用于评估疾病负担和进展的系统和方法

What is claimed is : 1. A method for automatically processing 3D images of a subject to determine values of one or more patient index(indices) that measure (e.g., overall) disease burden and/or risk for a subject, the method comprising : (a) receiving, by a processor of a computing device, a 3D functional image of the subject obtained using a functional imaging modality; (b) segmenting, by the processor, a plurality of 3D hotspot volumes within the 3D functional image, each 3D hotspot volume corresponding to a local region of elevated intensity with respect to its surrounding and representing a potential cancerous lesion within the subject, thereby obtaining a set of 3D hotspot volumes; (c) computing, by the processor, for each particular one of one or more individual hotspot quantification metrics, a value of the particular individual hotspot quantification metric for each individual 3D hotspot volume of the set; and (d) determining, by the processor, the values of the one or more patient index(indices), wherein each of at least a portion of the patient indices is associated with one or more specific individual hotspot quantification metrics and is a function of at least a portion (e.g., substantially all; e.g., a particular subset) of the values of the one or more specific individual hotspot quantification metric(s) computed for the set of 3D hotspot volumes. 2. The method of claim 1, wherein at least one particular patient index of the one or more patient index values is associated with a single specific individual hotspot quantification metric and is computed as a function (e.g., a mean, a median, a mode, a sum, etc.) of substantially all (e.g., all; e.g., excluding only statistical outliers) values of the specific individual hotspot quantification metric computed for the set of 3D hotspot volumes. 3. The method of claim 2, wherein the single specific individual hotspot quantification metric is an individual hotspot intensity metric that quantifies intensity within a 3D hotspot volume (e.g., computed, for an individual 3D hotspot volume, as a function of intensities of voxels of the 3D hotspot volume). 4. The method of claim 3, wherein the individual hotspot intensity metric is a mean hotspot intensity (e.g., computed, for an individual 3D hotspot volume, as a mean of intensities of voxels within the 3D hotspot volume). 5. The method of any one of claims 3 to 4, wherein the particular patient index is computed as a sum of substantially all the values of the individual hotspot intensity metric computed for the set of 3D hotspot volumes. 6. The method of claim 6, wherein the single specific individual hotspot quantification metric is a lesion volume (e.g., computed for a particular 3D hotspot volume as a sum of volumes of each individual voxel within the particular 3D hotspot volume). 7. The method of claim 6, wherein (values of) the particular patient index is computed as a sum of substantially all the lesion volume values computed for the set of 3D hotspot volumes (e.g., such that the particular patient index value provides a measure of total lesion volume within the subject). 8. The method of any one of the preceding claims, wherein a particular one of the one or more overall patient index(indices) is associated with two or more specific individual hotspot quantification metrics and is computed as a function (e.g., a weighted sum, a weighted mean, etc.) of substantially all values of the two or more specific individual hotspot quantification metric computed for the set of 3D hotspot volumes. 9. The method of claim 8, wherein the two or more specific individual hotspot quantification metrics comprise (i) an individual hotspot intensity metric and (ii) a lesion volume. 10. The method of claim 9, wherein the individual hotspot intensity metric is an individual lesion index that maps a value of hotspot intensity to a value on a standardized scale. 11. The method of claim 9 or 10, wherein (values of) the particular patient index is computed as a sum of intensity-weighted lesion (e.g., hotspot) volumes by : for each individual 3D hotspot volume of substantially all the 3D hotspot volumes, weighting a value of the lesion volume by a value of the individual hotspot intensity metric (e.g., computing the product of the lesion volume value and the value of the individual hotspot intensity metric), thereby computing a plurality of intensity-weighted lesion volumes; and computing, as the value of the particular patient index, a sum of substantially all the intensity-weighted lesion volumes. 12. The method of any one of the preceding claims, wherein the one or more individual hotspot quantification metrics comprise one or more individual hotspot intensity measures that quantify intensity within a 3D hotspot volume (e.g., computed, for an individual 3D hotspot volume, as a function of intensities of voxels of the 3D hotspot volume). 13. The method of claim 12, wherein the one or more individual hotspot quantification metric comprise one or more members selected from the group consisting of : a mean hotspot intensity (e.g., computed, for a particular 3D hotspot volume, as a mean of intensities of voxels within the particular 3D hotspot volume); a maximum hotspot intensity (e.g., computed, for a particular 3D hotspot volume, as a maximum of intensities of voxels within the particular 3D hotspot volume); and a median hotspot intensity (e.g., computed, for a particular 3D hotspot volume, as a median of intensities of voxels within the 3D hotspot volume). 14. The method of claim 12 or 13, wherein the one or more individual hotspot intensity metric(s) comprise a peak intensity of a 3D hotspot volume [e.g., wherein, for a particular 3D hotspot volume, a value of the peak intensity is computed by : (i) identifying a maximum intensity voxel within the particular 3D hotspot volume; (ii) identifying voxels within a sub-region about (e.g., comprising voxels within a particular threshold distance of) the maximum intensity voxel and within the particular 3D hotspot; and (iii) computing, as the corresponding peak intensity, a mean of intensities of the voxels within the sub-region]. 15. The method of any one of claims 12 to 14, wherein the one or more individual hotspot intensity metrics comprise an individual lesion index that maps a value of hotspot intensity to a value on a standardized scale. 16. The method of claim 15, comprising : identifying, by the processor, within the 3D functional image, one or more 3D reference volume(s), each corresponding to a particular reference tissue region; determining, by the processor, one or more reference intensity values, each associated with a particular 3D reference volume of the one or more 3D reference volume(s) and corresponding to a measure of intensity within the particular 3D reference volume; and at step (c), for each 3D hotspot volume within the set : determining, by the processor, a corresponding value of a particular individual hotspot intensity metric (e.g., a mean hotspot intensity, a median hotspot intensity, a maximum hotspot intensity, etc.); and determining, by the processor, a corresponding value of the individual lesion index based on the corresponding value of the particular individual hotspot intensity metric and the one or more reference intensity values. 17. The method of claim 16, comprising : mapping each of the one or more reference intensity values to a corresponding reference index value on a scale; and for each 3D hotspot volume, determining the corresponding value of the individual lesion index using the reference intensity values and corresponding reference index values to interpolate a corresponding individual lesion index value on the scale based on the corresponding value of the particular individual hotspot intensity metric. 18. The method of either one of claims 16 or 17, wherein the reference tissue regions comprise one or more members selected from the group consisting of : a liver, an aorta, and a parotid gland. 19. The method of any one of claims 16 to 18, wherein : a first reference intensity value (i) is a blood reference intensity value associated with a reference volume corresponding to an aorta portion, and (ii) maps to a first reference index value; a second reference intensity value (i) is a liver reference intensity value associated with a reference volume corresponding to a liver, and (ii) maps to a second reference index value; and the second reference intensity value is greater than the first reference intensity value and the second reference index value is greater than the first reference index value. 20. The method of any one of claims 16 to 19, wherein the reference intensity values comprises a maximum reference intensity value that maps to a maximum reference index value, and wherein 3D hotspot volumes for which corresponding values of the particular individual hotspot intensity metric are greater than the maximum reference intensity value are assigned individual lesion index values equal to the maximum reference index value. 21. The method of any one of the preceding claims, comprising : identifying, within the set of 3D hotspot volumes, one or more subsets, each associated with a particular tissue region and/or lesion classification; and computing, for each particular subset of the one or more subsets, a corresponding value of one or more particular patient index(indices) using values of the individual hotspot quantification metrics computed for 3D hotspot volumes within the particular subset. 22. The method of claim 21, wherein each of the one or more subsets is associated with a particular one of one or more tissue region(s) and the method comprises identifying, for each particular tissue region, a subset of the 3D hotspot volumes located within a volume of interest corresponding to the particular tissue region. 23. The method of claim 22, wherein the one or more tissue region(s) comprise one or more members selected from the group consisting of : a skeletal region comprising one or more bones of the subject, a lymph region, and a prostate region. 24. The method of any one of claims 21 to 23, wherein each of the one or more subsets is associated with a particular one of one or more lesion sub-types [e.g., according to a lesion classification scheme (e.g., a miTNM classification)] and the method comprises determining, for each 3D hotspot volume, a corresponding lesion sub-type and assigning the 3D hotspot volumes to the one or more subsets according to their corresponding lesion sub-types. 25. The method of any one of the preceding claims, comprising using at least a portion of the values of the one or more patient index(indices) as inputs to a prognostic model (e.g., a statistical model, such as a regression; e.g., a classification model, whereby a patient is assigned to a particular class based on a comparison of the one or more patient index values with one or more thresholds; e.g., a machine learning model, where the values of the one or more patient indices are received as input) that generates, as output, an expectation value and/or range (e.g., a class) indicative of a likely value of a particular patient outcome (e.g., a time, e.g., in number of months, representing an expected survival, time to progression, time to radiographic progression, etc.). 26. The method of any one of the preceding claims comprising using at least a portion of the values of the one or more patient index(indices) as inputs to a predictive model (e.g., a statistical model, such as a regression; e.g., a classification model, whereby a patient is assigned to a particular class based on a comparison of the one or more patient index values with one or more thresholds; e.g., a machine learning model, where the values of the one or more patient indices are received as input) that generates, as output, an eligibility score for each of one or more treatment options (e.g., Abiraterone, Enzalutamide, Apalutamide, Darolutamide, Sipuleucel-T, Ra223, Docetaxel, Carbazitaxel, Pembrolizumab, Olaparib, Rucaparib, 177Lu-PSMA-617, etc.) and/or classes of therapeutics [e.g., androgen biosynthesis inhibitors (e.g., Abiraterone), androgen receptor inhibitors (e.g., Enzalutamide, Apalutamide, Darolutamide), a cellular immunotherapy (e.g., Sipuleucel-T), internal radiotherapy treatment (Ra223), antineoplastics (e.g., Docetaxel, Carbazitaxel), immune checkpoint inhibitor (Pembrolizumab), PARP inhibitors (e.g., Olaparib, Rucaparib), PSMA binding agent], wherein the eligibility score for a particular treatment option and/or therapeutic class indicates a prediction of whether the patient will benefit from the particular treatment and/or therapeutic class. 27. The method of any one of the preceding claims, comprising generating (e.g., automatically) a report [e.g., an electronic document, e.g., within a graphical user interface (e.g., for validation/sign-off by a user)] comprising at least a portion of the values of the one or more patient index(indices). 28. The method of any one of the preceding claims, wherein step (b) comprises using one or more machine learning modules [e.g., one or more neural networks (e.g., one or more convolutional neural networks)] to perform one or more functions selected from the group consisting of : detecting a plurality of hotspots, wherein each of at least a portion of the plurality of 3D hotspot volumes corresponds to a particular detected hotspot and is produced by segmenting the particular detected hotspot; segmenting at least a portion of the plurality of 3D hotspot volumes; and classifying at least a portion of the 3D hotspot volumes (e.g., determining a likelihood that each 3D hotspot volume represents an underlying cancerous lesion). 29. The method of any one of the preceding claims, wherein the 3D functional image comprises a PET or SPECT image obtained following administration of an agent to the subject. 30. The method of claim 29, wherein the agent comprises a PSMA binding agent. 31. The method of claim 29 or 30, wherein the agent comprises 18F. 32. The method of claim 30 or 31, wherein the agent comprises [18F]DCFPyL. 33. The method of claim 30, wherein the agent comprises PSMA-11. 34. The method of claim 30, wherein the agent comprises one or more members selected from the group consisting of 99mTc, 68Ga, 177Lu, 225 Ac, 111In, 123I, 124I, and 131I. 35. A method for automated analysis of a time series of medical images [e.g., three- dimensional images, e.g., nuclear medicine images (e.g., bone scan (scintigraphy), PET, and/or SPECT), e.g., anatomical images (e.g., CT, X-ray, MRI), e.g., combined nuclear medicine and anatomical images (e.g., overlaid)] of a subject, the method comprising : (a) receiving and/or accessing, by a processor of a computing device, the time series of medical images of the subject; and (b) identifying, by the processor, a plurality of hotspots within each of the medical images and determining, by the processor, one, two, or all three of (i), (ii), and (iii) as follows : (i) a change in the number of identified lesions (ii) a change in an overall volume of identified lesions (e.g., a change in the sum of the volumes of each identified lesion), and (iii) a change in PSMA (e.g., lesion index) weighted total volume (e.g., a sum of the products of lesion index and lesion volume for all lesions in a region of interest) [e.g., wherein the change identified in step (b) is used to identify (1) a disease status [e.g., progression, regression, or no change], (2) make a treatment management decision [e.g. active surveillance, prostatectomy, anti-androgen therapy, prednisone, radiation, radio-therapy, radio-PSMA therapy, or chemotherapy], or (3) treatment efficacy (e.g. wherein the subject has begun treatment or has continued treatment with a medicament or other therapy following an initial set of images in the time series of medical images)] [e.g., wherein step (b) comprises using a machine learning module/model]. 36. A method for analyzing a plurality of medical images of a subject (e.g., to evaluate disease state and/or progression within the subject), the method comprising : (a) receiving and/or accessing, by a processor of a computing device, the plurality of medical images of the subject and obtaining, by the processor, a plurality of 3D hotspot maps, each corresponding to a particular medical image (of the plurality) and identifying one or more hotspots (e.g., representing potential underlying physical lesions within the subject) within the particular medical image; (b) for each particular one (medical image) of the plurality of medical images, determining, by the processor, using a machine learning module [e.g., a deep learning network (e.g., a Convolutional Neural Network (CNN))], a corresponding 3D anatomical segmentation map that identifies a set of organ regions [e.g., representing soft tissue and/or bone structures within the subject (e.g., one or more of a cervical spine; thoracic spine; lumbar spine; left and right hip bones, sacrum and coccyx; left side ribs and left scapula; right side ribs and right scapula; left femur; right femur; skull, brain and mandible)] within the particular medical image, thereby generating a plurality of 3D anatomical segmentation maps; (c) determining, by the processor, using (i) the plurality of 3D hotspot maps and (ii) the plurality of 3D anatomical segmentation maps, an identification of one or more lesion correspondences, each (lesion correspondence) identifying two or more corresponding hotspots within different medical images and determined (e.g., by the processor) to represent a same underlying physical lesion within the subject; and (d) determining, by the processor, based on the plurality of 3D hotspot maps and the identification of the one or more lesion correspondences, values of one or more metrics {e.g., one or more hotspot quantification metrics and/or changes therein [e.g., that quantify a change in properties, such as volume, radiopharmaceutical uptake, shape, etc. of individual hotspots and/or the underlying physical lesions that they represent (e.g., over time/between multiple medical images)]; e.g., patient indices (e.g., that that measure overall disease burden and/or state and/or risk for a subject) and/or changes thereof; e.g., values classifying a patient (e.g., as belonging to and/or having a particular disease state, progression, etc. category) e.g., prognostic metrics [e.g., indicative of and/or which quantify a likelihood of one or more clinical outcomes (e.g., a disease state, progression, likely survival, treatment efficacy, and the like) (e.g., overall survival); e.g., predictive metrics (e.g., indicative of a predicted response to therapy and/or other clinical outcome)}. 37. The method of claim 36, wherein the plurality of medical images comprise one or more anatomical images (e.g., CT, X-Ray, MRI, Ultrasound, etc.). 38. The method of any one of claims 36-37, wherein the plurality of medical images comprise one or more nuclear medicine images [e.g., bone scan (scintigraphy) (e.g., obtained following administration to the subject of a radiopharmaceutical, such as 99mTc-MDP), PET (e.g., obtained following administration to the subject of a radiopharmaceutical, such as [18F]DCFPyL, [68Ga]PSMA-11, [18F] PSMA-1007, rhPSMA-7.3 (18F), [18F]-JK-PSMA- 7, etc.), or SPECT (e.g., obtained following administration to the subject of a radiopharmaceutical, such as a 99mTc-labeled PSMA binding agent)]. 39. The method of any one of any one of claims 36-38, wherein the plurality of medical images comprise one or more composite images, each comprising an anatomical and a nuclear medicine pair (e.g., overlaid / co-registered with each other; e.g., having been acquired for the subject at a substantially same time) (e.g., one or more PET/CT images). 40. The method of any one of any one of claims 36-39, wherein the plurality of medical images are or comprises a time series of medical images, each medical image of the time series associated with and having been acquired at a different particular time. 41. The method of claim 40, where the time series of medical images comprises a first medical image acquired before administering (e.g., one or more cycles of) a particular therapeutic agent [e.g., a PSMA binding agent (e.g., PSMA-617; e.g., PSMA I&T); e.g., a radiopharmaceutical; e.g., a radionuclide-labeled PSMA binding agent (e.g., 177Lu-PSMA- 617; e.g., 177Lu-PSMA I&T)] to the subject and a second medical image acquired after administering (e.g., the one or more cycles of) the particular therapeutic agent to the subject. 42. The method of claim 41, comprising classifying the subject as a responder and/or a non-responder to the particular therapeutic agent based on the values of one or more metrics determined at step (d). 43. The method of any one of claims 36-42, wherein step (a) comprises generating each hotspot map by (e.g., automatically) segmenting at least a portion of the corresponding medical image (e.g., a sub-image thereof, such as a nuclear medicine image) (e.g., using a second, hotspot segmentation, machine learning module [e.g., wherein the hotspot segmentation machine module comprises a deep learning network (e.g., a Convolutional Neural Network (CNN))]). 44. The method of any one of claims 36-43, wherein each hotspot map comprises, for each of at least a portion of the hotspots identified therein, one or more labels identifying one or more assigned anatomical regions and/or lesion sub-types (e.g., a miTNM classification label). 45. The method of any one of claims 36-44, wherein : the plurality of hotspot maps comprises (i) a first hotspot map corresponding to a first medical image (e.g., and identifying a first set of one or more hotspots therein) and (ii) a second hotspot map corresponding to a second medical image (e.g., and identifying a second set of one or more hotspots therein); the plurality of 3D anatomical segmentation maps comprises (i) a first 3D anatomical segmentation map identifying the set of organ regions within the first medical image and (ii) a second 3D anatomical segmentation map identifying the set of organ regions within the second medical image; and step (c) comprises registering (i) the first hotspot map with (ii) the second hotspot map using the first 3D anatomical segmentation map and the second 3D anatomical segmentation map (e.g., to determine one or more registration fields (e.g., a full 3D registration field; e.g., a pointwise registration) using the set of organ regions and/or one or more subsets thereof as landmarks within the first and second 3D anatomical segmentation maps and using the one or more determined registration fields to co-register the first and second hotspot maps). 46. The method of any one of claims 36-45, wherein step (c) comprises : determining, for a group of two or more hotspots, each a member of a different hotspot map and identified within a different medical image, values of one or more lesion correspondence metrics (e.g., a volume overlap; e.g., a center of mass distance; e.g., a lesion type match); and determining the two or more hotspots of the group to represent a same particular underlying physical lesion based on the values of the one or more lesion correspondence metrics, thereby including the two or more hotspots of the group in one of the one or more lesion correspondences. 47. The method of any one of claims 36-46, wherein step (d) comprises determining one, two, or all three of (i), (ii), and (iii) as follows : (i) a change in the number of identified lesions (ii) a change in an overall volume of identified lesions (e.g., a change in the sum of the volumes of each identified lesion), and (iii) a change in PSMA (e.g., lesion index) weighted total volume (e.g., a sum of the products of lesion index and lesion volume for all lesions in a region of interest) [e.g., wherein the change identified in step (b) is used to identify (1) a disease status [e.g., progression, regression, or no change], (2) make a treatment management decision [e.g. active surveillance, prostatectomy, anti-androgen therapy, prednisone, radiation, radio-therapy, radio-PSMA therapy, or chemotherapy], or (3) treatment efficacy (e.g. wherein the subject has begun treatment or has continued treatment with a medicament or other therapy following an initial set of images in the time series of medical images)]. 48. The method of any one of claims 36-47, comprising determining (e.g., based on values of the one or more metrics; e.g., at step (d)) values of one or more prognostic metrics indicative of disease state/progression and/or treatment [e.g., determining an expected overall survival (OS) for the subject (e.g., a predicted number of months)]. 49. The method of any one claims 36-48, comprising using values of the one or more metrics (e.g., a change in tumor volume, SUV mean, SUV max, PSMA score, number of new lesions, number of disappeared lesions, total number of tracked lesions) as inputs to a prognostic model (e.g., a statistical model, such as a regression; e.g., a classification model, whereby a patient is assigned to a particular class based on a comparison of the one or more patient index values with one or more thresholds; e.g., a machine learning model, where the values of the one or more patient indices are received as input) that generates, as output, an expectation value and/or range (e.g., a class) indicative of a likely value of a particular patient outcome (e.g., a time, e.g., in number of months, representing an expected survival, time to progression, time to radiographic progression, etc.). 50. The method of any one claims 36-49, comprising using values of the one or more metrics (e.g., a change in tumor volume, SUV mean, SUV max, PSMA score, number of new lesions, number of disappeared lesions, total number of tracked lesions) as inputs to a response model (e.g., a statistical model, such as a regression; e.g., a classification model, whereby a patient is assigned to a particular class based on a comparison of the one or more patient index values with one or more thresholds; e.g., a machine learning model, where the values of the one or more patient indices are received as input) that generates, as output, a classification (e.g., a binary classification) indicative of a patient response to treatment. 51. The method of any one claims 36-50, comprising using values of the one or more metrics (e.g., a change in tumor volume, SUV mean, SUV max, PSMA score, number of new lesions, number of disappeared lesions, total number of tracked lesions) as inputs to a predictive model (e.g., a statistical model, such as a regression; e.g., a classification model, whereby a patient is assigned to a particular class based on a comparison of the one or more patient index values with one or more thresholds; e.g., a machine learning model, where the values of the one or more patient indices are received as input) that generates, as output, an eligibility score for each of one or more treatment options (e.g., Abiraterone, Enzalutamide, Apalutamide, Darolutamide, Sipuleucel-T, Ra223, Docetaxel, Carbazitaxel, Pembrolizumab, Olaparib, Rucaparib, 177Lu-PSMA-617, etc.) and/or classes of therapeutics [e.g., androgen biosynthesis inhibitors (e.g., Abiraterone), androgen receptor inhibitors (e.g., Enzalutamide, Apalutamide, Darolutamide), a cellular immunotherapy (e.g., Sipuleucel-T), internal radiotherapy treatment (Ra223), antineoplastics (e.g., Docetaxel, Carbazitaxel), immune checkpoint inhibitor (Pembrolizumab), PARP inhibitors (e.g., Olaparib, Rucaparib), PSMA binding agent], wherein the eligibility score for a particular treatment option and/or therapeutic class indicates a prediction of whether the patient will benefit from the particular treatment and/or therapeutic class. 52. A method for analyzing a plurality of medical images of a subject, the method comprising : (a) obtaining (e.g., receiving and/or accessing, and/or generating), by a processor of a computing device, a first 3D hotspot map for the subject; (b) obtaining (e.g., receiving and/or accessing, and/or generating), by the processor, a first 3D anatomical segmentation map associated with the first 3D hotspot map; (c) obtaining (e.g., receiving and/or accessing, and/or generating), by the processor, a second 3D hotspot map for the subject; (d) obtaining (e.g., receiving and/or accessing, and/or generating), by the processor, a second 3D anatomical segmentation map associated with the second 3D hotspot map; (e) determining, by the processor, a registration field (e.g., a full 3D registration field; e.g., a pointwise registration) using/based on the first 3D anatomical segmentation map and the second 3D anatomical segmentation map; (f) registering, by the processor, the first 3D hotspot map and the second 3D hotspot map, using the determined registration field, thereby generating a co-registered pair of 3D hotspot maps; (g) determining, by the processor, an identification one or more lesion correspondences using the co-registered pair of 3D hotspot maps; and (h) storing and/or providing, by the processor, the identification of the one or more lesion correspondences for display and/or further processing. 53. A method for analyzing a plurality of medical images of a subject (e.g., to evaluat……