Predicting Metastatic Progression of High Risk Localized Prostate Cancer
Project Number1I01CX002622-01
Contact PI/Project LeaderRETTIG, MATTHEW B Other PIs
Awardee OrganizationVA GREATER LOS ANGELES HEALTHCARE SYSTEM
Description
Abstract Text
ABSTRACT.
Prostate cancer (CaP) is the most commonly diagnosed malignancy other than non-melanoma skin cancer
amongst Veterans. Approximately 7% of US CaP cases are diagnosed and treated in the Veteran population.
High risk (HR), localized CaP represents 20-25% of the approximately 250,000 new cases of CaP expected in
the US in 2022. The outcomes of HR CaP are variable, with some patients remaining in remission and others
suffering from metastatic progression and death. Our ability to discriminate between patients who will fare well
following curative-intent treatment versus those destined for lethal metastatic progression remains poor. Our
overall objective is to apply artificial intelligence (AI) algorithms to generate novel predictors of metastasis-free
survival (MFS), the only validated surrogate for overall survival in localized CaP, from a large repository of digital
pathology and radiographic images. We will then combine these AI-derived biomarkers with clinical-pathologic
and social determinants of health (SDoH) variables collected from Veterans with HR CaP to develop and test
multivariable prognostic models that improve our ability to predict MFS.
AI, including computer vision and machine learning approaches, allows extraction of image patterns for sub-
visual based characterization of CaP. Routine diagnostic prostate needle biopsy pathology slides that have been
digitized as well as digital radiographic images (e.g. MRI) can be leveraged for machine learning derived from
either (1) hand-crafted features (guided by existing domain knowledge) which are then used as the inputs to
develop the machine-learning model based on the selected features, or (2) the raw data itself, which are used
as inputs to develop the model through convolutional neural networks or other methods in an unsupervised
manner. The former leverages existing domain knowledge and may require less input data, whereas the latter
is not limited by prior knowledge, but requires more training data. We hypothesize that machine learning models
based on multimodal data derived from MRI and digital pathology can be combined with clinic-pathologic and
SDoH data to generate “super classifiers” that more accurately predict outcome without the need for costly tissue
destructive methods.
We propose to establish a collection of digital pathology and prostate MRI images along with clinic-pathologic
and SDoH data from >5,000 Veterans with HR CaP who have been treated with curative intent and a minimum
of 5 years of follow-up using our existing approved biorepository protocol. Subsequently, we will determine the
most robust AI algorithm for each data source, and then test combinations of algorithms to generate a
“superclassifier” that integrates AI-derived predictive models with standard clinico-pathologic and SDoH
variables to predict MFS. Improved prognostication could illuminate strategies for treatment intensification or de-
intensification that can be formally tested in future clinical trials. The substantial infrastructure and databases
generated by this proposal as part of our repository will be accessible by intramural VA and extramural
investigators for future approved studies.
Public Health Relevance Statement
NARRATIVE.
Most Veterans are diagnosed with prostate cancer when the disease is confined to the prostate and amenable
to cure. However, a significant proportion of localized tumors display aggressive features associated with a
high risk of recurrence following definitive treatment (e.g. surgery or radiation). Our ability to predict which
patients with high-risk prostate cancer will develop lethal metastasis is limited. We will leverage the VA
healthcare system and assemble a massive dataset of digital images from diagnostic prostate biopsies and
magnetic resonance imaging linked to standard clinico-pathologic factors and social determinants of health
variables. Application of artificial intelligence (AI) approaches and integration of digital biomarkers with other
variables will yield a “superclassifier” to quantify the likelihood of metastasis-free survival and determine
treatment intensification interventions to reduce metastasis.
NIH Spending Category
No NIH Spending Category available.
Project Terms
AlgorithmsArtificial IntelligenceBiological MarkersCategoriesCessation of lifeClinicClinicalClinical DataClinical ManagementClinical TrialsCollectionComplexComputer Vision SystemsDataData CollectionData SetData SourcesDatabasesDevelopmentDiagnosisDiagnosticDiagnostic ImagingDigital RadiographyDigital biomarkerDiseaseDisease remissionExtramural ActivitiesEyeFOLH1 geneFutureGenomicsGoalsGuidelinesHealthcare SystemsHematoxylin and Eosin Staining MethodHistopathologyHumanImageIndividualInformation SystemsInfrastructureIntegrated Health Care SystemsInterventionKnowledgeLinkMachine LearningMagnetic Resonance ImagingMalignant NeoplasmsMalignant neoplasm of prostateMethodsModelingMolecularNational Comprehensive Cancer NetworkNeedle biopsy procedureNeoplasm MetastasisOperative Surgical ProceduresOutcomePathologicPathologyPatientsPatternPositron-Emission TomographyProstateProtocols documentationRadiationRecurrenceResearch PersonnelRiskScienceSkin CarcinomaSlideStagingStainsStatistical Data InterpretationStratificationStructureTestingTissuesTrainingUnited States Department of Veterans AffairsValidationVeteransVeterans Health AdministrationVisualartificial intelligence algorithmbiobankcancer careconvolutional neural networkcostdata repositorydata resourcedata warehousedigital imagingdigital pathologydigital repositoriesfeature selectionfollow-uphealth datahigh riskimprovedimproved outcomemachine learning modelmilitary veteranmultidimensional datamultimodal datamultiple omicsnoveloutcome predictionprecision oncologypredictive modelingprognosticprognostic modelprognosticationprostate biopsyprostate cancer riskradiological imagingradiomicsrepositorysocial health determinantssuccesstooltranscriptomicstreatment strategytumor
No Sub Projects information available for 1I01CX002622-01
Publications
Publications are associated with projects, but cannot be identified with any particular year of the project or fiscal year of funding. This is due to the continuous and cumulative nature of knowledge generation across the life of a project and the sometimes long and variable publishing timeline. Similarly, for multi-component projects, publications are associated with the parent core project and not with individual sub-projects.
No Publications available for 1I01CX002622-01
Patents
No Patents information available for 1I01CX002622-01
Outcomes
The Project Outcomes shown here are displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed are those of the PI and do not necessarily reflect the views of the National Institutes of Health. NIH has not endorsed the content below.
No Outcomes available for 1I01CX002622-01
Clinical Studies
No Clinical Studies information available for 1I01CX002622-01
News and More
Related News Releases
No news release information available for 1I01CX002622-01
History
No Historical information available for 1I01CX002622-01
Similar Projects
No Similar Projects information available for 1I01CX002622-01