Document text
Principal Investigator: Qian Dong
Organization: UNIVERSITY OF MICHIGAN AT ANN ARBOR
Fiscal Year: 2024
Award: $577,373
Funding agency: National Cancer Institute
Abstract
Multiple myeloma (MM) is the second most common hematologic malignancy (after non-Hodgkin lymphoma)
in the U.S. Over the past decade, despite the advent of novel therapies that has improved the life expectancy of
patients with MM, MM is still incurable. Patient outcome varies widely with overall survival (OS) ranging from
less than 1 year to greater than 10 years. The large variability of patient overall survival resulting from the high
heterogeneous microenvironment of MM heightens the needs of risk-adapted treatment for long-term control,
which are largely relied on accurate assessment of tumor evolution and survival prediction. The International
Myeloma Working Group (IMWG) guideline and several other different prognostic models have been used to
assess treatment outcomes. These systems utilize different subsets of laboratory values from clinic tests as
assessment criteria, which may not indicate the full extent of tumor burden. MRI is the gold standard imaging
modality for detection of bone marrow involvement. It provides global representation of the tumor burden, even
for patient with non-secretory or hypo-secretory MM. We hypothesize that integrating multimodal information
delivered by time serial noninvasive MR imaging and clinical tests will provide more robust and accurate
modeling of MM evolution during and after treatment, and thus can predict treatment outcomes more reliably at
an early time. Our goal is to develop a framework of decision support system (DSS) that integrates MR images
and clinical tests to assist physicians in making informed decisions on tailoring treatment for an individual MM
patient. The proposed study aims to (1) Investigate the effectiveness of MRI radiomic features in characterizing
MM infiltration and their correlations with treatment outcomes, (2) Investigate the circumstances how the
combination of MRI radiomics and clinical tests complements each other and is more powerful in early prediction
of treatment outcomes. To achieve these aims, we will retrospectively collect a large data set of MM cases with
baseline and follow-up MRI scans and clinical tests for development and validation of the DSS system. We will
utilize advanced artificial intelligence (AI) techniques including recurrent neural networks and reinforcement
learning to train predictive models with time serial MRI and clinical data acquired at multiple time points, which
allows the trained models to be deployed flexibly to each individual time point for treatment assessment to
facilitate early prediction. Furthermore, these advanced AI techniques can learn intertemporal dependencies
from available data to compensate for the missing data or exams at single time points in serial exams which may
occur in real-world clinical situation. With a flexible modular architecture design of our DSS system, we will
investigate the inter- and intra-relationships between MRI and laboratory variables for better understanding of
their complementarity in characterizing tumor burden during MM treatment and their association with treatment
outcomes. As a final step, using an independent multi-institutional test set, we will validate the performance of
the developed DSS in predicting the recurrence risk at an early time point during treatment.
Terms: <AI system><Active Follow-up><Affect><After Care><After-Treatment><Aftercare><Allelism Test><Anatomic Sites><Anatomic structures><Anatomy><Architecture><Area><Artificial Intelligence><Big Data><Big Data Analytics><Big Data Methods><Big Data Tools><BigData><Bone Marrow><Bone Marrow Involvement><Bone Marrow Reticuloendothelial System><Bone marrow biopsy><Clinic><Clinical><Clinical Data><Clinical Management><Clinical Trials><Compensation><Complementation Test><Computer Reasoning><Data><Decision Support Systems><Dependence><Detection><Development><Disease><Disorder><Drops><Drugs><Dysfunction><Early Diagnosis><Effectiveness><Engineering / Architecture><Evolution><Foundations><Functional disorder><Genetic Complementation Test><Goals><Guidelines><Health Care Costs><Health Costs><Healthcare Costs><Hematologic Cancer><Hematologic Malignancies><Hematologic Neoplasms><Hematological Malignancies><Hematological Neoplasms><Hematological Tumor><Hematopoietic Cancer><Heterogeneity><Image><Individual><Infiltration><Institution><International><Ionizing Electromagnetic Radiation><Ionizing radiation><Laboratories><Learning><Lesion><Life Expectancy><MR Imaging><MR Tomography><MRI><MRI Scans><MRIs><Machine Intelligence><Magnetic Resonance Imaging><Magnetic Resonance Imaging Scan><Malignant Hematologic Neoplasm><Medical Imaging, Magnetic Resonance / Nuclear Magnetic Resonance><Medication><Modeling><Molecular><Monitor><Morbidity><Morbidity - disease rate><Multiple Myeloma><NMR Imaging><NMR Tomography><Non-Hodgkin's Lymphoma><Nonhodgkins Lymphoma><Nuclear Magnetic Resonance Imaging><Pathologic><Patient outcome><Patient-Centered Outcomes><Patient-Focused Outcomes><Patients><Pattern><Performance><Pharmaceutical Preparations><Physicians><Physiologic pulse><Physiopathology><Plasma-Cell Myeloma><Play><Predicting Risk><Prediction of Response to Therapy><Predictive Value><Prognosis><Psychological reinforcement><Pulse><Radiation-Ionizing Total><Recommendation><Recurrence><Recurrent><Regimen><Reinforcement><Risk><Role><Serial Magnetic Resonance Imaging><Severities><Source><Staging><Surrogate End Points><Surrogate Endpoint><System><Techniques><Testing><Therapeutic><Therapeutic Agents><Time><Training><Trans Test><Treatment outcome><Tumor Burden><Tumor Load><Validation><Zeugmatography><active followup><cancer microenvironment><clinical decision-making><clinical translation><clinically translatable><complementation analysis><complementation approach><computer based prediction><customized therapy><customized treatment><design><designing><developmental><drug development><drug/agent><early detection><flexibility><flexible><follow up><follow-up><followed up><followup><forecasting risk><image-based method><imaging><imaging method><imaging modality><improved><in vivo><individualized medicine><individualized patient treatment><individualized therapeutic strategy><individualized therapy><individualized treatment><insight><ionizing output><large data sets><large datasets><machine learning based method><machine learning method><machine learning methodologies><mortality><multi-modality><multimodality><myeloma><myelomatosis><new drug treatments><new drugs><new pharmacological therapeutic><new therapeutics><new therapy><next generation therapeutics><non-Hodgkins disease><novel drug treatments><novel drugs><novel pharmaco-therapeutic><novel pharmacological therapeutic><novel therapeutics><novel therapy><outcome prediction><pathophysiology><patient oriented outcomes><patient specific therapies><patient specific treatment><patient variability><patient variation><post treatment><precision medicine><precision-based medicine><predict risk><predict risks><predict therapeutic response><predict therapy response><predicted risk><predicted risks><predicting risks><predictive modeling><predictive risk><predicts risk><prognosis model><prognostic ability><prognostic model><prognostic power><prognostic utility><prognostic value><radiomics><recurrent neural network><response to therapy><response to treatment><risk prediction><risk predictions><serial MRI><social role><success><survival prediction><tailored medical treatment><tailored therapy><tailored treatment><therapeutic response><therapy prediction><therapy response><treatment prediction><treatment response><treatment response prediction><treatment responsiveness><tumor><tumor microenvironment><unique treatment><validations><variability between patients><variation between patients><work group><working group>