantially flat electrode elements 602A-D, which are arranged on substrates 604A-D and electrically and physically connected (for example, via conductive wiring 606A-D). For each substrate 604A-D, the electrode elements 602A-D corresponding to the substrate may be electrically connected to each other and physically connected to each of the substrates 604A-D. For example, the electrode elements 602A-D may be controlled as a group such that they receive and execute the same command signal, and for each corresponding transducer 600A-D, the electrode elements 602A-D receive and execute the same command signal. For example, electrode elements 602A to D may be controlled individually for each transducer 600A to D, so that one electrode element may receive and execute different commands than another electrode element in the corresponding transducer 600A to D.

[0053] The substrates 604A-D may include, for example, cloth, foam, flexible plastic, and / or conductive medical gel. Two transducers (e.g., 600A and 600D) may be a first pair of transducers configured to apply an alternating electric field to a target area of ​​the subject's body. Two other transducers (e.g., 600B and 600C) may be a second pair of transducers similarly configured to apply an alternating electric field to a target area.

[0054] Transducers 600A-D may be coupled to an AC voltage generator 620, and the system may further include a controller 610 communicatively coupled to the AC voltage generator 620. The controller 610 may include a computer including one or more processors 624 and a memory 626 accessible by one or more processors. The memory 626 may store instructions, when executed by one or more processors, for controlling the AC voltage generator 620 to induce an alternating electric field between transducer pairs 600A-D according to one or more voltage waveforms, and / or causing the computer to perform one or more methods disclosed herein. The controller 610 may monitor operations performed by the AC voltage generator 620 (e.g., via processor(s) 624). One or more sensors 628 may be coupled to the controller 610 to provide the controller 610 with measurements or other information.

[0055] Electrode elements 602A-D can be capacitively coupled. In one example, electrode elements 602A-D are ceramic electrode elements coupled to each other via conductive wiring 606A-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.

[0056] In some embodiments, the voltage generating component may supply transducers 600A to D 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.

[0057] The structure of transducers 600A-D can take various forms. The transducer may be fixed 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 the transducer to the subject's body. Suitable materials may include, for example, cloth, foam, flexible plastic, and / or conductive medical gel. The transducer may be conductive or non-conductive.

[0058] 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 TT field to the body of a subject and (b) being positioned at locations specified herein. In certain embodiments, at least one electrode element of the first, second, third, or fourth transducer may include at least one ceramic disc adapted to generate an alternating electric field. In non-limiting 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.

[0059] Figure 7A shows a schematic diagram of an exemplary design of a transducer for applying an alternating electric field. The transducer array 701 includes 20 electrode elements 702 arranged on a substrate 703, which are electrically and physically connected to one another by conductive wiring 704. In some embodiments, the electrode elements 702 may include ceramic disks.

[0060] Figure 7B is a schematic diagram showing an exemplary design of a transducer for applying an alternating electric field. Each transducer 705 may include substantially flat electrode elements 706. In some embodiments, the electrode elements 706 are a non-ceramic dielectric material arranged across a plurality of flat conductors. Examples of non-ceramic dielectric materials arranged on flat conductors include polymer films arranged on pads on a printed circuit board or on substantially flat metal pieces. In some embodiments, such polymer films have a high dielectric constant, for example, a dielectric constant greater than 10. In some embodiments, the electrode elements 706 may have a variety of shapes. For example, the electrode elements may be triangular, rectangular, circular, oval, ovaloid, ovoid, or elliptical in shape, or substantially triangular, substantially rectangular, substantially circular, substantially oval, substantially ovaloid, substantially ovoid, or substantially elliptical in shape. In some embodiments, each of the electrode elements 706 may have the same shape, a similar shape, and / or a different shape.

[0061] Figure 9 shows an example of a computer device for use in embodiments of the present invention. For example, the device 900 may be a computer for implementing certain inventive techniques disclosed herein, such as generating composite medical images as shown in Figure 1. For example, steps 102-118 in Figure 1, steps 202-212 in Figure 2, steps 302-308 in Figure 3, and / or steps 402-410 in Figure 4 may be performed by a computer such as the computer device 900. For example, the device 900 may be used as the controller 610 in Figure 6, or as a separate computer device located remotely from the controller 610. The device 900 may include one or more processors 902, memory 903, one or more input devices, and one or more output devices 905.

[0062] In some embodiments, based on input 901, one or more processors 902 may generate control signals to control a voltage generator in order to implement one or more embodiments described herein. For example, input 901 may be a user input. For example, input 901 may be from another computer communicating with controller device 900. Input 901 may be received in conjunction with one or more input devices (not shown) of device 900.

[0063] Memory 903 may be accessible by one or more processors 902 (for example, via link 904) so ​​that one or more processors 902 can read information to and write information to memory 903. Instructions that, when executed by one or more processors 902, implement one or more embodiments described herein may be stored in memory 903.

[0064] One or more output devices 905 may provide information about the operation of the present invention, such as the selection of the transducer array, the voltages generated, and other operational information. Output devices 905 may provide visualization data according to a particular embodiment of the present invention.

[0065] The device 900 may include one or more processors (such as one or more processors 902) and memory accessible by one or more processors (such as memory 903), the memory storing instructions that, when executed by one or more processors, cause the device to perform one or more of the methods described herein.

[0066] The memory 903 may be a non-temporary processor-readable medium containing a set of instructions, which, when executed by a processor (such as one or more processors 902), cause the processor to perform one or more of the methods disclosed herein.

[0067] Exemplary Embodiments The present invention includes other exemplary embodiments ("Embodiments") as follows:

[0068] Embodiment 1: A computer implementation method for enhancing a medical image, the method comprising: acquiring a first medical image of a subject, wherein the first medical image has a plurality of voxels and the first medical image has a portion of voxels missing within a region of interest; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels and the second medical image has voxels within the portion of the region of interest; and generating a combined medical image based on the first medical image and the second medical image, wherein the combined medical image does not have a portion of voxels missing within the region of interest.

[0069] Embodiment 2: The method according to Embodiment 1, wherein the first medical image has a portion of the region of interest missing a slice, and the second medical image has voxels within the portion of the region of interest missing a slice in the first medical image.

[0070] Embodiment 3: The method according to Embodiment 1, wherein the first medical image is truncated in the region of interest, and the second medical image has voxels within the portion of the region of interest in which the first medical image is truncated.

[0071] Embodiment 4: The method according to Embodiment 1, wherein the first medical image has a lower resolution than the second medical image in a first direction.

[0072] Embodiment 5: The method according to Embodiment 1, wherein the first medical image has a plane-to-plane spacing of approximately 3 mm to approximately 5 mm, or a plane-to-plane spacing of approximately 2 mm to approximately 9 mm, and the second medical image has a plane-to-plane spacing of approximately 1 mm, or a plane-to-plane spacing of less than 1 mm.

[0073] Embodiment 6: The method according to Embodiment 1, wherein the first medical image and the second medical image have the same magnetic resonance imaging (MRI) modality, and the first medical image and the second medical image have different acquisition directions.

[0074] Embodiment 7: The method according to Embodiment 1, comprising: padding the first medical image to pad the missing voxels within the portion of the region of interest to obtain a padded first medical image; padding the second medical image to pad any missing voxels within the portion of the region of interest to obtain a padded second medical image; resampling the padded first medical image and the padded second medical image at the same interval size to obtain a resampled first medical image and a resampled second medical image; aligning the resampled second medical image with the resampled first medical image to obtain an aligned second medical image; and performing the same image processing on the resampled first medical image and the aligned second medical image to obtain a processed first medical image and a processed second medical image, wherein the combined medical image is generated based on the processed first medical image and the processed second medical image.

[0075] Embodiment 8: The method according to Embodiment 7, wherein aligning the resampled second medical images includes registering the resampled second medical images with the resampled first medical images using rigid body transformation.

[0076] Embodiment 9: The method according to Embodiment 7, wherein the resampled second medical image and the resampled first medical image have the same coordinate system and the same voxel size.

[0077] Embodiment 10: The method according to Embodiment 7, wherein performing the same image processing includes performing histogram matching on the resampled first medical image and performing histogram matching on the resampled second medical image.

[0078] Embodiment 11: The method according to Embodiment 7, wherein generating the combined medical image includes comparing the voxel values ​​in the processed first medical image with the voxel values ​​in the processed second medical image to determine the voxels in the combined medical image.

[0079] Embodiment 12: The method according to Embodiment 11, wherein the values ​​of the voxels in the processed first medical image are based on histogram matching of the first medical image, and the values ​​of the voxels in the processed second medical image are based on histogram matching of the second medical image.

[0080] Embodiment 13: The method according to Embodiment 7, wherein performing the same image processing comprises generating the first weighting map for the resampled first medical image and generating the second weighting map for the aligned second medical image.

[0081] Embodiment 14: The method according to Embodiment 13, wherein the first weighting map has values ​​representing the distance between a voxel in the first medical image and the same voxel in the resampled first medical image, and the second weighting map has values ​​representing the distance between a voxel in the first medical image and the same voxel in the aligned second medical image.

[0082] Embodiment 15: The method according to Embodiment 7, wherein performing the same image processing includes performing histogram matching on the resampled first medical image, performing histogram matching on the aligned second medical image, generating a first weighting map for the resampled first medical image, and generating a second weighting map for the aligned second medical image.

[0083] Embodiment 16: The method according to Embodiment 7, wherein generating the combined medical image comprises, for each voxel in the combined medical image, summing a first combination of the corresponding voxel in the processed first medical image and the corresponding voxel in the resampled first medical image and a second combination of the corresponding voxel in the processed second medical image and the corresponding voxel in the aligned second medical image.

[0084] Embodiment 17: The method according to Embodiment 7, wherein generating the combined medical image comprises summing a first weighting value for voxels in the resampled first medical image and a second weighting value for voxels in the aligned second medical image, wherein the first weighting value is based on a first weighting map having values ​​representing the distance between voxels in the first medical image and identical voxels in the resampled first medical image, and the second weighting value is based on a second weighting map having values ​​representing the distance between voxels in the first medical image and identical voxels in the aligned second medical image.

[0085] Embodiment 18: The method according to Embodiment 1, comprising: acquiring a third medical image of a subject, wherein the combined medical image has missing voxels in a second portion of the region of interest, the third medical image has a plurality of voxels, and the third medical image has missing voxels in the second portion of the region of interest; and generating a second combined medical image based on the combined medical image and the third medical image, wherein the second combined medical image does not have missing voxels in the second portion of the region of interest.

[0086] Embodiment 19: The method according to Embodiment 1, further comprising generating at least one transducer position for delivering a tumor treatment site to the subject based on the combined medical image.

[0087] Embodiment 20: A computer implementation method for enhancing a medical image, the method comprising: acquiring a first medical image of a subject, wherein the first medical image has a plurality of voxels and the first medical image has missing slices in a portion of the region of interest; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels and the second medical image has voxels in the portion of the region of interest where the slices are missing in the first medical image; performing histogram matching on the first medical image to acquire a first histogram image; performing histogram matching on the second medical image to acquire a second histogram image; and generating a combined medical image based on the resampled first medical image, the aligned second medical image, the first histogram image, and the second histogram image, wherein the combined medical image does not have missing slices in the portion of the region of interest.

[0088] Embodiment 21: The method according to Embodiment 20, wherein generating the combined medical image includes: for each voxel in the combined medical image, comparing the value of the voxel in the first histogram image with the value of the voxel in the second histogram image to determine which histogram image has the lowest gray level value; if the first histogram image has the lowest gray level value, copying the corresponding voxel from the resampled first medical image to the combined medical image; and if the second histogram image has the lowest gray level value, copying the corresponding voxel from the aligned second medical image to the combined medical image.

[0089] Embodiment 22: A computer implementation method for enhancing a medical image, the method comprising: acquiring a first medical image of a subject, wherein the first medical image has a plurality of voxels; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the first medical image has a lower resolution in a first direction than the second medical image; generating a first weighting map for the first medical image having values ​​representing the distance between voxels in the first medical image and identical voxels in a resampled first medical image; generating a second weighting map for the second medical image having values ​​representing the distance between voxels in the first medical image and identical voxels in a resampled second medical image; and generating a combined medical image based on the first medical image, the second medical image, the first weighting map, and the second weighting map, wherein the combined medical image has a lower resolution in a first direction.

[0090] Embodiment 23: The method according to Embodiment 22, wherein generating the first weighting map includes generating a first checkerboard image for the first medical image, and generating the second weighting map includes generating a second checkerboard image for the second medical image.

[0091] Embodiment 24: The method for generating the first and second weighting maps, comprising generating a first checkerboard image and a second checkerboard image for a first medical image and a second medical image, respectively, wherein each checkerboard image alternates between values ​​of -1 and 1; assigning a value to each voxel in the first checkerboard image calculated by dividing the value of the voxel in the first checkerboard image by the sum of the values ​​of the voxels in the first and second checkerboard images; and assigning a negative value to each voxel in the second checkerboard image, which is the method for generating the first and second weighting maps, the method for generating the first and second weighting maps, the method for generating the first and second checkerboard images, wherein the value of the voxel in the first checkerboard image is calculated by dividing the value of the voxel in the first checkerboard image by the sum of the values ​​of the voxels in the first checkerboard image.

[0092] Embodiment 25: The method according to Embodiment 22, wherein generating the combined medical image comprises, for each voxel, summing the product of the first weighting map and the resampled first medical image and the product of the second weighting map and the resampled second medical image.

[0093] Embodiment 26: Apparatus for selecting transducer positions for delivering a tumor treatment area to a subject, the apparatus comprising one or more processors, and a memory accessible by the one or more processors, the memory storing instructions causing the apparatus to perform a method that, when executed by the one or more processors, includes: acquiring a first medical image of a subject, wherein the first medical image has a plurality of voxels, and the first medical image has missing voxels in a portion of the region of interest; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the second medical image has voxels in the portion of the region of interest; and generating a combined medical image based on the first and second medical images, wherein the combined medical image does not have missing voxels in the portion of the region of interest.

[0094] Embodiment 27: A non-temporary processor-readable medium, the non-temporary processor-readable medium comprising a series of instructions recorded thereon, the series of instructions, when executed by a processor, causing the processor to perform a method comprising: acquiring a first medical image of a subject, wherein the first medical image has a plurality of voxels, and the first medical image has missing voxels in a portion of the region of interest; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the second medical image has voxels in the portion of the region of interest; and generating a combined medical image based on the first and second medical images, wherein the combined medical image does not have missing voxels in the portion of the region of interest.

[0095] Embodiment 28: Apparatus for selecting transducer position for delivering tumor treatment area to subject, wherein the apparatus comprises 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, provides the apparatus with the ability to acquire a first medical image of subject, wherein the first medical image has a plurality of voxels, and the first medical image has a missing slice within a portion of the region of interest, and acquire a second medical image of subject, wherein the second medical image has a plurality of voxels, and the second medical image has a missing slice in the first medical image. A device including a memory for storing instructions for causing a method to perform a method comprising: acquiring a first medical image having voxels within a portion of the region of interest; performing histogram matching on the first medical image and acquiring a first histogram image; performing histogram matching on the second medical image and acquiring a second histogram image; and generating a combined medical image based on the resampled first medical image, the aligned second medical image, the first histogram image, and the second histogram image, wherein the combined medical image does not have missing slices in the portion of the region of interest.

[0096] Embodiment 29: A non-temporary processor-readable medium wherein the non-temporary processor-readable medium is a series of instructions recorded thereon, and when the series of instructions is executed by a processor, the processor is instructed to acquire a first medical image of a subject, wherein the first medical image has a plurality of voxels, and the first medical image has a missing slice within a portion of the region of interest, and to acquire a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the second medical image has a missing voxel within the portion of the region of interest where the slice is missing in the first medical image. A non-temporary processor-readable medium comprising a set of instructions causing a method to perform a method comprising: acquiring; performing histogram matching on the first medical image and acquiring a first histogram image; performing histogram matching on the second medical image and acquiring a second histogram image; and generating a combined medical image based on the resampled first medical image, the aligned second medical image, the first histogram image, and the second histogram image, wherein the combined medical image is not missing slices in the portion of the region of interest.

[0097] Embodiment 30: Apparatus for selecting transducer positions for delivering a tumor treatment area to a subject, wherein the apparatus comprises one or more processors and a memory accessible by the one or more processors, the memory, when executed by the one or more processors, provides the apparatus with the following functions: acquiring a first medical image of the subject, wherein the first medical image has a plurality of voxels; acquiring a second medical image of the subject, wherein the second medical image has a plurality of voxels, wherein the first medical image has a lower resolution than the second medical image in a first direction; and with respect to the first medical image, the first A device including a memory for storing instructions for causing a method to be performed, which includes generating a first weighting map having values ​​representing the distance between a voxel in a medical image and the same voxel in a resampled first medical image; generating a second weighting map for the second medical image having values ​​representing the distance between a voxel in the first medical image and the same voxel in a resampled second medical image; and generating a combined medical image based on the first medical image, the second medical image, the first weighting map, and the second weighting map, wherein the combined medical image has a lower resolution in the first direction.

[0098] Embodiment 31: A non-temporary processor-readable medium wherein the non-temporary processor-readable medium is a series of instructions recorded thereon, and when the series of instructions is executed by a processor, the processor is given the instructions to acquire a first medical image of a subject, the first medical image having a plurality of voxels, and to acquire a second medical image of the subject, the second medical image having a plurality of voxels, the first medical image having a lower resolution than the second medical image in a first direction, and to resample the first medical image with respect to the voxels in the first medical image. A non-temporary processor-readable medium comprising a set of instructions causing a method to perform: generating a first weighting map having values ​​representing the distance between identical voxels in a first medical image; generating a second weighting map for a second medical image having values ​​representing the distance between a voxel in the first medical image and an identical voxel in a resampled second medical image; and generating a combined medical image based on the first medical image, the second medical image, the first weighting map, and the second weighting map, wherein the combined medical image has a lower resolution in the first direction.

[0099] Embodiments shown in any heading or portion of this disclosure may be combined with embodiments shown in the same or other headings or portions of this disclosure, unless otherwise stated herein or unless the context expressly contradicts the description. For example, an embodiment described in dependent claim form with respect 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).

[0100] 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 have the entire scope as defined by the following claims and their equivalents. [Explanation of symbols]

[0101] 620 AC Voltage Generator 610 Controller 624 processors 626 memory 628 sensors (multiple sensors possible) 900 equipment 902 One or more processors 903 memory 905 One or more output devices

Claims

1. A computer implementation method for enhancing medical images, wherein the method is The method involves obtaining a first medical image of a subject, wherein the first medical image has multiple voxels, and the first medical image has missing voxels within a portion of the region of interest. The acquisition of a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the second medical image has voxels within the portion of the region of interest. A method comprising generating a combined medical image based on the first medical image and the second medical image, wherein the combined medical image is generated such that no voxels are missing within the portion of the region of interest.

2. In the first medical image, a slice is missing within a portion of the region of interest, and in the second medical image, a slice is present in the portion of the region of interest where the slice is missing in the first medical image. The first medical image is truncated in the region of interest, and the second medical image has voxels in the part of the region of interest where the first medical image is truncated, The first medical image has a lower resolution than the second medical image in the first direction, The method according to claim 1, wherein the first medical image and the second medical image have the same magnetic resonance imaging (MRI) modality, and the first medical image and the second medical image have different acquisition directions, or one or more of the above.

3. To pad the missing voxels in the portion of the region of interest, the first medical image is padded to obtain a padded first medical image. To pad the second medical image to fill in any missing voxels within the portion of the region of interest, thereby obtaining a padded second medical image, The padded first medical image and the padded second medical image are resampled at the same interval size to obtain the resampled first medical image and the resampled second medical image. The resampled second medical image is aligned with the resampled first medical image to obtain an aligned second medical image. This includes performing the same image processing on the resampled first medical image and the aligned second medical image, and obtaining the processed first medical image and the processed second medical image. The method according to claim 1, wherein the combined medical image is generated based on the processed first medical image and the processed second medical image.

4. Performing the same image processing as described above means Performing histogram matching on the resampled first medical image, The method according to claim 3, comprising performing histogram matching on the resampled second medical image.

5. The values ​​of the voxels in the processed first medical image are determined based on histogram matching of the first medical image. The method according to claim 3, wherein the values ​​of the voxels in the processed second medical image are based on histogram matching of the second medical image.

6. Performing the same image processing as described above means To generate a first weighting map for the resampled first medical image, The method according to claim 3, comprising generating a second weighting map for the aligned second medical images.

7. The first weighting map has values ​​representing the distance between a voxel in the first medical image and the same voxel in the resampled first medical image. The method according to claim 6, wherein the second weighting map has values ​​representing the distance between a voxel in the first medical image and the same voxel in the aligned second medical image.

8. Performing the same image processing as described above means Performing histogram matching on the resampled first medical image, Performing histogram matching on the aforementioned aligned second medical images, To generate a first weighting map for the resampled first medical image, The method according to claim 3, comprising generating a second weighting map for the aligned second medical images.

9. The generation of the aforementioned combined medical image is For each voxel in the aforementioned combined medical image, A first combination of the corresponding voxel in the processed first medical image and the corresponding voxel in the resampled first medical image, The method according to claim 3, comprising summing a second combination of a corresponding voxel in the processed second medical image and a corresponding voxel in the aligned second medical image.

10. The method according to claim 1, further comprising generating at least one transducer position for delivering a tumor treatment site to the subject based on the combined medical image.

11. A computer implementation method for enhancing medical images, wherein the method is The method involves obtaining a first medical image of a subject, wherein the first medical image has multiple voxels, and the first medical image has a missing slice within a portion of the region of interest. The acquisition of a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the second medical image has voxels within the portion of the region of interest where slices are missing in the first medical image. Perform histogram matching on the first medical image and obtain a first histogram image. Perform histogram matching on the second medical image mentioned above to obtain a second histogram image, A method comprising generating a combined medical image based on the resampled first medical image, the aligned second medical image, the first histogram image, and the second histogram image, wherein the combined medical image is generated such that no slices are missing in the portion of the region of interest.

12. The generation of the aforementioned combined medical image is For each voxel in the aforementioned combined medical image, The values ​​of the voxels in the first histogram image and the values ​​of the voxels in the second histogram image are compared to determine which histogram image has the lowest gray level value, If the first histogram image has the lowest gray level value, the corresponding voxel from the resampled first medical image is copied to the combined medical image. The method according to claim 11, further comprising copying the corresponding voxels from the aligned second medical image to the combined medical image if the second histogram image has the lowest gray level value.

13. A computer implementation method for enhancing medical images, wherein the method is The acquisition of a first medical image of a subject, wherein the first medical image has multiple voxels, The acquisition of a second medical image of the subject, wherein the second medical image has a plurality of voxels, and the first medical image has a lower resolution than the second medical image in a first direction. With respect to the first medical image, a first weighted map is generated which has a value representing the distance between a voxel in the first medical image and the same voxel in the resampled first medical image. With respect to the second medical image, a second weighting map is generated which has a value representing the distance between a voxel in the first medical image and the same voxel in the resampled second medical image, A method comprising generating a combined medical image based on the first medical image, the second medical image, the first weighting map, and the second weighting map, wherein the combined medical image has a lower resolution in the first direction.

14. Generating the first weighting map includes generating a first checkerboard image for the first medical image, The method according to claim 13, wherein generating the second weighting map comprises generating a second checkerboard image for the second medical image.

15. The generation of the aforementioned combined medical image is The method according to claim 13, comprising summing for each voxel the product of the first weighting map and the resampled first medical image and the product of the second weighting map and the resampled second medical image.

Images