Network for medical image analysis, decision support systems, and related graphical user interface (GUI) applications

Abstract

This invention provides systems and methods for improved analysis of medical imaging tests and for communication of their results, diagnoses, prognoses, treatment recommendations, and patient-associated risks. [Solution] For example, a cloud-based platform and a supported graphical user interface (GUI) decision tool are presented herein for use by healthcare professionals and / or patients to assist in the process of making decisions about the course of cancer treatment and / or to track the progression of treatment and / or disease.

Description

[Technical Field]

[0001] Cross-references to related applications This application claims the interests of U.S. Provisional Application No. 62 / 413,936, filed on 27 October 2016, the contents of which are incorporated herein by reference in their entirety.

[0002] Technical field The present invention generally relates to systems and methods for creating, analyzing, and / or presenting medical image data. More specifically, in certain embodiments, the present invention relates to a cloud-based platform and supported GUI decision-making tools for use by healthcare professionals and / or their patients, for example, to assist in the process of making decisions about the course of cancer treatment and / or to track treatment and / or disease progression. [Background technology]

[0003] background Targeted imaging analysis involves the use of radiolabeled small molecules that bind to specific receptors, enzymes, and proteins in the body that change during disease progression. After administration to the patient, these molecules circulate in the bloodstream until they find their target. The bound radiopharmaceutical remains at the site of the disease, while the rest of the drug leaves the body. The radioactive portion of the molecule acts as a beacon, allowing images depicting the location and concentration of the disease to be obtained using commonly available nuclear medicine cameras, known as single-photon emission computed tomography (SPECT) or positron emission tomography (PET) cameras, which are found in most hospitals worldwide. Physicians can then use this information to determine the presence and extent of the disease in the patient. Physicians can also use this information to provide the patient with a course of recommended treatment and to track disease progression.

[0004] A variety of software-based analytical techniques are available for the analysis and enhancement of PET and SPECT images, and are usable by radiologists or physicians. There are also several radiopharmaceuticals available for imaging specific types of cancer. For example, the small molecule diagnostic 1404 targets the extracellular domain of prostate-specific membrane antigen (PSMA), a protein that is amplified on the surface of over 95% of prostate cancer cells and is a validated target for the detection of primary and metastatic prostate cancer. 1404 is labeled with technetium-99m, a gamma-emitting isotope that is widely available, relatively inexpensive, easy to prepare efficiently, and has attractive spectral properties for nuclear medicine imaging applications.

[0005] Another example of a radiopharmaceutical is PyL(trademark), a fluorinated PSMA-targeted PET contrast agent for prostate cancer, which is in clinical trials. 18 (Also known as F]DCFPyL). In a proof-of-concept study published in the April 2015 issue of the Journal of Molecular Imaging and Biology, PET imaging using PyL(trademark) demonstrated high levels of PyL(trademark) uptake within the sites of suspected metastatic disease and primary tumors, suggesting the potential for high sensitivity and specificity in detecting prostate cancer.

[0006] Oncologists may use images from a patient's targeted PET or targeted SPECT scan as input in assessing whether the patient has a specific disease, such as prostate cancer, what stage of the disease is evident, what the recommended course of treatment (if any) would be, whether surgical intervention is indicated, and the likely prognosis. Oncologists may use radiologist reports in this assessment. A radiologist report is a technical evaluation of the PET or SPECT images prepared by a radiologist for the physician who requested the imaging test, and includes, for example, the type of test performed, medical history, comparisons between images, the techniques used to perform the test, the radiologist's findings and insights, and the overall impression and recommendations the radiologist may have based on the imaging results. The signed radiologist report is sent to the physician who ordered the test for physician review, followed by a discussion between the physician and the patient regarding the results and treatment recommendations.

[0007] Therefore, the process involves having a radiologist perform imaging tests on the patient, analyzing the acquired images, preparing a radiologist's report, forwarding that report to the requesting physician, having the physician develop an assessment and treatment recommendations, and having the physician communicate the results, recommendations, and risks to the patient. The process may also involve repeating imaging tests due to uncertain results, or ordering further tests based on initial results.

[0008] If imaging tests indicate that a patient has a specific disease or condition (e.g., cancer), the physician will discuss various treatment options, including surgery, as well as the risks of doing nothing, adopting a cautious wait-and-see approach, or employing an active surveillance approach instead of undergoing surgery.

[0009] There are limitations associated with this process, both from the physician's and the patient's perspective. While the radiologist's report is certainly useful, physicians must ultimately rely on their own experience when formulating assessments and recommendations for patients. Moreover, patients must place great trust in their physicians. Physicians may show patients their PET / SPECT images and inform them of numerical risks associated with various treatment options or specific prognoses, but patients may struggle greatly to understand the meaning of this information. Furthermore, especially if cancer is diagnosed but the patient chooses not to have surgery, the patient's family is likely to have many questions. Patients and / or family members may seek supplementary information online and may be misled about the risks of the diagnosed condition. Difficult ordeals can lead to greater emotional distress. Therefore, there is still a need for improved analysis of medical imaging tests and systems and methods for communicating their results, diagnoses, prognoses, treatment recommendations, and patient-related risks. [Prior art documents] [Non-patent literature]

[0010] [Non-Patent Document 1] April 2015 issue of the Journal of Molecular Imaging and Biology [Overview of the Initiative] [Means for solving the problem]

[0011] Summary of the Invention For example, cloud-based platforms and supported graphical user interface (GUI) decision-making tools are presented herein for use by healthcare professionals and / or patients to assist in the process of making decisions about the course of cancer treatment and / or to track the progression of treatment and / or disease.

[0012] For example, a network-based (e.g., cloud-based) support platform is presented herein that enables multiple users to store, access, analyze, and / or provide feedback on a given set of image data for a patient, the platform supporting software tools for automated analysis of targeted PET / SPECT / or other images, generation of radiologist reports, and application of machine learning algorithms to update the process by which images are analyzed (e.g., updating segmentation and / or classification routines based on a growing image database). In certain embodiments, targeted PET / SPECT images may be obtained using PyL® and / or 1404 as radiopharmaceuticals. In certain embodiments, multiple (authorized) users may access the information to participate in discussions on data interpretation, for example.

[0013] Software tools (e.g., mobile apps) featuring graphical user interface (GUI) elements with controls for adjusting the presentation of 3D risk images corresponding to patient organs (and / or other tissues) for comparison with reference images (for example, for use in communicating results to patients as decision support) are also presented herein. For example, the tool may be supported by the network-based support platform described above. The tool can provide an easily understandable, user-friendly, interactive, and controllable pictorial display for communicating information about the patient's condition to the patient (and / or physician, or, with the patient's permission, to the patient's family). For example, a patient with a detected risk of cancer may be shown a map indicating the area and / or degree of risk, and this risk map can be compared to another risk map in which a given course of treatment is recommended. For example, the tool can help the patient decide whether or not to undergo surgery (for example, for a detected risk of prostate cancer). Patients can visually compare their risk map to a map representing a typical risk level to which surgery would be recommended. Below this typical risk level, it may be reasonable for them to choose not to undergo surgery and instead engage in observation or active surveillance. Therefore, low-risk patients who have been told by their doctor that they have a non-zero risk of cancer may find comfort in a visual, controllable comparison between their situation and someone else's (for example, if the reference to which the patient's risk situation is compared is conducive to the patient's age, weight, and / or other risk factors).

[0014] In one embodiment, the present invention relates to a processor (for example, of a network or internet host server) and a memory having instructions stored thereon, which, when executed by the processor, perform the following functions (i) to (v): (i) receive medical images [for example, target PET images, target SPECT images, computed tomography (CT) images, magnetic resonance (MR) images, ultrasound (US) images, gamma camera (i.e., scintillation camera) images, and one or more of any combination, fusion, or derivatives of the above] and a database [for example, target PET / SPECT / gamma camera images, and compositions comprising one or more radiopharmaceuticals (for example, [18F]DCFPyL and / or 1404 and / or technetium-99m {for example, technetium-99m methylenediphosphonate ( 99m(ii) to receive and store medical images acquired using Tc MDP)}) and / or acquired with or without the use of non-radioactive agents, each medical image associated with a specific patient, when requested by the user (e.g., following automated verification that the user is properly qualified to receive the requested images and / or data), and (iii) to automatically analyze one or more of the medical images [e.g., a risk index (e.g., BSI) and / or a risk map with graphical symbols (e.g., texture coding or color coding) that mark areas of current disease risk or risk of disease recurrence, e.g., cancer; e.g., a visual representation (e.g., a 3D representation) of tissue (e.g., an organ or other part of the body); e.g., a risk map of tissue (iv) generating a radiologist report for a patient based on one or more of the medical images for the patient, and (v) applying machine learning algorithms to update the process for automatically analyzing one or more of the medical images using stored image data in a database [for example, the automated analysis of one or more medical images in (iii) and / or (v) above, as follows: (a) automated fusion of tissue images (e.g., PET, SPECT, CT, MRI, and / or US), (b) geographic identification of one or more organs, organ structures, sub-organs, organ regions, and / or other regions of the patient's imaged tissue, and the production of geographically identified 3D images of the tissue using superimposed PET, SPECT, CT, MRI, and / or US data, (c) using data from a database, tissue images, and / or 3D images in (b),This applies to a network-based (e.g., cloud-based) decision support system with memory that causes a processor to perform one or more of the following: (d) calculation of risk information, risk fields, or risk maps containing one or more risk indicators; and (c) use of the calculated risk information (e.g., data from a database) to produce a 3D risk picture for a patient.

[0015] In a particular embodiment, the medical images in the database include a series of medical images of a first patient taken over time (for example, over the course of multiple visits to one or more doctors), and an instruction causes the processor to determine the value of at least a first risk index for each medical image in the series, thereby tracking the determined value of at least a first risk index for the first patient over time.

[0016] In a particular embodiment, medical images are 99m The instruction includes a single-photon emission computed tomography (SPECT) scan of the first patient acquired following the administration of a contrast agent containing Tc-labeled 1404 to the first patient (for example, to identify one or more hotspots), and a computed tomography (CT) scan of the first patient (for example, to identify anatomical features), wherein the instruction causes the processor to superimpose the SPECT scan onto the CT scan to create a composite image of the first patient (SPECT-CT).

[0017] In a particular embodiment, the medical image is [18F]DCFPyL( 18 The instruction includes a positron emission tomography (PET) scan of the first patient acquired following the administration of a contrast agent (DCFPyL labeled with F) to the first patient (for example, to identify one or more hotspots), and a CT scan of the first patient, wherein the instruction causes the processor to superimpose the PET scan onto the CT scan to create a composite image (PET-CT) of the first patient.

[0018] In a particular embodiment, the medical image is technetium-99m methylenediphosphonate ( 99m This includes administering a contrast agent (Tc MDP) to the first patient, followed by a whole-body scan of the first patient (e.g., including anterior and posterior views) performed using a gamma camera.

[0019] In a particular embodiment, the medical image includes a composite image of a first patient, the composite image includes a CT scan superimposed with nuclear medicine images (e.g., SPECT scan, e.g., PET scan) acquired substantially at the same time as the CT scan, following the administration of a contrast agent containing a radionuclide (e.g., radionuclide-labeled) prostate-specific membrane antigen (PSMA) conjugate to the first patient, and the instruction is to (a) use the composite image to distinguish one of the imaged tissues in the nuclear medicine image or (e.g., parts of the nuclear medicine image that are contained within and / or outside the 3D boundary from one another) The processor is made to geographically identify 3D boundaries for each of multiple regions [e.g., organs (e.g., prostate, e.g., liver, e.g., one or more lungs, e.g., lymph nodes), organ structures, suborgans, organ regions, and / or other regions (e.g., one or more specific bones, e.g., the patient's skeletal region), e.g., the region of interest], and (c) automatically analyze the composite image by using the nuclear medicine image together with the identified 3D boundaries of one or more regions to (i) calculate the values ​​for each of one or more risk indicators and / or (ii) calculate a risk map.

[0020] In certain embodiments, the instructions cause the processor to calculate a value of one or more risk metrics for at least one of the one or more risk metrics, for each of one or more regions, based on intensity values of nuclear medicine images within the 3D boundaries of the regions (e.g., by identifying a plurality of hot spots within the 3D boundaries of the regions in the nuclear medicine image, and calculating the total number and / or total volume of the identified hot spots), determining a corresponding cancer tissue level within the region, and calculating a value of the risk metric based on the determined cancer tissue levels within the one or more regions.

[0021] In certain embodiments, the nuclear medicine image is a SPECT scan.

[0022] In certain embodiments, the contrast agent includes a metal chelated to a PSMA binder, the metal being a radionuclide [e.g., the metal is a radioactive isotope of technetium (Tc) (e.g., the metal is technetium-99m ( 99m Tc)), e.g., the metal is a radioactive isotope of rhenium (Re) (e.g., the metal is rhenium-188 ( 188 Re)), e.g., the metal is rhenium-186 ( 186 Re)), e.g., the metal is a radioactive isotope of yttrium (Y) (e.g., the metal is 90 Y), e.g., the metal is a radioactive isotope of lutetium (Lu) (e.g., the metal is 177 Lu), e.g., the metal is a radioactive isotope of gallium (Ga) (e.g., the metal is 68 Ga, e.g., the metal is 67 Ga), e.g., the metal is a radioactive isotope of indium (e.g., 111 In), e.g., the metal is a radioactive isotope of copper (Cu) (e.g., the metal is 67 Cu)].

[0023] In certain embodiments, the contrast agent 99m includes Tc-MIP-1404.

[0024] In a particular embodiment, the nuclear medicine image is a PET scan.

[0025] In certain embodiments, the radioactive nuclide is a radioactive isotope of a halogen [for example, a radioactive isotope of fluorine (for example)] 18 F) For example, radioactive isotopes of iodine (for example) 123 I, for example 124 I, for example 125 I, for example 126 I, for example 131 I) For example, radioactive isotopes of bromine (for example) 75 Br, for example 76 Br, for example 77 Br, for example 80 Br, for example 80m Br, for example 82 Br, for example 83 Br), for example, radioactive isotopes of astatine (for example) 211 At)

[0026] In a particular embodiment, the contrast agent is [18F]DCFPyL( 18 Includes F-labeled DCFPyL.

[0027] In certain embodiments, the radioactive nuclide is a radioactive isotope of gallium (Ga) (for example, 68 Ga) is the answer.

[0028] In a particular embodiment, the medical image contains radionuclides (for example, 99m Contrast agents containing Tc (for example, contrast agents) 99mThe instruction includes a nuclear medicine image of a first patient (e.g., a whole-body scan made using a gamma camera) following administration of a first patient (including Tc MDP), and the instruction causes the processor to (a) geographically identify the boundaries (e.g., 2D boundaries, e.g., 3D boundaries) for each of one or more regions of imaged tissue in the nuclear medicine image [e.g., organs (e.g., prostate, e.g., liver, e.g., one or more lungs, e.g., lymph nodes), organ structures, suborgans, organ regions, and / or other regions (e.g., one or more specific bones, e.g., skeletal regions of the patient), e.g., region of interest] (e.g., so that the portions contained within and / or outside the boundaries of the nuclear medicine image are distinguishable from one another), and (c) automatically analyze the nuclear medicine image by using the nuclear medicine image together with the identified boundaries of one or more regions to (i) calculate the respective values ​​of one or more risk indicators and / or (ii) calculate a risk map.

[0029] In a particular embodiment, the instruction determines, for each of one or more regions, the corresponding cancer tissue level within the region based on the intensity values ​​of the nuclear medicine image within the region boundary (for example, by identifying multiple hotspots within the region boundary in the nuclear medicine image, and by calculating the total number and / or overall product of the identified hotspots), and The processor is instructed to calculate the value of the risk indicator by calculating the value of the risk indicator based on the determined cancer tissue level in one or more regions.

[0030] In a particular embodiment, the system is a cloud-based system.

[0031] In a particular embodiment, the processor is a processor in one or more network or internet host servers.

[0032] In another embodiment, the present invention relates to (i) to (v) below: (i) a processor in a server computing device receives (for example, from a client computing device over a network) medical images [including, for example, targeted PET images, targeted SPECT images, computed tomography (CT) images, magnetic resonance (MR) images, ultrasound (US) images, gamma camera (i.e., scintillation camera) images, and one or more of any combination, fusion, or derivatives of the above] and stores them in a database [for example, targeted PET / SPECT / gamma camera images include one or more radiopharmaceuticals, for example, [18F]DCFPyL and / or 1404 and / or technetium-99m compositions, for example, technetium-99m methylenediphosphonate ( 99m(ii) The medical images are acquired using Tc MDP) and / or without the use of non-radioactive agents or drugs, and each medical image is associated with a specific patient, (ii) the processor accesses one or more medical images and / or related data from a database associated with a specific patient when requested by the user (e.g., following automated verification that the user is properly qualified to receive the requested images and / or data), and (iii) the processor automatically analyzes one or more of the medical images [e.g., a risk map with graphical symbols (e.g., texture coding or color coding) marking areas of current disease risk or risk of disease recurrence, e.g., cancer; e.g., a visual representation (e.g., 3D representation) of tissue (e.g., organ or other part of the body); e.g., the risk map is associated with a PET / SPECT / CT / MRI of the tissue]. (iv) The processor generates a radiologist report for the patient in accordance with one or more of the medical images for the patient, and (v) the processor applies machine learning algorithms to update the process for automatically analyzing one or more of the medical images using stored image data in a database [for example, automatically analyzing one or more medical images in (iii) and / or (v) above is the following: (a) automatically fusing images of the tissue (e.g., PET, SPECT, CT, MRI, and / or US); (b) geographically identifying one or more organs, organ structures, suborgans, organ regions, and / or other regions of the patient's imaged tissue, and producing a geographically identified 3D image of the tissue using the overlaid PET, SPECT, CT, MRI, and / or US data; (c) using data from a database, images of the tissue, and / or the 3D image in (b),This applies to methods that include (d) calculating risk information, risk fields, or risk maps that include one or more risk indicators, and (c) using the risk information calculated in (d) to produce a 3D risk picture for a patient (e.g., data from a database).

[0033] In a particular embodiment, the medical images in the database include a series of medical images of a first patient taken over time (for example, over the course of multiple visits to one or more doctors), and the method includes determining the value of at least a first risk indicator for each medical image in the series, thereby tracking the determined value of at least a first risk indicator over time.

[0034] In a particular embodiment, the reception and storage of medical images includes repeatedly receiving and storing multiple medical images of a first patient over time, each acquired at a different time (for example, during different visits to one or more doctors), to obtain a series of medical images of the first patient.

[0035] In a particular embodiment, medical images are 99m The method comprises administering a contrast agent containing Tc-labeled 1404 to a first patient, followed by a single-photon emission computed tomography (SPECT) scan of the first patient acquired (for example, to identify one or more hotspots), and a computed tomography (CT) scan of the first patient (for example, to identify anatomical features), wherein the method includes superimposing the SPECT scan onto the CT scan to create a composite image of the first patient (SPECT-CT).

[0036] In a particular embodiment, the medical image is [18F]DCFPyL( 18The method comprises administering a contrast agent containing F-labeled DCFPyL to a first patient, followed by a positron emission tomography (PET) scan of the first patient and a CT scan of the first patient, wherein the method includes superimposing the PET scan onto the CT scan to create a composite image (PET-CT) of the first patient.

[0037] In a particular embodiment, the medical image is technetium-99m methylenediphosphonate ( 99m This includes administering a contrast agent (Tc MDP) to the first patient, followed by a whole-body scan of the first patient (e.g., including anterior and posterior views) performed using a gamma camera.

[0038] In a particular embodiment, the medical image includes a composite image of a first patient, the composite image including a CT scan superimposed with nuclear medicine images (e.g., SPECT scan, e.g., PET scan) acquired substantially at the same time as the administration of a contrast agent containing a prostate-specific membrane antigen (PSMA) conjugate containing a radionuclide to the first patient, the method comprising (a) using the composite image to geographically identify the 3D boundaries to each of one or more regions of imaged tissue in the nuclear medicine image [e.g., organs (e.g., prostate, e.g., liver, e.g., one or more lungs, e.g., lymph nodes), organ structures, suborgans, organ regions, and / or other regions (e.g., one or more specific bones, e.g., skeletal regions of the patient), e.g., region of interest] (e.g., one or more specific bones, e.g., skeletal regions of the patient), e.g., region of interest) (e.g., the portion of the nuclear medicine image contained within and / or outside the 3D boundaries of the nuclear medicine image is distinguishable from one or more), and (c) automatically analyzing the composite image by using the nuclear medicine image together with the identified 3D boundaries of one or more regions to calculate (i) the respective values ​​of one or more risk indicators and / or (ii) a risk map.

[0039] In a particular embodiment, step (c) includes, for at least one of the risk indicators, for each of one or more regions, determining the corresponding cancer tissue level in the region based on the intensity values ​​of the nuclear medicine image within the 3D boundary of the region (for example, by identifying multiple hotspots within the 3D boundary of the region in the nuclear medicine image and calculating the total number and / or overall product of the identified hotspots), and calculating the value of the risk indicator based on the determined cancer tissue level in one or more regions.

[0040] In a particular embodiment, the nuclear medicine image is a SPECT scan.

[0041] In certain embodiments, the contrast agent comprises a metal chelated to a PSMA binder, where the metal is a radionuclide [for example, the metal is a radioisotope of technetium (Tc) (for example, the metal is technetium-99m( 99m For example, a metal is a radioactive isotope of rhenium (Tc) (for example, a metal is rhenium-188( 188 Re) is, for example, the metal is rhenium-186( 186 For example, metals are radioactive isotopes of yttrium (Y) (for example, metals are 90 Y is, for example, a metal is a radioactive isotope of lutetium (Lu) (for example, a metal is 177 For example, a metal is a radioactive isotope of gallium (Ga) (for example, a metal is 68 For example, a metal is Ga. 67 For example, a metal is a radioactive isotope of indium (for example, 111 In) is, for example, the metal is a radioactive isotope of copper (Cu) (for example, the metal is 67 (It is Cu).

[0042] In a particular embodiment, the contrast agent is 99m Includes Tc-MIP-1404.

[0043] In a particular embodiment, the nuclear medicine image is a PET scan.

[0044] In certain embodiments, the radioactive nuclide is a radioactive isotope of a halogen [for example, a radioactive isotope of fluorine (for example)] 18 F) For example, radioactive isotopes of iodine (for example) 123 I, for example 124 I, for example 125 I, for example 126 I, for example 131 I) For example, radioactive isotopes of bromine (for example) 75 Br, for example 76 Br, for example 77 Br, for example 80 Br, for example 80m Br, for example 82 Br, for example 83 Br), for example, radioactive isotopes of astatine (for example) 211 At)

[0045] In a particular embodiment, the contrast agent is [18F]DCFPyL( 18 Includes F-labeled DCFPyL.

[0046] In certain embodiments, the radioactive nuclide is a radioactive isotope of gallium (Ga) (for example, 68 Ga) is the answer.

[0047] In a particular embodiment, the medical image contains radionuclides (for example, 99m Contrast agents containing Tc (for example, contrast agents) 99mThe method comprises (a) geographically identifying boundaries (e.g., 2D boundaries, e.g., 3D boundaries) for each of one or more regions of imaged tissue in the nuclear medicine image [e.g., organs (e.g., prostate, e.g., liver, e.g., one or more lungs, e.g., lymph nodes), organ structures, suborgans, organ regions, and / or other regions (e.g., one or more specific bones, e.g., skeletal regions of the patient), e.g., region of interest] (e.g., so that the portions contained within and / or outside the 3D boundaries of the nuclear medicine image are distinguishable from one another; and (c) automatically analyzing the nuclear medicine image by using the nuclear medicine image together with the identified boundaries of one or more regions to calculate (i) the respective values ​​of one or more risk indicators and / or (ii) a risk map.

[0048] In a particular embodiment, step (c) includes, for at least one of the risk indicators, for each of one or more regions, determining the corresponding cancer tissue level within the region based on the intensity values ​​of the nuclear medicine image within the region boundary (for example, by identifying multiple hotspots within the 3D boundary of the region in the nuclear medicine image and calculating the total number and / or overall product of the identified hotspots), and calculating the value of the risk indicator based on the determined cancer tissue level within one or more regions.

[0049] In a particular embodiment, the processor is the processor of a cloud-based system.

[0050] In a particular embodiment, the processor is a processor in one or more network or internet host servers.

[0051] In another aspect, the present invention relates to a system comprising a processor (for example, of a network or internet host server, or of a portable computing device) and a memory having instructions stored thereon, which, when executed by the processor, cause the processor to generate and / or cause the display thereof (for example, cause the display of the GUI element on a laptop computer or a remote computing device, via a mobile app, for example), the GUI element having user-selectable and / or user-adjustable graphical controls (e.g., slider bars, option buttons, text bars, dropdown boxes, windows, animations, and / or other arbitrary GUI widgets) for selecting and / or adjusting a digital presentation of a patient's 3D risk picture for comparison with a reference image displayed by the processor (for example, for use in communicating results to a patient as decision support) (for example, the reference image displayed to the user or presented for user selection can be adjusted according to one or more predetermined variables associated with the patient, e.g., the patient's age, time since diagnosis, previous treatments, and / or future treatments), and the memory.

[0052] In certain embodiments, interactive GUI elements are produced from a patient's medical images [for example, including: targeted PET images, targeted SPECT images, magnetic resonance (MR) images, ultrasound (US) images, gamma camera (i.e., scintillation camera) images, and one or more combinations, fusions, or derivatives of any of the above] and / or other images or information (for example, other images received and stored in a database of a network-based decision support system of any of the embodiments and / or models described herein).

[0053] In another aspect, the present invention relates to a method for tracking the progression and treatment response of prostate cancer over time for one or more patients, comprising: (a) repeatedly receiving multiple medical images for each of one or more patients over time (e.g., over the course of multiple visits to one or more physicians) by a processor of a computing device (e.g., a server computing device), storing them in a database, to obtain a series of medical images taken over time for each of one or more patients; and (b) for each of one or more patients, the processor automatically analyzes the series of medical images for the patient to determine the value of one or more risk indicators for each medical image in the series [e.g., the condition and / or progression of prostate cancer in the patient]. The method includes (c) determining the value of one or more risk indicators corresponding to a numerical value representing a row (e.g., a numerical value identifying a specific cancer stage, e.g., a numerical value corresponding to a determined overall survival rate for a patient), thereby tracking the determined value of one or more risk indicators over the course of prostate cancer progression and treatment for a patient; and (a) for each of one or more patients, the processor storing the determined value of one or more risk indicators for the patient for further processing, and / or the processor causing the display of a graphical representation of the determined value of one or more risk indicators for the patient (e.g., causing the display of a graph showing the change in the determined value of one or more risk indicators for the patient over time).

[0054] In a particular embodiment, a series of medical images for a specific patient among one or more patients (i) each of which is a first radiopharmaceutical (e.g., 99m(ii) a first image subseries comprising one or more medical images (e.g., SPECT scans, e.g., synthetic SPECT-CT images) acquired using a first nuclear imaging modality following administration to a specific patient of a first radiopharmaceutical (e.g., Tc-MIP-1404) (for example, the first radiopharmaceutical facilitates imaging of localized diseases such as localized prostate cancer), and (ii) each of the second radiopharmaceuticals (e.g., [18F]DCFPyL, e.g., 99m The procedure includes a second image subseries, which includes one or more medical images (e.g., PET scans, synthetic PET-CT images, whole-body scans) acquired using a second nuclear imaging modality, following the administration of a Tc MDP) (for example, the second radiopharmaceutical facilitates imaging of metastatic diseases, e.g., metastatic prostate cancer) to a specific patient, and therefore the values ​​of one or more risk indicators determined in step (b) for a specific patient include a first subseries of values ​​for a first risk indicator determined by automated analysis of the first image subseries, and a second subseries of values ​​for a second risk indicator determined by automated analysis of the second image subseries.

[0055] In a particular embodiment, when the prostate cancer of a particular patient is localized (e.g., substantially localized to the patient's prostate), a first image subseries of medical images is acquired over a first time period, and when the prostate cancer of a particular patient is metastatic (e.g., spread to areas outside the patient's prostate), a second image subseries of medical images is acquired over a second time period.

[0056] In a particular embodiment, a first image subseries comprises one or more composite SPECT-CT images, each composite SPECT-CT image comprises a CT scan superimposed on SPECT scans acquired substantially at the same time, and a second image subseries comprises one or more composite PET-CT images, each composite PET-CT image comprises a CT scan superimposed on PET scans acquired substantially at the same time, and step (b) is to use the composite SPECT-CT images to geographically identify the 3D boundary of the prostate region (e.g., corresponding to the patient's prostate) within the SPECT scan of the composite SPECT-CT image (e.g., so that portions of the nuclear medicine image contained within and / or outside the 3D boundary of the prostate region are distinguishable from one another), and to use the SPECT scan together with the identified 3D boundary of the prostate region to calculate a value of a first risk index (e.g., calculated based on the area of ​​the SPECT scan corresponding to the identified 3D boundary of the prostate region). Alternatively, the method includes automatically analyzing each of a plurality of composite SPECT-CT images and using the composite PET-CT image to geographically identify the 3D boundaries of one or more metastatic regions within the PET scan of the composite PET-CT image, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate [e.g., organs (e.g., prostate, e.g., liver, e.g., one or more lungs, e.g., lymph nodes), organ structures, lower organs, organ regions, and / or other regions (e.g., one or more specific bones, e.g., skeletal regions corresponding to the patient's skeleton), e.g., the region of interest], and automatically analyzing each of the one or more composite PET-CT images by using the PET scan together with the identified 3D boundaries of the one or more metastatic regions to calculate a value for a second risk index.

[0057] In a particular embodiment, a first image subseries comprises one or more composite SPECT-CT images, each composite SPECT-CT image comprises a CT scan superimposed on SPECT scans acquired substantially at the same time, and a second image subseries comprises one or more whole-body scans, step (b) geographically identifying the 3D boundary of the prostate region (e.g., corresponding to the patient's prostate) within the SPECT scan of the composite SPECT-CT image (e.g., so that portions of the nuclear medicine image contained within and / or outside the 3D boundary of the prostate region are distinguishable from one another), and using the SPECT scan together with the identified 3D boundary of the prostate region, calculate a value of a first risk index (e.g., SP corresponding to the identified 3D boundary of the prostate region). The method comprises automatically analyzing each of one or more composite SPECT-CT images by (calculated based on the area of ​​the ECT scan), geographically identifying the boundaries of one or more metastatic regions in a whole-body scan, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate [(e.g., one or more specific bones, e.g., skeletal regions corresponding to the patient's skeleton), e.g., the region of interest] (e.g., so that the portions of the whole-body scan contained within and / or outside the boundaries of one or more metastatic regions are distinguishable from one another), and automatically analyzing each of one or more whole-body scans by using a PET scan together with the identified 3D boundaries of one or more metastatic regions to calculate a value for a second risk index.

[0058] In another aspect, the present invention relates to a system for tracking the progression and treatment effectiveness of prostate cancer over time for one or more patients, comprising a processor (e.g., a network or internet host server) and a memory having instructions stored thereon, which, when executed by the processor, (a) repeatedly receive multiple medical images for each of one or more patients over time and store them in a database to obtain a series of medical images taken over time for each of one or more patients (e.g., over the course of multiple visits to one or more doctors), and (b) for each of one or more patients, automatically analyze the series of medical images for the patient to obtain a value for one or more risk indicators for each medical image in the series [e.g., prostate in the patient] The system includes memory, which causes a processor to determine the value of one or more risk indicators corresponding to numerical values ​​representing the condition and / or progression of adenocarcinoma (e.g., numerical values ​​identifying a specific cancer stage, e.g., numerical values ​​corresponding to a determined overall survival rate for a patient), thereby tracking the determined value of one or more risk indicators over the progression and treatment of prostate cancer in a patient, and (c) for each of one or more patients, store the determined value of one or more risk indicators for the patient for further processing, and / or cause a graphical representation of the determined value of one or more risk indicators for the patient (e.g., cause a graph to show the change in the determined value of one or more risk indicators for the patient over time).

[0059] In a particular embodiment, a series of medical images for a specific patient among one or more patients (i) each of which is a first radiopharmaceutical (e.g., 99m(ii) a first image subseries comprising one or more medical images (e.g., SPECT scans, e.g., synthetic SPECT-CT images) acquired using a first nuclear imaging modality following administration to a specific patient of a first radiopharmaceutical (e.g., Tc-MIP-1404) (for example, the first radiopharmaceutical facilitates imaging of localized diseases such as localized prostate cancer), and (ii) each of the second radiopharmaceuticals (e.g., [18F]DCFPyL, e.g., 99m The procedure includes a second image subseries, which includes one or more medical images (e.g., PET scans, synthetic PET-CT images, whole-body scans) acquired using a second nuclear imaging modality, following the administration of a Tc MDP) (for example, the second radiopharmaceutical facilitates imaging of metastatic diseases, e.g., metastatic prostate cancer) to a specific patient, and therefore the values ​​of one or more risk indicators determined in step (b) for a specific patient include a first subseries of values ​​for a first risk indicator determined by automated analysis of the first image subseries, and a second subseries of values ​​for a second risk indicator determined by automated analysis of the second image subseries.

[0060] In a particular embodiment, when the prostate cancer of a particular patient is localized (e.g., substantially localized to the patient's prostate), a first image subseries of medical images is acquired over a first time period, and when the prostate cancer of a particular patient is metastatic (e.g., spread to areas outside the patient's prostate), a second image subseries of medical images is acquired over a second time period.

[0061] In a particular embodiment, a first image subseries comprises one or more composite SPECT-CT images, each composite SPECT-CT image comprises a CT scan superimposed on SPECT scans acquired substantially at the same time, and a second image subseries comprises one or more composite PET-CT images, each composite PET-CT image comprises a CT scan superimposed on PET scans acquired substantially at the same time, and the instruction, in step (b), geographically identifies the 3D boundary of the prostate region (e.g., corresponding to the patient's prostate) within the SPECT scan of the composite SPECT-CT image (e.g., so that portions of the nuclear medicine image contained within and / or outside the 3D boundary of the prostate region are distinguishable from one another), and calculates a value of a first risk index (e.g., calculated based on the area of ​​the SPECT scan corresponding to the identified 3D boundary of the prostate region) using the SPECT scan together with the identified 3D boundary of the prostate region. Alternatively, the processor may perform the following actions: automatically analyze each of a plurality of composite SPECT-CT images; geographically identify the 3D boundaries of one or more metastatic regions within the PET scan of the composite PET-CT image using the composite PET-CT image, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate [e.g., organs (e.g., prostate, e.g., liver, e.g., one or more lungs, e.g., lymph nodes), organ structures, lower organs, organ regions, and / or other regions (e.g., one or more specific bones, e.g., skeletal regions corresponding to the patient's skeleton), e.g., the region of interest], and automatically analyze each of the one or more composite PET-CT images by using the PET scan together with the identified 3D boundaries of the one or more metastatic regions to calculate a value for a second risk index.

[0062] In a particular embodiment, a first image subseries comprises one or more composite SPECT-CT images, each composite SPECT-CT image comprises a CT scan superimposed on SPECT scans acquired substantially at the same time, and a second image subseries comprises one or more whole-body scans. The instruction is to, in step (b), use the composite SPECT-CT image to geographically identify the 3D boundary of the prostate region (e.g., corresponding to the patient's prostate) within the SPECT scan of the composite SPECT-CT image (e.g., so that portions of the nuclear medicine image contained within and / or outside the 3D boundary of the prostate region are distinguishable from one another), and to use the SPECT scan together with the identified 3D boundary of the prostate region to calculate a value of a first risk index (e.g., SP corresponding to the identified 3D boundary of the prostate region). The processor is made to automatically analyze each of one or more composite SPECT-CT images by (calculated based on the area of ​​the ECT scan), geographically identify the boundaries of one or more metastatic regions in a whole-body scan, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate [(e.g., one or more specific bones, e.g., skeletal regions corresponding to the patient's skeleton), e.g., the region of interest] (e.g., so that the portions of the whole-body scan contained within and / or outside the boundaries of one or more metastatic regions are distinguishable from one another), and automatically analyze each of one or more whole-body scans by using a PET scan together with the identified 3D boundaries of one or more metastatic regions to calculate a value for a second risk index.

[0063] Embodiments described in relation to one aspect of the present invention may be applied to other aspects of the present invention (for example, features of an embodiment described in relation to one independent claim, e.g., a method claim, are intended to be applicable to other embodiments of another independent claim, e.g., a system claim, and vice versa).

[0064] The aforementioned and other purposes, aspects, features, and advantages of this disclosure will be more clearly and better understood by referring to the following description, which is taken up in conjunction with the accompanying drawings. [Brief explanation of the drawing]

[0065] [Figure 1] Figure 1 is a screenshot of the graphical user interface (GUI) showing mobile app icons for three cloud-based services according to an exemplary embodiment.

[0066] [Figure 2] Figure 2 is a schematic diagram illustrating the relationship between a platform running an application and a computing device (e.g., a personal computer, or a mobile computing device, e.g., a smartphone) according to an exemplary embodiment of the present invention.

[0067] [Figure 3] Figure 3 is a screenshot of a GUI window within a BSI cloud application (displayed to the user) that, according to an exemplary embodiment, allows the user to input information about a patient and upload and / or access medical images for the patient, such as a series of images taken over a period of time.

[0068] [Figure 4] Figure 4 is a screenshot of a GUI window within the BSI cloud application showing a representative full-body gamma camera image illustrating a hotspot automatically identified by the system, according to an exemplary embodiment, where the corresponding overall calculated BSI value for a particular set of images is obtained at a given time.

[0069] [Figure 5]Figure 5 is a screenshot of a GUI window within the BSI Cloud application showing an automatically or semi-automatically generated radiologist report, which can be signed and dated by a radiologist, according to an exemplary embodiment.

[0070] [Figure 6] Figure 6 is a block diagram illustrating the set of features provided by the cloud-based platform and supported graphical user interface (GUI) decision-making tools described herein, according to an exemplary embodiment.

[0071] [Figure 7] Figure 7 is a block diagram of an example cloud computing environment used in a particular embodiment.

[0072] [Figure 8] Figure 8 is a block diagram of an illustrative computing device and an illustrative mobile computing device used in a particular embodiment.

[0073] [Figure 9] Figure 9 is a block diagram of an exemplary architecture for implementing the cloud-based platform described herein, according to an exemplary embodiment.

[0074] [Figure 10] Figure 10 is a schematic diagram illustrating the stages of prostate cancer progression, along with various therapies and diagnostic imaging modalities appropriate for different disease states, according to an exemplary embodiment.

[0075] [Figure 11] Figure 11 is a block flow diagram of a process for tracking prostate cancer progression and treatment effectiveness over time, according to an exemplary embodiment.

[0076] The features and advantages of this disclosure will become more apparent from the detailed description below when taken in conjunction with the drawings. In the drawings, the same reference letter identifies a corresponding element throughout. In the drawings, the same reference number generally refers to identical, functionally similar, and / or structurally similar elements. [Modes for carrying out the invention]

[0077] Detailed explanation The claimed systems, devices, methods, and processes are intended to encompass variations and adaptations developed using information from the embodiments described herein. Adaptations and / or modifications of the systems, devices, methods, and processes described herein may be performed by those skilled in the art.

[0078] Throughout the description, whenever an article, device, or system is described as having, including, or comprising certain components, or whenever a process or method is described as having, including, or comprising certain steps, it is intended that there are articles, devices, and systems of the present invention that are essentially comprised of or derived from the listed components, and processes and methods of the present invention that are essentially comprised of or derived from the listed processing steps.

[0079] It should be understood that, as long as the present invention remains operational, the order of the steps or the order in which certain actions are performed is not important. Furthermore, two or more steps or actions may be performed simultaneously.

[0080] Any reference to any publication in this specification, for example in the “Background Art” section, does not constitute an endorsement that such publication serves as prior art relating to any of the claims presented herein. The “Background Art” section is presented for clarity purposes and is not intended to be a description of the prior art relating to any of the claims.

[0081] Headings are provided for the reader's convenience. The presence and / or retention of headings is not intended to limit the scope of the subject matter described herein.

[0082] A. Medical imaging modalities, associated radiopharmaceuticals, and calculated risk indicators Figure 1 shows mobile app icons 100 for three cloud-based services according to an exemplary embodiment. As described below, the cloud-based services of the platform described herein provide medical image processing and analysis in a fully automated manner and / or in combination with user interaction (e.g., in a semi-automated manner). Medical images include nuclear medicine images acquired using nuclear imaging modalities such as whole-body scans with gamma cameras, positron emission tomography (PET) scans, and single-photon emission tomography (SPECT) scans.

[0083] In certain embodiments, nuclear medicine imaging uses a contrast agent containing a radiopharmaceutical. The nuclear medicine imaging is acquired following the administration of the radiopharmaceutical to the patient and provides information about the distribution of the radiopharmaceutical within the patient. The radiopharmaceutical is a compound containing a radionuclide.

[0084] As used herein, “radionic nuclide” refers to a moiety containing at least one radioisotope of an element. Suitable exemplary radionuclides include, but are not limited to, those described herein. In some embodiments, the radionuclide is a nuclide used in positron emission tomography (PET). In some embodiments, the radionuclide is a nuclide used in single-photon emission computed tomography (SPECT). In some embodiments, a non-limiting list of radionuclides is provided. 99m Tc, 111 In, 64 Cu, 67 Ga, 68 Ga, 186 Re, 188Re, 153 Sm, 177 Lu, 67 Cu, 123 I, 124 I, 125 I, 126 I, 131 I, 11 C, 13 N, 15 O, 18 F, 153 Sm, 166 Ho, 177 Lu, 149 Pm, 90 Y, 213 Bi, 103 Pd, 109 Pd, 159 Gd, 140 La, 198 Au, 199 Au, 169 Yb, 175 Yb, 165 Dy, 166 Dy, 105 Rh, 111 Ag, 89 Zr, 225 Ac, 82 Rb, 75 Br, 76 Br, 77 Br, 80 Br, 80m Br, 82 Br, 83 Br, 211 At, and 192 include Ir.

[0085] As used herein, the term "radiopharmaceutical" refers to a compound containing a radionuclide. In certain embodiments, the radiopharmaceutical is used for diagnostic and / or therapeutic purposes. In certain embodiments, the radiopharmaceutical includes small molecules labeled with one or more radionuclides, antibodies labeled with one or more radionuclides, and antigen-binding portions of antibodies labeled with one or more radionuclides.

[0086] Nuclear medicine imaging (e.g., PET scans, SPECT scans, whole-body scans, synthetic PET-CT images, synthetic SPECT-CT images) detects radiation emitted from the radionuclides of radiopharmaceuticals to form images. The distribution of a particular radiopharmaceutical within a patient can be determined by biological mechanisms such as blood flow or perfusion, as well as by specific enzyme-binding or receptor-binding interactions. Different radiopharmaceuticals may utilize different biological mechanisms and / or specific enzyme-binding or receptor-binding interactions, and therefore may be designed to selectively concentrate in specific types of tissues and / or regions within a patient when administered. Regions within a patient with higher concentrations of radiopharmaceutical emit more radiation than other regions, and therefore these regions appear brighter in nuclear medicine images. Thus, intensity variations in nuclear medicine images can be used to map the distribution of radiopharmaceuticals within a patient. This mapped distribution of radiopharmaceuticals within a patient can be used, for example, to infer the presence of cancerous tissue in various regions of the patient's body.

[0087] For example, when administering to a patient, technetium-99m methylenediphosphonate ( 99m Tc MDP selectively accumulates within the patient's skeletal region, particularly in areas with abnormal bone formation associated with malignant bone lesions. This selective concentration of the radiopharmaceutical in these areas produces identifiable hotspots—high-intensity, localized areas within nuclear medicine images. Therefore, the presence of malignant bone lesions associated with metastatic prostate cancer can be inferred by identifying such hotspots within a whole-body scan of the patient. As described below, risk indicators correlate with the patient's overall survival and other prognostic metrics representing disease state, progression, treatment response, etc., to the patient. 99m It is calculable based on an automated analysis of intensity variations in whole-body scans acquired following administration of Tc MDP. In certain embodiments, other radiopharmaceuticals are, 99m It can also be used in a similar manner to Tc MDP.

[0088] In certain embodiments, the specific radiopharmaceutical used depends on the specific nuclear medicine imaging modality used. For example, 18 Sodium fluoride (NaF) is also 99m Similar to Tc MDP, it accumulates within bone lesions but can be used in conjunction with PET imaging. In certain embodiments, PET imaging may also utilize a radioactive form of vitamin choline that is readily absorbed by prostate cancer cells.

[0089] In certain embodiments, radiopharmaceuticals that selectively bind to a particular protein or receptor of interest, in particular those whose expression is increased in cancer tissue, may be used. Such proteins or receptors of interest include, but are not limited to, tumor antigens such as CEA expressed in colorectal cancer, Her2 / neu expressed in multiple cancers, BRCA1 and BRCA2 expressed in breast and ovarian cancers, and TRP-1 and TRP-2 expressed in melanoma.

[0090] For example, human prostate-specific membrane antigen (PSMA) is upregulated in prostate cancer, including metastatic disease. PSMA is expressed in almost all prostate cancers, and its expression is further increased in poorly differentiated carcinomas, metastatic carcinomas, and hormone-refractory carcinomas. Therefore, radiopharmaceuticals corresponding to PSMA conjugates labeled with one or more radionuclides (e.g., PSMA high-affinity compounds) can be used to acquire nuclear medicine images of a patient, from which the presence and / or condition of prostate cancer in various regions of the patient (e.g., including, but not limited to, skeletal regions) can be assessed. In certain embodiments, nuclear medicine images acquired using PSMA conjugates are used to identify the presence of cancerous tissue within the prostate when the disease is in a localized state. In certain embodiments, nuclear medicine images acquired using radiopharmaceuticals containing PSMA conjugates are used to identify the presence of cancerous tissue in various regions, including not only the prostate but also other organs and tissue regions such as the lungs, lymph nodes, and bones, as is relevant when the disease is metastatic.

[0091] In particular, when administered to patients, PSMA-conjugates labeled with radionuclides selectively accumulate in cancer tissue based on their affinity for PSMA. 99m In a manner similar to that described for Tc MDP, selective concentration of a radionuclide-labeled PSMA conjugate at specific sites within the patient produces detectable hotspots in nuclear medicine imaging. As the PSMA conjugate concentrates within various cancerous tissues and areas of the body expressing PSMA, localized cancers within the patient's prostate and / or metastatic cancers in various areas of the patient's body can be detected and assessed. As described below, overall survival and risk indices correlating with other prognostic metrics such as disease state, progression, and treatment response can be calculated based on automated analysis of intensity variations in nuclear medicine imaging acquired following administration of the PSMA conjugate radiopharmaceutical to the patient.

[0092] PSMA conjugates labeled with various radionuclides may be used as radiopharmaceutical contrast agents for nuclear medicine imaging to detect and evaluate prostate cancer. In certain embodiments, the specific radionuclide-labeled PSMA conjugate used depends on factors such as the specific imaging modality (e.g., PET, e.g., SPECT) and the specific area of ​​the patient to be imaged (e.g., organ). For example, one radionuclide-labeled PSMA conjugate is suitable for PET imaging, while another is suitable for SPECT imaging. For example, one radionuclide-labeled PSMA conjugate facilitates imaging of the patient's prostate and is primarily used when the disease is localized, while other PSMA conjugates facilitate imaging of organs and areas throughout the patient's body and are useful for evaluating metastatic prostate cancer.

[0093] Various PSMA conjugates and their radionuclide-labeled versions are described in U.S. Patents 8,778,305, 8,211,401, and 8,962,799, each of which is incorporated herein by reference in its entirety. PET imaging of PSMA conjugates labeled with Ai radionuclide

[0094] In certain embodiments, a radionuclide-labeled PSMA conjugate is a radionuclide-labeled PSMA conjugate suitable for PET imaging.

[0095] In certain embodiments, the PSMA binder labeled with a radionuclide is [18F]DCFPyL (also known as PyL(trademark) or DCFPyL-18F) [ka] or a pharmaceutically acceptable salt thereof.

[0096] In a particular embodiment, the PSMA binder labeled with a radionuclide is [18F]DCFBC [ka] or a pharmaceutically acceptable salt thereof.

[0097] In a particular embodiment, the PSMA binder labeled with a radionuclide is 68 Ga-PSMA-HBED-CC( 68 (Also known as Ga-PSMA-11) [ka] or a pharmaceutically acceptable salt thereof.

[0098] In a particular embodiment, the PSMA binder labeled with a radionuclide is PSMA-617 [ka] or a pharmaceutically acceptable salt thereof. In certain embodiments, the PSMA binder labeled with a radionuclide is 68 This is PSMA-617 labeled with Ga. 68 The comprising Ga-PSMA-617, or a pharmaceutically acceptable salt thereof. In certain embodiments, the PSMA binder labeled with a radionuclide is 177 This is PSMA-617 labeled with Lu. 177 Contains Lu-PSMA-617, or a pharmaceutically acceptable salt thereof.

[0099] In a particular embodiment, the PSMA binder labeled with a radionuclide is PSMA-I&T [ka]

[0100] or a pharmaceutically acceptable salt thereof. In certain embodiments, the PSMA binder labeled with a radionuclide is 68 This is a Ga-labeled PSMA-I&T. 68 Contains Ga-PSMA-I&T, or pharmaceutically acceptable salts thereof.

[0101] In a particular embodiment, the PSMA binder labeled with a radionuclide is PSMA-1007 [ka]

[0102] or a pharmaceutically acceptable salt thereof. In certain embodiments, the PSMA binder labeled with a radionuclide is 18 It is PSMA-1007 labeled with F. 18 Contains F-PSMA-1007, or a pharmaceutically acceptable salt thereof.

[0103] A.ii SPECT imaging of PSMA conjugates labeled with radionuclides. In certain embodiments, a radionuclide-labeled PSMA conjugate is a radionuclide-labeled PSMA conjugate suitable for SPECT imaging.

[0104] In certain embodiments, the PSMA binder labeled with a radionuclide is 1404 (also known as MIP-1404) [ka] or a pharmaceutically acceptable salt thereof.

[0105] In certain embodiments, the PSMA binder labeled with a radionuclide is 1405 (also known as MIP-1405) [ka] or a pharmaceutically acceptable salt thereof.

[0106] In certain embodiments, the PSMA binder labeled with a radionuclide is 1427 (also known as MIP-1427) [ka] or a pharmaceutically acceptable salt thereof.

[0107] In certain embodiments, the PSMA binder labeled with a radionuclide is 1428 (also known as MIP-1428). [ka] or a pharmaceutically acceptable salt thereof.

[0108] In certain embodiments, the PSMA binder is made of a radioactive isotope of a metal [for example, a radioactive isotope of technetium (Tc) (for example, technetium-99m( 99m Tc)), for example, the radioactive isotope of rhenium (Re) (for example, rhenium-188( 188 Re), for example, rhenium-186( 186 Re)), for example, the radioactive isotope of yttrium (Y) (for example, 90 Y), for example, radioactive isotopes of lutetium (Lu) (for example, 177 Lu), for example, radioactive isotopes of gallium (Ga) (for example 68 Ga, for example 67 Ga), for example, radioactive isotopes of indium (for example, 111 In), for example, radioactive isotopes of copper (Cu) (for example, 67 It is labeled with a radionuclide by chelation with (Cu)).

[0109] In certain embodiments, 1404 is labeled with a radionuclide (for example, chelated with a radioisotope of a metal). In certain embodiments, the radionuclide-labeled PSMA binder is 99m 1404 labeled with Tc (for example, chelated with it). 99m Tc-MIP-1404 [ka] or a pharmaceutically acceptable salt thereof. In certain embodiments, 1404 is a radioactive isotope of another metal [e.g., a radioactive isotope of rhenium (Re) (e.g., rhenium-188( 188Re), for example, rhenium-186 ( 186 Re)), for example, the radioactive isotope of yttrium (Y) (for example, 90 Y), for example, radioactive isotopes of lutetium (Lu) (for example, 177 Lu), for example, radioactive isotopes of gallium (Ga) (for example 68 Ga, for example 67 Ga), for example, radioactive isotopes of indium (for example, 111 In), for example, radioactive isotopes of copper (Cu) (for example, 67 Chelated with Cu), as shown above 99m Compounds having a structure similar to that for Tc-MIP-1404 may be formed, and other metallic radioisotopes may be present. 99m It will be replaced with Tc.

[0110] In certain embodiments, 1405 is labeled with a radionuclide (for example, chelated with a radioisotope of a metal). In certain embodiments, the radionuclide-labeled PSMA binder is 99m 1405 labeled with Tc (for example, chelated with it). 99m Tc-MIP-1405 [ka] or a pharmaceutically acceptable salt thereof. In certain embodiments, 1405 may be other metallic radioisotopes [e.g., radioisotopes of rhenium (Re) (e.g., rhenium-188( 188 Re), for example, rhenium-186 ( 186 Re)), for example, the radioactive isotope of yttrium (Y) (for example, 90 Y), for example, radioactive isotopes of lutetium (Lu) (for example, 177 Lu), for example, radioactive isotopes of gallium (Ga) (for example 68 Ga, for example 67 Ga), for example, radioactive isotopes of indium (for example, 111 In), for example, radioactive isotopes of copper (Cu) (for example, 67Chelated with Cu), as shown above 99m Compounds having a structure similar to that for Tc-MIP-1405 may be formed, and other metallic radioisotopes may be present. 99m It will be replaced with Tc.

[0111] In a particular embodiment, 1427 is labeled (e.g., chelated) with a radioactive isotope of a metal, and the following formula is expressed. [ka]

[0112] Forms a compound or pharmaceutically acceptable salt thereof by, where M is a metal radioisotope labeled with 1427 [e.g., a radioisotope of technetium (Tc) (e.g., technetium-99m( 99m Tc)), for example, the radioactive isotope of rhenium (Re) (for example, rhenium-188( 188 Re), for example, rhenium-186( 186 Re)), for example, the radioactive isotope of yttrium (Y) (for example, 90 Y), for example, radioactive isotopes of lutetium (Lu) (for example, 177 Lu), for example, radioactive isotopes of gallium (Ga) (for example 68 Ga, for example 67 Ga), for example, radioactive isotopes of indium (for example, 111 In), for example, radioactive isotopes of copper (Cu) (for example, 67 It is Cu).

[0113] In a particular embodiment, 1428 is labeled (e.g., chelated) with a radioactive isotope of a metal, and the following formula is expressed. [ka]

[0114] Forms a compound or pharmaceutically acceptable salt thereof by, where M is a metal radioisotope labeled with 1428 [e.g., a radioisotope of technetium (Tc) (e.g., technetium-99m( 99m Tc)), for example, the radioactive isotope of rhenium (Re) (for example, rhenium-188( 188 Re), for example, rhenium-186( 186 Re)), for example, the radioactive isotope of yttrium (Y) (for example, 90 Y), for example, radioactive isotopes of lutetium (Lu) (for example, 177 Lu), for example, radioactive isotopes of gallium (Ga) (for example 68 Ga, for example 67 Ga), for example, radioactive isotopes of indium (for example, 111 In), for example, radioactive isotopes of copper (Cu) (for example, 67 It is Cu).

[0115] In a particular embodiment, the PSMA binder labeled with a radionuclide is PSMA I&S [ka]

[0116] or a pharmaceutically acceptable salt thereof. In certain embodiments, the PSMA binder labeled with a radionuclide is 99m This is a Tc-labeled PSMA I&S. 99m Contains Tc-PSMA I&S or pharmaceutically acceptable salts thereof.

[0117] A.iii Whole-body bone scan Referring to Figure 1, BSI Cloud 130 refers to a cloud-based decision support system that implements BSI values. BSI stands for Bone Scan Index, and the Bone Scan Index is based on the radionuclide technetium-99m methylenediphosphonate ( 99mThis value is calculated from a method for detecting skeletal lesions from a whole-body scan (as well as anterior and posterior views) using a gamma camera following administration of Tc MDP. Further explanation of BSI is provided, for example, in U.S. Patent No. 8,855,387, which is incorporated herein by whole reference in its entirety, and in U.S. Patent Application No. 15 / 282422, filed September 30, 2016, which is incorporated herein by whole reference in its entirety.

[0118] Specifically, BSI is calculated from a whole-body scan by segmenting the anterior and posterior views of the patient's whole-body scan and geographically identifying the boundaries of regions within the views that correspond to various parts of the patient's skeleton. Segmentation of the patient's skeleton can be performed using various methods, including active shape model-based techniques and the atlas image registration method described in U.S. Patent No. 8,855,387 (which registers the anterior and posterior views of the whole-body scan along with reference anterior and posterior views (called atlas images) of a reference whole-body scan that has already been segmented). Other methods based on machine learning techniques (e.g., artificial neural networks (ANNs), e.g., convolutional neural networks (CNNs)) may also be used.

[0119] The BSI value is calculated based on the intensity values ​​of whole-body scans within identified boundaries of various skeletal regions. As discussed above, hotspots corresponding to high-intensity localized areas within the whole-body scan view (anterior view and / or posterior view) can be detected. Hotspots may be detected and / or classified as corresponding to cancerous lesions (e.g., metastases) using a variety of methods, including machine learning techniques such as ANN, as described in U.S. Patent No. 8,855,387.

[0120] Hotspots corresponding to cancerous tissue lesions within a patient's skeleton, once detected, may be used to determine risk indicators that provide a measure of disease status for the patient. For example, the level of cancerous tissue within one or more regions, such as specific bones and / or the overall skeletal region, can be determined based on the characteristics of the detected hotspots (e.g., detected hotspots classified as metastases). For example, the level of cancerous tissue within a region (e.g., specific bones, e.g., the overall skeletal region) may be determined based on (e.g., as a function thereof) the total number of detected hotspots within the region, the total volume of detected hotspots within the region, the average intensity of detected hotspots, the maximum intensity of detected hotspots, and combinations thereof. Properties of one or more regions, such as their area or volume, may also be used. For example, the total number and / or total volume of detected hotspots may be standardized (e.g., divided) by the volume and / or area of ​​the region in which the hotspots are detected. Risk indicators may be determined directly, for example, as cancer tissue levels within a single region, or from cancer tissue levels across multiple regions (e.g., as a mean, e.g., as a scaled sum, e.g., as a ratio, etc.), or even based on determined cancer tissue levels within one or more regions using machine learning techniques.

[0121] For example, the BSI value is a risk index that quantifies the fraction of a patient's entire skeleton involved by cancerous tissue (e.g., a tumor) based on detected hotspots. BSI values ​​can be compared across different patients and used as an objective measure of disease status and risk for a particular patient. In particular, because the BSI is calculated in an automated manner, variability due to human factors such as the interpretation of images by radiologists is avoided.

[0122] Furthermore, a variety of actionable information can be obtained from a patient's BSI value. For example, BSI can correlate with prognostic values ​​that provide measures of disease state, progression, expected life expectancy (e.g., overall survival), and treatment effectiveness for a patient. Thus, a patient's BSI value can be used and tracked over time (e.g., over the course of multiple visits to one or more physicians) to provide the patient or their physician with objective metrics of what state the cancer is in, how quickly it is progressing, what the outlook is, and whether one or more specific treatments are proving effective.

[0123] A.iv Positron Emission Tomography (PET) Scan PyL Cloud 120 refers to a cloud-based system that uses medical images acquired using the drug PyL (trademark), and PyL (trademark) is... 18 The contrast agent is DCFPyL labeled with F([18F]DCFPyL). After injection of the contrast agent, the patient undergoes a positron emission tomography (PET) scan to identify the hotspot and a CT scan. Further information about PyL® contrast agents is provided above and, for example, in U.S. Patent No. 8,778,305, which is incorporated herein by reference in its entirety.

[0124] In certain embodiments, PET scans and CT scans are combined as a composite image, including a CT scan superimposed on a PET scan. As used herein, superimposing one image (e.g., a PET scan) onto another (e.g., a CT scan) refers to establishing a mapping between coordinates and / or pixels or voxels in two images representing the same physical location (e.g., within a patient). CT scans provide accurate anatomical information in the form of detailed three-dimensional (3D) images of internal organs, bones, soft tissues, and blood vessels. Thus, the 3D boundaries of specific regions of the imaged tissue can be accurately identified by analysis of the CT scan. For example, automated segmentation of CT scans is feasible to identify the 3D boundaries of specific organs (e.g., prostate, lymph nodes, one or more lungs), suborgans, organ regions, and other regions of the imaged tissue, such as specific bones and overall skeletal regions of a patient. Automated segmentation of CT scans is achievable through a variety of techniques, including machine learning techniques [e.g., ANN-based methods (e.g., including convolutional neural networks (CNNs)], atlas image registration, and combinations thereof. In certain embodiments, manual segmentation of CT images may also be available, either alone or in combination with automated segmentation techniques (for example, to refine 3D boundaries identified via automated segmentation, or to provide an initial starting point for automated segmentation techniques).

[0125] Once the 3D boundaries of various regions are identified within the CT scan of the composite image through mapping between the CT and PET scans, the identified 3D boundaries can be transferred to the PET image. Therefore, the regions of the PET image that are included within and / or outside of the identified 3D boundaries can be precisely identified.

[0126] In certain embodiments, a composite image including a CT scan superimposed on a PET scan is acquired using a dedicated PET-CT scanner, which is common in many hospitals, and uploaded as a medical image to a cloud-based platform described herein. In certain embodiments, the PET scan and the corresponding CT scan are acquired separately (but substantially at the same time) and uploaded to the cloud-based platform described herein. In such cases, the separately acquired PET scan and CT scan can be automatically fused to create a composite image.

[0127] In certain embodiments, once the 3D boundaries of various regions are identified within a PET scan, one or more risk indicators can be calculated in a manner similar to that described above with respect to BSI. Specifically, in certain embodiments, the intensity values ​​of the PET scan related to the 3D boundaries of the identified regions (e.g., inside and / or outside of them) can be used to determine the level of cancerous tissue within the identified regions, for example, based on the characteristics of detected hotspots (e.g., detected hotspots corresponding to metastases). Based on the determined level of cancerous tissue, risk indicators can then be calculated. For example, hotspots within a PET scan are identifiable and can be used to calculate one or more risk indicators based on characteristics such as their size, number, and distribution within the identified regions. Similar to BSI, risk indicators determined from a PET scan can be correlated with prognostic values ​​and tracked over time (e.g., over the course of multiple visits to one or more physicians) to provide the patient or their physician with objective metrics of what state the cancer is in, how quickly it is progressing, what the outlook is, and whether one or more specific treatments are proving effective. The techniques described herein for PET imaging using PyL® as a radiopharmaceutical are applicable to a variety of other radiopharmaceuticals, including, but not limited to, NaF, radioisotopes of choline, and the PSMA binders described in the Ai section above, as described above.

[0128] Av Single-photon emission computed tomography (SPECT) scan 1404 Cloud 130 is a drug 99m This refers to a cloud-based system that uses medical images acquired using Tc-MIP-1404. 99m Tc-MIP-1404 is, as described above, Tc 99mThis is labeled 1404. After the injection of contrast agent, the patient undergoes a single-photon emission computed tomography (SPECT) scan to identify, for example, hotspots, and a computed tomography (CT) scan to identify, for example, anatomical features. These images are superimposed to create a composite image (SPECT / CT). 99m Further information regarding the Tc-MIP-1404 contrast agent is provided above and, for example, in U.S. Patents 8,211,401 and 8,962,799, both of which are incorporated herein by reference in their entirety.

[0129] SPECT scans and CT scans can be analyzed in a manner similar to that described above for PET scans and CT scans to determine one or more risk indicators. Specifically, like PET scans and CT scans, SPECT scans and CT scans can be combined in a composite image—a composite SPECT-CT image—in which the CT scan is superimposed on the SPECT scan. Similar to composite PET-CT images, composite SPECT-CT images may be received directly as medical images (e.g., acquired in a hospital via a dedicated SPECT-CT imager) by the cloud-based platform described herein, or they may be created by the cloud-based platform following the receipt of separate SPECT scans and CT scans.

[0130] Similar to PET-CT images, the 3D boundaries of various regions of the imaged tissue are discernible within the SPECT image by overlaying the composite image with the CT image. Intensity variations within the SPECT image with respect to the 3D boundaries can be used to calculate one or more risk indicators. Similar to the methods for calculating risk indicators from composite PET-CT images, this may include determining the level of cancerous tissue within a identified region, for example, by detecting hotspots within the 3D boundaries of the identified region. Such risk indicators can be tracked over time (e.g., over multiple visits to one or more physicians) to correlate prognostic values ​​and provide the patient or their physician with objective metrics of what stage the cancer is in, how quickly it is progressing, what the outlook is, and whether one or more specific treatments are proving effective. 99m The techniques described herein for SPECT imaging using Tc-MIP-1404 as a radiopharmaceutical are applicable to a variety of other radiopharmaceuticals, including, but not limited to, the PSMA conjugates described in Section A.ii above, as described above.

[0131] B. Platform services and computing device components Figure 2 is a schematic diagram 200 illustrating the relationship between a platform running an application and a computing device (e.g., a personal computer, or a mobile computing device, e.g., a smartphone) according to an exemplary embodiment of the present invention. The platform performs various services, such as user authentication ("authentication"), storage of images and other data ("slice boxes"), etc.—many more services than those shown may be provided. The application may have both platform components and device components (e.g., a native app on a client device).

[0132] Figure 9 shows an illustrative architecture 900 for implementing the cloud-based platform described herein and providing various services such as the BSI Cloud Service, PyL Cloud Service, and 1404 Cloud Service described above. The architecture shown in Figure 9 can be used to implement the platform described herein on various data centers, including publicly available data centers. The data center provides infrastructure in the form of servers and networks, and provides services for networking, messaging, authentication, logging, and storage, for example. Architecture 900 for the platform uses a series of functional units with a limited scope called microservices. Each microservice deals with an isolated set of tasks, such as image storage, risk metric calculation, medical image type identification, and other tasks. Services (e.g., microservices) can communicate with each other using standard protocols such as the Hypertext Transfer Protocol (HTTP). By organizing the platform into a network of microservices, as shown in architecture 900 in Figure 9, parts of the platform can be individually scaled to meet high demand and ensure minimal downtime.

[0133] In certain embodiments, such an architecture allows components to be improved or replaced without affecting other parts of the platform. The illustrative architecture 900 shown in Figure 9 includes a set of microservices 920 common to two or more applications within the platform. The left panel 910 and the right panel 930 show the microservices within the two applications. The microservice network shown in the left panel 910 implements a version of the BSI cloud service as described above, providing automated calculation of the BSI index (aBSI), which is a risk index derived from automated analysis of whole-body scans acquired using a gamma camera. The microservice network shown in the right panel 930 implements a version of the 1404 cloud service as described above, providing automated calculation of the SPECT index, which is a risk index derived from automated analysis of synthetic SPECT-CT images.

[0134] C. Image acquisition, analysis, and presentation of results Figure 3 shows a GUI window 300 within the BSI cloud application (displayed to the user) that allows the user to input information about the patient and upload and / or access medical images for the patient, such as a series of images taken over a certain period of time.

[0135] Figure 4 shows a GUI window 400 within the BSI cloud application displaying representative full-body gamma camera images showing hotspots automatically identified by the system, with the corresponding overall calculated BSI value for a given set of images acquired at a given time. Graph 410 on the left shows how the BSI value changed (increased) over time for this particular patient.

[0136] Figure 5 shows a GUI window within the BSI cloud application displaying an automatically or semi-automatically generated radiologist report 510, which can be signed and dated by the radiologist. In certain embodiments, automatically identified hotspots may be adjusted by the radiologist (or other healthcare professional treating the patient), and the changes are reflected in the report. For example, identified hotspots may be deactivated by the radiologist, and new hotspots may be activated by the radiologist, and such changes may affect the calculated BSI value displayed in the report.

[0137] Figure 6 is a block flow diagram of an exemplary network-based (e.g., cloud-based) decision support system according to an exemplary embodiment of the present invention. Figure 6 shows various functions that may be performed by the cloud-based service described herein. These include (i) receiving a set of medical images and storing them in a database; (ii) accessing one or more of the medical images for transmission to the user for display on a user computing device; (iii) automatically analyzing the medical images by a processor to calculate a risk index (e.g., BSI) and / or generate a risk map; (iv) generating a radiologist report for the patient in accordance with the patient's images and / or risk index / risk map, and applying machine learning algorithms to update the process for the automated analysis of function (iii).

[0138] Figure 10 is a schematic diagram showing the clinical stages of prostate cancer progression, along with various therapies 1020 and diagnostic imaging modalities 1030 appropriate for various disease states. As shown in the schematic diagram, different imaging modalities and / or different radiopharmaceuticals may be appropriate depending on the clinical state of the patient's prostate cancer. Similarly, different risk indicators calculated based on different imaging modalities and / or different radiopharmaceuticals may be most appropriate depending on the state of the patient's prostate cancer.

[0139] For example, in a particular embodiment, synthetic SPECT-CT imaging may be used when a patient has or is suspected of having localized prostate cancer. SPECT scans of synthetic SPECT-CT images used for evaluation of localized prostate cancer facilitate imaging of localized prostate cancer. 99m These images can be obtained following the administration of certain radiopharmaceuticals, such as Tc-MIP-1404. Therefore, SPECT-CT images themselves, their derivatives, and risk indicators calculated from SPECT-CT images can all be used to assess the risk, disease state, progression, and treatment response to localized prostate cancer.

[0140] In certain embodiments, other imaging techniques may be used when a patient has or is suspected of having metastatic prostate cancer that has spread outside the prostate. For example, 99mWhole-body scans acquired following Tc-MDP administration can be used to assess the tumor volume within the patient's skeleton. As discussed above, the BSI value calculated from whole-body scans can be used to assess the risk, disease state, progression, and treatment response when the patient's prostate cancer metastasizes to the skeleton. In certain embodiments, certain imaging modalities and / or radiopharmaceuticals can be used to evaluate prostate cancer in both localized and metastatic states. For example, as illustrated in Figure 10, PET-CT imaging can be used to evaluate prostate cancer in both localized and metastatic states. As shown in the figure, such PET-CT images may be acquired using a suitable radiopharmaceutical, such as PyL®, which facilitates imaging of both localized and metastatic prostate cancer.

[0141] In certain embodiments, a cloud-based platform facilitates the evaluation of prostate cancer progression and treatment effectiveness over time. For example, as illustrated in the illustrative process 1100 of the block flow chart in Figure 11, in certain embodiments, medical images of a particular patient are repeatedly received and stored over time in the course of multiple visits by the patient to one or more physicians and / or clinical specialists (e.g., radiologists) 1110. In this manner, a series of medical images for the patient is acquired. The series of medical images can be automatically analyzed to determine the values ​​of one or more risk indicators so as to track changes in the determined values ​​over time 1120. The determined risk indicator values ​​may be stored (e.g., for further processing) 1130a. In certain embodiments, this process causes a graphical representation of the determined risk indicator values, such as a graph, to be displayed (e.g., on a user computing device, e.g., via a web-based portal) 1130b.

[0142] In particular, the ability of the cloud-based platform described herein to receive, store, and analyze various different types of medical images, such as synthetic SPECT-CT images, whole-body scans, and synthetic PET-CT images, means that the medical images do not need to be of the same type.

[0143] For example, the first subseries of medical images shows a patient whose prostate cancer is localized. 99m The images may be acquired using a first imaging modality and a first radiopharmaceutical, such as SPECT-CT imaging with Tc-MIP-1404. If the patient's prostate cancer has progressed to a metastatic stage, a second subseries of images may include images acquired via a different second imaging modality and / or a different second radiopharmaceutical. For example, a second subseries of medical images may be PET-CT images acquired using PyL(trademark). For example, a second subseries of medical images may be, 99m It may be a whole-body scan acquired using Tc-MDP.

[0144] Risk indicators can be calculated for a first image subseries and a second image subseries to provide a unified picture of the patient's prostate cancer progression and treatment over time. This method can be applied to multiple patients, for example, in clinical trial settings, as well as for decision-making purposes regarding specific stages of disease progression and treatment for each patient, in order to compare the effectiveness of a particular treatment with other treatments or controls.

[0145] D. Computer systems and network environments Figure 7 shows an exemplary network environment 700 for use in the methods and systems described herein. For a brief overview, a block diagram of an exemplary cloud computing environment 700 is shown and described with reference to Figure 7. The cloud computing environment 700 may include one or more resource providers 702a, 702b, 702c (collectively referred to as 702). Each resource provider 702 may include computing resources. In some implementations, computing resources may include any hardware and / or software used to process data. For example, computing resources may include hardware and / or software capable of running algorithms, computer programs, and / or computer applications. In some implementations, exemplary computing resources may include an application server and / or a database with storage and retrieval capabilities. Each resource provider 702 may be connected to any other resource provider 702 within the cloud computing environment 700. In some implementations, resource providers 702 may be connected on a computer network 708. Each resource provider 702 may be connected to one or more computing devices 704a, 704b, 704c (collectively referred to as 704) on the computer network 708.

[0146] The cloud computing environment 700 may include a resource manager 706. The resource manager 706 may be connected to resource providers 702 and computing devices 704 on a computer network 708. In some implementations, the resource manager 706 may facilitate the provision of computing resources to one or more computing devices 704 by one or more resource providers 702. The resource manager 706 may receive requests for computing resources from specific computing devices 704. The resource manager 706 may identify one or more resource providers 702 that are capable of providing the computing resources requested by computing devices 704. The resource manager 706 may select a resource provider 702 to provide computing resources. The resource manager 706 may facilitate connections between resource providers 702 and specific computing devices 704. In some implementations, the resource manager 706 may establish connections between specific resource providers 702 and specific computing devices 704. In some implementations, the resource manager 706 may redirect a specific computing device 704 to a specific resource provider 702 that has the requested computing resources.

[0147] Figure 8 shows examples of computing devices 800 and mobile computing devices 850 that can be used in the methods and systems described herein. Computing device 800 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Mobile computing device 850 is intended to represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are meant to be examples only and not limiting.

[0148] The computing device 800 includes a processor 802, memory 804, storage device 806, a high-speed interface 808 connected to memory 804 and several high-speed expansion ports 810, and a low-speed interface 812 connected to a low-speed expansion port 814 and storage device 806. Each of the processor 802, memory 804, storage device 806, high-speed interface 808, high-speed expansion ports 810, and low-speed interface 812 may be interconnected using various buses and mounted on a common motherboard, or in other configurations as needed. The processor 802 can process instructions for execution within the computing device 800, including instructions stored in memory 804 or on storage device 806 for displaying graphical information to a GUI on an external input / output device such as a display 816 connected to the high-speed interface 808. In other implementations, multiple processors and / or multiple buses may be used with multiple memories and memory types as needed. Furthermore, multiple computing devices may be connected, each providing a required portion of the operation (for example, as a server bank, a group of blade servers, or a multiprocessor system). Therefore, when the term is used herein, if it is described as multiple functions being performed by a “processor,” this includes embodiments in which multiple functions are performed by any number of processors (one or more) of any number of computing devices (one or more). Moreover, if it is described as a function being performed by a “processor,” this includes embodiments in which the function is performed by any number of processors (one or more) of any number of computing devices (one or more) (for example, in a distributed computing system).

[0149] Memory 804 stores information within the computing device 800. In some implementations, memory 804 is one or more volatile memory units. In some implementations, memory 804 is one or more non-volatile memory units. Memory 804 may also be another form of computer-readable medium, such as a magnetic disk or an optical disk.

[0150] The storage device 806 can provide a large-capacity storage device to the computing device 800. In some implementations, the storage device 806 may be, or include, a computer-readable medium such as a floppy disk device, a hard disk device, an optical disk device, or a tape device, flash memory, or other similar solid-state memory device, or it may be, or include, an array of devices including devices in a storage area network or other configuration. Instructions are stored in an information carrier. When an instruction is executed by one or more processing devices (e.g., processor 802), it performs one or more methods, such as those described above. Instructions are also stored in one or more storage devices, such as computer-readable or machine-readable media (e.g., memory 804, storage device 806, or memory on processor 802).

[0151] The high-speed interface 808 manages bandwidth-intensive operations for the computing device 800, while the low-speed interface 812 manages bandwidth-intensive operations. Such a functional allocation is merely an example. In some implementations, the high-speed interface 808 is connected to memory 804, to a display 816 (e.g., via a graphics processor or accelerator), and to a high-speed expansion port 810 that can accept various expansion cards (not shown). In some implementations, the low-speed interface 812 is connected to the storage device 806 and the low-speed expansion port 814. The low-speed expansion port 814, which may include various communication ports (e.g., USB, Bluetooth®, Ethernet®, Wireless Ethernet®), may be connected to one or more input / output devices, such as a keyboard, pointing device, scanner, or network device such as a switch or router, for example, via a network adapter.

[0152] The computing device 800 may be implemented in several different forms, as shown in the figure. For example, the computing device 800 may be implemented as a standard server 820, or multiple times within a group of such servers. In addition, the computing device 800 may be implemented within a personal computer, such as a laptop computer 822. The computing device 800 may be implemented as part of a rack server system 824. Alternatively, components from the computing device 800 may be combined with other components in a mobile device (not shown), such as a mobile computing device 850. Each of such devices may contain one or more of the computing device 800 and the mobile computing device 850, and the entire system may consist of multiple computing devices communicating with each other.

[0153] The mobile computing device 850 includes, among other various components, a processor 852, memory 864, input / output devices such as a display 854, a communication interface 866, and a transceiver 868. The mobile computing device 850 may also include storage devices such as a microdrive or other devices to provide additional storage. Each of the processor 852, memory 864, display 854, communication interface 866, and transceiver 868 is interconnected using various buses, and some of the components may be mounted on a common motherboard or in other ways as needed.

[0154] The processor 852 can execute instructions within the mobile computing device 850, including instructions stored in memory 864. The processor 852 may be implemented as a chipset of chips including multiple separate analog and digital processors. The processor 852 may provide coordination for other components of the mobile computing device 850, such as a user interface, applications run by the mobile computing device 850, and control of wireless communications by the mobile computing device 850.

[0155] The processor 852 may communicate with the user through a control interface 858 and a display interface 856 connected to a display 854. The display 854 may be, for example, a TFT (thin-film transistor liquid crystal display) display or an OLED (organic light-emitting diode) display, or other suitable display technology. The display interface 856 may include suitable circuitry for driving the display 854 to present graphical and other information to the user. The control interface 858 may receive commands from the user and translate those commands for submission to the processor 852. In addition, an external interface 862 may provide communication to the processor 852 to enable the mobile computing device 850 to communicate with other devices in the vicinity. The external interface 862 may provide wired communication in some implementations and wireless communication in other implementations, and multiple interfaces may also be used.

[0156] Memory 864 stores information within the mobile computing device 850. Memory 864 may be implemented as one or more computer-readable media, one or more volatile memory units, or one or more non-volatile memory units. Extended memory 874 is also provided and may be connected to the mobile computing device 850 via an expansion interface 872, which may include, for example, a SIMM (Single In-Line Memory Module) card interface. Extended memory 874 may provide the mobile computing device 850 with extra storage space and may also store applications or other information about the mobile computing device 850. Specifically, extended memory 874 may include instructions that perform or supplement the processes described above, and may also include secure information. For example, extended memory 874 may be provided to the mobile computing device 850 as a security module and may be programmed to have instructions that enable secure use of the mobile computing device 850. In addition, secure applications may be provided via SIMM cards, along with additional information such as placing identification information on the SIMM card in a hack-proof manner.

[0157] The memory may include, for example, flash memory and / or NVRAM memory (non-volatile random access memory), as discussed below. In some implementations, instructions are stored in an information carrier and, when executed by one or more processing devices (e.g., processor 852), perform one or more actions, such as those described above. Instructions can also be stored in one or more storage devices, such as one or more computer-readable or machine-readable media (e.g., memory 864, extended memory 874, or memory on processor 852). In some implementations, instructions can be received in a propagated signal, for example, on transceiver 868 or external interface 862.

[0158] The mobile computing device 850 may communicate wirelessly through a communication interface 866, which may include digital signal processing circuitry if necessary. The communication interface 866 may provide communication under various modes or protocols, including, in particular, GSM® voice calls (Global System for Mobile communications), SMS (Short Message Service), EMS (Extended Messaging Service), or MMS messaging (Multimedia Messaging Service), CDMA (Code Division Multiple Access), TDMA (Time Division Multiple Access), PDC (Personal Digital Cellular), WCDMA® (Wideband Code Division Multiple Access), CDMA2000, or GPRS (General Purpose Packet Radio Service). Such communication may be performed, for example, through a transceiver 868 using a certain radio frequency. In addition, short-range communication may be performed using Bluetooth®, Wi-Fi®, or other such transceivers (not shown). In addition, the GPS (Global Positioning System) receiver module 870 may provide additional navigation and positional wireless data to the mobile computing device 850, which may be used as needed by an application running on the mobile computing device 850.

[0159] The mobile computing device 850 may also communicate audibly using an audio codec 860, which may receive spoken information from the user and convert it into usable digital information. The audio codec 860 may also generate audible sound for the user, for example, through a speaker in the handset of the mobile computing device 850. Such sound may include sounds from voice telephone calls, recorded sounds (e.g., voice messages, music files, etc.), and sounds generated by applications running on the mobile computing device 850.

[0160] The mobile computing device 850 may be implemented in several different forms, as shown in the figure. For example, the mobile computing device 850 may be implemented as a cellular telephone 880. The mobile computing device 850 may also be implemented as part of a smartphone 882, a personal digital assistant (PDCA), or other similar mobile device.

[0161] Various implementations of the systems and techniques described herein can be realized in digital electronic circuits, integrated circuits, specially designed ASICs (application-specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, the programmable processor being special-purpose or multi-purpose and receiving data and instructions from a storage system, at least one input device, and at least one output device, and may be coupled to send data and instructions to them.

[0162] These computer programs (also known as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented in high-level procedural programming languages ​​and / or object-oriented programming languages, as well as in assembly / machine languages. As used herein, the terms machine-readable medium and computer-readable medium refer to any computer program product, apparatus, and / or device (e.g., magnetic disks, optical disks, memory, programmable logic devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including machine-readable medium that receives machine instructions as machine-readable signals. The term machine-readable signal refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0163] To provide user interaction, the systems and techniques described herein can be implemented on a computer having a display device for displaying information to the user (e.g., a CRT (cathode ray tube) monitor or an LCD (liquid crystal display) monitor) and a keyboard and pointing device (e.g., a mouse or trackball) on which the user can provide input to the computer. Other types of devices can also be used to provide user interaction. For example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including acoustic input, speech input, or tactile input.

[0164] The systems and techniques described herein can be implemented in computing systems including backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., client computers having a graphical user interface or web browser that allows users to interact with implementations of the systems and techniques described herein), or in computing systems including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the internet.

[0165] A computing system may include a client and a server. Clients and servers are generally geographically distant from each other and typically interact through a communication network. The client-server relationship arises from computer programs running on each computer that have a client-server relationship with each other. In some implementations, the modules and / or services described herein (e.g., cloud-based services such as BSI Cloud 110, PyL Cloud 120, 1404 Cloud 130, e.g., any of the microservices described herein) can be isolated, combined, or incorporated into a single or combined module and / or service. The modules and / or services depicted in the diagrams are not intended to limit the systems described herein to the software architecture shown therein.

[0166] While the present invention has been shown and described in particular with respect to specific preferred embodiments, it should be understood by those skilled in the art that various modifications in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Examples of embodiments of the present invention include the following: (Item 1) Processor and A memory having instructions stored thereon, wherein when the instructions are executed by the processor, the following functions (i) to (v): (i) Receiving and storing medical images in a database, where each medical image is associated with a specific patient. (ii) Accessing one or more of the medical images and / or related data associated with a specific patient from the database when requested by the user for transmission to the user for display on the user computing device. (iii) Automatically analyze one or more of the aforementioned medical images, (iv) generating a radiologist report for the patient in accordance with one or more of the medical images for the patient, and (v) Applying machine learning algorithms to update the process for automatically analyzing one or more of the medical images using the stored image data in the database. The processor is made to perform one or more of the following, using memory and A network-based decision support system equipped with the following features. (Item 2) The system according to item 1, wherein the medical images in the database include a series of medical images of a first patient taken over time, and the instruction causes the processor to determine the value of at least a first risk indicator for each medical image in the series, thereby tracking the determined value of at least the first risk indicator for the first patient over time. (Item 3) The aforementioned medical image, 99m A system according to any one of the preceding items, comprising a single-photon emission computed tomography (SPECT) scan of the first patient obtained following administration of a contrast agent containing Tc-labeled 1404 to the first patient, and a computed tomography (CT) scan of the first patient, wherein the instruction causes the processor to superimpose the SPECT scan onto the CT scan to create a composite image (SPECT-CT) of the first patient. (Item 4) The system according to any one of the preceding items, wherein the medical image includes a positron emission tomography (PET) scan of the first patient and a CT scan of the first patient, obtained following the administration of a contrast agent containing [18F]DCFPyL to the first patient, and the instruction causes the processor to superimpose the PET scan onto the CT scan to create a composite image (PET-CT) of the first patient. (Item 5) The aforementioned medical image shows technetium-99m methylenediphosphonate ( 99m The system according to any one of the preceding items, comprising administering a contrast agent (Tc MDP) to a first patient, followed by a whole-body scan of the first patient using a gamma camera. (Item 6) The medical image includes a composite image of a first patient, the composite image includes a CT scan overlaid with nuclear medicine images acquired substantially at the same time as the CT scan, following the administration of a contrast agent containing a prostate-specific membrane antigen (PSMA) conjugate containing a radionuclide to the first patient, and the instruction is, (a) Using the composite image, geographically identify the 3D boundaries for each of the one or more regions of the imaged tissue in the nuclear medicine image, and (c) Using the nuclear medicine image together with the identified 3D boundaries of one or more regions, (i) calculate the values ​​of each of one or more risk indicators and / or (ii) calculate a risk map. The system according to any one of the preceding items, wherein the processor is made to automatically analyze the composite image by means of the system. (Item 7) The instruction applies to at least one of the one or more risk indicators: For each of the one or more regions, the corresponding cancer tissue level within the region is determined based on the intensity value of the nuclear medicine image within the 3D boundary of the region, and The value of the risk indicator is calculated based on the determined cancer tissue level within one or more of the aforementioned regions. The system according to item 6, wherein the processor is made to calculate the value of the risk indicator. (Item 8) The system according to either item 6 or 7, wherein the nuclear medicine image is a SPECT scan. (Item 9) The system according to item 8, wherein the contrast agent comprises a metal chelated to the PSMA binder, and the metal is the radionuclide. (Item 10) The aforementioned contrast agent 99m The system described in item 9, including Tc-MIP-1404. (Item 11) The system according to either item 6 or 7, wherein the nuclear medicine image is a PET scan. (Item 12) The system described in item 11, wherein the radioactive nuclide is a radioisotope of a halogen. (Item 13) The system according to item 12, wherein the contrast agent comprises [18F]DCFPyL. (Item 14) The system described in item 11, wherein the radioactive nuclide is a radioactive isotope of gallium (Ga). (Item 15) The medical image includes a nuclear medicine image of the first patient following the administration of a contrast agent containing a radionuclide to the first patient, and the instruction is, (a) Geographically identifying the boundaries of each of one or more regions of the imaged tissue in the nuclear medicine image, and (c) Using the nuclear medicine image along with the identified boundaries of one or more regions, (i) calculate the values ​​of each of one or more risk indicators and / or (ii) calculate a risk map. The system according to any one of the preceding items, wherein the processor is made to automatically analyze the nuclear medicine images. (Item 16) The instruction applies to at least one of the one or more risk indicators: For each of the one or more regions, the corresponding cancer tissue level within the region is determined based on the intensity value of the nuclear medicine image within the boundary of the region, and The value of the risk indicator is calculated based on the determined cancer tissue level within one or more of the aforementioned regions. The system according to item 15, wherein the processor is made to calculate the value of the risk indicator by means of the processor. (Item 17) The system described in any one of the preceding items is a cloud-based system. (Item 18) The system according to any one of the preceding items, wherein the processor is a processor of one or more network or internet host servers. (Item 19) (i) through (v) below: (i) Receiving and storing medical images in a database using the processor of a server computing device, wherein each medical image is associated with a specific patient. (ii) The processor accesses one or more of the medical images and / or related data associated with a specific patient from the database when a user request is made for transmission to the user for display on the user computing device. (iii) automatically analyzing one or more of the medical images by the processor; (iv) generating a radiologist's report for the patient by the processor according to one or more of the medical images for the patient, and (v) applying a machine learning algorithm by the processor to update a process for automatically analyzing one or more of the medical images using the stored image data in the database. A method comprising any one or more of the above. (Item 20) The medical images in the database include a series of medical images of a first patient taken over time, and the method includes determining values of at least a first risk index for each medical image of the series, thereby tracking over time the determined values of at least the first risk index. The method according to Item 19. (Item 21) The receiving and storing of the medical images include repeatedly receiving and storing over time a plurality of medical images of the first patient each obtained at a different time to obtain the series of medical images of the first patient. The method according to Item 20. (Item 22) The medical images are 99m a single photon emission computed tomography (SPECT) scan of the first patient obtained following administration of a contrast agent containing 1404 labeled with (Item 23) The medical image includes a positron emission tomography (PET) scan of the first patient obtained following administration of a contrast agent comprising [18F]DCFPyL to the first patient, and a CT scan of the first patient, and the method includes constructing a synthetic image (PET-CT) of the first patient by overlaying the PET scan on the CT scan, the method according to any one of items 19 to 22. (Item 24) The medical image includes a whole body scan of the first patient performed using a gamma camera following administration of a contrast agent comprising technetium 99m methylene diphosphonate ( 99m Tc MDP) to the first patient, the method according to any one of items 19 to 23. (Item 25) The medical image includes a synthetic image of a first patient, the synthetic image including a CT scan overlaid with a nuclear medicine image obtained following administration of a contrast agent comprising a prostate specific membrane antigen (PSMA) binder containing a radionuclide to the first patient at substantially the same time, the method including (a) using the synthetic image to geographically identify 3D boundaries for each of one or more regions of imaged tissue within the nuclear medicine image, and (c) using the nuclear medicine image with the identified 3D boundaries of the one or more regions to calculate (i) a value for each of one or more risk indicators and / or (ii) a risk map to automatically analyze the synthetic image, the method according to any one of items 19 to 24. (Item 26) Step (c) is for at least one risk indicator of the one or more risk indicators for each of the one or more regions, determining a corresponding cancer tissue level within the region based on intensity values of the nuclear medicine image within the 3D boundary of the region, and calculating the value of the risk indicator based on the determined cancer tissue levels within the one or more regions The method of item 25, comprising calculating the value of the risk indicator by means of the method. (Item 27) The method according to either item 25 or 26, wherein the nuclear medicine image is a SPECT scan. (Item 28) The method according to item 27, wherein the contrast agent contains a metal chelated to the PSMA binder, and the metal is the radionuclide. (Item 29) The aforementioned contrast agent 99m The method described in item 28, including Tc-MIP-1404. (Item 30) The method according to either item 25 or 26, wherein the nuclear medicine image is a PET scan. (Item 31) The method according to item 30, wherein the radioactive nuclide is a radioactive isotope of a halogen. (Item 32) The method according to item 31, wherein the contrast agent comprises [18F]DCFPyL. (Item 33) The method according to item 30, wherein the radioactive nuclide is a radioactive isotope of gallium (Ga). (Item 34) The medical image includes a nuclear medicine image of the first patient obtained following the administration of a contrast agent containing a radionuclide to the first patient, and the method is (a) Geographically identifying the boundaries of each of one or more regions of the imaged tissue in the nuclear medicine image, and (c) Using the nuclear medicine image along with the identified boundaries of one or more regions, (i) calculate the values ​​of each of one or more risk indicators and / or (ii) calculate a risk map. The method according to any one of items 19 to 33, comprising automatically analyzing the nuclear medicine images by means of the method. (Item 35) Step (c) is performed for at least one of the one or more risk indicators, For each of the one or more regions, the corresponding cancer tissue level within the region is determined based on the intensity value of the nuclear medicine image within the boundary of the region, and The value of the risk indicator is calculated based on the determined cancer tissue level within one or more of the aforementioned regions. The method of item 34, comprising calculating the value of the risk indicator by means of the method. (Item 36) The method according to any one of items 19 to 35, wherein the processor is a processor for a cloud-based system. (Item 37) The method according to any one of items 19 to 36, wherein the processor is a processor of one or more network or internet host servers. (Item 38) Processor and A memory having instructions stored thereon, wherein when the instructions are executed by the processor, the processor causes the processor to generate and display interactive graphical user interface (GUI) elements, and the GUI elements have user-selectable and / or user-adjustable graphical controls for selecting and / or adjusting the digital presentation of a patient's 3D risk picture for comparison with a reference image displayed by the processor. A system equipped with these features. (Item 39) The system according to item 38, wherein the interactive GUI elements are produced from the patient's medical images and / or other images or information. (Item 40) A method for tracking the progression of prostate cancer and the effectiveness of treatment over time in one or more patients, (a) Over time, the processor of the computing device repeatedly receives multiple medical images for each of the one or more patients, stores them in a database, and obtains a series of medical images taken over time for each of the one or more patients. (b) For each of the one or more patients, the processor automatically analyzes the series of medical images for the patient to determine the value of one or more risk indicators for each medical image in the series, thereby tracking the determined value of the one or more risk indicators over the course of prostate cancer progression and treatment for the patient. (c) For each of the one or more patients, the processor stores the determined value of the one or more risk indicators for the patient for further processing, and / or the processor causes a graphical representation of the determined value of the one or more risk indicators for the patient. A method that includes this. (Item 41) The series of medical images for a specific patient among the one or more patients is (i) A first image subseries, each comprising one or more medical images acquired using a first nuclear imaging modality following the administration of the first radiopharmaceutical to the particular patient, (ii) A second image subseries, each comprising one or more medical images acquired using a second nuclear imaging modality following the administration of the second radiopharmaceutical to the particular patient, Includes, The method according to item 40, wherein the value of the one or more risk indicators determined in step (b) for the particular patient includes a first subseries of values ​​for the first risk indicator determined by automated analysis of the first image subseries and a second subseries of values ​​for the second risk indicator determined by automated analysis of the second image subseries. (Item 42) The method according to item 41, wherein when the prostate cancer of the particular patient is localized, the medical images of the first image subseries are acquired over a first time period, and when the prostate cancer of the particular patient is metastatic, the medical images of the second image subseries are acquired over a second time period. (Item 43) where the first image subseries includes one or more synthetic SPECT-CT images, each synthetic SPECT-CT image including a CT scan overlaid with a SPECT scan acquired substantially at the same time, the second image subseries includes one or more synthetic PET-CT images, each synthetic PET-CT image including a CT scan overlaid with a PET scan acquired substantially at the same time, step (b) comprises using the synthetic SPECT-CT image to geographically identify a 3D boundary of the prostate region within the SPECT scan of the synthetic SPECT-CT image, and using the SPECT scan together with the identified 3D boundary of the prostate region to calculate a value of the first risk indicator to automatically analyze each of the one or more synthetic SPECT-CT images, and using the synthetic PET-CT image to geographically identify a 3D boundary of one or more metastatic regions within the PET scan of the synthetic PET-CT image, the one or more metastatic regions including regions corresponding to patient tissue locations outside the prostate, and using the PET scan together with the identified 3D boundary of the one or more metastatic regions to calculate a value of the second risk indicator to automatically analyze each of the one or more synthetic PET-CT images, and The method according to any one of items 41 or 42, comprising. (Item 44) where the first image subseries includes one or more synthetic SPECT-CT images, each synthetic SPECT-CT image including a CT scan overlaid with a SPECT scan acquired substantially at the same time, the second image subseries includes one or more whole body scans, step (b) comprises Using the composite SPECT-CT image, geographically identify the 3D boundary of the prostate region within the SPECT scan of the composite SPECT-CT image, and Using the SPECT scan along with the identified 3D boundary of the prostate region, the value of the first risk indicator is calculated. This automatically analyzes each of the one or more composite SPECT-CT images, Geographically identifying the boundaries of one or more metastatic regions within the whole-body scan, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate, and Using the PET scan along with the identified 3D boundaries of the one or more metastatic regions, the value of the second risk indicator is calculated. This automatically analyzes each of the one or more whole-body scan composite SPECT-CT images. The method described in either item 41 or 42, including the method described in item 41 or 42. (Item 45) A system for tracking the progression of prostate cancer and the effectiveness of treatment over time in one or more patients, Processor and A memory having instructions stored thereon, wherein when the instructions are executed by the processor, (a) Repeatedly receiving multiple medical images for each of the one or more patients over time, storing them in a database, and obtaining a series of medical images taken over time for each of the one or more patients, (b) For each of the one or more patients, automatically analyze the series of medical images for the patient to determine the value of one or more risk indicators for each medical image in the series, and thereby track the determined value of the one or more risk indicators over the course of prostate cancer progression and treatment for the patient, (c) For each of the one or more patients, store the determined value of the one or more risk indicators for the patient for further processing, and / or cause a graphical representation of the determined value of the one or more risk indicators for the patient. The processor is made to perform this operation, and memory and A system equipped with these features. (Item 46) The series of medical images for a specific patient among the one or more patients is (i) A first image subseries, each comprising one or more medical images acquired using a first nuclear imaging modality following the administration of the first radiopharmaceutical to the particular patient, (ii) A second image subseries, each comprising one or more medical images acquired using a second nuclear imaging modality following the administration of the second radiopharmaceutical to the particular patient, Includes, Accordingly, the system according to item 45, wherein the value of the one or more risk indicators determined in step (b) for the particular patient includes a first subseries of values ​​for the first risk indicator determined by automated analysis of the first image subseries and a second subseries of values ​​for the second risk indicator determined by automated analysis of the second image subseries. (Item 47) The system according to item 46, wherein when the prostate cancer of the particular patient is localized, the medical images of the first image subseries are acquired over a first time period, and when the prostate cancer of the particular patient is metastatic, the medical images of the second image subseries are acquired over a second time period. (Item 48) The first image subseries comprises one or more composite SPECT-CT images, each composite SPECT-CT image comprising a CT scan in which SPECT scans acquired substantially at the same time are superimposed. The second image subseries comprises one or more composite PET-CT images, each composite PET-CT image comprising a CT scan superimposed on PET scans acquired substantially at the same time. The instruction in step (b) Using the composite SPECT-CT image, geographically identify the 3D boundary of the prostate region within the SPECT scan of the composite SPECT-CT image, and Using the SPECT scan along with the identified 3D boundary of the prostate region, the value of the first risk indicator is calculated. This automatically analyzes each of the one or more composite SPECT-CT images, Using the synthesized PET-CT image, geographically identify the 3D boundaries of one or more metastatic regions within the PET scan of the synthesized PET-CT image, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate, and Using the PET scan along with the identified 3D boundaries of the one or more metastatic regions, the value of the second risk indicator is calculated. This allows for the automatic analysis of each of the one or more composite PET-CT images. The system according to item 46 or 47, which causes the processor to perform the above. (Item 49) The first image subseries comprises one or more composite SPECT-CT images, each composite SPECT-CT image comprising a CT scan in which SPECT scans acquired substantially at the same time are superimposed. The second image subseries includes one or more whole-body scans, The instruction in step (b) Using the composite SPECT-CT image, geographically identify the 3D boundary of the prostate region within the SPECT scan of the composite SPECT-CT image, and Using the SPECT scan along with the identified 3D boundary of the prostate region, the value of the first risk indicator is calculated. This automatically analyzes each of the one or more composite SPECT-CT images, Geographically identifying the boundaries of one or more metastatic regions within the whole-body scan, wherein the one or more metastatic regions include regions corresponding to patient tissue locations outside the prostate, and Using the PET scan along with the identified 3D boundaries of the one or more metastatic regions, the value of the second risk indicator is calculated. This allows for the automatic analysis of each of the one or more whole-body scans. The system according to item 46 or 47, which causes the processor to perform the above.

Claims

[Claim 1] The method described in the specification.

Images