+

WO2017106819A1 - Procédés et systèmes de représentation, de stockage et d'accès à des quantités dérivées d'imagerie médicale calculables - Google Patents

Procédés et systèmes de représentation, de stockage et d'accès à des quantités dérivées d'imagerie médicale calculables Download PDF

Info

Publication number
WO2017106819A1
WO2017106819A1 PCT/US2016/067463 US2016067463W WO2017106819A1 WO 2017106819 A1 WO2017106819 A1 WO 2017106819A1 US 2016067463 W US2016067463 W US 2016067463W WO 2017106819 A1 WO2017106819 A1 WO 2017106819A1
Authority
WO
WIPO (PCT)
Prior art keywords
imaging
data
case
queries
analysis
Prior art date
Application number
PCT/US2016/067463
Other languages
English (en)
Inventor
Andrew J. Buckler
Keith A. MOULTON
Mary Buckler
Lawrence Martell
David S. Paik
Xiaonan Ma
Samantha St. Pierre
Original Assignee
Elucid Bioimaging Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US15/237,249 external-priority patent/US10755810B2/en
Application filed by Elucid Bioimaging Inc. filed Critical Elucid Bioimaging Inc.
Publication of WO2017106819A1 publication Critical patent/WO2017106819A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies

Definitions

  • Imaging particularly with safe and non-invasive methods, represents the most powerful methods for locating the disease origin, capturing its detailed pathology, directing therapy, and monitoring progression to health. Imaging is also an extremely valuable and low cost method to mitigate human and financial costs by allowing for appropriate early interventions that are both less expensive and disruptive.
  • Quantitative imaging techniques are developed for use in the clinical care of patients and in the conduct of clinical trials. In clinical practice, quantitative imaging may be used to detect and characterize disease before, during, and after a course of therapy, and used to predict the course of disease.
  • Quantitative imaging assessment of phenotype implemented in an architecture which proactively optimizes interoperability with modern clinical IT systems provides power to the clinician as they manage their patients across the continuum of disease severity for improved patient classification across surgical, medical, and surveillance pathways. More timely and accurate assessments yield improved outcomes and more efficient use of health care resources, benefits that far outweigh the cost of the tool - at a level of granularity and sophistication closer to the complexity of the disease itself rather than holding the assumption that it can be simplified to a level which belies the underlying biology.
  • Ex vivo biomarkers e.g., genomic, proteomic, etc.
  • in vivo biomarkers e.g., imaging
  • biobanks e.g., Karolinska Institute Biobank, British Columbia BioLibrary
  • probes and tracers can also be banked.
  • the Radiotracer Clearinghouse has been developed to broker the sharing of Positron Emission Tomography (PET) and Single Positron Emission Computed Tomography radiotracers between stakeholders for in vivo biomarker research.
  • PET Positron Emission Tomography
  • various databases store information on ex vivo biomarkers (e.g., Early Detection Research Network Biomarker Database, Infectious Disease Biomarker Database).
  • information resources for in vivo biomarkers, specifically quantitative imaging biomarkers are notably lacking.
  • Quantitative imaging techniques also have potential applications in translational research.
  • quantitative imaging biomarkers are used to define endpoints of clinical trials.
  • Technology linking these levels through the analysis of quantitative imaging and non-imaging data, coupled with multi-scale modeling elucidates both pre-symptomatic and clinical disease processes.
  • few technologies facilitate bridging the two bodies of knowledge; at the molecular/cellular level and at the organism level.
  • the present invention is addressed to the problem of clinician data overload by enabling a new class of decision support informatics tools to within the realities of existing work flows.
  • the present invention provides information resources for in vivo biomarkers development and application to define endpoints of clinical trials which may be coupled with multi-scale modeling of both pre-symptomatic and clinical disease processes.
  • the invention supports statistical hypothesis testing to determine and present analytical performance, determine the clinical relevance and establish to what extent a biomarker reading is an intermediate endpoint capable of being measured prior to a definitive endpoint that is causally rather than coincidentally related.
  • the present invention provides a logical and mathematical framework to establish how extant study data may be used to establish performance in contexts that have not been explicitly tested.
  • the present invention relates the logical world of ontology development with the biostatistical analyses that characterize performance, enabling the extrapolation of statistical validation results along arbitrary ontology hierarchies, and enabling formal generalization of a validation activity.
  • the method of these teachings includes representing an identification scheme for individual cases comprising demographics, observations, findings, and other descriptive information, characterizing targets for image analysis to the one case to support tracking of a given anatomy, suspected pathology, confirmed pathology, or medical intervention at one or more timepoints, storing access information to one or more medical images of each target at each timepoint, storing one or more levels of image-derived analysis, the image-derived analysis comprising at least one of imaging features, measured quantities, phenotypic descriptions, or predictions relative to the one case, the one or more levels of image-derived analysis being obtained by: obtaining a group of medical images corresponding to the one case, calculating imaging features for the group of medical images, applying a machine learning trained method, possibly incorporating one or more non-imaging inputs, in
  • the method also includes providing semantic search ability to access any stored data item, individually or in sets, within or across cases, within or across studies, within or across groups, within or across targets, for imaging or non-imaging associated data, according to concepts in an ontology according to relationships, without requiring the queries to be defined beforehand, the data store hereinafter referred to as a knowledgebase.
  • the semantic search ability includes a component that traverses concepts in an ontology according to relationships
  • the method of these teachings further includes applying the component that traverses concepts in an ontology according to relationships, using an imaging ontology, in order to obtain a number of Resource Description Framework (RDF) triples; the number of RDF triples hereinafter referred to as a triple store.
  • RDF Resource Description Framework
  • Figure 1 is an overview schematic of the invention, comprising one or more compute services that perform various functions such as curation and processing connected by one or more integration adapter components to established healthcare IT systems and/or to one or more data services which contains the system of record database and exposes outputs in various forms including but not limited to DICOM SR, CDISC, HL7 CDA, and SPARQL endpoints;
  • Figure la shows a variety of computational applications for which the method of these teachings can be applied
  • Figure lb is an overall schematic of an example embodiment for obtaining the one or more levels of image-derived analysis
  • Figure lc shows an overall schematic of an example framework that allows efficient development of image-derived analysis tools while also setting up access to functionality needed for more complete statistical evaluation of performance and representation of results in a semantically-expressive knowledge representation;
  • Figure Id shows the central data abstractions including various views and representations of data, sometimes referred collectively or in parts to the "blackboard", or Biomarker Knowledge Base;
  • Figure le shows an overall schematic of an example embodiment for how data services are interfaced and implemented through a client-server model in example layers
  • Figure 1 g shows primary methods used by a client component in one embodiment of these teachings
  • Figure 2 summarizes functions supported by the invention for individual patient care. Imaging is increasingly used at all stages in the cycle of care for individual patients including applications that can predict the effectiveness of interventions based on patient-specific measurements, guide selection and administration of therapy, and monitor for utility and recurrence in follow-up protocols;
  • Figure 3 summarizes functions supported by the invention for drug development.
  • Applications of imaging in clinical trials and therapeutic development supports activities on the critical path of development and enable novel approaches that can be used to accelerate development programs and/or positively impact the effectiveness and financial performance of sponsor programs;
  • Figure 4 illustrates key questions the informatics services would address for putative biomarkers and tests that measure them;
  • Figure 5 is an overview schematic of the functions supported by the invention for biological research and/or methods validation, showing the heterogeneous inputs, curated reference data sets, high-throughput batch computing, and some of the outputs supported by the inventions query and inference capabilities;
  • Figure 6 shows interfaces of the method and system of these teachings to existing medical information structures
  • Figure 7 shows an exemplary ontology that may be used to tie quantitative imaging measurements to health conditions and disease processes as well as represent their technical and clinical performance together;
  • the left panel is a class hierarchy and the right panel are properties that define relationships between the classes;
  • Figure 8 shows an example interaction between a client and a server to support a patient report generation sequence
  • Figures 9a, 9b show exemplary relationships between encrypted and unencrypted data to support segregation of protected health information from data which may be accessed by surveillance or discovery applications;
  • Figures 10a, 10b shows principal classes with exemplary data and methods used in a patient encounter reporting application including longitudinal trend analysis
  • Figure 11 shows a subset of classes which may be stored within the graph database used to represent provenance of clinical readings.
  • Figure 12 shows an exemplary organization of performance metrics and extractions enabled by the invention, in this view seen as a summary of performance data processed in periodic runs based on running queries and performing analyses.
  • the Web Ontology Language is a family of knowledge representation languages for authoring ontologies; where ontologies are a formal way to describe taxonomies and classification networks.
  • Stardog is a semantic graph database, implemented in Java, that provides support for RDF and all OWL 2 profiles providing extensive reasoning capabilities and uses SPARQL as a query language.
  • Qt is a cross-platform application framework that is widely used for developing application software.
  • the method of these teachings includes representing an identification scheme for individual cases comprising demographics, observations, findings, and other descriptive information, characterizing targets for image analysis to the one case to support tracking of a given anatomy, suspected pathology, confirmed pathology, or medical intervention at one or more timepoints, storing access information to one or more medical images of each target at each timepoint, storing one or more levels of image-derived analysis, the image derived analysis comprising at least one of imaging features, measured quantities, phenotypic descriptions, or predictions relative to the one case, the one or more levels of image-derived analysis being obtained by: obtaining a group of medical images corresponding to the one case, calculating imaging features for the group of medical images, applying a trained method, incorporating one or more non-imaging inputs, in order to obtain quantitative properties, hereinafter referred to as analytes for the one case, and using the analytes to obtain a group of phenotypes for the one case.
  • the method also includes Providing semantic search ability to access any stored data item, individually or in sets, within or across cases, within or across Studies, within or across groups, within or across targets, for imaging or non-imaging associated data, according to concepts in an ontology according to relationships, without requiring the queries to be defined beforehand, the data store hereinafter referred to as a knowledgebase.
  • the semantic search ability includes a component that traverses concepts in an ontology according to relationships
  • the method of these teachings further includes applying the component that traverses concepts in an ontology according to relationships, using an imaging ontology, in order to obtain a number of Resource Description Framework (RDF) triples; the number of RDF triples hereinafter referred to as a triple store.
  • RDF Resource Description Framework
  • Image-derived information is made available by performing analyses with semantic annotations accessible using semantic web technology for personalized medicine and discovery science.
  • Figure la shows a variety of other computational applications for which the method of these teachings can be applied.
  • Figure lb is an overall schematic of an example embodiment for obtaining the one or more levels of image-derived analysis.
  • a schematic of an exemplary system 100 is depicted.
  • the exemplary system and exemplary embodiments are disclosed in U.S. Published Patent Application for U.S. Patent Application No. 14/959,732, which is incorporated by reference herein in its entirety and for all purposes.
  • the exemplary embodiments are referred to as computer aided phenotyping (CAP) systems.
  • CAP systems computer aided phenotyping
  • the exemplary embodiments are herein after referred to as CAP systems or, individually as imaged target- CAP (for example, when the imaged target is a vascular tissue, the exemplary embodiment is referred to as vascuCAP.
  • the analyzer module 120 advantageously implements a hierarchical analytics framework which first identifies and quantifies biological
  • properties/analytes 130 utilizing a combination of (i) imaging features 122 from one or more acquired images 121 A of a patient 50 and (ii) non-imaging input data 121B for a patient 50 and then identifies and characterizes one or more pathologies (e.g., prognostic phenotypes) 124 based on the quantified biological properties/analytes 123.
  • the analyzer module 120 may operate independent of ground truth or validation references by
  • pre-trained e.g., machine learned algorithms for drawing its inferences.
  • the analyzer may include algorithms for calculating imaging features 122 from the acquired images 121 A of the patient 50.
  • some of the image features 122 may be computed on a per- voxel basis while others may be computed on a region-of-interest basis.
  • Example non-imaging inputs 121B which may be utilized along with acquired images 121 A may include data from laboratory systems, patient-reported symptoms, or patient history.
  • the image features 122 and non-imaging inputs may be utilized by the analyzer module 120 to calculate the biological properties/analytes 123.
  • the biological properties/analytes are typically quantitative, objective properties (e.g., objectively verifiable rather than being stated as impression or appearances) that may represent e.g., a presence and degree of a marker (such as a chemical substance) or other measurements such as structure, size, or anatomic characteristics of region of interest.
  • the quantified biological properties/analytes 123 may be displayed or exported for direct consumption by the user, e.g., by a clinician, in addition to or independent of further processing by an analyzer module which operates by calculating imaging features, some of which are computed on a per- voxel basis and others on a region-of-interest basis.
  • non-imaging inputs which may be drawn from laboratory systems, patient-reported symptoms, or patient history for the calculation of one or more biological analytes, noted as quantitative, objective properties.
  • analyte best fits those properties that represent presence and degree of substances but for generality, this term may also apply to other measurements such as structure, size, or anatomic characteristics. What matters is that they are objectively verifiable rather than being stated as impression or appearances. They represent that which is, not how it may or may not appear.
  • These properties or analytes may be displayed or exported for direct consumption by the clinician and/.or they may be used in further processing steps.
  • Phenotypes are defined in a disease-specific manner independent of imaging, often being drawn from ex vivo pathophysiological samples for which there is documented relationship to outcome expected.
  • RDF or other graph database
  • the invention may further provide that outcome for the user or it may not.
  • the cohort tool module 130 enables defining a cohort of patients for group analyses thereof, e.g., based on a selected set of criteria related to the cohort study in question.
  • An example cohort analysis may be for a group of patients enrolled in a clinical trial, e.g., with the patient's further being grouped based on one or more arms of the trial for example a treatment vs. control arm.
  • Another type of cohort analysis may be for a set of subjects for which ground truth or references exist, and this type of cohort may be further decomposed into a training set or "development" set and a test or "holdout” set.
  • Development sets may be supported so as to train 112 the algorithms and models within analyzer module 120, and holdout sets may be supported so as to evaluate/validate 113 the performance of the algorithms or models within analyzer module 120.
  • the trainer module 110 may be utilized to train 112 the algorithms and models within analyzer module 120.
  • the trainer module 110 may rely on ground truth 111 and/or reference annotations 114 so as to derive weights or models, e.g., according to established machine learning paradigms or by informing algorithm developers.
  • classification and regression models are employed which may be highly adaptable, e.g., capable of uncovering complex relationships among the predictors and the response.
  • their ability to adapt to the underlying structure within the existing data can enable the models to find patterns that are not reproducible for another sample of subjects.
  • Adapting to irreproducible structures within the existing data is commonly known as model over-fitting. To avoid building an over-fit model, a systematic approach may be applied that prevents a model from finding spurious structure and enable the end-user to have confidence that the final model will predict new samples with a similar degree of accuracy on the set of data for which the model was evaluated.
  • the primary function is to represent various imaging-derived information.
  • examples of these data further disclosed in U.S. Published Patent Application for U.S. Patent Application No. 14/959,732, include the following features.
  • Structural measurements have long been and remain the single most used measurements in patient care.
  • the category is broad and the measurements are of objects of varying sizes, so generalizations should be made with care.
  • Tissue Characteristics The quantitative assessment of the individual constituent tissue components, by way of example for atherosclerotic plaques including lipid rich necrotic core (LRNC), fibrosis, intraplaque hemorrhage, permeability, and calcification, can provide crucial information concerning the relative structural integrity of the plaque that could aid the physician's decisions on course of medical or surgical therapy. From the imaging technology point of view, the ability to do this lies less with spatial resolution as with contrast resolution and tissue discrimination made possible by differing tissues responding to incident energy differently so as to produce a differing receive signal.
  • LRNC lipid rich necrotic core
  • fibrosis fibrosis
  • intraplaque hemorrhage intraplaque hemorrhage
  • permeability permeability
  • Each imaging modality does this to some extent; terms in ultrasound such as “echolucency”, the CT number in Hounsfield Units, and differentiated MR intensities as a function of various sequences such as (but not limited to) Tl, T2 and T2*.
  • Dynamic tissue behavior (e.g., Permeability): In addition to morphological features, there is increasing recognition that dynamic features are valuable quantitative indicators of pathology. Dynamic sequences where the acquisition is taken at multiple closely-spaced times (known as phases) expand the repertoire beyond spatially-resolved values t include temporally-resolved values which may be used for compartment modeling or other techniques to determine the tissues' dynamic response to stimulus (such as but not limited to wash-in and wash-out of contrast agent).
  • dynamic contrast enhanced imaging with ultrasound or MR e.g., in the carotid arteries or delayed contrast enhancement (e.g., in the coronary arteries)
  • sensitive assessments of the relative permeability e.g., K trans and V p parameters from kinetic analysis
  • these dynamic series can also aid in the differentiation between increased permeability versus other compartment modeling scenarios, e.g., intraplaque hemorrhage.
  • Hemodynamics The basic hemodynamic parameters of the circulation have a direct effect on many pathologies.
  • Blood pressures, blood flow velocity, fractional flow reserve (FFR) and vessel wall shear stress may be measured by techniques ranging from very simple oscillometry to sophisticated imaging analysis. Using common principles of fluid dynamics, calculations of shear stress can be ascertained for different regions. In addition, the effects of antihypertensive drugs on hemodynamics have been followed for short and long-term studies.
  • the central data stored are represented in the Knowledge Base, which follows a "blackboard" design pattern and is, in one embodiment, implemented as an RDF Triple Store.
  • the data organization of this embodiment flows from the hierarchy of requirements and specifies three primary types of database assets.
  • the Clinical user products deploy an RDF triplestore, implemented by a data unification platform leveraging smart graph technology, for example, Stardog, and which may be deployed as "localhost” or on another server, and used to store triples representing quantitative results data.
  • the Research user product augments the triplestore with metadata used for determining the similarity of the patient case with similar cases drawn from a cohort with imported data from systems which provide portals made available to collaborators for the collection of source study data.
  • the "blackboard" design pattern is implemented in a draft database or in a relational database.
  • Figure Id shows the central data abstraction referred to as the "blackboard”, also known as the Biomarker Knowledge Base.
  • Meta-data facilitating analysis of cases in reference data sets (intended to be
  • the knowledgebase is implemented as an RDF Triple Store. It links data across the data services using handles or universal resource identifiers (URIs).
  • URIs universal resource identifiers
  • Figure le shows how data services are interfaced through and implemented through a client-server model in example layers.
  • the mappings may be placed in the same graph or distributed across separate named graphs for each ontology which may be optimized with respect to the overhead of inference being scoped in such a way that a given query or operation is scoped to specific graphs rather than always being all graphs.
  • the semantic search ability includes a component that traverses concepts in an ontology such as given in Figure 7 according to relationships, and the method of these teachings further includes applying the component that traverses concepts in an ontology according to relationships, using an imaging ontology, in order to obtain a number of Resource Description Framework (RDF) triples; the number of RDF triples hereinafter referred to as a triple store.
  • RDF Resource Description Framework
  • the method also includes accessing predetermined data services, generating queries from the plurality of RDF triples in order to collect data sets, and using the queries and the predetermined data services to collect data sets.
  • Figure If shows an information flow schematic organized using four layers as depicted in Figure lc. Three of those layers provide high-level to low-level functionality. The functionality layers from highest to lowest are; Application, Analytics, and Data. Clinical Users and System Administrators interact with features in the Application layer. Components in the Application layer interact with the Analytics layer. Components in the Analytics layer interact with the Data layer. The fourth layer, shown vertically, represents programming interfaces used by researchers and Clinical Developers. Those interfaces provide programmatic access to the three vertical layers.
  • Stakeholders of this view include System Developers, System Administrators, Clinical Users, Support Technicians, with Scalability, Performance, Interoperability, Extensibility concerns.
  • the invention can be deployed in two main
  • vascuCAP is deployed on a HIPAA compliant data center. Clients access that API server over a secure HTTP connection. Clients can be desktop or tablet browsers. No hardware except for the computers running the web browsers is deployed on the customer site.
  • the deployed server may be on a public cloud or an extension of the customer's private network using a VPN. Stakeholders of this view include System Administrators, Support Technicians, which have Interoperability, Security, Failover & Disaster Recovery, Regulatory concerns.
  • these teachings comprise a client and a server.
  • the client is a C++ application and the server is a Python application.
  • These components interact using HTML 5.0, CSS 5.0 and JavaScript. Wherever possible open standards may be used for interfaces including but not limited to; HTTP(S), REST, DICOM, SPARQL, and JSON. 3 rd party libraries are also used as depicted in Figure le which shows the primary pieces of the technology stack.
  • phenotypic information may be derived using predictive models.
  • client software is implemented as an application using Qt GUI primitives. It operates according to the following flow:
  • the User creates a Workitem by loading DICOM Study and Patient Information using Workitem Generation screen
  • the user can view or search for workitems using Workitem View screen
  • the User selects/edits image series to identify the target(s) for analysis
  • the User identifies the target(s) for analysis, setting proximal and distal path
  • the User can edit/modify various settings to conclude on the calculation values they deem most appropriate for the case
  • the User may select image snapshots for insertion into the report 7.
  • the User reviews then accepts the report,
  • the user can export the Report
  • Primary Application Control establishes framework for concurrent, multi-patient, analysis and reporting sessions using one or more of the following classes:
  • class sessionltem to provide a data structure for recording analyses within the session
  • class StatusWatcher to echo stdout and a processed version of stderr to the status bar (in addition to being written to the log files), class cap
  • class capTools provides common basis for tool bars as exist across modules.
  • a Work Item Package supports abstractions for work items, as containers for artifacts pertaining to patient analyses, and lists of them using one or more of the following classes:
  • class workltem the main class with the list as a whole and the methods to display and interact with it.
  • a Series Survey Package may provide functionality associated with importing, reviewing, specification, and switching across sets of image series processed within a work item using one or more of the following classes:
  • class seriesSurvey in namepace Ui
  • QWidget the main class with the series set as a whole and the methods to display and interact with it.
  • a Target Definition Package may provide functionality associated with defining, importing, reviewing, specification, and switching across analysis targets processed within a work item using one or more of the following classes:
  • class processingParameters provides functionality for user review and selection of processing parameters associateed with analysis of targets
  • class valueMap represents individual value maps, for example, wall thickness class targetDef
  • class targetDefine in namepace Ui
  • QWidget the main class with the list of definitions as a whole and the methods to access and interact with it.
  • a Patient Analyze Package may serve as a central point of user activity to analyze a patient at a given timepoint using one or more of the following classes:
  • • class readingsSelector provides functionality for user selection and specification for readings associateed with analysis of targets • class patient Analyze (in namepace Ui) (subclassed from Q Widget): the main class with the list of definitions as a whole and the methods to access and interact with it. Manages all computation and display aspects analyses comprising multiple targets and multiple image series for a given workltem session.
  • a Patient Reporting Package may allow users to compose and prepare of analysis result exports and reports using one or more of the following classes:
  • class patientReport in namepace Ui
  • Q Widget the main class with the list of definitions as a whole and the methods to access and interact with it. Supports fucntionality to transfer appropriate data and interact with server for reporting functions.
  • server software is implemented comprised of the following components:
  • core identifiers are stored and accessed with encryption in, for example, mysql, with “detailed” but non-identifiable information stored in, for example, Stardog.
  • a client application performs image processing etc. to make report content. It then securely packages this data and transitions to the server-side reporting application, obtaining an ID used in subsequent steps.
  • the server catches the http multipart, stores the issued report instance, potentially logs a billing item ID to charge against, and return the report ID to the client which will be used to host the viewing/editing session as well as provide continuity for maintaining versions and provenance.
  • Figures 9a, 9b depict how individual identity of patients is protected and segregated from quantitative information in such a way that relationships to specific patients are available for clinical care by clinicians with access rights but not otherwise, however, enabling use of the data for research purposes provided adequate consent is in place using institutionally-approved processes for data access to anonymized data.
  • the view session draws from data as depicted in Figures 10a, 10b and 11 for report composition, and the data depicted in Figure 12 is available on request to substantiate the results and document provenance.
  • the view session has the facility to trap an export signal and store the returned PDF, DICOM S/R, HL7 CD A, or other formatted result to disk or transfer to EMR.
  • the server may also support a function to compose a list of applicable reports based on a user identity from a browser Query the reports that are available for the institution(s) with which the user has a relationship, allowing selection which uses ID.
  • All functions are password protected, transfers of protected health information are encrypted, and users may have 1 or more institutional affiliations for billing purposes and in filtering report listings.
  • a client workstation initiates a report generation sequence by sending an HTTP multipart form POST to the API endpoint (using Qt HTTP multipart class http://doc.qt.io/qt-4.8/qhttpmultipart.htmI)
  • To Launch the Report Generator UI Redirect a browser (or Qts browser widget) to
  • contests of the POST are a JSON document with any cross-section identifiers that should be selected by default.
  • This method returns the HTML report. To return a PDF formatted version of the report
  • the Compare Multiple Timepoints function is to track target lesions over time.
  • the Reporting application may use the triplestore to retrieve information across multiple encounters, and thereby enable a longitudinal trend analysis of given identified lesions or targets, as well as summary measures for the patient as a whole.
  • Cohort Tool The purpose of Cohort Tool is to aggregate evidence across cohorts for research purposes, whether by a user for their research or to characterize performance of a CAP system relative to its intended uses. Specifically, the Cohort Tool is developed to allow users to:
  • Cohort Tool There are two fundamental reasons for Cohort Tool: first, it can be used to validate to validate CAP systems for regulatory purposes, and also, users use it for their own research purposes. Regulatory approval for clinical use and regulatory qualification for research use depend on demonstrating proof of performance relative to the intended application of the biomarker: In one embodiment, triples are used in the Cohort Tool.
  • the semantic search ability component is the "Specify" component described in Andrew J. Buckler, et al., A Novel Knowledge Representation Framework for the Statistical Validation of Quantitative Imaging Biomarkers, J Digit Imaging (2013) 26:614-629, which is incorporated by reference herein in its entirety and for all purposes.
  • Specify is a web-based component and helps a user to traverse concepts in the ontology according to their relationships to create statements represented as Resource Description Framework (RDF) triples, and to store them in an RDF store.
  • RDF Resource Description Framework
  • An exemplary component for accessing predetermined data services, generating queries from the plurality of RDF triples in order to collect data sets, and using the queries and the predetermined data services to collect data sets is the "Formulate" component in Andrew J. Buckler, et al., A Novel Knowledge Representation Framework for the Statistical Validation of Quantitative Imaging Biomarkers, J Digit Imaging (2013) 26:614-629
  • Formulate traverses the graph defined by the triples to a root-target entity (e.g. CTImage)— and leverages the nodes traversed to construct criteria for the query. These queries are sent to services providing the target entities.
  • Formulate is defined as an implementation of the following behavioral model.
  • Data retrieved by Formulate or otherwise directly obtained is organized according to a set of conventions that draws from the popular ISA-Tab model.
  • an ISA-Tab "like" convention is adopted. Investigation, Study, and Assay are the three key entities around which the ISA-Tab framework is built; these assist in structuring metadata and describing the relationship of samples to data.”
  • scripted programs written in, for example, Python may build and use information in the knowledgebase, for example, using scripted operations called process_ground_truth can provide capability to Record Annotations and/or Phenotypes from Histology and/or Other Truth References:
  • a scripted operation called process workitem list can provide capability to execute quantitative imaging computations and/or harvest observations from them across large collections:
  • a scripted operation called make_ranges can provide capability to draw from knowledgebase to create lists of cases matching similarity criteria:
  • One use case enabled by the invention is to compute the technical performance of a diagnostic measurement made by quantitative imaging applications such as those depicted in Figure 13. That use case is implemented as follows.
  • a target is one or more vessels - like the Carotid Arteries. Some targets are pre-selected to be part of a performance evaluation group.
  • An exemplary reading for a target in the vascuCAP_CT_Development Reference Dataset group is presented herein below:
  • BodySite LeftlnternalCarotid Artery
  • Performers of the readings may be computation algorithms (like vascuCAP) or may be human performers. One of the performers is specified to be the system under test (vascuCAP in this example) while other performers are specified to the reference or ground truth for the reading. These readings are stored in an instance of an RDF (a.k.a. graph) database product.
  • RDF a.k.a. graph
  • a user can request the group resource of a group using its human-readable
  • a user uses a REST API to request the computation of performance of the returned group resource.
  • the server uses SPARQL to query for all Targets in the user specified group - like the VascuCAP CT Development Reference Dataset group.
  • the triplestore knowledgebase itself is used to discover what readings exist and may also hold look-up tables to set a more specific scope of analysis.
  • lookup performance standards for the reading may be specified as the performance of a reference system (like a predicate device).
  • the JSON file returned is transformed into an HTML report (a.k.a. Dashboard) and displayed to the user.
  • process_technical_performance may provide capability to discover relationship among observations in knowledgebase and compute analytic performance metrics based on them: # for each of cutA and cutB
  • a scripted operation called optimize_settings can provide capability to combine process_workitem_list and process_technical_performance so as to evaluate the relative performance of differing settings for the purpose of optimizing the defaults for those settings on new cases:
  • override_list in enumerate(override lists):
  • FIG. 8 See Figure 8 for an example means organizing of tracking performance over time in a folder structure, or a "dashboard" display may be used to make this data available to web browsers.
  • Patient outcomes can be categorically assessed events at specific time points, such as the type of response at the end of a course of therapy, or whether the patient is alive at 1 year.
  • patient outcomes can be defined as time-to-event, such as progression-free- survival (PFS) or overall survival (OS).
  • PFS progression-free- survival
  • OS overall survival
  • the prediction problem will be approached from two complementary but distinct perspectives. They lead to two types of information, both of which are important in the evaluation of imaging as predictor such as the data depicted in Figures 9a through 11 when correlated with outcome data for the patients individually and using the cohort representation scheme, and the information made available as depicted in Figure 12 provides necessary statistical validation results for interpreting the uncertainty and measurement error as it exists in the inputs.
  • a first perspective is the evaluation of the positive and negative predictive value of a test.
  • biomarker values are used to classify patients as “responders” or “non-responders” by imaging, and rates of response or time-to-event data (e.g., PFS, OS) are compared between these groups of patients.
  • rates of response or time-to-event data e.g., PFS, OS
  • a second perspective is when the goal of the biomarker is, for example, to predict survival.
  • Table 1 Frequency of each plaque type for the original data.
  • pre-processing steps may be taken prior to building predictive models.
  • near zero variance predictors were removed.
  • a near-zero variance predictor is defined as having few unique values relative to the number of samples and a high imbalance in the frequency of the values. Based on this definition, near-zero variance predictors contain very little information.
  • highly correlated predictors were removed. In this analysis, any predictor with a pairwise correlation greater than 0.9 with another predictor is identified. When two predictors are identified as being highly correlated, the predictor with the highest average correlation with the other predictors is removed. Details about how these pre- processing steps affected each predictor set are provided in the analysis section of each predictor set.
  • Recursive Partitioning Recursive partitioning
  • RPart Recursive Partitioning Recursive partitioning
  • the tuning parameter for the version of RPart used in these analyses is the depth of the tree.
  • RPart models are highly interpretable, but are unstable.
  • Random Forests Random forests is a tree-based method built on an ensemble of trees. An RF model does the following process many times: selects a bootstrap sample of the training set and builds a tree on the bootstrap sample. Within each tree, a randomly selected number of predictors is chosen and the optimal split is selected only from that sample.
  • the tuning parameter for RF is the number of randomly selected predictors for each split. Building an ensemble of trees in this way reduces the variance seen by using just a single tree. RF predictions are more accurate and stable, but are not interpretable as compared to a recursive partitioning tree.
  • the assessment framework for predictive markers stems from the accepted definition of a surrogate marker as being a measure which can substitute for a more difficult, distant, or expensive-to-measure endpoint in predicting the effect of a treatment or therapy in a clinical trial.
  • Definitions of surrogacy revolve around the elucidation of the joint and conditional distributions of the desired endpoint, putative surrogate and their dependence on a specified therapy. Therefore, what may work adequately for a given endpoint and one type of therapy may not be adequate for the same endpoint and a different type of therapy.
  • Disease screening calls for a prognostic marker where it is neither necessary nor possible to anticipate all the potential therapies for which a surrogate marker might be desired.
  • biomarkers are on the causal pathway to the symptomatic disease and its clinical outcomes and can function as surrogate markers for at least one element of disease.
  • Storage and representation of the data as described herein allows correlation of changes within a person over time between different elements of disease including different measures of structural change.
  • Putative biomarkers must have adequate precision for estimating the joint relationship between proposed biomarkers and desired endpoints.
  • the present invention makes it possible to identify a number of promising biomarkers for use in early development of treatments and that can be tested in trials as surrogates for treatment effects.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computational Linguistics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

L'invention concerne des procédés et des systèmes destinés à rendre des informations dérivées d'images disponibles en effectuant des analyses avec annotations sémantiques accessibles en utilisant une technologie Web sémantique pour médecine personnalisée et découverte scientifique. Des cas individuels sont identifiés conformément à un schéma d'identification. Les cibles pour l'analyse d'image pour chaque cas sont caractérisées en vue de prendre en charge le suivi d'une anatomie données, d'une pathologie soupçonnée, d'une pathologie confirmée ou d'une intervention médicale à un ou plusieurs moments dans le temps. Des informations d'accès à une ou plusieurs images médicales de chaque cible à chacun desdits moments dans le temps sont produites et stockées. Un ou plusieurs niveaux d'analyse dérivée d'images sont obtenus et stockés. L'analyse dérivée d'images comprend au moins l'un des éléments suivants : des caractéristiques d'imagerie, des quantités mesurées, des descriptions phénotypiques ou des prédictions concernant ledit cas. Une capacité de recherche sémantique accède au niveau des éléments de données stockés, pour des données associées d'imagerie ou non d'imagerie, selon des concepts dans une ontologie conformément à des relations, sans qu'il soit nécessaire de définir des interrogations à l'avance. Des interrogations de la base de connaissances sont formées en accédant à des services de données prédéterminée en vue de collecter des ensembles de données. Les ensembles de données peuvent être utilisés pour tester une hypothèse, l'hypothèse se rapportant à la prise en charge du suivi de l'anatomie donnée, de la pathologie soupçonnée, de la pathologie confirmée ou de l'intervention médicale.
PCT/US2016/067463 2015-12-18 2016-12-19 Procédés et systèmes de représentation, de stockage et d'accès à des quantités dérivées d'imagerie médicale calculables WO2017106819A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201562269473P 2015-12-18 2015-12-18
US62/269,473 2015-12-18
US15/237,249 2016-08-15
US15/237,249 US10755810B2 (en) 2015-08-14 2016-08-15 Methods and systems for representing, storing, and accessing computable medical imaging-derived quantities

Publications (1)

Publication Number Publication Date
WO2017106819A1 true WO2017106819A1 (fr) 2017-06-22

Family

ID=59057755

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2016/067463 WO2017106819A1 (fr) 2015-12-18 2016-12-19 Procédés et systèmes de représentation, de stockage et d'accès à des quantités dérivées d'imagerie médicale calculables

Country Status (1)

Country Link
WO (1) WO2017106819A1 (fr)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10813612B2 (en) 2019-01-25 2020-10-27 Cleerly, Inc. Systems and method of characterizing high risk plaques
US11094060B1 (en) 2020-01-07 2021-08-17 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11210786B2 (en) 2020-01-07 2021-12-28 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
CN114255462A (zh) * 2020-09-22 2022-03-29 西门子医疗有限公司 用于分析组织病理学图像数据的方法和设备
US11861833B2 (en) 2020-01-07 2024-01-02 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11922627B2 (en) 2022-03-10 2024-03-05 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination
US12144669B2 (en) 2022-03-10 2024-11-19 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination
US12299885B2 (en) 2023-12-06 2025-05-13 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6108635A (en) * 1996-05-22 2000-08-22 Interleukin Genetics, Inc. Integrated disease information system
US20070130206A1 (en) * 2005-08-05 2007-06-07 Siemens Corporate Research Inc System and Method For Integrating Heterogeneous Biomedical Information
US20100070448A1 (en) * 2002-06-24 2010-03-18 Nosa Omoigui System and method for knowledge retrieval, management, delivery and presentation
US20150154275A1 (en) * 2012-12-18 2015-06-04 Sap Se Data Warehouse Queries Using SPARQL

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6108635A (en) * 1996-05-22 2000-08-22 Interleukin Genetics, Inc. Integrated disease information system
US20100070448A1 (en) * 2002-06-24 2010-03-18 Nosa Omoigui System and method for knowledge retrieval, management, delivery and presentation
US20070130206A1 (en) * 2005-08-05 2007-06-07 Siemens Corporate Research Inc System and Method For Integrating Heterogeneous Biomedical Information
US20150154275A1 (en) * 2012-12-18 2015-06-04 Sap Se Data Warehouse Queries Using SPARQL

Cited By (56)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11317883B2 (en) 2019-01-25 2022-05-03 Cleerly, Inc. Systems and methods of characterizing high risk plaques
US11759161B2 (en) 2019-01-25 2023-09-19 Cleerly, Inc. Systems and methods of characterizing high risk plaques
US11751831B2 (en) 2019-01-25 2023-09-12 Cleerly, Inc. Systems and methods for characterizing high risk plaques
US10813612B2 (en) 2019-01-25 2020-10-27 Cleerly, Inc. Systems and method of characterizing high risk plaques
US11642092B1 (en) 2019-01-25 2023-05-09 Cleerly, Inc. Systems and methods for characterizing high risk plaques
US11350899B2 (en) 2019-01-25 2022-06-07 Cleerly, Inc. Systems and methods for characterizing high risk plaques
US11730437B2 (en) 2020-01-07 2023-08-22 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12141976B2 (en) 2020-01-07 2024-11-12 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11232564B2 (en) 2020-01-07 2022-01-25 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11238587B2 (en) 2020-01-07 2022-02-01 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11244451B1 (en) 2020-01-07 2022-02-08 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11276170B2 (en) 2020-01-07 2022-03-15 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12283046B2 (en) 2020-01-07 2025-04-22 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11288799B2 (en) 2020-01-07 2022-03-29 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11302002B2 (en) 2020-01-07 2022-04-12 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11302001B2 (en) 2020-01-07 2022-04-12 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11308617B2 (en) 2020-01-07 2022-04-19 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11315247B2 (en) 2020-01-07 2022-04-26 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11321840B2 (en) 2020-01-07 2022-05-03 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11132796B2 (en) 2020-01-07 2021-09-28 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11341644B2 (en) 2020-01-07 2022-05-24 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11120549B2 (en) 2020-01-07 2021-09-14 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11367190B2 (en) 2020-01-07 2022-06-21 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11501436B2 (en) 2020-01-07 2022-11-15 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11120550B2 (en) 2020-01-07 2021-09-14 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11660058B2 (en) 2020-01-07 2023-05-30 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11672497B2 (en) 2020-01-07 2023-06-13 Cleerly. Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11690586B2 (en) 2020-01-07 2023-07-04 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11113811B2 (en) 2020-01-07 2021-09-07 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11737718B2 (en) 2020-01-07 2023-08-29 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11210786B2 (en) 2020-01-07 2021-12-28 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11751830B2 (en) 2020-01-07 2023-09-12 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11751826B2 (en) 2020-01-07 2023-09-12 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11751829B2 (en) 2020-01-07 2023-09-12 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11094060B1 (en) 2020-01-07 2021-08-17 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11766229B2 (en) 2020-01-07 2023-09-26 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11766230B2 (en) 2020-01-07 2023-09-26 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11779292B2 (en) 2020-01-07 2023-10-10 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11832982B2 (en) 2020-01-07 2023-12-05 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11861833B2 (en) 2020-01-07 2024-01-02 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11896415B2 (en) 2020-01-07 2024-02-13 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12245882B2 (en) 2020-01-07 2025-03-11 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12178627B2 (en) 2020-01-07 2024-12-31 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11967078B2 (en) 2020-01-07 2024-04-23 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11969280B2 (en) 2020-01-07 2024-04-30 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12023190B2 (en) 2020-01-07 2024-07-02 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12076175B2 (en) 2020-01-07 2024-09-03 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12097063B2 (en) 2020-01-07 2024-09-24 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US11094061B1 (en) 2020-01-07 2021-08-17 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12171606B2 (en) 2020-01-07 2024-12-24 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
US12156759B2 (en) 2020-01-07 2024-12-03 Cleerly, Inc. Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
CN114255462A (zh) * 2020-09-22 2022-03-29 西门子医疗有限公司 用于分析组织病理学图像数据的方法和设备
US12144669B2 (en) 2022-03-10 2024-11-19 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination
US11948301B2 (en) 2022-03-10 2024-04-02 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination
US11922627B2 (en) 2022-03-10 2024-03-05 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination
US12299885B2 (en) 2023-12-06 2025-05-13 Cleerly, Inc. Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination

Similar Documents

Publication Publication Date Title
US10755810B2 (en) Methods and systems for representing, storing, and accessing computable medical imaging-derived quantities
Band et al. Application of explainable artificial intelligence in medical health: A systematic review of interpretability methods
Zou et al. A review of uncertainty estimation and its application in medical imaging
Montagnon et al. Deep learning workflow in radiology: a primer
Reyes et al. On the interpretability of artificial intelligence in radiology: challenges and opportunities
Alonso-Betanzos et al. Big-data analysis, cluster analysis, and machine-learning approaches
Pezoulas et al. Synthetic data generation methods in healthcare: A review on open-source tools and methods
Kansagra et al. Big data and the future of radiology informatics
WO2017106819A1 (fr) Procédés et systèmes de représentation, de stockage et d'accès à des quantités dérivées d'imagerie médicale calculables
US12079208B2 (en) Data processing method, apparatus, and device
Singh et al. Artificial intelligence for cardiovascular disease risk assessment in personalised framework: a scoping review
Parimbelli et al. A review of AI and Data Science support for cancer management
Schlesinger et al. Deep learning for cardiovascular risk stratification
Velu et al. Data mining in predicting liver patients using classification model
Kumar et al. Deep-learning-enabled multimodal data fusion for lung disease classification
Petmezas et al. Recent advancements and applications of deep learning in heart failure: Α systematic review
Samaras et al. Classification models for assessing coronary artery disease instances using clinical and biometric data: an explainable man-in-the-loop approach
Zhou et al. A comprehensive review of deep learning-based models for heart disease prediction
Papandrianos et al. AI-based classification algorithms in SPECT myocardial perfusion imaging for cardiovascular diagnosis: a review
Valsaraj et al. Development and validation of echocardiography-based machine-learning models to predict mortality
Nazirun et al. Prediction Models for Type 2 Diabetes Progression: A Systematic Review
Amiri Leveraging AI-Enabled Information Systems for Healthcare Management
Chen et al. Application of artificial intelligence to clinical practice in inflammatory bowel disease–what the clinician needs to know
Seneviratne et al. Semantically enabling clinical decision support recommendations
Cicek et al. Machine learning for prognostic prediction in coronary artery disease with SPECT data: a systematic review and meta-analysis

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16876894

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16876894

Country of ref document: EP

Kind code of ref document: A1

点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载