Methods and apparatus for multi-resolution medical imaging and image reconstruction

Abstract

Systems and methods for generating multi-resolution detection data based on multi-resolution scans, and for reconstructing medical images based on the multi-resolution detection data, are disclosed. In some examples, an image scanning system includes a first detector ring with a first crystal resolution, and a second detector ring with a second crystal resolution that differs from the first crystal resolution. For example, the first crystal resolution may be greater than the second crystal resolution. The image scanning system can capture a first scan with the first detector ring, and a second scan with the second detector ring. Further, the image scanning system generates first detection data based on the first scan, and second detection data based on the second scan. The image scanning system transmits the first detection data and the second detection data to reconstruct at least one image.

Description

Docket No.: 2024P21676WOMETHODS AND APPARATUS FOR MULTI-RESOLUTION MEDICAL IMAGING AND IMAGE RECONSTRUCTION FIELD

[0001] Aspects of the present disclosure relate in general to medical diagnostic systems and, more particularly, to capturing and reconstructing images from nuclear imaging systems for diagnostic and reporting purposes.BACKGROUND

[0002] Nuclear imaging systems can employ various technologies to capture images. For example, some nuclear imaging systems employ positron emission tomography (PET) or single-photon emission computed tomography (SPECT) to capture anatomical images. PET is a nuclear medicine imaging technique that produces tomographic images representing the distribution of positron emitting isotopes within a body, while SPECT relies on the detection of gamma rays to produce tomographic images representing the distribution of radioactive tracer molecules within a body. Some nuclear imaging systems combine images from PET and a co-modality, such as computed tomography (CT) or Magnetic Resonance Imaging (MRI). CT is an imaging technique that uses x-rays to produce anatomical images. Magnetic Resonance Imaging (MRI) is an imaging technique that uses magnetic fields and radio waves to generate anatomical and functional images, and may also be used as a comodality. These nuclear imaging systems can combine images from PET and comodality scanners during an image fusion process to produce images that show information from both the PET scan and the co-modality scan (e.g., PET / CT systems). Moreover, the nuclear imaging systems may generate an attenuation map that can be used to correct the PET measurement data during image reconstruction.

[0003] More recently, long-axial field-of-view (LAFOV) systems, such as LAFOV PET / CT systems, allow for wider scans, such as full body scans, in a single field of view. These LAFOV systems may capture a scan of a patient’s body at a particular resolution. In some situations, however, a medical provider may wish to image certain organs of a patient at relatively greater resolution. For instance, the medical provider may want to image the patient’s body at one resolution, and the patient’s head at aDocket No.: 2024P21676WOgreater resolution. In these examples, the patient may be scanned at least once with an LAFOV system, and a second time with a greater resolution scanner, such as a high-resolution PET scanner or super-resolution PET scanner. These multiple scans introduce additional costs not only for to obtain and maintain multiple scanners, but to generate the scans as well. In addition, the patient must take time to undergo multiple scans on various scanners. As such, there are opportunities to address deficiencies in nuclear imaging systems.SUMMARY

[0004] Systems and methods for generating multi-resolution detection data based on multi-resolution scans, and for reconstructing medical images based on the multiresolution detection data, are disclosed.

[0005] In some embodiments, a method by an image scanning system includes capturing a first scan by a first detector ring, the first detector ring having a first crystal resolution. The method also includes capturing a second scan by a second detector ring, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution.

[0006] In some embodiments, an image scanning system includes a first detector ring having a first crystal resolution, and a second detector ring have a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution.

[0007] In some embodiments, a computer-implemented method includes receiving a first scan captured by a first detector ring of an image scanning system, the first detector ring having a first crystal resolution. The method also includes receiving a second scan captured by a second detector ring of the image scanning system, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution. Further, the method includes generating first detection data based on the first scan and second detection data based on the second scan. The method also includes storing the first detection data and the second detection data within a memory device.Docket No.: 2024P21676WO

[0008] In some embodiments, a non-transitory computer readable medium stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations including receiving a first scan captured by a first detector ring of an image scanning system, the first detector ring having a first crystal resolution. The operations also include receiving a second scan captured by a second detector ring of the image scanning system, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution. Further, the operations include generating first detection data based on the first scan and second detection data based on the second scan. The operations also include storing the first detection data and the second detection data within a memory device.

[0009] In some embodiments, an image scanning system includes a first detector ring, a second detector ring, a memory device, and at least one processor communicatively coupled the memory device. The at least one processor is configured to receive a first scan captured by the first detector ring, the first detector ring having a first crystal resolution. The at least one processor is also configured to receive a second scan captured by the second detector ring, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution. Further, the at least one processor is configured to generate first detection data based on the first scan and second detection data based on the second scan. The at least one processor is configured to store the first detection data and the second detection data within the memory device.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The following will be apparent from elements of the figures, which are provided for illustrative purposes and are not necessarily drawn to scale.

[0011] FIG. 1 illustrates a nuclear imaging system, in accordance with some embodiments.Docket No.: 2024P21676WO

[0012] FIG. 2 illustrates a block diagram of an example computing device that can perform one or more of the functions described herein, in accordance with some embodiments.

[0013] FIG. 3 illustrates a nuclear imaging system, in accordance with some embodiments.

[0014] FIGS. 4A and 4B illustrate exemplary portions of a nuclear image scanning system, in accordance with some embodiments.

[0015] FIG. 5 is a flowchart of an example method of generating multi-resolution detection data and reconstructing a corresponding image, in accordance with some embodiments.

[0016] FIG. 6 is a flowchart of an example method of generating multi-resolution detection data based on scans by multi-resolution detector rings of an image scanning system, in accordance with some embodiments.DETAILED DESCRIPTION

[0017] This description of the exemplary embodiments is intended to be read in connection with the accompanying drawings, which are to be considered part of the entire written description. Independent of the grammatical term usage, individuals with male, female, or other gender identities are included within the term.

[0018] The exemplary embodiments are described with respect to the claimed systems as well as with respect to the claimed methods. Furthermore, the exemplary embodiments are described with respect to methods and systems for image reconstruction, as well as with respect to methods and systems for training functions used for image reconstruction. Features, advantages, or alternative embodiments herein can be assigned to the other claimed objects and vice versa. For example, claims for the providing systems can be improved with features described or claimed in the context of the methods, and vice versa. In addition, the functional features of described or claimed methods are embodied by objective units of a providing system.Docket No.: 2024P21676WOSimilarly, claims for methods and systems for training image reconstruction functions can be improved with features described or claimed in context of the methods and systems for image reconstruction, and vice versa.

[0019] Various embodiments of the present disclosure can employ machine learning methods or processes to provide clinical information from nuclear imaging systems. For example, the embodiments can employ machine learning methods or processes to reconstruct images based on captured measurement data, and provide the reconstructed images for clinical diagnosis. In some embodiments, machine learning methods or processes are trained to improve the reconstruction of images.

[0020] Long-axial field-of-view (LAFOV) positron emission tomography (PET) imaging systems can include a scanner with multiple detector rings (e.g., in the axial direction). Each detector ring can include multiple detector electronic assemblies (DEAs), with each DEA including various detection elements (e.g., PET scintillation detectors). Each detection element may house scintillation crystals that detect emitted gamma rays from a scanned subject. When a crystal detects an event, the PET imaging system generates one or more signals characterizing the detected event. For example, the PET imaging system can generate an energy signal characterizing a detected energy level (e.g., energy deposition), a first position signal characterizing a first dimension position (e.g., X coordinate) of the detecting crystal, and a second position signal characterizing a second dimension position (e.g., Y coordinate) of the detected crystal. The PET imaging system may also generate a time signal characterizing a detection time of the detected event.

[0021] The detection elements of each DEA may include detection elements with crystals of a particular size (e.g., height, width). For example, a DEA may include detection elements with crystals that are 3.2 by 3.2 mm. Based on the size of the crystals, a detection element can provide detections at a corresponding resolution. For instance, a detector element with crystals measuring 3.2 mm by 3.2 mm may be expected to have a detection resolution of 3.6 mm, whereas a detector element withDocket No.: 2024P21676WOcrystals measuring 1.6 mm by 1.6 mm may be expected to have a detection resolution of 2.8 mm.

[0022] As described further herein, and in contrast to conventional LAFOV imaging systems, in some examples a LAFOV PET imaging system can include one or more detector rings with first DEAs that include first detector elements with crystals of a first size, which allows for the first DEAs to provide detections at a first resolution. For instance, the crystals in the first detector elements may be 3.2 mm x 3.2 mm x 20 mm in size, thereby allowing the first detector elements to provide a detection resolution of approximately 3.6 mm (e.g., in the center of the field-of-view (FOV) of a corresponding first detector element). The LAFOV PET imaging system also includes one or more detector rings with second DEAs that include second detector elements with crystals of a second size, which allows for these second DEAs to provide detections at a second resolution. The second size may be smaller than the first size. For instance, the crystals in the second detector elements may be 1.6 mm x 1.6 mm x 20 mm in size, thereby allowing these second detector elements to provide detections at a detection resolution of approximately 2.8 mm (e.g., in the center of the FOV of a corresponding second detector element). As such, the LAFOV PET imaging system can generate detection data (e.g., time-coincident data pairs, sinograms) at the first resolution, as well as detection data at the second resolution. This may allow, for instance, for a patient to be simultaneously scanned at various resolutions. For instance, during a full body scan, the patient’s head may be scanned at a greater resolution than then patient’s body.

[0023] To provide the greater resolution, the second detector elements can include additional crystals in a same sized crystal encasing (e.g., same sized crystal storing volume) as the crystal encasing for the first detector elements. For example, the first and second detector elements may have a volume of 32 x 64 x 20 mm. In other words, their “holding volume” for crystals is 32 x 64 x 20 mm. Based on its volume, the first detector elements can be fitted with 10 x 20 x 1 units of 3.2 x 3.2 x 20 mm crystals. For example, because the width of the first detector elements is 32 mm, the first detector elements can store up to ten crystals that have a width of 3.2 mm. Similarly, because the height of the first detector elements is 64 mm, the second detectorDocket No.: 2024P21676WOelements can store up to twenty crystals that have a height of 3.2 mm. Moreover, the second detector elements can be fitted with 20 x 40 x 1 units of 1.6 x 1.6 x 20 mm crystals. For example, because the width of the second detector elements is also 32 mm, the second detector elements can store up to twenty crystals that have a width of 1.6 mm. Similarly, because the height of the second detector elements is also 64 mm, the second detector elements can store up to forty crystals that have a height of 1.6 mm. As such, while the first detector elements can detect events at a first resolution, the second detector elements can detect events at a second resolution. Table 1 below shows exemplary configurations for a detector element.Table 11

[0024] In some examples, a LAFOV PET imaging system includes at least one detector ring that can detect events at a first resolution, and at least one detector ring that can detect events at a second resolution. The first resolution may differ (e.g., be greater than) the second resolution. For instance, the LAFOV PET imaging system may include one detector ring that detects events at a resolution of 2.8 mm. To accomplish this resolution, the detector ring can include DEAs that include detector elements with crystals of a first size (e.g., 1.6 x 1.6 x 20 mm). The LAFOV PET imaging system can also include multiple detector rings (e.g., 2, 3, 4, etc.) that detects events at, for instance, at a resolution of 3.6 mm. To accomplish this resolution, each of the multiple detector rings can include DEAs that include detector elements with crystals of a second size (e.g., 3.2 x 3.2 x 20 mm). In other examples, a LAFOV PET imaging system can include multiple detector rings that can detect events at the first resolution,1The expected resolution values assume an 85 mm bore size of the scanner and 1 mm point source diameters.Docket No.: 2024P21676WOand multiple detector rings that can detect events at the second resolution. In yet other examples, a LAFOV PET imaging system can include multiple detector rings that can detect events at the first resolution, and one detector ring that can detect events at the second resolution.

[0025] Among other advantages, the embodiments described herein can provide high resolution imaging in LAFOV imaging systems. The embodiments may also allow for the simultaneous acquisition of normal system resolution and high resolution images. Moreover, the embodiments may provide the ability to combine imaging data from various resolution DEAs to provide system resolution images. Persons of ordinary skill in the art would recognize these and other benefits as well.

[0026] Referring now to the figures, FIG. 1 illustrates a nuclear imaging system 100 that includes multi-resolution image scanning system 102 and image reconstruction system 104. The multi-resolution image scanning system 102 can be LAFOV PET scanner that can capture PET images, a LAFOV PET / MR scanner that can capture PET and MR images, a LAFOV PET / CT scanner that can capture PET and CT images, or any other suitable LAFOV image scanner. For example, as illustrated, multi-resolution image scanning system 102 can capture PET images (e.g., of a person), and can generate PET measurement data based on the captured PET images. The PET measurement data (e.g., sinogram data, list-mode data) can represent anything imaged in the scanner's field-of-view (FOV) containing positron emitting isotopes. Moreover, the PET measurement data may identify detection events (e.g., time-coincident data pairs) and related timing information.

[0027] The multi-resolution image scanning system 102 includes various detector rings, including a first resolution detector ring 110 and multiple second resolution detector rings 112A, 112B, 112C. In this example, the first resolution detector ring 110 is axially adjacent to the second resolution detector ring 112A. In other examples, the first resolution detector ring 110 may be axially adjacent to one or more of the second resolution detector rings 112A, 112B, 112C. Each of the first resolution detector ring 110 and multiple second resolution detector rings 112A, 112B, 112C can scan a patientDocket No.: 2024P21676WO103 and, based on the scans, generate corresponding detection data (e.g., sinograms). The resolution of the detection data generated by the first resolution detector ring 110 may differ from the resolution of the detection data generated by each of the second resolution detector rings 112A, 112B, 112C.

[0028] For example, each of the first resolution detector ring 110 and multiple second resolution detector rings 112A, 112B, 112C can include detector elements of a same sized encasing (e.g., they may have a volume of 32 x 64 x 20 mm), but that differ in the size of crystals they hold. For example, the first resolution detector ring 110 includes detector elements with a first resolution, while the multiple second resolution detector rings 112A, 112B, 112C include detector elements with a second resolution. For example, the first resolution detector ring 110 may include DEAs with detector elements that have a resolution of 2.8 mm. To accomplish this resolution, these detector elements can include crystals of a first size (e.g., 1.6 x 1.6 x 20 mm). Further, the multiple second resolution detector rings 112A, 112B, 112C may include DEAs with detector elements that have a resolution of 3.3 mm, for instance. To accomplish this resolution, these detector elements can include crystals of a second, and larger, size (e.g., 2.7 x 2.7 x 20 mm) than the first size of the crystals within the first resolution detector ring 110. As described herein, because the first crystals of the first resolution detector ring 110 are smaller than the second crystals of the multiple second resolution detector rings 112A, 112B, 112C, the detector elements of the first resolution detector ring 110 can hold more of the crystals in a same sized encasing than the detector elements of the multiple second resolution detector rings 112A, 112B, 112C.

[0029] Although in this example the first resolution detector ring 110 is placed before the multiple second resolution detector rings 112A, 112B, 112C, in other examples the first resolution detector ring 110 can be placed in any other position relative to any of the multiple second resolution detector rings 112A, 112B, 112C. For instance, the first resolution detector ring 110 can be placed in the second, third, or fourth, detector ring position (i.e., after the multiple second resolution detector rings 112A, 112B, 112C). In addition, in some examples, rather than a single first resolution detector ring 110, the multi-resolution image scanning system 102 can include multipleDocket No.: 2024P21676WOfirst resolution detector rings 110. Similarly, rather than multiple second resolution detector rings 112A, 112B, 112C, in some examples the multi-resolution image scanning system 102 can include a single second resolution detector ring 112A, 112B, 112C.

[0030] As illustrated, the multi-resolution image scanning system 102 further includes a patient table 105 as well as a table motion controller 106. The table motion controller 106 is configured to move the patient table 105 (e.g., in the axial direction) so as to place a patient 103 at a desired position for scanning. For example, the table motion controller 106 can move the patient table 105 through the first resolution detector ring 110 and various second resolution detector rings 112A, 112B, 112C. In some examples, the table motion controller 106 can move the patient table 105 such as to position the patient’s 103 head under the first resolution detector ring 110, while positioning at least a portion of the patient’s 103 body under the second resolution detector rings 112A, 112B, 112C.

[0031] Additionally, the image reconstruction system 104 can receive detection data (e.g. , sinograms) generated by one or more of the first resolution detector ring 110 and various second resolution detector rings 112A, 112B, 112C. For example, the image reconstruction system 104 can receive from the multi-resolution image scanning system 102 first resolution detection data based on captured scans by the first resolution detector ring 110, and second resolution detection data based on captured scans by each of the second resolution detector rings 112A, 112B, 112C.

[0032] In some examples, the image reconstruction system 104 may also receive co-modality data from the multi-resolution image scanning system 102, such as CT or MRI measurement data. For example, the multi-resolution image scanning system 102 may support PET / CT scans, and thus can generate CT measurement data based on the CT scans, and transmit the CT measurement data to the image reconstruction system 104. Alternatively, the multi-resolution image scanning system 102 may support PET / MRI scans, and thus can generate MRI measurement data based on the MRI scans, and transmit the MRI measurement data to the image reconstruction systemDocket No.: 2024P21676WO104. In some examples, the multi-resolution image scanning system 102 can generate attenuation maps based on co-modality scans, and can transmit the attenuation maps to the image reconstruction system 104.

[0033] As described further herein, the image reconstruction system 104 can reconstruct an image based on the detection data received from the multi-resolution image scanning system 102. For instance, in some examples, the image reconstruction system 104 can reconstruct an image based on the detection data (e.g., time-coincident data pairs, sinograms) generated for scans captured by the first resolution detector ring 110 (e.g., higher-resolution detection data). The image reconstruction system 104 can also reconstruct an image based the detection data generated for scans captured by one or more of the second resolution detector rings 112A, 112B, 112C (e.g. , relatively lower-resolution detection data).

[0034] As an example, FIG. 4A illustrates the generation of first sinogram data 402 based on one or more scans 403 by the first resolution detector ring 110. The image reconstruction system 104 can receive the first sinogram data 402, and can reconstruct a first image 412. FIG. 4A further illustrates the generation of second sinogram data 404 based on scans 405 by the second resolution detector rings 112A, 112B, 112C. The image reconstruction system 104 can receive the second sinogram data 404, and can reconstruct a second image 414. The first image 412 may be of a different resolution (e.g., greater resolution) than the second image 414.

[0035] In yet other examples, the image reconstruction system 104 can reconstruct an image based on the detection data generated for scans captured by the first resolution detector ring 110 and the detection data generated for scans captured by one or more of the second resolution detector rings 112A, 112B, 112C. For example, as illustrated in FIG. 4B, the multi-resolution image scanning system 102 can generate third sinogram data 452 based on scans by the first resolution detector ring 110 and the second resolution detector rings 112A, 112B, 112C. The image reconstruction system 104 can receive the third sinogram data 452, and can reconstruct a third image 462.Docket No.: 2024P21676WO

[0036] FIG. 2 illustrates a computing device 200 that can be employed by, for example, the image reconstruction system 104. For instance, computing device 200 can implement one or more of the functions of the image reconstruction system 104 described herein.

[0037] Computing device 200 can include one or more processors 201 , working memory 202, one or more input-output devices 203, instruction memory 207, a transceiver 204, one or more communication ports 209, and a display 206, all operatively coupled to one or more data buses 208. Data buses 208 allow for communication among the various devices. Data buses 208 can include wired, or wireless, communication channels.

[0038] Processors 201 can include one or more distinct processors, each having one or more cores. Each of the distinct processors can have the same or different structure. Processors 201 can include one or more central processing units (CPUs), one or more graphics processing units (GPUs), application specific integrated circuits (ASICs), digital signal processors (DSPs), and the like. Further, each of the one or more processors 201 can be configured to perform a certain function or operation by executing code, stored on instruction memory 207, embodying the function or operation. For example, processors 201 can be configured to perform one or more of the functions, methods, or operations disclosed herein.

[0039] Instruction memory 207 can store instructions that can be accessed (e.g., read) and executed by processors 201. For example, instruction memory 207 can be a non-transitory, computer-readable storage medium such as a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory, a removable disk, CD-ROM, any non-volatile memory, or any other suitable memory. For example, instruction memory 207 can store instructions that, when executed by one or more processors 201 , cause one or more processors 201 to perform one or more of the functions of image reconstruction system 104, such as one or more of the histo-image generation processes, the multi-view attenuation histo-image generation processes, and / or the machine learning processes described herein.Docket No.: 2024P21676WO

[0040] Processors 201 can store data to, and read data from, working memory 202. For example, processors 201 can store a working set of instructions to working memory 202, such as instructions loaded from instruction memory 207. Processors 201 can also use working memory 202 to store dynamic data created during the operation of computing device 200. Working memory 202 can be a random access memory (RAM) such as a static random access memory (SRAM) or dynamic random access memory (DRAM), or any other suitable memory.

[0041] Input-output devices 203 can include any suitable device that allows for data input or output. For example, input-output devices 203 can include one or more of a keyboard, a touchpad, a mouse, a stylus, a touchscreen, a physical button, a speaker, a microphone, or any other suitable input or output device.

[0042] Communication port(s) 209 can include, for example, a serial port such as a universal asynchronous receiver / transmitter (LIART) connection, a Universal Serial Bus (USB) connection, or any other suitable communication port or connection. In some examples, communication port(s) 209 allows for the programming of executable instructions in instruction memory 207. In some examples, communication port(s) 209 allow for the transfer (e.g., uploading or downloading) of data.

[0043] Display 206 can display user interface 205. User interface 205 can enable user interaction with computing device 200. For example, user interface 205 can be a user interface for an application that allows for the viewing of final image volumes 191. In some examples, a user can interact with user interface 205 by engaging input-output devices 203. In some examples, display 206 can be a touchscreen, where user interface 205 is displayed on the touchscreen.

[0044] Transceiver 204 allows for communication with a network, such as a Wi-Fi network, an Ethernet network, a cellular network, or any other suitable communication network. For example, if operating in a cellular network, transceiver 204 is configured to allow communications with the cellular network. Processor(s) 201 is operable to receive data from, or send data to, a network via transceiver 204.Docket No.: 2024P21676WO

[0045] FIG. 3 illustrates further exemplary details of the nuclear imaging system 100. As illustrated, the multi-resolution image scanning system 102 may generate, based on a scan by the first resolution detector ring 110, first resolution PET detection data 311. The multi-resolution image scanning system 102 may also generate, based on a scan by one or more of the second resolution detector rings 112, second resolution PET detection data 313. The first resolution detector ring 110 may capture scans at a different resolution (e.g., higher resolution) than the scans captured by the second resolution detector rings 112. As such, the first resolution PET detection data 311 and second resolution PET detection data 313 have differing imaging resolutions. For instance, the first resolution PET detection data 311 may be of a greater resolution than the second resolution PET detection data 313. The multi-resolution image scanning system 102 may transmit the first resolution PET detection data 311 and the second resolution PET detection data 313 to the image reconstruction system 104.

[0046] As further illustrated, the image reconstruction system 104 includes a PET image reconstruction engine 302 and a memory device 310. In some examples, the image reconstruction system 104 are implemented in hardware, such as in one or more field-programmable gate arrays (FPGAs), one or more application-specific integrated circuits (ASICs), one or more state machines, one or more computing devices, digital circuitry, or any other suitable circuitry. For example, all or parts of the PET image reconstruction engine 302 may be implemented within one or more FPGAs. In some examples, parts or all of the image reconstruction system 104 can be implemented in software as executable instructions such that, when executed by one or more processors, cause the one or more processors to perform respective functions as described herein. The instructions can be stored in a non-transitory, computer-readable storage medium, and can be read and executed by the one or more processors.

[0047] The PET image reconstruction engine 302 can receive the first resolution PET detection data 311 and the second resolution PET detection data 313 and reconstruct an image (e.g., a 3-dimensional (3D) image) based on one or more of the first resolution PET detection data 311 and the second resolution PET detection dataDocket No.: 2024P21676WO

[0048] For instance, in some examples, the PET image reconstruction engine 302 applies an image reconstruction process to the first resolution PET detection data 311 and the second resolution PET detection data 313 to reconstruct a final image volume 391.

[0049] In some examples, the image reconstruction process includes rebinning the lines of responses of the first resolution PET detection data 311 to a same bin size as the lines of responses of the second resolution PET detection data 313 (e.g., due to their varying resolutions). Once the first resolution PET detection data 311 is rebinned, the PET image reconstruction engine 302 reconstructs the final image volume 191 based on the rebinned first resolution PET detection data 311 and the second resolution PET detection data 313. For instance, the PET image reconstruction engine 302 may apply a filtered-back-projection (FBP) process to the rebinned first resolution PET detection data 311 and the second resolution PET detection data 313 to generate the final image volume 191. Other reconstruction processes can include, for instance, Maximum-likelihood expectation maximization (ML-EM), Ordered subset expectation maximization (OSEM), or any other suitable reconstruction process.

[0050] Similarly, rather than rebinning the lines of responses of the first resolution PET detection data 311, the PET image reconstruction engine 302 can rebin the lines of responses of the second resolution PET detection data 313 to a same bin size as the lines of responses of the first resolution PET detection data 311. The PET image reconstruction engine 302 then reconstructs the final image volume 191 (e.g., using FBP, ML-EM, OSEM, etc.) based on the first resolution PET detection data 311 and the rebinned second resolution PET detection data 313.

[0051] In other examples, the image reconstruction process includes backprojecting the first resolution PET detection data 311 and the second resolution PET detection data 313 to one image, and then forward projecting the image to multiple (e.g., two) sinograms. The PET image reconstruction engine 302 then reconstructs the final image volume 191 (e.g., using FBP, ML-EM, OSEM, etc.) based on the sinograms.Docket No.: 2024P21676WO

[0052] In some examples, the PET image reconstruction engine 302 may apply one or more trained machine learning processes to the first resolution PET detection data 311 and the second resolution PET detection data 313 and, based on applying the one or more trained machine learning processes, may generate the final image volume 191. For example, the PET image reconstruction engine 302 may input the first resolution PET detection data 311 and the second resolution PET detection data 313 to a trained neural network 319 (e.g., convolutional neural network (CNN)) and, in response, may generate output data characterizing the final image volume 191.

[0053] In some examples, to train the neural network 319, the image reconstruction system 104 inputs pairs of first resolution PET detection data 311 and the second resolution PET detection data 313 to the neural network 319, and compares the output data to expected final image volume data. For example, the image reconstruction system 104 may compute one or more metric values based on the output data and the expected final image volume data. Each metric may be, for example, an area-under-curve (AUC) value, any receiver operating characteristic (ROC) curve or precision-recall (PR) curve value, or any other suitable metric value. The image reconstruction system 104 may determine whether the neural network is trained based on the one or more metric values. For instance, the image reconstruction system 104 may determine that the neural network 319 is trained when a metric value at least meets (e.g., is the same as or greater than) a threshold value. If the metric value does not at least meet the threshold value, the image reconstruction system 104 continues training the neural network 319 until the metric value does at least meet the threshold value. Once trained, the image reconstruction system 104 may store parameters (e.g., hyperparameters, weights, coefficients, etc.) characterizing the trained neural network in the memory device 310. The image reconstruction system 104 may retrieve the parameters from the memory device 310 to establish and execute the trained neural network 319.

[0054] In some instances, the image reconstruction system 104 receives an attenuation map 305 (e g., based on a co-modality scan, such as a CT scan) from the multi-resolution image scanning system 102. The image reconstruction system 104Docket No.: 2024P21676WOmay perform operations to correct the first resolution PET detection data 311 and the second resolution PET detection data 313 for attenuation based on the attenuation map 305. For instance, the image reconstruction system 104 may apply one or more attenuation correction processes to the output of the trained machine learning process and the attenuation map 305 and, based on applying the one or more attenuation correction processes, may generate the final image volume 191.

[0055] In some examples, the PET image reconstruction engine 302 reconstructs a first resolution image 379 based on the first resolution PET detection data 311 using any of the reconstruction processes described herein, or any other suitable reconstruction process. Additionally or alternatively, the PET image reconstruction engine 302 may reconstruct a second resolution image 381 based on the second resolution PET detection data 313 using any of the reconstruction processes described herein, or any other suitable reconstruction process.

[0056] In some examples, the PET image reconstruction engine 302 stores one or more of the final image volume 191 , first resolution image 379, and second resolution image 381 in memory device 310. In some examples, the image reconstruction system 104 transmits one or more of the final image volume 191 , first resolution image 379, and second resolution image 381 for display, such as for display on display 460. Display 460 may be, for example, in a same room as the nuclear imaging system 100, or in a remote location (e.g., a separate healthcare facility).

[0057] FIG. 5 is a flowchart of an example method 500 to generate multiresolution detection data and, in some examples, reconstruct a corresponding image. The method can be performed by, for example, the nuclear imaging system 100 described herein.

[0058] Beginning at block 502, a first scan is captured by a first detector ring of an image scanning system, where the first detector ring has a first crystal resolution. For example, the first resolution detector ring 110 of the multi-resolution image scanning system 102 may capture a scan (e.g., scan 403) of the head of the patient 103. At block 504, a second scan is captured by a second detector ring of the image scanningDocket No.: 2024P21676WOsystem, where the second detector ring has a second crystal resolution. For example, the second resolution detector ring 112A of the multi-resolution image scanning system 102 may capture a scan (e.g., scan 405) of the body of the patient 103. The first crystal resolution differs from the second crystal resolution.

[0059] Further, at block 506, first detection data is generated based on the first scan. For instance, the multi-resolution image scanning system 102 may generate first detection data, such as first sinogram data 402, based on the scan 403. Similarly, at block 508, second detection data is generated based on the second scan. For instance, the multi-resolution image scanning system 102 may generate second detection data, such as second sinogram data 404, based on the scan 405.

[0060] At block 510 the first detection data and the second detection data is stored within a memory device (e.g., memory device 310).

[0061] In some examples, at block 512, an image is reconstructed based on the first detection data and the second detection data. For instance, and as described herein, the multi-resolution image scanning system 102 may transmit the first detection data (e.g., first sinogram data 402) and the second detection data (e.g., second sinogram data 404) to the image reconstruction system 104. Further, the image reconstruction system 104 may reconstruct an image based on the first sinogram data and the second detection data. In some examples, the image reconstruction system 104 inputs the first detection data and the second detection data to a trained neural network (e.g., executed neural network 319) and, in response, the trained neural network generates output data characterizing the reconstructed image.

[0062] Further, in some examples, at block 514 the image is provided for display. For instance, the image reconstruction system 104 may transmit the image to display 460 for display.

[0063] FIG. 6 is a flowchart of an example method 600 to generate multiresolution detection data based on scans by multi-resolution detector rings of an imageDocket No.: 2024P21676WOscanning system. The method can be performed by, for example, the multi-resolution image scanning system 102 described herein.

[0064] Beginning at block 602, a first scan is captured by a first detector ring of an image scanning system, where the first detector ring can detect events at a first crystal resolution. Further, at block 604, a second scan is captured by a second detector ring of the image scanning system, where the second detector ring can detect events at a second crystal resolution. The first crystal resolution of the first detector ring is different than the second crystal resolution of the second detector ring. For example, the first crystal resolution may be 2.8 mm, while the second crystal resolution may be 3.6 mm.

[0065] Further, at block 606, first detection data is generated based on the first scan, where the first detection data characterizes detected events at the first crystal resolution. Similarly, at block 608, second detection data is generated based on the second scan, where the second detection data characterizes detected events at the second crystal resolution. The first detection data and second detection data can be, for example, sinograms. At block 610, the first detection data and the second detection data are transmitted. For instance, the multi-resolution image scanning system 102 may transmit the first detection data and the second detection data to the image reconstruction system 104 for image reconstruction, as described herein.

[0066] The following is a list of non-limiting illustrative embodiments disclosed herein:

[0067] Illustrative Embodiment 1 : A computer-implemented method comprising:receiving a first scan captured by a first detector ring of an image scanning system, the first detector ring having a first crystal resolution;receiving a second scan captured by a second detector ring of the image scanning system, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;Docket No.: 2024P21676WO generating first detection data based on the first scan;generating second detection data based on the second scan; andstoring the first detection data and the second detection data within a memory device.

[0068] Illustrative Embodiment 2: The computer-implemented method of illustrative embodiment 1 , wherein the first crystal resolution is greater than the second crystal resolution.

[0069] Illustrative Embodiment 3: The computer-implemented method of any of illustrative embodiments 1-2, further comprising applying a reconstruction process to the first detection data and, based on the application of the reconstruction process, generating a first image.

[0070] Illustrative Embodiment 4: The computer-implemented method of any of illustrative embodiments 1-3, further comprising applying the reconstruction process to the second detection data and, based on the application of the reconstruction process, generating a second image.

[0071] Illustrative Embodiment 5: The computer-implemented method of illustrative embodiment 4, wherein an image resolution of the first image is greater than an image resolution of the second image.Docket No.: 2024P21676WO

[0072] Illustrative Embodiment 6: The computer-implemented method of any of illustrative embodiments 1-5, wherein the first scan is of at least a portion of a head of a patient and the second scan is of at least a portion of a body of the patient, the second scan excluding the portion of the head of the patient.

[0073] Illustrative Embodiment 7: The computer-implemented method of any of illustrative embodiments 1-6, further comprising applying a reconstruction process to the first detection data and the second detection data and, based on the application of the reconstruction process, generating an image.

[0074] Illustrative Embodiment 8: The computer-implemented method of any of illustrative embodiments 1-7, wherein the first scan and the second scan are positron emission tomography (PET) scans.

[0075] Illustrative Embodiment 9: A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:receiving a first scan captured by a first detector ring of an image scanning system, the first detector ring having a first crystal resolution;receiving a second scan captured by a second detector ring of the image scanning system, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;generating first detection data based on the first scan;generating second detection data based on the second scan; andDocket No.: 2024P21676WO storing the first detection data and the second detection data within a memory device.

[0076] Illustrative Embodiment 10: The non-transitory computer readable medium of illustrative embodiment 9 wherein the first crystal resolution is greater than the second crystal resolution.

[0077] Illustrative Embodiment 11 : The non-transitory computer readable medium of any of illustrative embodiments 9-10 wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform operations comprising applying a reconstruction process to the first detection data and, based on the application of the reconstruction process, generating a first image.

[0078] Illustrative Embodiment 12: The non-transitory computer readable medium of any of illustrative embodiments 9-11 wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform operations comprising applying a reconstruction process to the second detection data and, based on the application of the reconstruction process, generating a second image.Docket No.: 2024P21676WO

[0079] Illustrative Embodiment 13: The non-transitory computer readable medium of illustrative embodiment 12, wherein an image resolution of the first image is greater than an image resolution of the second image.

[0080] Illustrative Embodiment 14: The non-transitory computer readable medium of any of illustrative embodiments 9-13, wherein the first scan is of at least a portion of a head of a patient and the second scan is of at least a portion of a body of the patient, the second scan excluding the portion of the head of the patient.

[0081] Illustrative Embodiment 15: The non-transitory computer readable medium of any of illustrative embodiments 9-14 wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform operations comprising applying a reconstruction process to the first detection data and the second detection data and, based on the application of the reconstruction process, generating an image.

[0082] Illustrative Embodiment 16: The non-transitory computer readable medium of any of illustrative embodiments 9-15, wherein the first scan and the second scan are positron emission tomography (PET) scans.

[0083] Illustrative Embodiment 17: An image scanning system comprising:a first detector ring having a first crystal resolution;Docket No.: 2024P21676WO a second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;a memory device; andat least one processor communicatively coupled to the memory device and configured to:receive a first scan captured by the first detector ring;receive a second scan captured by the second detector ring; generate first detection data based on the first scan;generate second detection data based on the second scan; and store the first detection data and the second detection data within the memory device.

[0084] Illustrative Embodiment 18: The system of illustrative embodiment 17, wherein the first crystal resolution is greater than the second crystal resolution.

[0085] Illustrative Embodiment 19: The system of any of illustrative embodiments 17-18, wherein the at least one processor is further configured to apply a reconstruction process to the first detection data and, based on the application of the reconstruction process, generate a first image.

[0086] Illustrative Embodiment 20: The system of any of illustrative embodiments 17-19, wherein the at least one processor is further configured to apply theDocket No.: 2024P21676WO reconstruction process to the second detection data and, based on the application of the reconstruction process, generate a second image.

[0087] Illustrative Embodiment 21 : The system of illustrative embodiment 20, wherein an image resolution of the first image is greater than an image resolution of the second image.

[0088] Illustrative Embodiment 22: The system of any of illustrative embodiments 17-21, wherein the first scan is of at least a portion of a head of a patient and the second scan is of at least a portion of a body of the patient, the second scan excluding the portion of the head of the patient.

[0089] Illustrative Embodiment 23: The system of any of illustrative embodiments 17-22, wherein the at least one processor is further configured to apply a reconstruction process to the first detection data and the second detection data and, based on the application of the reconstruction process, generate an image.

[0090] Illustrative Embodiment 24: The system of any of illustrative embodiments 17-23, wherein the first scan and the second scan are positron emission tomography (PET) scans.

[0091] Illustrative Embodiment 25: The system of any of illustrative embodiments 17-24, wherein the first detector ring comprises first crystals of a first size, and theDocket No.: 2024P21676WO second detector ring comprises second crystals of a second size, wherein the first size differs from the second size.

[0092] Illustrative Embodiment 26: The system of any of illustrative embodiments 17-25, wherein the first size is less than the second size, and the first crystal resolution is greater than the second crystal resolution.

[0093] Illustrative Embodiment 27: The system of any of illustrative embodiments 17-26, wherein the first crystals are positioned within first detector elements of the first detector ring, and the second crystals are positioned within second detector elements of the first detector ring.

[0094] Illustrative Embodiment 28: The system of illustrative embodiment 27, wherein the first detector elements and the second detector elements have a same sized crystal encasing.

[0095] Illustrative Embodiment 29: The system of any of illustrative embodiments 17-28, wherein the first detector ring is axially adjacent to the second detector ring.

[0096] Illustrative Embodiment 30: The system of any of illustrative embodiments 17-29, wherein the at least one processor is further configured to transmit the first detection data and the second detection data, the transmission causing a reconstructionDocket No.: 2024P21676WO of at least one image based on at least one of the first detection data and the second detection data.

[0097] Illustrative Embodiment 31: An image scanning system comprising:a means for receiving a first scan captured by a first detector ring having a first crystal resolution;a means for receiving a second scan captured by a second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;a means for generating first detection data based on the first scan;a means for generating second detection data based on the second scan; and a means for storing the first detection data and the second detection data within the memory device.

[0098] Illustrative Embodiment 32: The system of illustrative embodiment 31 , wherein the first crystal resolution is greater than the second crystal resolution.

[0099] Illustrative Embodiment 33: The system of any of illustrative embodiments 31-32, further comprising a means for applying a reconstruction process to the first detection data and, based on the application of the reconstruction process, generating a first image.Docket No.: 2024P21676WO

[0100] Illustrative Embodiment 34: The system of any of illustrative embodiments 31-33, further comprising a means for applying the reconstruction process to the second detection data and, based on the application of the reconstruction process, generating a second image.

[0101] Illustrative Embodiment 35: The system of illustrative embodiment 34, wherein an image resolution of the first image is greater than an image resolution of the second image.

[0102] Illustrative Embodiment 36 The system of any of illustrative embodiments 31-35, wherein the first scan is of at least a portion of a head of a patient and the second scan is of at least a portion of a body of the patient, the second scan excluding the portion of the head of the patient.

[0103] Illustrative Embodiment 37: The system of any of illustrative embodiments 31-36, further comprising a means for applying a reconstruction process to the first detection data and the second detection data and, based on the application of the reconstruction process, generating an image.

[0104] Illustrative Embodiment 38: The system of any of illustrative embodiments 31-37, wherein the first scan and the second scan are positron emission tomography (PET) scans.Docket No.: 2024P21676WO

[0105] Illustrative Embodiment 39: The system of any of illustrative embodiments 31-38, wherein the first detector ring comprises first crystals of a first size, and the second detector ring comprises second crystals of a second size, wherein the first size differs from the second size.

[0106] Illustrative Embodiment 40: The system of any of illustrative embodiments 31-39, wherein the first size is less than the second size, and the first crystal resolution is greater than the second crystal resolution.

[0107] Illustrative Embodiment 41 : The system of any of illustrative embodiments 31-40, wherein the first crystals are positioned within first detector elements of the first detector ring, and the second crystals are positioned within second detector elements of the first detector ring.

[0108] Illustrative Embodiment 42: The system of illustrative embodiment 41 , wherein the first detector elements and the second detector elements have a same sized crystal encasing.

[0109] Illustrative Embodiment 43: The system of any of illustrative embodiments 31-42, wherein the first detector ring is axially adjacent to the second detector ring.

[0110] Illustrative Embodiment 44: The system of any of illustrative embodiments 31-43, further comprising a means for transmitting the first detection data and theDocket No.: 2024P21676WOsecond detection data, the transmission causing a reconstruction of at least one image based on at least one of the first detection data and the second detection data.

[0111] The apparatuses and processes are not limited to the specific embodiments described herein. In addition, components of each apparatus and each process can be practiced independent and separate from other components and processes described herein.

[0112] The previous description of embodiments is provided to enable any person skilled in the art to practice the disclosure. The various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without the use of inventive faculty. The present disclosure is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

Docket No.: 2024P21676WOWhat is claimed is:

1. A computer-implemented method comprising:receiving a first scan captured by a first detector ring of an image scanning system, the first detector ring having a first crystal resolution;receiving a second scan captured by a second detector ring of the image scanning system, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;generating first detection data based on the first scan;generating second detection data based on the second scan; andstoring the first detection data and the second detection data within a memory device.

2. The computer-implemented method of claim 1 , wherein the first crystal resolution is greater than the second crystal resolution.

3. The computer-implemented method of claim 1 , further comprising applying a reconstruction process to the first detection data and, based on the application of the reconstruction process, generating a first image.

4. The computer-implemented method of claim 3, further comprising applying the reconstruction process to the second detection data and, based on the application of the reconstruction process, generating a second image.

5. The computer-implemented method of claim 4, wherein an image resolution of the first image is greater than an image resolution of the second image.31DM2\20754322.1Docket No.: 2024P21676WO6. The computer-implemented method of claim 1 , wherein the first scan is of at least a portion of a head of a patient and the second scan is of at least a portion of a body of the patient, the second scan excluding the portion of the head of the patient.

7. The computer-implemented method of claim 1 , further comprising applying a reconstruction process to the first detection data and the second detection data and, based on the application of the reconstruction process, generating an image.

8. The computer-implemented method of claim 1 , wherein the first scan and the second scan are positron emission tomography (PET) scans.

9. A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:receiving a first scan captured by a first detector ring of an image scanning system, the first detector ring having a first crystal resolution;receiving a second scan captured by a second detector ring of the image scanning system, the second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;generating first detection data based on the first scan;generating second detection data based on the second scan; and storing the first detection data and the second detection data within a memory device.32DM2\20754322.1Docket No.: 2024P21676WO10. The non-transitory computer readable medium of claim 9 wherein the first crystal resolution is greater than the second crystal resolution.

11. The non-transitory computer readable medium of claim 9 wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform operations comprising applying a reconstruction process to the first detection data and, based on the application of the reconstruction process, generating a first image.

12. The non-transitory computer readable medium of claim 11 wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform operations comprising applying a reconstruction process to the second detection data and, based on the application of the reconstruction process, generating a second image.

13. The non-transitory computer readable medium of claim 9 wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform operations comprising applying a reconstruction process to the first detection data and the second detection data and, based on the application of the reconstruction process, generating an image.

14. An image scanning system comprising:a first detector ring having a first crystal resolution;a second detector ring having a second crystal resolution, wherein the second crystal resolution differs from the first crystal resolution;33DM2\20754322.1Docket No.: 2024P21676WOa memory device; andat least one processor communicatively coupled to the memory device and configured to:receive a first scan captured by the first detector ring;receive a second scan captured by the second detector ring; generate first detection data based on the first scan;generate second detection data based on the second scan; and store the first detection data and the second detection data within the memory device.

15. The system of claim 14, wherein the first detector ring comprises first crystals of a first size, and the second detector ring comprises second crystals of a second size, wherein the first size differs from the second size.

16. The system of claim 15, wherein the first size is less than the second size, and the first crystal resolution is greater than the second crystal resolution.

17. The system of claim 15, wherein the first crystals are positioned within first detector elements of the first detector ring, and the second crystals are positioned within second detector elements of the first detector ring.

18. The system of claim 17, wherein the first detector elements and the second detector elements have a same sized crystal encasing.34DM2\20754322.1Docket No.: 2024P21676WO19. The system of claim 14, wherein the first detector ring is axially adjacent to the second detector ring.

20. The system of claim 14, wherein the at least one processor is further configured to transmit the first detection data and the second detection data, the transmission causing a reconstruction of at least one image based on at least one of the first detection data and the second detection data.35DM2\20754322.1

Images